Journal articles
Tyrrell J, O'Loughlin J, Casanova F, Bowden J, Freathy R, Watkins E (In Press). BMI and Well-being in people of East Asian and European Ancestry: a Mendelian Randomisation Study.
Translational PsychiatryAbstract:
BMI and Well-being in people of East Asian and European Ancestry: a Mendelian Randomisation Study
Previous studies have linked higher Body Mass Index (BMI) to lower subjective well-being in adult European ancestry populations. However, our understanding of these relationships across different populations is limited. Here, we investigated the association between BMI and well-being in people of a) East Asian and b) European ancestry in the China Kadoorie Biobank (CKB) and UK Biobank (UKB), respectively. Mendelian randomisation (MR) methods were used to test the relationship between BMI with a) health satisfaction and b) life satisfaction. One-sample MR enabled us to test effects in men and women separately and to test the role of cultural contexts by stratifying our analyses by urban and rural home location in both China and the UK. Further, we implemented a control function method to test the linearity of the BMI-well-being relationship. We found evidence of different associations between BMI and well-being in individuals of East Asian versus European ancestry. For example, a genetically-instrumented higher BMI tentatively associated with higher health satisfaction in people of East Asian ancestry, especially in females (ß: 0.041, 95% CI: 0.002, 0.081). In contrast, there was a robust inverse association between higher genetically-instrumented BMI and health satisfaction in all European ancestry UKB participants (ß: -0.183, 95% CI: -0.200, -0.165, Pdifference
Abstract.
Stein MJ, Baurecht H, Sedlmeier AM, Konzok J, Bohmann P, Fontvieille E, Peruchet-Noray L, Bowden J, Friedenreich CM, Fervers B, et al (2023). Association between circadian physical activity patterns and mortality in the UK Biobank.
Int J Behav Nutr Phys Act,
20(1).
Abstract:
Association between circadian physical activity patterns and mortality in the UK Biobank.
BACKGROUND: the benefit of physical activity (PA) for increasing longevity is well-established, however, the impact of diurnal timing of PA on mortality remains poorly understood. We aimed to derive circadian PA patterns and investigate their associations with all-cause mortality. METHODS: We used 24 h PA time series from 96,351 UK Biobank participants aged between 42 and 79 years at accelerometry in 2013-2015. Functional principal component analysis (fPCA) was applied to obtain circadian PA patterns. Using multivariable Cox proportional hazard models, we related the loading scores of these fPCs to estimate risk of mortality. RESULTS: During 6.9 years of follow-up, 2,850 deaths occurred. Four distinct fPCs accounted for 96% of the variation of the accelerometry data. Using a loading score of zero (i.e. average overall PA during the day) as the reference, a fPC1 score of + 2 (high overall PA) was inversely associated with mortality (Hazard ratio, HR = 0.91; 95% CI: 0.84-0.99), whereas a score of -2 (low overall PA) was associated with higher mortality (1.69; 95% CI: 1.57-1.81; p for non-linearity
Abstract.
Author URL.
Karageorgiou V, Casanova F, O'Loughlin J, Green H, McKinley TJ, Bowden J, Tyrrell J (2023). Body mass index and inflammation in depression and treatment-resistant depression: a Mendelian randomisation study.
BMC Med,
21(1).
Abstract:
Body mass index and inflammation in depression and treatment-resistant depression: a Mendelian randomisation study.
BACKGROUND: Major depressive disorder (MDD) has a significant impact on global burden of disease. Complications in clinical management can occur when response to pharmacological modalities is considered inadequate and symptoms persist (treatment-resistant depression (TRD)). We aim to investigate inflammation, proxied by C-reactive protein (CRP) levels, and body mass index (BMI) as putative causal risk factors for depression and subsequent treatment resistance, leveraging genetic information to avoid confounding via Mendelian randomisation (MR). METHODS: We used the European UK Biobank subcohort ([Formula: see text]), the mental health questionnaire (MHQ) and clinical records. For treatment resistance, a previously curated phenotype based on general practitioner (GP) records and prescription data was employed. We applied univariable and multivariable MR models to genetically predict the exposures and assess their causal contribution to a range of depression outcomes. We used a range of univariable, multivariable and mediation MR models techniques to address our research question with maximum rigour. In addition, we developed a novel statistical procedure to apply pleiotropy-robust multivariable MR to one sample data and employed a Bayesian bootstrap procedure to accurately quantify estimate uncertainty in mediation analysis which outperforms standard approaches in sparse binary outcomes. Given the flexibility of the one-sample design, we evaluated age and sex as moderators of the effects. RESULTS: in univariable MR models, genetically predicted BMI was positively associated with depression outcomes, including MDD ([Formula: see text] ([Formula: see text] CI): 0.133(0.072, 0.205)) and TRD (0.347(0.002, 0.682)), with a larger magnitude in females and with age acting as a moderator of the effect of BMI on severity of depression (0.22(0.050, 0.389)). Multivariable MR analyses suggested an independent causal effect of BMI on TRD not through CRP (0.395(0.004, 0.732)). Our mediation analyses suggested that the effect of CRP on severity of depression was partly mediated by BMI. Individuals with TRD ([Formula: see text]) observationally had higher CRP and BMI compared with individuals with MDD alone and healthy controls. DISCUSSION: Our work supports the assertion that BMI exerts a causal effect on a range of clinical and questionnaire-based depression phenotypes, with the effect being stronger in females and in younger individuals. We show that this effect is independent of inflammation proxied by CRP levels as the effects of CRP do not persist when jointly estimated with BMI. This is consistent with previous evidence suggesting that overweight contributed to depression even in the absence of any metabolic consequences. It appears that BMI exerts an effect on TRD that persists when we account for BMI influencing MDD.
Abstract.
Author URL.
Decina CS, Hopkins R, Bowden J, Shields BM, Lawlor DA, Warrington NM, Evans DM, Freathy RM, Beaumont RN (2023). Investigating a possible causal relationship between maternal serum urate concentrations and offspring birthweight: a Mendelian randomization study.
Int J Epidemiol,
52(1), 178-189.
Abstract:
Investigating a possible causal relationship between maternal serum urate concentrations and offspring birthweight: a Mendelian randomization study.
BACKGROUND: Higher urate levels are associated with higher systolic blood pressure (SBP) in adults, and in pregnancy with lower offspring birthweight. Mendelian randomization (MR) analyses suggest a causal effect of higher urate on higher SBP and of higher maternal SBP on lower offspring birthweight. If urate causally reduces birthweight, it might confound the effect of SBP on birthweight. We therefore tested for a causal effect of maternal urate on offspring birthweight. METHODS: We tested the association between maternal urate levels and offspring birthweight using multivariable linear regression in the Exeter Family Study of Childhood Health (EFSOCH; n = 872) and UK Biobank (UKB; n = 133 187). We conducted two-sample MR to test for a causal effect of maternal urate [114 single-nucleotide polymorphisms (SNPs); n = 288 649 European ancestry] on offspring birthweight (n = 406 063 European ancestry; maternal SNP effect estimates adjusted for fetal effects). We assessed a causal relationship between urate and SBP using one-sample MR in UKB women (n = 199 768). RESULTS: Higher maternal urate was associated with lower offspring birthweight with similar confounder-adjusted magnitudes in EFSOCH [22 g lower birthweight per 1-SD higher urate (95% CI: -50, 6); P = 0.13] and UKB [-28 g (95% CI: -31, -25); P = 1.8 × 10-75]. The MR causal effect estimate was directionally consistent, but smaller [-11 g (95% CI: -25, 3); PIVW = 0.11]. In women, higher urate was causally associated with higher SBP [1.7 mmHg higher SBP per 1-SD higher urate (95% CI: 1.4, 2.1); P = 7.8 × 10-22], consistent with that previously published in women and men. CONCLUSION: the marked attenuation of the MR result of maternal urate on offspring birthweight compared with the multivariable regression result suggests previous observational associations may be confounded. The 95% CIs of the MR result included the null but suggest a possible small effect on birthweight. Maternal urate levels are unlikely to be an important contributor to offspring birthweight.
Abstract.
Author URL.
O'Loughlin J, Casanova F, Fairhurst-Hunter Z, Hughes A, Bowden J, Watkins ER, Freathy RM, Millwood IY, Lin K, Chen Z, et al (2023). Mendelian randomisation study of body composition and depression in people of East Asian ancestry highlights potential setting-specific causality.
BMC Med,
21(1).
Abstract:
Mendelian randomisation study of body composition and depression in people of East Asian ancestry highlights potential setting-specific causality.
BACKGROUND: Extensive evidence links higher body mass index (BMI) to higher odds of depression in people of European ancestry. However, our understanding of the relationship across different settings and ancestries is limited. Here, we test the relationship between body composition and depression in people of East Asian ancestry. METHODS: Multiple Mendelian randomisation (MR) methods were used to test the relationship between (a) BMI and (b) waist-hip ratio (WHR) with depression. Firstly, we performed two-sample MR using genetic summary statistics from a recent genome-wide association study (GWAS) of depression (with 15,771 cases and 178,777 controls) in people of East Asian ancestry. We selected 838 single nucleotide polymorphisms (SNPs) correlated with BMI and 263 SNPs correlated with WHR as genetic instrumental variables to estimate the causal effect of BMI and WHR on depression using the inverse-variance weighted (IVW) method. We repeated these analyses stratifying by home location status: China versus UK or USA. Secondly, we performed one-sample MR in the China Kadoorie Biobank (CKB) in 100,377 participants. This allowed us to test the relationship separately in (a) males and females and (b) urban and rural dwellers. We also examined (c) the linearity of the BMI-depression relationship. RESULTS: Both MR analyses provided evidence that higher BMI was associated with lower odds of depression. For example, a genetically-instrumented 1-SD higher BMI in the CKB was associated with lower odds of depressive symptoms [OR: 0.77, 95% CI: 0.63, 0.95]. There was evidence of differences according to place of residence. Using the IVW method, higher BMI was associated with lower odds of depression in people of East Asian ancestry living in China but there was no evidence for an association in people of East Asian ancestry living in the USA or UK. Furthermore, higher genetic BMI was associated with differential effects in urban and rural dwellers within China. CONCLUSIONS: This study provides the first MR evidence for an inverse relationship between BMI and depression in people of East Asian ancestry. This contrasts with previous findings in European populations and therefore the public health response to obesity and depression is likely to need to differ based on sociocultural factors for example, ancestry and place of residence. This highlights the importance of setting-specific causality when using genetic causal inference approaches and data from diverse populations to test hypotheses. This is especially important when the relationship tested is not purely biological and may involve sociocultural factors.
Abstract.
Author URL.
Liu R, Xiang M, Pilling LC, Melzer D, Wang L, Manning KJ, Steffens DC, Bowden J, Fortinsky RH, Kuchel GA, et al (2023). Mid-life leukocyte telomere length and dementia risk: an observational and mendelian randomization study of 435,046 UK Biobank participants.
Aging Cell,
22(7).
Abstract:
Mid-life leukocyte telomere length and dementia risk: an observational and mendelian randomization study of 435,046 UK Biobank participants.
Telomere attrition is one of biological aging hallmarks and may be intervened to target multiple aging-related diseases, including Alzheimer's disease and Alzheimer's disease related dementias (AD/ADRD). The objective of this study was to assess associations of leukocyte telomere length (TL) with AD/ADRD and early markers of AD/ADRD, including cognitive performance and brain magnetic resonance imaging (MRI) phenotypes. Data from European-ancestry participants in the UK Biobank (n = 435,046) were used to evaluate whether mid-life leukocyte TL is associated with incident AD/ADRD over a mean follow-up of 12.2 years. In a subsample without AD/ADRD and with brain imaging data (n = 43,390), we associated TL with brain MRI phenotypes related to AD or vascular dementia pathology. Longer TL was associated with a lower risk of incident AD/ADRD (adjusted Hazard Ratio [aHR] per SD = 0.93, 95% CI 0.90-0.96, p = 3.37 × 10-7 ). Longer TL also was associated with better cognitive performance in specific cognitive domains, larger hippocampus volume, lower total volume of white matter hyperintensities, and higher fractional anisotropy and lower mean diffusivity in the fornix. In conclusion, longer TL is inversely associated with AD/ADRD, cognitive impairment, and brain structural lesions toward the development of AD/ADRD. However, the relationships between genetically determined TL and the outcomes above were not statistically significant based on the results from Mendelian randomization analysis results. Our findings add to the literature of prioritizing risk for AD/ADRD. The causality needs to be ascertained in mechanistic studies.
Abstract.
Author URL.
Karageorgiou V, Gill D, Bowden J, Zuber V (2023). Sparse dimensionality reduction approaches in Mendelian randomisation with highly correlated exposures.
Elife,
12Abstract:
Sparse dimensionality reduction approaches in Mendelian randomisation with highly correlated exposures.
Multivariable Mendelian randomisation (MVMR) is an instrumental variable technique that generalises the MR framework for multiple exposures. Framed as a regression problem, it is subject to the pitfall of multicollinearity. The bias and efficiency of MVMR estimates thus depends heavily on the correlation of exposures. Dimensionality reduction techniques such as principal component analysis (PCA) provide transformations of all the included variables that are effectively uncorrelated. We propose the use of sparse PCA (sPCA) algorithms that create principal components of subsets of the exposures with the aim of providing more interpretable and reliable MR estimates. The approach consists of three steps. We first apply a sparse dimension reduction method and transform the variant-exposure summary statistics to principal components. We then choose a subset of the principal components based on data-driven cutoffs, and estimate their strength as instruments with an adjusted F-statistic. Finally, we perform MR with these transformed exposures. This pipeline is demonstrated in a simulation study of highly correlated exposures and an applied example using summary data from a genome-wide association study of 97 highly correlated lipid metabolites. As a positive control, we tested the causal associations of the transformed exposures on coronary heart disease (CHD). Compared to the conventional inverse-variance weighted MVMR method and a weak instrument robust MVMR method (MR GRAPPLE), sparse component analysis achieved a superior balance of sparsity and biologically insightful grouping of the lipid traits.
Abstract.
Author URL.
Wade KH, Yarmolinsky J, Giovannucci E, Lewis SJ, Millwood IY, Munafò MR, Meddens F, Burrows K, Bell JA, Davies NM, et al (2022). Applying Mendelian randomization to appraise causality in relationships between nutrition and cancer.
Cancer Causes Control,
33(5), 631-652.
Abstract:
Applying Mendelian randomization to appraise causality in relationships between nutrition and cancer.
Dietary factors are assumed to play an important role in cancer risk, apparent in consensus recommendations for cancer prevention that promote nutritional changes. However, the evidence in this field has been generated predominantly through observational studies, which may result in biased effect estimates because of confounding, exposure misclassification, and reverse causality. With major geographical differences and rapid changes in cancer incidence over time, it is crucial to establish which of the observational associations reflect causality and to identify novel risk factors as these may be modified to prevent the onset of cancer and reduce its progression. Mendelian randomization (MR) uses the special properties of germline genetic variation to strengthen causal inference regarding potentially modifiable exposures and disease risk. MR can be implemented through instrumental variable (IV) analysis and, when robustly performed, is generally less prone to confounding, reverse causation and measurement error than conventional observational methods and has different sources of bias (discussed in detail below). It is increasingly used to facilitate causal inference in epidemiology and provides an opportunity to explore the effects of nutritional exposures on cancer incidence and progression in a cost-effective and timely manner. Here, we introduce the concept of MR and discuss its current application in understanding the impact of nutritional factors (e.g. any measure of diet and nutritional intake, circulating biomarkers, patterns, preference or behaviour) on cancer aetiology and, thus, opportunities for MR to contribute to the development of nutritional recommendations and policies for cancer prevention. We provide applied examples of MR studies examining the role of nutritional factors in cancer to illustrate how this method can be used to help prioritise or deprioritise the evaluation of specific nutritional factors as intervention targets in randomised controlled trials. We describe possible biases when using MR, and methodological developments aimed at investigating and potentially overcoming these biases when present. Lastly, we consider the use of MR in identifying causally relevant nutritional risk factors for various cancers in different regions across the world, given notable geographical differences in some cancers. We also discuss how MR results could be translated into further research and policy. We conclude that findings from MR studies, which corroborate those from other well-conducted studies with different and orthogonal biases, are poised to substantially improve our understanding of nutritional influences on cancer. For such corroboration, there is a requirement for an interdisciplinary and collaborative approach to investigate risk factors for cancer incidence and progression.
Abstract.
Author URL.
Liu J, Richmond RC, Bowden J, Barry C, Dashti HS, Daghlas I, Lane JM, Jones SE, Wood AR, Frayling TM, et al (2022). Assessing the Causal Role of Sleep Traits on Glycated Hemoglobin: a Mendelian Randomization Study.
Diabetes Care,
45(4), 772-781.
Abstract:
Assessing the Causal Role of Sleep Traits on Glycated Hemoglobin: a Mendelian Randomization Study.
OBJECTIVE: to examine the effects of sleep traits on glycated hemoglobin (HbA1c). RESEARCH DESIGN AND METHODS: This study triangulated evidence across multivariable regression (MVR) and one- (1SMR) and two-sample Mendelian randomization (2SMR) including sensitivity analyses on the effects of five self-reported sleep traits (i.e. insomnia symptoms [difficulty initiating or maintaining sleep], sleep duration, daytime sleepiness, napping, and chronotype) on HbA1c (in SD units) in adults of European ancestry from the UK Biobank (for MVR and 1SMR analyses) (n = 336,999; mean [SD] age 57 [8] years; 54% female) and in the genome-wide association studies from the Meta-Analyses of Glucose and Insulin-Related Traits Consortium (MAGIC) (for 2SMR analysis) (n = 46,368; 53 [11] years; 52% female). RESULTS: Across MVR, 1SMR, 2SMR, and their sensitivity analyses, we found a higher frequency of insomnia symptoms (usually vs. sometimes or rarely/never) was associated with higher HbA1c (MVR 0.05 SD units [95% CI 0.04-0.06]; 1SMR 0.52 [0.42-0.63]; 2SMR 0.24 [0.11-0.36]). Associations remained, but point estimates were somewhat attenuated after excluding participants with diabetes. For other sleep traits, there was less consistency across methods, with some but not all providing evidence of an effect. CONCLUSIONS: Our results suggest that frequent insomnia symptoms cause higher HbA1c levels and, by implication, that insomnia has a causal role in type 2 diabetes. These findings could have important implications for developing and evaluating strategies that improve sleep habits to reduce hyperglycemia and prevent diabetes.
Abstract.
Author URL.
Spiller W, Hartwig FP, Sanderson E, Davey Smith G, Bowden J (2022). Interaction-based Mendelian randomization with measured and unmeasured gene-by-covariate interactions.
PLOS ONE,
17(8), e0271933-e0271933.
Abstract:
Interaction-based Mendelian randomization with measured and unmeasured gene-by-covariate interactions
Studies leveraging gene-environment (GxE) interactions within Mendelian randomization (MR) analyses have prompted the emergence of two similar methodologies: MR-GxE and MR-GENIUS. Such methods are attractive in allowing for pleiotropic bias to be corrected when using individual instruments. Specifically, MR-GxE requires an interaction to be explicitly identified, while MR-GENIUS does not. We critically examine the assumptions of MR-GxE and MR-GENIUS in the absence of a pre-defined covariate, and propose sensitivity analyses to evaluate their performance. Finally, we explore the effect of body mass index (BMI) upon systolic blood pressure (SBP) using data from the UK Biobank, finding evidence of a positive effect of BMI on SBP. We find both approaches share similar assumptions, though differences between the approaches lend themselves to differing research settings. Where a suitable gene-by-covariate interaction is observed MR-GxE can produce unbiased causal effect estimates. MR-GENIUS can circumvent the need to identify interactions, but as a consequence relies on either the MR-GxE assumptions holding globally, or additional information with respect to the distribution of pleiotropic effects in the absence of an explicitly defined interaction covariate.
Abstract.
Grace SL, Bowden J, Walkey HC, Kaur A, Misra S, Shields BM, McKinley TJ, Oliver NS, McDonald TJ, Johnston DG, et al (2022). Islet Autoantibody Level Distribution in Type 1 Diabetes and Their Association with Genetic and Clinical Characteristics.
J Clin Endocrinol Metab,
107(12), e4341-e4349.
Abstract:
Islet Autoantibody Level Distribution in Type 1 Diabetes and Their Association with Genetic and Clinical Characteristics.
CONTEXT: the importance of the autoantibody level at diagnosis of type 1 diabetes (T1D) is not clear. OBJECTIVE: We aimed to assess the association of glutamate decarboxylase (GADA), islet antigen-2 (IA-2A), and zinc transporter 8 (ZnT8A) autoantibody levels with clinical and genetic characteristics at diagnosis of T1D. METHODS: We conducted a prospective, cross-sectional study. GADA, IA-2A, and ZnT8A were measured in 1644 individuals with T1D at diagnosis using radiobinding assays. Associations between autoantibody levels and the clinical and genetic characteristics for individuals were assessed in those positive for these autoantibodies. We performed replication in an independent cohort of 449 people with T1D. RESULTS: GADA and IA-2A levels exhibited a bimodal distribution at diagnosis. High GADA level was associated with older age at diagnosis (median 27 years vs 19 years, P = 9 × 10-17), female sex (52% vs 37%, P = 1 × 10-8), other autoimmune diseases (13% vs 6%, P = 3 × 10-6), and HLA-DR3-DQ2 (58% vs 51%, P =. 006). High IA-2A level was associated with younger age of diagnosis (median 17 years vs 23 years, P = 3 × 10-7), HLA-DR4-DQ8 (66% vs 50%, P = 1 × 10-6), and ZnT8A positivity (77% vs 52%, P = 1 × 10-15). We replicated our findings in an independent cohort of 449 people with T1D where autoantibodies were measured using enzyme-linked immunosorbent assays. CONCLUSION: Islet autoantibody levels provide additional information over positivity in T1D at diagnosis. Bimodality of GADA and IA-2A autoantibody levels highlights the novel aspect of heterogeneity of T1D. This may have implications for T1D prediction, treatment, and pathogenesis.
Abstract.
Author URL.
Tudball MJ, Hughes RA, Tilling K, Bowden J, Zhao Q (2022). Sample-constrained partial identification with application to selection bias. Biometrika, 110(2), 485-498.
Hazewinkel A, Bowden J, Wade KH, Palmer T, Wiles NJ, Tilling K (2022). Sensitivity to missing not at random dropout in clinical trials: Use and interpretation of the trimmed means estimator.
Statistics in Medicine,
41(8), 1462-1481.
Abstract:
Sensitivity to missing not at random dropout in clinical trials: Use and interpretation of the trimmed means estimator
AbstractOutcome values in randomized controlled trials (RCTs) may be missing not at random (MNAR), if patients with extreme outcome values are more likely to drop out (eg, due to perceived ineffectiveness of treatment, or adverse effects). In such scenarios, estimates from complete case analysis (CCA) and multiple imputation (MI) will be biased. We investigate the use of the trimmed means (TM) estimator for the case of univariable missingness in one continuous outcome. The TM estimator operates by setting missing values to the most extreme value, and then “trimming” away equal fractions of both groups, estimating the treatment effect using the remaining data. The TM estimator relies on two assumptions, which we term the “strong MNAR” and “location shift” assumptions. We derive formulae for the TM estimator bias resulting from the violation of these assumptions for normally distributed outcomes. We propose an adjusted TM estimator, which relaxes the location shift assumption and detail how our bias formulae can be used to establish the direction of bias of CCA and TM estimates, to inform sensitivity analyses. The TM approach is illustrated in a sensitivity analysis of the CoBalT RCT of cognitive behavioral therapy (CBT) in 469 individuals with 46 months follow‐up. Results were consistent with a beneficial CBT treatment effect, with MI estimates closer to the null and TM estimates further from the null than the CCA estimate. We propose using the TM estimator as a sensitivity analysis for data where extreme outcome value dropout is plausible.
Abstract.
Sirkis T, Jones B, Bowden J (2022). Should RECOVERY have used response adaptive randomisation? Evidence from a simulation study.
BMC MEDICAL RESEARCH METHODOLOGY,
22(1).
Author URL.
Türkmen D, Masoli JAH, Kuo C, Bowden J, Melzer D, Pilling LC (2022). Statin treatment effectiveness and the <i>SLCO1B1</i>*5 reduced function genotype: Long‐term outcomes in women and men.
British Journal of Clinical Pharmacology,
88(7), 3230-3240.
Abstract:
Statin treatment effectiveness and the SLCO1B1*5 reduced function genotype: Long‐term outcomes in women and men
ObjectiveTo estimate the effect of rs4149056 (SLCO1B1*5) genotype (decreases statin transport) on cholesterol control and treatment duration in male and female primary care patients prescribed common statin medications.Methods and AnalysisThis study comprised 69 185 European‐ancestry UK Biobank cohort participants prescribed simvastatin or atorvastatin (aged 40‐79 years at first prescription, treatment duration 1 month to 29 years, mean 5.7 years). Principal outcomes were clinically high total cholesterol (>5 mmol/L) at baseline, plus treatment discontinuation.ResultsA total of 48.4% of 591 females homozygous for SLCO1B1*5 decreased function genotype had raised cholesterol vs 41.7% of those with functioning SLCO1B1 (odds ratio 1.31, 95% confidence interval [CI] 1.1‐1.55, P = .001). Fewer males had high cholesterol and the genotype effect was attenuated. In primary care prescribing, females homozygous for SLCO1B1*5 were more likely to stop receiving these statins (29.5%) than women with normal SLCO1B1 (25.7%) (hazard ratio [HR] 1.19, 95% CI 1.03‐1.37, P = .01), amounting to five discontinuations per 100 statin‐years in the SLCO1B1*5 group vs four in the normal SLCO1B1 function group. This remained significant after the first year of treatment (HR for discontinuing >1 year after first prescription 1.3, 95% CI 1.08‐1.56, P = .006). In men SLCO1B1*5 was only associated with treatment discontinuation in the first year.ConclusionsIn this large community sample of patients on commonly prescribed statins, the SLCO1B1*5 decreased function variant had much larger effects on cholesterol control and treatment duration in women than in men. Efforts to improve the effectiveness of statin therapy in women may need to include SLCO1B1*5 genotype‐guided statin selection.
Abstract.
Karageorgiou V, Tyrrell J, McKinley TJ, Bowden J (2022). Weak and pleiotropy robust Sex-stratified Mendelian Randomization in the one sample and two sample settings.
HUMAN HEREDITY,
VOL.(SUPPL 1), 24-25.
Author URL.
PILLING LC, DUDBRIDGE F, MELZER D, BOWDEN J, FRAYLING TM (2021). 188-LB: Type 2 Diabetes is Genetically Correlated with Multiple Long-Term Conditions but These Correlations Are Only Partly Explained by BMI. Diabetes, 70(Supplement_1).
Pilling LC, Turkmen D, Fullalove H, Atkins JL, Delgado J, Kuo C-L, Kuchel GA, Ferrucci L, Bowden J, Masoli JAH, et al (2021). Analysis of <i>CYP2C19</i> genetic variants with ischaemic events in UK patients prescribed clopidogrel in primary care: a retrospective cohort study.
BMJ OPEN,
11(12).
Author URL.
Kennedy NA, Goodhand JR, Bewshea C, Nice R, Chee D, Lin S, Chanchlani N, Butterworth J, Cooney R, Croft NM, et al (2021). Anti-SARS-CoV-2 antibody responses are attenuated in patients with IBD treated with infliximab.
Gut,
70(5), 865-875.
Abstract:
Anti-SARS-CoV-2 antibody responses are attenuated in patients with IBD treated with infliximab
ObjectiveAntitumour necrosis factor (anti-TNF) drugs impair protective immunity following pneumococcal, influenza and viral hepatitis vaccination and increase the risk of serious respiratory infections. We sought to determine whether infliximab-treated patients with IBD have attenuated serological responses to SARS-CoV-2 infections.DesignAntibody responses in participants treated with infliximab were compared with a reference cohort treated with vedolizumab, a gut-selective anti-integrin α4β7 monoclonal antibody that is not associated with impaired vaccine responses or increased susceptibility to systemic infections. 6935 patients were recruited from 92 UK hospitals between 22 September and 23 December 2020.ResultsRates of symptomatic and proven SARS-CoV-2 infection were similar between groups. Seroprevalence was lower in infliximab-treated than vedolizumab-treated patients (3.4% (161/4685) vs 6.0% (134/2250), p<0.0001). Multivariable logistic regression analyses confirmed that infliximab (vs vedolizumab; OR 0.66 (95% CI 0.51 to 0.87), p=0.0027) and immunomodulator use (OR 0.70 (95% CI 0.53 to 0.92), p=0.012) were independently associated with lower seropositivity. In patients with confirmed SARS-CoV-2 infection, seroconversion was observed in fewer infliximab-treated than vedolizumab-treated patients (48% (39/81) vs 83% (30/36), p=0.00044) and the magnitude of anti-SARS-CoV-2 reactivity was lower (median 0.8 cut-off index (0.2–5.6) vs 37.0 (15.2–76.1), p<0.0001).ConclusionsInfliximab is associated with attenuated serological responses to SARS-CoV-2 that were further blunted by immunomodulators used as concomitant therapy. Impaired serological responses to SARS-CoV-2 infection might have important implications for global public health policy and individual anti-TNF-treated patients. Serological testing and virus surveillance should be considered to detect suboptimal vaccine responses, persistent infection and viral evolution to inform public health policy.Trial registration numberISRCTN45176516.
Abstract.
Wang J, Zhao Q, Bowden J, Hemani G, Davey Smith G, Small DS, Zhang NR (2021). Causal inference for heritable phenotypic risk factors using heterogeneous genetic instruments.
PLoS Genet,
17(6).
Abstract:
Causal inference for heritable phenotypic risk factors using heterogeneous genetic instruments.
Over a decade of genome-wide association studies (GWAS) have led to the finding of extreme polygenicity of complex traits. The phenomenon that "all genes affect every complex trait" complicates Mendelian Randomization (MR) studies, where natural genetic variations are used as instruments to infer the causal effect of heritable risk factors. We reexamine the assumptions of existing MR methods and show how they need to be clarified to allow for pervasive horizontal pleiotropy and heterogeneous effect sizes. We propose a comprehensive framework GRAPPLE to analyze the causal effect of target risk factors with heterogeneous genetic instruments and identify possible pleiotropic patterns from data. By using GWAS summary statistics, GRAPPLE can efficiently use both strong and weak genetic instruments, detect the existence of multiple pleiotropic pathways, determine the causal direction and perform multivariable MR to adjust for confounding risk factors. With GRAPPLE, we analyze the effect of blood lipids, body mass index, and systolic blood pressure on 25 disease outcomes, gaining new information on their causal relationships and potential pleiotropic pathways involved.
Abstract.
Author URL.
Jenkins DA, Wade KH, Carslake D, Bowden J, Sattar N, Loos RJF, Timpson NJ, Sperrin M, Rutter MK (2021). Estimating the causal effect of BMI on mortality risk in people with heart disease, diabetes and cancer using Mendelian randomization.
Int J Cardiol,
330, 214-220.
Abstract:
Estimating the causal effect of BMI on mortality risk in people with heart disease, diabetes and cancer using Mendelian randomization.
BACKGROUND: Observational data have reported that being overweight or obese, compared to being normal weight, is associated with a lower risk for death - the "obesity paradox". We used Mendelian randomization (MR) to estimate causal effects of body mass index (BMI) on mortality risks in people with coronary heart disease (CHD), type 2 diabetes mellitus (T2DM) or malignancy in whom this paradox has been often reported. METHODS: We studied 457,746 White British UK Biobank participants including three subgroups with T2DM (n = 19,737), CHD (n = 21,925) or cancer (n = 42,612) at baseline and used multivariable-adjusted Cox models and MR approaches to describe relationships between BMI and mortality risk. RESULTS: Observational Cox models showed J-shaped relationships between BMI and mortality risk including within disease subgroups in which the BMI values associated with minimum mortality risk were within overweight/obese ranges (26.5-32.5 kg/m2). In all participants, MR analyses showed a positive linear causal effect of BMI on mortality risk (HR for mortality per unit higher BMI: 1.05; 95% CI: 1.03-1.08), also evident in people with CHD (HR: 1.08; 95% CI: 1.01-1.14). Point estimates for hazard ratios across all BMI values in participants with T2DM and cancer were consistent with overall positive linear effects but confidence intervals included the null. CONCLUSION: These data support the idea that population efforts to promote intentional weight loss towards the normal BMI range would reduce, not enhance, mortality risk in the general population including, importantly, individuals with CHD.
Abstract.
Author URL.
Barry C, Liu J, Richmond R, Rutter MK, Lawlor DA, Dudbridge F, Bowden J (2021). Exploiting collider bias to apply two-sample summary data Mendelian randomization methods to one-sample individual level data.
PLOS Genetics,
17(8), e1009703-e1009703.
Abstract:
Exploiting collider bias to apply two-sample summary data Mendelian randomization methods to one-sample individual level data
Over the last decade the availability of SNP-trait associations from genome-wide association studies has led to an array of methods for performing Mendelian randomization studies using only summary statistics. A common feature of these methods, besides their intuitive simplicity, is the ability to combine data from several sources, incorporate multiple variants and account for biases due to weak instruments and pleiotropy. With the advent of large and accessible fully-genotyped cohorts such as UK Biobank, there is now increasing interest in understanding how best to apply these well developed summary data methods to individual level data, and to explore the use of more sophisticated causal methods allowing for non-linearity and effect modification.
In this paper we describe a general procedure for optimally applying any two sample summary data method using one sample data. Our procedure first performs a meta-analysis of summary data estimates that are intentionally contaminated by collider bias between the genetic instruments and unmeasured confounders, due to conditioning on the observed exposure. These estimates are then used to correct the standard observational association between an exposure and outcome. Simulations are conducted to demonstrate the method’s performance against naive applications of two sample summary data MR. We apply the approach to the UK Biobank cohort to investigate the causal role of sleep disturbance on HbA1c levels, an important determinant of diabetes.
Our approach can be viewed as a generalization of Dudbridge et al. (Nat. Comm. 10: 1561), who developed a technique to adjust for index event bias when uncovering genetic predictors of disease progression based on case-only data. Our work serves to clarify that in any one sample MR analysis, it can be advantageous to estimate causal relationships by artificially inducing and then correcting for collider bias.
Abstract.
Pilling LC, Türkmen D, Fullalove H, Atkins JL, Delgado J, Kuo C-L, Kuchel GA, Ferrucci L, Bowden J, Masoli JAH, et al (2021). Genetic variation in activating clopidogrel: longer-term outcomes in a large community cohort.
Abstract:
Genetic variation in activating clopidogrel: longer-term outcomes in a large community cohort
AbstractBackgroundThe antiplatelet drug clopidogrel is commonly prescribed for stroke and myocardial infarction (MI) prevention. Clopidogrel prodrug is predominantly activated by liver enzyme CYP2C19. CYP2C19 Loss-of-function (LoF) genetic variants have been linked to excess morbidity mainly in patients hospitalized for acute ischemic events and related interventions. Little is known about the magnitude of impact of LoF variants in family practice, especially over long periods of exposure. We aimed to determine whether CYP2C19 LoF alleles increase risk of ischemic stroke and MI in primary care patients prescribed clopidogrel for up to 18 years.MethodsRetrospective cohort analysis of 7,483 European-ancestry adults from the UK Biobank study with genetic and linked primary care data, aged 36 to 79 years at first clopidogrel prescription. We examined CYP2C19 LoF variant (*2-*8) associations with incident hospital-diagnosed ischemic stroke and MI in patients prescribed clopidogrel for at least 2 months using time-to-event models, with secondary analysis of the. 17 gain of function variant.Results28.7% (n=2,144/7,483) of included subjects (mean age 63 years at first clopidogrel prescription) carried at least one CYP2C19 intermediate or low metabolizer LoF variant. 1.9% of LoF variant carriers had an incident ischemic stroke whilst prescribed clopidogrel (mean 2.6 years, range 2 months to 18 years), versus 1.3% without the variants (0.6% absolute excess: Hazard Ratio 1.53: 95% CI 1.04 to 2.26, p=0.031). Additionally, 26.4% of CYP2C19 LoF variant carriers had an incident MI versus 24.1% (HR 1.14: 1.04 to 1.26, p=.008). Adjustment for aspirin co-prescription produced similar estimates. In lifetables using observed incidence rates, 22.5% (95% CI 14.4% to 34.0%) of CYP2C19 LoF carriers on clopidogrel were projected to develop an ischemic stroke by age 79 (the oldest age in the study), compared with 15.4% (95% CI 11.4% to 20.5%) in non-carriers: the absolute excess stroke incidence with LoF variants was 7.1% by age 79.ConclusionIn family practice patients on clopidogrel, CYP2C19 LoF variants are associated with substantially higher incidence of ischemic events. Genotype-guided (or routine) prescription of antiplatelet medications unaffected by CYP2C19 variants may improve outcomes in patients for whom clopidogrel is currently indicated.
Abstract.
Tudball MJ, Bowden J, Hughes RA, Ly A, Munafò MR, Tilling K, Zhao Q, Davey Smith G (2021). Mendelian randomisation with coarsened exposures.
Genet Epidemiol,
45(3), 338-350.
Abstract:
Mendelian randomisation with coarsened exposures.
A key assumption in Mendelian randomisation is that the relationship between the genetic instruments and the outcome is fully mediated by the exposure, known as the exclusion restriction assumption. However, in epidemiological studies, the exposure is often a coarsened approximation to some latent continuous trait. For example, latent liability to schizophrenia can be thought of as underlying the binary diagnosis measure. Genetically driven variation in the outcome can exist within categories of the exposure measurement, thus violating this assumption. We propose a framework to clarify this violation, deriving a simple expression for the resulting bias and showing that it may inflate or deflate effect estimates but will not reverse their sign. We then characterise a set of assumptions and a straight-forward method for estimating the effect of SD increases in the latent exposure. Our method relies on a sensitivity parameter which can be interpreted as the genetic variance of the latent exposure. We show that this method can be applied in both the one-sample and two-sample settings. We conclude by demonstrating our method in an applied example and reanalysing two papers which are likely to suffer from this type of bias, allowing meaningful interpretation of their effect sizes.
Abstract.
Author URL.
Bowden J (2021). Realising the full potential of MR-PHeWAS in cancer.
Br J Cancer,
124(3), 529-530.
Abstract:
Realising the full potential of MR-PHeWAS in cancer.
MR-PHeWAS is a powerful new design for discovering causal mechanisms between a disease and its many candidate risk factors in a hypothesis-free manner. This technique has great potential in the field of cancer research, provided that both powerful and principled statistical approaches are used.
Abstract.
Author URL.
Hazewinkel A-D, Bowden J, Wade KH, Palmer T, Wiles N, Tilling K (2021). Sensitivity to missing not at random dropout in clinical trials: use and interpretation of the Trimmed Means Estimator.
Abstract:
Sensitivity to missing not at random dropout in clinical trials: use and interpretation of the Trimmed Means Estimator
AbstractOutcome values in randomized controlled trials (RCTs) may be missing not at random (MNAR), if patients with extreme outcome values are more likely to drop out (e.g. due to perceived ineffectiveness of treatment, or adverse effects). In such scenarios, estimates from complete case analysis (CCA) and multiple imputation (MI) will be biased. The trimmed means (TM) estimator operates by setting missing values to the most extreme value, and then “trimming” away equal fractions of both treatment groups, estimating the treatment effect using the remaining data. The TM estimator relies on two assumptions, which we term the “strong MNAR” and “location shift” assumptions. In this article, we derive formulae for the bias resulting from the violation of these assumptions for normally distributed outcomes. We propose an adjusted estimator, which relaxes the location shift assumption and detail how our bias formulae can be used to establish the direction of bias of CCA, MI and TM estimates under a range of plausible data scenarios, to inform sensitivity analyses. The TM approach is illustrated with simulations and in a sensitivity analysis of the CoBalT RCT of cognitive behavioural therapy (CBT) in 469 individuals with 46 months follow-up. Results were consistent with a beneficial CBT treatment effect. The MI estimates are closer to the null than the CCA estimate, whereas the TM estimate was further from the null. We propose using the TM estimator as a sensitivity analysis for data where it is suspected that extreme outcome values are missing.
Abstract.
Türkmen D, Masoli JAH, Kuo C-L, Bowden J, Melzer D, Pilling LC (2021). Statin treatment effectiveness and the <i>SLCO1B1</i>*5 reduced function genotype: long-term outcomes in women and men.
Abstract:
Statin treatment effectiveness and the SLCO1B1*5 reduced function genotype: long-term outcomes in women and men
ABSTRACTObjectiveTo estimate the effect of the SLCO1B1*5 genotype (decreases statin transport) on cholesterol control and treatment duration in male and female primary care patients prescribed common statin medications.Methods and Analysis69,185 European-ancestry UK Biobank cohort participants prescribed simvastatin or atorvastatin (aged 40 to 79 years at first prescription; treatment duration 1 month to 29 years, mean 5.7 years). Principal outcomes were clinically high total cholesterol (>5mmol/L) at baseline, plus treatment discontinuation.Results48.4% of 591 females homozygous for SLCO1B1*5 decreased function genotype had raised cholesterol, vs. 41.7% of those with functioning SLCO1B1 (Odds Ratio 1.31: 95% Confidence Intervals 1.1 to 1.55, p=0.001). Fewer males had high cholesterol, and the genotype effect was attenuated. In primary care prescribing, females homozygous for SLCO1B1*5 were more likely to stop receiving these statins (29.5%) than women with normal SLCO1B1 (25.7%) (Hazard Ratio 1.19: 95%CI 1.03 to 1.37, p=0.01), amounting to five discontinuations per 100 statin-years in the SLCO1B1*5 group vs four in the normal SLCO1B1 function group. This remained significant after the first year of treatment (HR for discontinuing >1 year after first prescription 1.3: 95%CI 1.08 to 1.56; p=0.006). In men SLCO1B1*5 was only associated with treatment discontinuation in the first year.ConclusionsIn this large community sample of patients on commonly prescribed statins, the SLCO1B1*5 decreased function variant had much larger effects on cholesterol control and treatment duration in women than in men. Efforts to improve effectiveness of statin therapy in women may need to include SLCO1B1*5 genotype-guided statin selection.What is already known about this subjectGenetic variants affecting SLCO1B1 (statin transporter) gene function increase concentrations of unmetabolized statin molecules (mostly simvastatin and atorvastatin). Previous studies of statin-treated patients have reported reduced likelihood of achieving target cholesterol levels plus increased adverse effects and medication non-adherence mainly in the first year of treatment.However, little data have been available on key outcomes over longer follow-ups or on outcomes by sex, despite large differences in statin treatment patterns between men and women.What this study addsIn 69,185 UK Biobank participants reporting simvastatin or atorvastatin use at baseline assessment, substantially more women had clinically high total cholesterol (>5 mmol/L) compared to men (42% vs. 25%). Female carriers of the SLCO1B1*5 (decreased SLCO1B1 function) genetic variant were especially likely to have high cholesterol, despite being on statin treatment.In primary care records of atorvastatin and simvastatin prescribing (>10 years follow-up), female carriers of SLCO1B1*5 were more likely to stop statins. In men, SLCO1B1*5 was only associated with discontinuing statin treatment in the first year after starting treatment.
Abstract.
Bowden J, Pilling LC, Türkmen D, Kuo C-L, Melzer D (2021). The Triangulation WIthin a STudy (TWIST) framework for causal inference within Pharmacogenetic research.
Abstract:
The Triangulation WIthin a STudy (TWIST) framework for causal inference within Pharmacogenetic research
AbstractIn this paper we review the methodological underpinnings of the general pharmacogenetic approach for uncovering genetically-driven treatment effect heterogeneity. This typically utilises only individuals who are treated and relies on fairly strong baseline assumptions to estimate what we term the ‘genetically moderated treatment effect’ (GMTE). When these assumptions are seriously violated, we show that a robust but less efficient estimate of the GMTE that incorporates information on the population of untreated individuals can instead be used. In cases of partial violation, we clarify when Mendelian randomization and a modified confounder adjustment method can also yield consistent estimates for the GMTE. A decision framework is then described to decide when a particular estimation strategy is most appropriate and how specific estimators can be combined to further improve efficiency. Triangulation of evidence from different data sources, each with their inherent biases and limitations, is becoming a well established principle for strengthening causal analysis. We call our framework ‘Triangulation WIthin a STudy’ (TWIST)’ in order to emphasise that an analysis in this spirit is also possible within a single data set, using causal estimates that are approximately uncorrelated, but reliant on different sets of assumptions. We illustrate these approaches by re-analysing primary-care-linked UK Biobank data relating to CYP2C19 genetic variants, Clopidogrel use and stroke risk, and data relating to APOE genetic variants, statin use and Coronary Artery Disease.
Abstract.
Bowden J, Pilling LC, Türkmen D, Kuo C-L, Melzer D (2021). The Triangulation WIthin a STudy (TWIST) framework for causal inference within pharmacogenetic research.
PLOS Genetics,
17(9), e1009783-e1009783.
Abstract:
The Triangulation WIthin a STudy (TWIST) framework for causal inference within pharmacogenetic research
In this paper we review the methodological underpinnings of the general pharmacogenetic approach for uncovering genetically-driven treatment effect heterogeneity. This typically utilises only individuals who are treated and relies on fairly strong baseline assumptions to estimate what we term the ‘genetically moderated treatment effect’ (GMTE). When these assumptions are seriously violated, we show that a robust but less efficient estimate of the GMTE that incorporates information on the population of untreated individuals can instead be used. In cases of partial violation, we clarify when Mendelian randomization and a modified confounder adjustment method can also yield consistent estimates for the GMTE. A decision framework is then described to decide when a particular estimation strategy is most appropriate and how specific estimators can be combined to further improve efficiency. Triangulation of evidence from different data sources, each with their inherent biases and limitations, is becoming a well established principle for strengthening causal analysis. We call our framework ‘Triangulation WIthin a STudy’ (TWIST)’ in order to emphasise that an analysis in this spirit is also possible within a single data set, using causal estimates that are approximately uncorrelated, but reliant on different sets of assumptions. We illustrate these approaches by re-analysing primary-care-linked UK Biobank data relating to CYP2C19 genetic variants, Clopidogrel use and stroke risk, and data relating to APOE genetic variants, statin use and Coronary Artery Disease.
Abstract.
Windmeijer F, Liang X, Hartwig FP, Bowden J (2021). The confidence interval method for selecting valid instrumental variables.
Journal of the Royal Statistical Society. Series B: Statistical Methodology,
83(4), 752-776.
Abstract:
The confidence interval method for selecting valid instrumental variables
We propose a new method, the confidence interval (CI) method, to select valid instruments from a larger set of potential instruments for instrumental variable (IV) estimation of the causal effect of an exposure on an outcome. Invalid instruments are such that they fail the exclusion conditions and enter the model as explanatory variables. The CI method is based on the CIs of the per instrument causal effects estimates and selects the largest group with all CIs overlapping with each other as the set of valid instruments. Under a plurality rule, we show that the resulting standard IV, or two-stage least squares (2SLS) estimator has oracle properties. This result is the same as for the hard thresholding with voting (HT) method of Guo et al. (Journal of the Royal Statistical Society : Series B, 2018, 80, 793–815). Unlike the HT method, the number of instruments selected as valid by the CI method is guaranteed to be monotonically decreasing for decreasing values of the tuning parameter. For the CI method, we can therefore use a downward testing procedure based on the Sargan (Econometrica, 1958, 26, 393–415) test for overidentifying restrictions and a main advantage of the CI downward testing method is that it selects the model with the largest number of instruments selected as valid that passes the Sargan test.
Abstract.
Minelli C, Del Greco M F, van der Plaat DA, Bowden J, Sheehan NA, Thompson J (2021). The use of two-sample methods for Mendelian randomization analyses on single large datasets.
Int J Epidemiol,
50(5), 1651-1659.
Abstract:
The use of two-sample methods for Mendelian randomization analyses on single large datasets.
BACKGROUND: with genome-wide association data for many exposures and outcomes now available from large biobanks, one-sample Mendelian randomization (MR) is increasingly used to investigate causal relationships. Many robust MR methods are available to address pleiotropy, but these assume independence between the gene-exposure and gene-outcome association estimates. Unlike in two-sample MR, in one-sample MR the two estimates are obtained from the same individuals, and the assumption of independence does not hold in the presence of confounding. METHODS: with simulations mimicking a typical study in UK Biobank, we assessed the performance, in terms of bias and precision of the MR estimate, of the fixed-effect and (multiplicative) random-effects meta-analysis method, weighted median estimator, weighted mode estimator and MR-Egger regression, used in both one-sample and two-sample data. We considered scenarios differing by the: presence/absence of a true causal effect; amount of confounding; and presence and type of pleiotropy (none, balanced or directional). RESULTS: Even in the presence of substantial correlation due to confounding, all two-sample methods used in one-sample MR performed similarly to when used in two-sample MR, except for MR-Egger which resulted in bias reflecting direction and magnitude of the confounding. Such bias was much reduced in the presence of very high variability in instrument strength across variants (IGX2 of 97%). CONCLUSIONS: Two-sample MR methods can be safely used for one-sample MR performed within large biobanks, expect for MR-Egger. MR-Egger is not recommended for one-sample MR unless the correlation between the gene-exposure and gene-outcome estimates due to confounding can be kept low, or the variability in instrument strength is very high.
Abstract.
Author URL.
Tudball MJ, Bowden J, Hughes RA, Ly A, Munafò MR, Tilling K, Zhao Q, Davey Smith G (2020). A simple framework for Mendelian randomisation of latent continuous exposures with discrete measurements.
Abstract:
A simple framework for Mendelian randomisation of latent continuous exposures with discrete measurements
AbstractA key assumption in Mendelian randomisation is that the relationship between the genetic instruments and the outcome is fully mediated by the exposure measurement, known as the exclusion restriction assumption. However, in epidemiological studies, the exposure measurement is often a discrete marker for some latent continuous trait. For example, latent liability to schizophrenia can be thought of as underlying the binary diagnosis measure. Genetically-driven variation in the outcome can exist within categories of the exposure measurement, thus violating this assumption. We propose a framework to clarify this violation, deriving a simple expression for the resulting bias and showing that it may inflate or deflate effect estimates but will not reverse their sign. We then characterise a set of assumptions and a straight-forward method for estimating the effect of standard deviation increases in the latent exposure. Our method relies on a sensitivity parameter which can be interpreted as the genetic variance of the latent exposure. We show that this method can be applied in both the one-sample and two-sample settings. We conclude by demonstrating our method in an applied example and re-analysing two papers which are likely to suffer from this type of bias, allowing meaningful interpretation of their effect sizes.
Abstract.
Liu J, Richmond RC, Bowden J, Barry C, Dashti HS, Daghlas I, Lane JM, Jones SE, Wood AR, Frayling TM, et al (2020). Assessing the causal role of sleep traits on glycated haemoglobin: a Mendelian randomization study.
Abstract:
Assessing the causal role of sleep traits on glycated haemoglobin: a Mendelian randomization study
ABSTRACTObjectiveTo examine the effects of sleep traits on glycated haemoglobin (HbA1c).DesignObservational multivariable regression (MVR), one-sample Mendelian randomization (1SMR), and two-sample summary data Mendelian randomization (2SMR).SettingUK Biobank (UKB) prospective cohort study and genome-wide association studies from the Meta-Analyses of Glucose and Insulin-related traits Consortium (MAGIC).ParticipantsIn MVR and 1SMR, participants were adults (mean (SD) age 57 (8) years; 54% female) from the UKB (n=336,999); in 2SMR, participants were adults (53 (11) years; 52% female) from MAGIC (n=46,368). All participants were adults of European ancestry.ExposuresSelf-reported insomnia frequency (usually vs sometimes or rarely/never); sleep duration: 24-hour sleep duration (hours/day); short sleep (≤6 hours vs 7-8 hours) and long sleep (≥9 hours vs 7-8 hours); daytime sleepiness and daytime napping (each consisting of 3 categories: never/rarely, sometimes, usually); chronotype (5 categories from definite morning to definite evening preference).Main outcome measureHbA1c in standard deviation (SD) units.ResultsAcross MV, 1SMR, 2SMR, and their sensitivity analyses we found a higher frequency of insomnia (usually vs sometimes or rarely/never) was associated with higher HbA1c (MVR: 0.053 SD units, 95% confidence interval (0.046 to 0.061), 1SMR: 0.52, (0.42 to 0.63), 2SMR: 0.22, (0.10 to 0.35)). Results remained significant but point estimates were somewhat attenuated after excluding people with diagnosed diabetes. For other sleep traits, there was less consistency with significant associations when using some, but not all methods.ConclusionsThis study suggests that insomnia increases HbA1c levels. These findings could have important implications for developing and evaluating strategies that improve sleep habits to reduce hyperglycaemia and prevent diabetes.SUMMARY BOXWhat is already known on this topicIn observational data, insomnia, short sleep duration, and evening preference are associated with higher risk for type 2 diabetes.Mendelian randomization (MR) studies have not found evidence of a causal effect of short sleep on type 2 diabetes or glycaemic traits but have indicated an effect of insomnia on type 2 diabetes. It is unclear whether insomnia influences HbA1c levels, a marker of long-term hyperglycaemia, in the general population.Recently identified genetic variants robustly associated with insomnia, sleep duration, daytime sleepiness, napping, and chronotype can be used in MR studies to explore causal effects of these sleep traits on HbA1c levels.What this study addsThis study suggests that a higher frequency of insomnia increases HbA1c levels in the general population and after excluding people with diabetes.We found no robust evidence for causal effects of other sleep traits on HbA1c levels.These findings improve our understanding of the impact of sleep traits on HbA1c levels and have important implications for developing and evaluating strategies that improve sleep habits to reduce hyperglycaemia and prevent diabetes.
Abstract.
Wang J, Zhao Q, Bowden J, Hemani G, Smith GD, Small DS, Zhang NR (2020). Causal inference for heritable phenotypic risk factors using heterogeneous genetic instruments.
Abstract:
Causal inference for heritable phenotypic risk factors using heterogeneous genetic instruments
AbstractOver a decade of genome-wide association studies (GWAS) have led to the finding of extreme polygenicity of complex traits. The phenomenon that “all genes affect every complex trait” complicates Mendelian Randomization (MR) studies, where natural genetic variations are used as instruments to infer the causal effect of heritable risk factors. We reexamine the assumptions of existing MR methods and show how they need to be clarified to allow for pervasive horizontal pleiotropy and heterogeneous effect sizes. We propose a comprehensive framework GRAPPLE to analyze the causal effect of target risk factors with heterogeneous genetic instruments and identify possible pleiotropic patterns from data. By using GWAS summary statistics, GRAPPLE can efficiently use both strong and weak genetic instruments, detect the existence of multiple pleiotropic pathways, determine the causal direction and perform multivariable MR to adjust for confounding risk factors. With GRAPPLE, we analyze the effect of blood lipids, body mass index, and systolic blood pressure on 25 disease outcomes, gaining new information on their causal relationships and the potential pleiotropic pathways.
Abstract.
Bowden J, Bornkamp B, Glimm E, Bretz F (2020). Connecting Instrumental Variable methods for causal inference to the. Estimand Framework.
Abstract:
Connecting Instrumental Variable methods for causal inference to the. Estimand Framework
Causal inference methods are gaining increasing prominence in pharmaceutical
drug development in light of the recently published addendum on estimands and
sensitivity analysis in clinical trials to the E9 guideline of the
International Council for Harmonisation. The E9 addendum emphasises the need to
account for post-randomization or `intercurrent' events that can potentially
influence the interpretation of a treatment effect estimate at a trial's
conclusion. Instrumental Variables (IV) methods have been used extensively in
economics, epidemiology and academic clinical studies for `causal inference',
but less so in the pharmaceutical industry setting until now. In this tutorial
paper we review the basic tools for causal inference, including graphical
diagrams and potential outcomes, as well as several conceptual frameworks that
an IV analysis can sit within. We discuss in detail how to map these approaches
to the Treatment Policy, Principal Stratum and Hypothetical `estimand
strategies' introduced in the E9 addendum, and provide details of their
implementation using standard regression models. Specific attention is given to
discussing the assumptions each estimation strategy relies on in order to be
consistent, the extent to which they can be empirically tested and sensitivity
analyses in which specific assumptions can be relaxed. We finish by applying
the methods described to simulated data closely matching two recent
pharmaceutical trials to further motivate and clarify the ideas
Abstract.
Author URL.
Sanderson E, Smith GD, Windmeijer F, Bowden J (2020). Corrigendum to: an examination of multivariable Mendelian randomization in the single-sample and two-sample summary data settings.
Int J Epidemiol,
49(3).
Author URL.
Pilling LC, Jones LC, Masoli JAH, Delgado J, Atkins JL, Bowden J, Fortinsky RH, Kuchel GA, Melzer D (2020). Low Vitamin D Levels and Risk of Incident Delirium in 351,000 Older <scp>UK</scp> Biobank Participants.
Journal of the American Geriatrics Society,
69(2), 365-372.
Abstract:
Low Vitamin D Levels and Risk of Incident Delirium in 351,000 Older UK Biobank Participants
BACKGROUND/OBJECTIVESDelirium is common in older adults, especially following hospitalization. Because low vitamin D levels may be associated with increased delirium risk, we aimed to determine the prognostic value of blood vitamin D levels, extending our previous genetic analyses of this relationship.DESIGNProspective cohort analysis.SETTINGCommunity‐based cohort study of adults from 22 cities across the United Kingdom (the UK Biobank).PARTICIPANTSAdults aged 60 and older by the end of follow‐up in the linked hospital inpatient admissions data, up to 14 years after baseline (n = 351,320).MEASUREMENTSAt baseline, serum vitamin D (25‐OH‐D) levels were measured. We used time‐to‐event models to estimate hazard ratios (HRs) and 95% confidence intervals (CIs) for the association between vitamin D deficiency and incident hospital‐diagnosed delirium, adjusted for age, sex, assessment month, assessment center, and ethnicity. We performed Mendelian randomization genetic analysis in European participants to further investigate vitamin D and delirium risk.RESULTSA total of 3,634 (1.03%) participants had at least one incident hospital‐diagnosed delirium episode. Vitamin D deficiency (<25 nmol/L) predicted a large incidence in delirium (HR = 2.49; 95% CI = 2.24–2.76; P = 3*10−68, compared with >50 nmol/L). Increased risk was not limited to the deficient group: insufficient levels (25–50 nmol/L) were also at increased risk (HR = 1.38; 95% CI = 1.28–1.49; P = 4*10−18). The association was independent of calcium levels, hospital‐diagnosed fractures, dementia, and other relevant cofactors. In genetic analysis, participants carrying more vitamin D–increasing variants had a reduced likelihood of incident delirium diagnosis (HR =. 80 per standard deviation increase in genetically instrumented vitamin D:. 73–.87; P = 2*10−7).CONCLUSIONProgressively lower vitamin D levels predicted increased risks of incident hospital‐diagnosed delirium, and genetic evidence supports a shared causal pathway. Because low vitamin D levels are simple to detect and inexpensive and safe to correct, an intervention trial to confirm these results is urgently needed.
Abstract.
Sanderson E, Spiller W, Bowden J (2020). Testing and Correcting for Weak and Pleiotropic Instruments in Two-Sample Multivariable Mendelian Randomisation.
Abstract:
Testing and Correcting for Weak and Pleiotropic Instruments in Two-Sample Multivariable Mendelian Randomisation
AbstractMultivariable Mendelian Randomisation (MVMR) is a form of instrumental variable analysis which estimates the direct effect of multiple exposures on an outcome using genetic variants as instruments. Mendelian Randomisation and MVMR are frequently conducted using two-sample summary data where the association of the genetic variants with the exposures and outcome are obtained from separate samples. If the genetic variants are only weakly associated with the exposures either individually or conditionally, given the other exposures in the model, then standard inverse variance weighting will yield biased estimates for the effect of each exposure. Here we develop a two-sample conditional F-statistic to test whether the genetic variants strongly predict each exposure conditional on the other exposures included in a MVMR model. We show formally that this test is equivalent to the individual level data conditional F-statistic, indicating that conventional rule-of-thumb critical values of F > 10, can be used to test for weak instruments. We then demonstrate how reliable estimates of the causal effect of each exposure on the outcome can be obtained in the presence of weak instruments and pleiotropy, by re-purpousing a commonly used heterogeneity Q-statistic as an estimating equation. Furthermore, the minimised value of this Q-statistic yields an exact test for heterogeneity due to pleiotropy. We illustrate our methods with an application to estimate the causal effect of blood lipid fractions on age related macular degeneration.
Abstract.
Hartwig FP, Davey Smith G, Schmidt AF, Sterne JAC, Higgins JPT, Bowden J (2020). The median and the mode as robust meta‐analysis estimators in the presence of small‐study effects and outliers.
Research Synthesis Methods,
11(3), 397-412.
Abstract:
The median and the mode as robust meta‐analysis estimators in the presence of small‐study effects and outliers
Meta‐analyses based on systematic literature reviews are commonly used to obtain a quantitative summary of the available evidence on a given topic. However, the reliability of any meta‐analysis is constrained by that of its constituent studies. One major limitation is the possibility of small‐study effects, when estimates from smaller and larger studies differ systematically. Small‐study effects may result from reporting biases (ie, publication bias), from inadequacies of the included studies that are related to study size, or from reasons unrelated to bias. We propose two estimators based on the median and mode to increase the reliability of findings in a meta‐analysis by mitigating the influence of small‐study effects. By re‐examining data from published meta‐analyses and by conducting a simulation study, we show that these estimators offer robustness to a range of plausible bias mechanisms, without making explicit modelling assumptions. They are also robust to outlying studies without explicitly removing such studies from the analysis. When meta‐analyses are suspected to be at risk of bias because of small‐study effects, we recommend reporting the mean, median and modal pooled estimates.
Abstract.
Langan D, Higgins JPT, Jackson D, Bowden J, Veroniki AA, Kontopantelis E, Viechtbauer W, Simmonds M (2019). A comparison of heterogeneity variance estimators in simulated random-effects meta-analyses.
Res Synth Methods,
10(1), 83-98.
Abstract:
A comparison of heterogeneity variance estimators in simulated random-effects meta-analyses.
Studies combined in a meta-analysis often have differences in their design and conduct that can lead to heterogeneous results. A random-effects model accounts for these differences in the underlying study effects, which includes a heterogeneity variance parameter. The DerSimonian-Laird method is often used to estimate the heterogeneity variance, but simulation studies have found the method can be biased and other methods are available. This paper compares the properties of nine different heterogeneity variance estimators using simulated meta-analysis data. Simulated scenarios include studies of equal size and of moderate and large differences in size. Results confirm that the DerSimonian-Laird estimator is negatively biased in scenarios with small studies and in scenarios with a rare binary outcome. Results also show the Paule-Mandel method has considerable positive bias in meta-analyses with large differences in study size. We recommend the method of restricted maximum likelihood (REML) to estimate the heterogeneity variance over other methods. However, considering that meta-analyses of health studies typically contain few studies, the heterogeneity variance estimate should not be used as a reliable gauge for the extent of heterogeneity in a meta-analysis. The estimated summary effect of the meta-analysis and its confidence interval derived from the Hartung-Knapp-Sidik-Jonkman method are more robust to changes in the heterogeneity variance estimate and show minimal deviation from the nominal coverage of 95% under most of our simulated scenarios.
Abstract.
Author URL.
Sanderson E, Davey Smith G, Windmeijer F, Bowden J (2019). An examination of multivariable Mendelian randomization in the single-sample and two-sample summary data settings.
Int J Epidemiol,
48(3), 713-727.
Abstract:
An examination of multivariable Mendelian randomization in the single-sample and two-sample summary data settings.
BACKGROUND: Mendelian randomization (MR) is a powerful tool in epidemiology that can be used to estimate the causal effect of an exposure on an outcome in the presence of unobserved confounding, by utilizing genetic variants that are instrumental variables (IVs) for the exposure. This has been extended to multivariable MR (MVMR) to estimate the effect of two or more exposures on an outcome. METHODS AND RESULTS: We use simulations and theory to clarify the interpretation of estimated effects in a MVMR analysis under a range of underlying scenarios, where a secondary exposure acts variously as a confounder, a mediator, a pleiotropic pathway and a collider. We then describe how instrument strength and validity can be assessed for an MVMR analysis in the single-sample setting, and develop tests to assess these assumptions in the popular two-sample summary data setting. We illustrate our methods using data from UK Biobank to estimate the effect of education and cognitive ability on body mass index. CONCLUSION: MVMR analysis consistently estimates the direct causal effect of an exposure, or exposures, of interest and provides a powerful tool for determining causal effects in a wide range of scenarios with either individual- or summary-level data.
Abstract.
Author URL.
Lane JM, Jones SE, Dashti HS, Wood AR, Aragam KG, van Hees VT, Strand LB, Winsvold BS, Wang H, Bowden J, et al (2019). Biological and clinical insights from genetics of insomnia symptoms.
Nature GeneticsAbstract:
Biological and clinical insights from genetics of insomnia symptoms
Insomnia is a common disorder linked with adverse long-term medical and psychiatric outcomes. The underlying pathophysiological processes and causal relationships of insomnia with disease are poorly understood. Here we identify 57 loci for self-reported insomnia symptoms in the UK Biobank (n = 453,379) and confirm their impact on self-reported insomnia symptoms in the HUNT study (n = 14,923 cases, 47,610 controls), physician-diagnosed insomnia in Partners Biobank (n = 2,217 cases, 14,240 controls), and accelerometer-derived measures of sleep efficiency and sleep duration in the UK Biobank (n = 83,726). Our results suggest enrichment of genes involved in ubiquitin-mediated proteolysis and of genes expressed in multiple brain regions, skeletal muscle, and adrenal gland. Evidence of shared genetic factors is found between frequent insomnia symptoms and restless legs syndrome, aging, cardio-metabolic, behavioral, psychiatric and reproductive traits. Evidence is found for a possible causal link between insomnia symptoms and coronary artery disease, depressive symptoms and subjective well-being.
Abstract.
Spiller W, Slichter D, Bowden J, Davey Smith G (2019). Detecting and correcting for bias in Mendelian randomization analyses using Gene-by-Environment interactions.
Int J Epidemiol,
48(3), 702-712.
Abstract:
Detecting and correcting for bias in Mendelian randomization analyses using Gene-by-Environment interactions.
BACKGROUND: Mendelian randomization (MR) has developed into an established method for strengthening causal inference and estimating causal effects, largely due to the proliferation of genome-wide association studies. However, genetic instruments remain controversial, as horizontal pleiotropic effects can introduce bias into causal estimates. Recent work has highlighted the potential of gene-environment interactions in detecting and correcting for pleiotropic bias in MR analyses. METHODS: We introduce MR using Gene-by-Environment interactions (MRGxE) as a framework capable of identifying and correcting for pleiotropic bias. If an instrument-covariate interaction induces variation in the association between a genetic instrument and exposure, it is possible to identify and correct for pleiotropic effects. The interpretation of MRGxE is similar to conventional summary MR approaches, with a particular advantage of MRGxE being the ability to assess the validity of an individual instrument. RESULTS: We investigate the effect of adiposity, measured using body mass index (BMI), upon systolic blood pressure (SBP) using data from the UK Biobank and a single weighted allelic score informed by data from the GIANT consortium. We find MRGxE produces findings in agreement with two-sample summary MR approaches. Further, we perform simulations highlighting the utility of the approach even when the MRGxE assumptions are violated. CONCLUSIONS: By utilizing instrument-covariate interactions in MR analyses implemented within a linear-regression framework, it is possible to identify and correct for horizontal pleiotropic bias, provided the average magnitude of pleiotropy is constant across interaction-covariate subgroups.
Abstract.
Author URL.
Jones SE, Lane JM, Wood AR, van Hees VT, Tyrrell J, Beaumont RN, Jeffries AR, Dashti HS, Hillsdon M, Ruth KS, et al (2019). Genome-wide association analyses of chronotype in 697,828 individuals provides insights into circadian rhythms.
Nature CommunicationsAbstract:
Genome-wide association analyses of chronotype in 697,828 individuals provides insights into circadian rhythms
Using genome-wide data from 697,828 UK Biobank and 23andMe participants, we increase the number of identified loci associated with being a morning person, a behavioural indicator of a person’s underlying circadian rhythm, from 24 to 351. Using data from 85,760 individuals with activity-monitor derived measures of sleep timing we demonstrate that the chronotype loci influence sleep timing: the mean sleep timing of the 5% of individuals carrying the most morningness alleles is 25 minutes earlier than the 5% carrying the fewest. The loci are enriched for genes involved in circadian regulation, cAMP, glutamate and insulin signalling pathways, and those expressed in the retina, hindbrain, hypothalamus, and pituitary. Using Mendelian Randomisation, we show that being a morning person is causally associated with better mental health but does not affect BMI or risk of Type 2 diabetes. This study offers insights into circadian biology and its links to disease in humans.
Abstract.
Wang H, Lane JM, Jones SE, Dashti HS, Ollila HM, Wood AR, van Hees VT, Brumpton B, Winsvold BS, Kantojärvi K, et al (2019). Genome-wide association analysis of self-reported daytime sleepiness identifies 42 loci that suggest biological subtypes.
Nature Communications,
10(1).
Abstract:
Genome-wide association analysis of self-reported daytime sleepiness identifies 42 loci that suggest biological subtypes
Excessive daytime sleepiness (EDS) affects 10–20% of the population and is associated with substantial functional deficits. Here, we identify 42 loci for self-reported daytime sleepiness in GWAS of 452,071 individuals from the UK Biobank, with enrichment for genes expressed in brain tissues and in neuronal transmission pathways. We confirm the aggregate effect of a genetic risk score of 42 SNPs on daytime sleepiness in independent Scandinavian cohorts and on other sleep disorders (restless legs syndrome, insomnia) and sleep traits (duration, chronotype, accelerometer-derived sleep efficiency and daytime naps or inactivity). However, individual daytime sleepiness signals vary in their associations with objective short vs long sleep, and with markers of sleep continuity. The 42 sleepiness variants primarily cluster into two predominant composite biological subtypes - sleep propensity and sleep fragmentation. Shared genetic links are also seen with obesity, coronary heart disease, psychiatric diseases, cognitive traits and reproductive ageing.
Abstract.
Dashti HS, Jones SE, Wood AR, Lane JM, van Hees VT, Wang H, Rhodes JA, Song Y, Patel K, Anderson SG, et al (2019). Genome-wide association study identifies genetic loci for self-reported habitual sleep duration supported by accelerometer-derived estimates.
Nat Commun,
10(1).
Abstract:
Genome-wide association study identifies genetic loci for self-reported habitual sleep duration supported by accelerometer-derived estimates.
Sleep is an essential state of decreased activity and alertness but molecular factors regulating sleep duration remain unknown. Through genome-wide association analysis in 446,118 adults of European ancestry from the UK Biobank, we identify 78 loci for self-reported habitual sleep duration (p
Abstract.
Author URL.
Bowden J, Del Greco M F, Minelli C, Zhao Q, Lawlor DA, Sheehan NA, Thompson J, Davey Smith G (2019). Improving the accuracy of two-sample summary-data Mendelian randomization: moving beyond the NOME assumption.
Int J Epidemiol,
48(3), 728-742.
Abstract:
Improving the accuracy of two-sample summary-data Mendelian randomization: moving beyond the NOME assumption.
BACKGROUND: Two-sample summary-data Mendelian randomization (MR) incorporating multiple genetic variants within a meta-analysis framework is a popular technique for assessing causality in epidemiology. If all genetic variants satisfy the instrumental variable (IV) and necessary modelling assumptions, then their individual ratio estimates of causal effect should be homogeneous. Observed heterogeneity signals that one or more of these assumptions could have been violated. METHODS: Causal estimation and heterogeneity assessment in MR require an approximation for the variance, or equivalently the inverse-variance weight, of each ratio estimate. We show that the most popular 'first-order' weights can lead to an inflation in the chances of detecting heterogeneity when in fact it is not present. Conversely, ostensibly more accurate 'second-order' weights can dramatically increase the chances of failing to detect heterogeneity when it is truly present. We derive modified weights to mitigate both of these adverse effects. RESULTS: Using Monte Carlo simulations, we show that the modified weights outperform first- and second-order weights in terms of heterogeneity quantification. Modified weights are also shown to remove the phenomenon of regression dilution bias in MR estimates obtained from weak instruments, unlike those obtained using first- and second-order weights. However, with small numbers of weak instruments, this comes at the cost of a reduction in estimate precision and power to detect a causal effect compared with first-order weighting. Moreover, first-order weights always furnish unbiased estimates and preserve the type I error rate under the causal null. We illustrate the utility of the new method using data from a recent two-sample summary-data MR analysis to assess the causal role of systolic blood pressure on coronary heart disease risk. CONCLUSIONS: We propose the use of modified weights within two-sample summary-data MR studies for accurately quantifying heterogeneity and detecting outliers in the presence of weak instruments. Modified weights also have an important role to play in terms of causal estimation (in tandem with first-order weights) but further research is required to understand their strengths and weaknesses in specific settings.
Abstract.
Author URL.
Sanderson E, Davey Smith G, Bowden J, Munafò MR (2019). Mendelian randomisation analysis of the effect of educational attainment and cognitive ability on smoking behaviour.
Nat Commun,
10(1).
Abstract:
Mendelian randomisation analysis of the effect of educational attainment and cognitive ability on smoking behaviour.
Recent analyses have shown educational attainment to be associated with a number of health outcomes. This association may, in part, be due to an effect of educational attainment on smoking behaviour. In this study, we apply a multivariable Mendelian randomisation design to determine whether the effect of educational attainment on smoking behaviour is due to educational attainment or general cognitive ability. We use individual data from the UK Biobank study (N = 120,050) and summary data from large GWA studies of educational attainment, cognitive ability and smoking behaviour. Our results show that more years of education are associated with a reduced likelihood of smoking that is not due to an effect of general cognitive ability on smoking behaviour. Given the considerable physical harms associated with smoking, the effect of educational attainment on smoking is likely to contribute to the health inequalities associated with differences in educational attainment.
Abstract.
Author URL.
Ward-Caviness CK, de Vries PS, Wiggins KL, Huffman JE, Yanek LR, Bielak LF, Giulianini F, Guo X, Kleber ME, Kacprowski T, et al (2019). Mendelian randomization evaluation of causal effects of fibrinogen on incident coronary heart disease.
PLoS One,
14(5).
Abstract:
Mendelian randomization evaluation of causal effects of fibrinogen on incident coronary heart disease.
BACKGROUND: Fibrinogen is an essential hemostatic factor and cardiovascular disease risk factor. Early attempts at evaluating the causal effect of fibrinogen on coronary heart disease (CHD) and myocardial infraction (MI) using Mendelian randomization (MR) used single variant approaches, and did not take advantage of recent genome-wide association studies (GWAS) or multi-variant, pleiotropy robust MR methodologies. METHODS AND FINDINGS: We evaluated evidence for a causal effect of fibrinogen on both CHD and MI using MR. We used both an allele score approach and pleiotropy robust MR models. The allele score was composed of 38 fibrinogen-associated variants from recent GWAS. Initial analyses using the allele score used a meta-analysis of 11 European-ancestry prospective cohorts, free of CHD and MI at baseline, to examine incidence CHD and MI. We also applied 2 sample MR methods with data from a prevalent CHD and MI GWAS. Results are given in terms of the hazard ratio (HR) or odds ratio (OR), depending on the study design, and associated 95% confidence interval (CI). In single variant analyses no causal effect of fibrinogen on CHD or MI was observed. In multi-variant analyses using incidence CHD cases and the allele score approach, the estimated causal effect (HR) of a 1 g/L higher fibrinogen concentration was 1.62 (CI = 1.12, 2.36) when using incident cases and the allele score approach. In 2 sample MR analyses that accounted for pleiotropy, the causal estimate (OR) was reduced to 1.18 (CI = 0.98, 1.42) and 1.09 (CI = 0.89, 1.33) in the 2 most precise (smallest CI) models, out of 4 models evaluated. In the 2 sample MR analyses for MI, there was only very weak evidence of a causal effect in only 1 out of 4 models. CONCLUSIONS: a small causal effect of fibrinogen on CHD is observed using multi-variant MR approaches which account for pleiotropy, but not single variant MR approaches. Taken together, results indicate that even with large sample sizes and multi-variant approaches MR analyses still cannot exclude the null when estimating the causal effect of fibrinogen on CHD, but that any potential causal effect is likely to be much smaller than observed in epidemiological studies.
Abstract.
Author URL.
Bowden J, Holmes MV (2019). Meta-analysis and Mendelian randomization: a review.
Res Synth Methods,
10(4), 486-496.
Abstract:
Meta-analysis and Mendelian randomization: a review.
Mendelian randomization (MR) uses genetic variants as instrumental variables to infer whether a risk factor causally affects a health outcome. Meta-analysis has been used historically in MR to combine results from separate epidemiological studies, with each study using a small but select group of genetic variants. In recent years, it has been used to combine genome-wide association study (GWAS) summary data for large numbers of genetic variants. Heterogeneity among the causal estimates obtained from multiple genetic variants points to a possible violation of the necessary instrumental variable assumptions. In this article, we provide a basic introduction to MR and the instrumental variable theory that it relies upon. We then describe how random effects models, meta-regression, and robust regression are being used to test and adjust for heterogeneity in order to improve the rigor of the MR approach.
Abstract.
Author URL.
Wright KM, Dono J, Brownbill AL, Pearson Nee Gibson O, Bowden J, Wycherley TP, Keech W, O'Dea K, Roder D, Avery JC, et al (2019). Sugar-sweetened beverage (SSB) consumption, correlates and interventions among Australian Aboriginal and Torres Strait Islander communities: a scoping review.
BMJ Open,
9(2).
Abstract:
Sugar-sweetened beverage (SSB) consumption, correlates and interventions among Australian Aboriginal and Torres Strait Islander communities: a scoping review.
OBJECTIVES: Sugar-sweetened beverage (SSB) consumption in Australian Aboriginal and Torres Strait Islander people is reported to be disproportionally high compared with the general Australian population. This review aimed to scope the literature documenting SSB consumption and interventions to reduce SSB consumption among Australian Aboriginal and Torres Strait Islander people. Findings will inform strategies to address SSB consumption in Aboriginal and Torres Strait Islander communities. METHODS: PubMed, SCOPUS, CINAHL, Informit, Joanna Briggs Institute EBP, Mura databases and grey literature were searched for articles published between January 1980 and June 2018. Studies were included if providing data specific to an Australian Aboriginal and/or Torres Strait Islander population's SSB consumption or an intervention that focused on reducing SSB consumption in this population. DESIGN: Systematic scoping review. RESULTS: 59 articles were included (1846 screened). While reported SSB consumption was high, there were age-related and community-related differences observed in some studies. Most studies were conducted in remote or rural settings. Implementation of nutrition interventions that included an SSB component has built progressively in remote communities since the 1980s with a growing focus on community-driven, culturally sensitive approaches. More recent studies have focused exclusively on SSB consumption. Key SSB-related intervention elements included incentivising healthier options; reducing availability of less-healthy options; nutrition education; multifaceted or policy implementation (store nutrition or government policy). CONCLUSIONS: There was a relatively large number of studies reporting data on SSB consumption and/or sales, predominantly from remote and rural settings. During analysis it was subjectively clear that the more impactful studies were those which were community driven or involved extensive community consultation and collaboration. Extracting additional SSB-specific consumption data from an existing nationally representative survey of Aboriginal and Torres Strait Islander people could provide detailed information for demographic subgroups and benchmarks for future interventions. It is recommended that a consistent, culturally appropriate, set of consumption measures be developed.
Abstract.
Author URL.
Jenkins DA, Bowden J, Robinson HA, Sattar N, Loos RJF, Rutter MK, Sperrin M (2018). Adiposity-Mortality Relationships in Type 2 Diabetes, Coronary Heart Disease, and Cancer Subgroups in the UK Biobank, and Their Modification by Smoking.
Diabetes Care,
41(9), 1878-1886.
Abstract:
Adiposity-Mortality Relationships in Type 2 Diabetes, Coronary Heart Disease, and Cancer Subgroups in the UK Biobank, and Their Modification by Smoking.
OBJECTIVE: the obesity paradox in which overweight/obesity is associated with mortality benefits is believed to be explained by confounding and reverse causality rather than by a genuine clinical benefit of excess body weight. We aimed to gain deeper insights into the paradox through analyzing mortality relationships with several adiposity measures; assessing subgroups with type 2 diabetes, with coronary heart disease (CHD), with cancer, and by smoking status; and adjusting for several confounders. RESEARCH DESIGN AND METHODS: We studied the general UK Biobank population (N = 502,631) along with three subgroups of people with type 2 diabetes (n = 23,842), CHD (n = 24,268), and cancer (n = 45,790) at baseline. A range of adiposity exposures were considered, including BMI (continuous and categorical), waist circumference, body fat percentage, and waist-to-hip ratio, and the outcome was all-cause mortality. We used Cox regression models adjusted for age, smoking status, deprivation index, education, and disease history. RESULTS: for BMI, the obesity paradox was observed among people with type 2 diabetes (adjusted hazard ratio for obese vs. normal BMI 0.78 [95% CI 0.65, 0.95]) but not among those with CHD (1.00 [0.86, 1.17]). The obesity paradox was pronounced in current smokers, absent in never smokers, and more pronounced in men than in women. For other adiposity measures, there was less evidence for an obesity paradox, yet smoking status consistently modified the adiposity-mortality relationship. CONCLUSIONS: the obesity paradox was observed in people with type 2 diabetes and is heavily modified by smoking status. The results of subgroup analyses and statistical adjustments are consistent with reverse causality and confounding.
Abstract.
Author URL.
Gill D, Brewer CF, Del Greco M F, Sivakumaran P, Bowden J, Sheehan NA, Minelli C (2018). Age at menarche and adult body mass index: a Mendelian randomization study.
Int J Obes (Lond),
42(9), 1574-1581.
Abstract:
Age at menarche and adult body mass index: a Mendelian randomization study.
BACKGROUND: Pubertal timing has psychological and physical sequelae. While observational studies have demonstrated an association between age at menarche and adult body mass index (BMI), confounding makes it difficult to infer causality. METHODS: the Mendelian randomization (MR) technique is not limited by traditional confounding and was used to investigate the presence of a causal effect of age at menarche on adult BMI. MR uses genetic variants as instruments under the assumption that they act on BMI only through age at menarche (no pleiotropy). Using a two-sample MR approach, heterogeneity between the MR estimates from individual instruments was used as a proxy for pleiotropy, with sensitivity analyses performed if detected. Genetic instruments and estimates of their association with age at menarche were obtained from a genome-wide association meta-analysis on 182,416 women. The genetic effects on adult BMI were estimated using data on 80,465 women from the UK Biobank. The presence of a causal effect of age at menarche on adult BMI was further investigated using data on 70,692 women from the GIANT Consortium. RESULTS: There was evidence of pleiotropy among instruments. Using the UK Biobank data, after removing instruments associated with childhood BMI that were likely exerting pleiotropy, fixed-effect meta-analysis across instruments demonstrated that a 1 year increase in age at menarche reduces adult BMI by 0.38 kg/m2 (95% CI 0.25-0.51 kg/m2). However, evidence of pleiotropy remained. MR-Egger regression did not suggest directional bias, and similar estimates to the fixed-effect meta-analysis were obtained in sensitivity analyses when using a random-effect model, multivariable MR, MR-Egger regression, a weighted median estimator and a weighted mode-based estimator. The direction and significance of the causal effect were replicated using GIANT Consortium data. CONCLUSION: MR provides evidence to support the hypothesis that earlier age at menarche causes higher adult BMI. Complex hormonal and psychological factors may be responsible.
Abstract.
Author URL.
Minelli C, van der Plaat DA, Leynaert B, Granell R, Amaral AFS, Pereira M, Mahmoud O, Potts J, Sheehan NA, Bowden J, et al (2018). Age at puberty and risk of asthma: a Mendelian randomisation study.
PLoS Med,
15(8).
Abstract:
Age at puberty and risk of asthma: a Mendelian randomisation study.
BACKGROUND: Observational studies on pubertal timing and asthma, mainly performed in females, have provided conflicting results about a possible association of early puberty with higher risk of adult asthma, possibly due to residual confounding. To overcome issues of confounding, we used Mendelian randomisation (MR), i.e. genetic variants were used as instrumental variables to estimate causal effects of early puberty on post-pubertal asthma in both females and males. METHODS AND FINDINGS: MR analyses were performed in UK Biobank on 243,316 women using 254 genetic variants for age at menarche, and on 192,067 men using 46 variants for age at voice breaking. Age at menarche, recorded in years, was categorised as early (14); age at voice breaking was recorded and analysed as early (younger than average), normal (about average age), or late (older than average). In females, we found evidence for a causal effect of pubertal timing on asthma, with an 8% increase in asthma risk for early menarche (odds ratio [OR] 1.08; 95% CI 1.04 to 1.12; p = 8.7 × 10(-5)) and an 8% decrease for late menarche (OR 0.92; 95% CI 0.89 to 0.97; p = 3.4 × 10(-4)), suggesting a continuous protective effect of increasing age at puberty. In males, we found very similar estimates of causal effects, although with wider confidence intervals (early voice breaking: OR 1.07; 95% CI 1.00 to 1.16; p = 0.06; late voice breaking: OR 0.93; 95% CI 0.87 to 0.99; p = 0.03). We detected only modest pleiotropy, and our findings showed robustness when different methods to account for pleiotropy were applied. BMI may either introduce pleiotropy or lie on the causal pathway; secondary analyses excluding variants associated with BMI yielded similar results to those of the main analyses. Our study relies on self-reported exposures and outcomes, which may have particularly affected the power of the analyses on age at voice breaking. CONCLUSIONS: This large MR study provides evidence for a causal detrimental effect of early puberty on asthma, and does not support previous observational findings of a U-shaped relationship between pubertal timing and asthma. Common biological or psychological mechanisms associated with early puberty might explain the similarity of our results in females and males, but further research is needed to investigate this. Taken together with evidence for other detrimental effects of early puberty on health, our study emphasises the need to further investigate and address the causes of the secular shift towards earlier puberty observed worldwide.
Abstract.
Author URL.
Trajanoska K, Morris JA, Oei L, Zheng HF, Evans DM, Kiel DP, Ohlsson C, Richards JB, Rivadeneira F, Forgett V, et al (2018). Assessment of the genetic and clinical determinants of fracture risk: Genome wide association and mendelian randomisation study.
The BMJ,
362Abstract:
Assessment of the genetic and clinical determinants of fracture risk: Genome wide association and mendelian randomisation study
Objectives to identify the genetic determinants of fracture risk and assess the role of 15 clinical risk factors on osteoporotic fracture risk. Design Meta-analysis of genome wide association studies (GWAS) and a two-sample mendelian randomisation approach. Setting 25 cohorts from Europe, United States, east Asia, and Australia with genome wide genotyping and fracture data. Participants a discovery set of 37 857 fracture cases and 227 116 controls; with replication in up to 147 200 fracture cases and 150 085 controls. Fracture cases were defined as individuals (>18 years old) who had fractures at any skeletal site confirmed by medical, radiological, or questionnaire reports. Instrumental variable analyses were performed to estimate effects of 15 selected clinical risk factors for fracture in a two-sample mendelian randomisation framework, using the largest previously published GWAS meta-analysis of each risk factor. Results of 15 fracture associated loci identified, all were also associated with bone mineral density and mapped to genes clustering in pathways known to be critical to bone biology (eg, SOST, WNT16, and ESR1) or novel pathways (FAM210A, GRB10, and ETS2). Mendelian randomisation analyses showed a clear effect of bone mineral density on fracture risk. One standard deviation decrease in genetically determined bone mineral density of the femoral neck was associated with a 55% increase in fracture risk (odds ratio 1.55 (95% confidence interval 1.48 to 1.63; P=1.5×10'68). Hand grip strength was inversely associated with fracture risk, but this result was not significant after multiple testing correction. The remaining clinical risk factors (including vitamin D levels) showed no evidence for an effect on fracture. Conclusions This large scale GWAS meta-analysis for fracture identified 15 genetic determinants of fracture, all of which also influenced bone mineral density. Among the clinical risk factors for fracture assessed, only bone mineral density showed a major causal effect on fracture. Genetic predisposition to lower levels of vitamin D and estimated calcium intake from dairy sources were not associated with fracture risk.
Abstract.
Hemani G, Bowden J, Davey Smith G (2018). Evaluating the potential role of pleiotropy in Mendelian randomization studies.
Hum Mol Genet,
27(R2), R195-R208.
Abstract:
Evaluating the potential role of pleiotropy in Mendelian randomization studies.
Pleiotropy, the phenomenon of a single genetic variant influencing multiple traits, is likely widespread in the human genome. If pleiotropy arises because the single nucleotide polymorphism (SNP) influences one trait, which in turn influences another ('vertical pleiotropy'), then Mendelian randomization (MR) can be used to estimate the causal influence between the traits. of prime focus among the many limitations to MR is the unprovable assumption that apparent pleiotropic associations are mediated by the exposure (i.e. reflect vertical pleiotropy), and do not arise due to SNPs influencing the two traits through independent pathways ('horizontal pleiotropy'). The burgeoning treasure trove of genetic associations yielded through genome wide association studies makes for a tantalizing prospect of phenome-wide causal inference. Recent years have seen substantial attention devoted to the problem of horizontal pleiotropy, and in this review we outline how newly developed methods can be used together to improve the reliability of MR.
Abstract.
Author URL.
Bowden J, Spiller W, Del Greco M F, Sheehan N, Thompson J, Minelli C, Davey Smith G (2018). Improving the visualization, interpretation and analysis of two-sample summary data Mendelian randomization via the Radial plot and Radial regression.
Int J Epidemiol,
47(6).
Author URL.
Bowden J, Spiller W, Del Greco M F, Sheehan N, Thompson J, Minelli C, Davey Smith G (2018). Improving the visualization, interpretation and analysis of two-sample summary data Mendelian randomization via the Radial plot and Radial regression.
Int J Epidemiol,
47(4), 1264-1278.
Abstract:
Improving the visualization, interpretation and analysis of two-sample summary data Mendelian randomization via the Radial plot and Radial regression.
BACKGROUND: data furnishing a two-sample Mendelian randomization (MR) study are often visualized with the aid of a scatter plot, in which single-nucleotide polymorphism (SNP)-outcome associations are plotted against the SNP-exposure associations to provide an immediate picture of the causal-effect estimate for each individual variant. It is also convenient to overlay the standard inverse-variance weighted (IVW) estimate of causal effect as a fitted slope, to see whether an individual SNP provides evidence that supports, or conflicts with, the overall consensus. Unfortunately, the traditional scatter plot is not the most appropriate means to achieve this aim whenever SNP-outcome associations are estimated with varying degrees of precision and this is reflected in the analysis. METHODS: We propose instead to use a small modification of the scatter plot-the Galbraith Radial plot-for the presentation of data and results from an MR study, which enjoys many advantages over the original method. On a practical level, it removes the need to recode the genetic data and enables a more straightforward detection of outliers and influential data points. Its use extends beyond the purely aesthetic, however, to suggest a more general modelling framework to operate within when conducting an MR study, including a new form of MR-Egger regression. RESULTS: We illustrate the methods using data from a two-sample MR study to probe the causal effect of systolic blood pressure on coronary heart disease risk, allowing for the possible effects of pleiotropy. The Radial plot is shown to aid the detection of a single outlying variant that is responsible for large differences between IVW and MR-Egger regression estimates. Several additional plots are also proposed for informative data visualization. CONCLUSIONS: the Radial plot should be considered in place of the scatter plot for visualizing, analysing and interpreting data from a two-sample summary data MR study. Software is provided to help facilitate its use.
Abstract.
Author URL.
Gage SH, Bowden J, Davey Smith G, Munafò MR (2018). Investigating causality in associations between education and smoking: a two-sample Mendelian randomization study.
Int J Epidemiol,
47(4), 1131-1140.
Abstract:
Investigating causality in associations between education and smoking: a two-sample Mendelian randomization study.
BACKGROUND: Lower educational attainment is associated with increased rates of smoking, but ascertaining causality is challenging. We used two-sample Mendelian randomization (MR) analyses of summary statistics to examine whether educational attainment is causally related to smoking. METHODS AND FINDINGS: We used summary statistics from genome-wide association studies (GWAS) of educational attainment and a range of smoking phenotypes (smoking initiation, cigarettes per day, cotinine levels and smoking cessation). of 74 single nucleotide polymorphisms (SNPs) that predict educational attainment, 57 (or their highly correlated proxies) were present in the smoking initiation, cigarettes per day and smoking cessation GWAS, and 72 in the cotinine GWAS. Various complementary MR techniques (inverse variance weighted regression, MR Egger, weighted median regression) were used to test the robustness of our results. We found broadly consistent evidence across these techniques that higher educational attainment leads to reduced likelihood of smoking initiation, reduced heaviness of smoking among smokers (as measured via self-report [e.g. inverse variance weighted beta -2.25, 95% confidence interval (CI) -3.81, -0.70, P = 0.005] and cotinine levels [e.g. inverse variance weighted beta -0.34, 95% CI -0.67, -0.01, P = 0.057]), and greater likelihood of smoking cessation among smokers (inverse variance weighted beta 0.65, 95% CI 0.35, 0.95, P = 5.54 × 10-5). Less consistent across the different techniques were associations between educational attainment and smoking initiation. CONCLUSIONS: Our findings indicate a causal association between low educational attainment and increased risk of smoking, and may explain the observational associations between educational attainment and adverse health outcomes such as risk of coronary heart disease.
Abstract.
Author URL.
Bowden J, Hemani G, Davey Smith G (2018). Invited Commentary: Detecting Individual and Global Horizontal Pleiotropy in Mendelian Randomization-A Job for the Humble Heterogeneity Statistic?.
Am J Epidemiol,
187(12), 2681-2685.
Abstract:
Invited Commentary: Detecting Individual and Global Horizontal Pleiotropy in Mendelian Randomization-A Job for the Humble Heterogeneity Statistic?
Mendelian randomization (MR) is gaining in recognition and popularity as a method for strengthening causal inference in epidemiology by utilizing genetic variants as instrumental variables. Concurrently with the explosion in empirical MR studies, there has been the steady production of new approaches for MR analysis. The recently proposed "global and individual tests for direct effects" (GLIDE) approach fits into a family of methods that aim to detect horizontal pleiotropy-at the individual single nucleotide polymorphism level and at the global level-and to adjust the analysis by removing outlying single nucleotide polymorphisms. In this commentary, we explain how existing methods can (and indeed are) being used to detect pleiotropy at the individual and global levels, although not explicitly using this terminology. By doing so, we show that the true comparator for GLIDE is not MR-Egger regression (as Dai et al. the authors of the accompanying article (Am J Epidemiol. 2018;187(12):2672-2680), claim) but rather the humble heterogeneity statistic.
Abstract.
Author URL.
Hartwig FP, Borges MC, Bowden J (2018). Mendelian Randomization Concerns-Reply.
JAMA Psychiatry,
75(4), 407-408.
Author URL.
Villar SS, Bowden J, Wason J (2018). Response-adaptive designs for binary responses: How to offer patient benefit while being robust to time trends?.
Pharm Stat,
17(2), 182-197.
Abstract:
Response-adaptive designs for binary responses: How to offer patient benefit while being robust to time trends?
Response-adaptive randomisation (RAR) can considerably improve the chances of a successful treatment outcome for patients in a clinical trial by skewing the allocation probability towards better performing treatments as data accumulates. There is considerable interest in using RAR designs in drug development for rare diseases, where traditional designs are not either feasible or ethically questionable. In this paper, we discuss and address a major criticism levelled at RAR: namely, type I error inflation due to an unknown time trend over the course of the trial. The most common cause of this phenomenon is changes in the characteristics of recruited patients-referred to as patient drift. This is a realistic concern for clinical trials in rare diseases due to their lengthly accrual rate. We compute the type I error inflation as a function of the time trend magnitude to determine in which contexts the problem is most exacerbated. We then assess the ability of different correction methods to preserve type I error in these contexts and their performance in terms of other operating characteristics, including patient benefit and power. We make recommendations as to which correction methods are most suitable in the rare disease context for several RAR rules, differentiating between the 2-armed and the multi-armed case. We further propose a RAR design for multi-armed clinical trials, which is computationally efficient and robust to several time trends considered.
Abstract.
Author URL.
Zhao Q, Wang J, Hemani G, Bowden J, Small DS (2018). Statistical inference in two-sample summary-data Mendelian randomization. using robust adjusted profile score.
Abstract:
Statistical inference in two-sample summary-data Mendelian randomization. using robust adjusted profile score
Mendelian randomization (MR) is a method of exploiting genetic variation to
unbiasedly estimate a causal effect in presence of unmeasured confounding. MR
is being widely used in epidemiology and other related areas of population
science. In this paper, we study statistical inference in the increasingly
popular two-sample summary-data MR design. We show a linear model for the
observed associations approximately holds in a wide variety of settings when
all the genetic variants satisfy the exclusion restriction assumption, or in
genetic terms, when there is no pleiotropy. In this scenario, we derive a
maximum profile likelihood estimator with provable consistency and asymptotic
normality. However, through analyzing real datasets, we find strong evidence of
both systematic and idiosyncratic pleiotropy in MR, echoing the omnigenic model
of complex traits that is recently proposed in genetics. We model the
systematic pleiotropy by a random effects model, where no genetic variant
satisfies the exclusion restriction condition exactly. In this case we propose
a consistent and asymptotically normal estimator by adjusting the profile
score. We then tackle the idiosyncratic pleiotropy by robustifying the adjusted
profile score. We demonstrate the robustness and efficiency of the proposed
methods using several simulated and real datasets.
Abstract.
Author URL.
Hemani G, Zheng J, Elsworth B, Wade KH, Haberland V, Baird D, Laurin C, Burgess S, Bowden J, Langdon R, et al (2018). The MR-Base platform supports systematic causal inference across the human phenome.
Elife,
7Abstract:
The MR-Base platform supports systematic causal inference across the human phenome.
Results from genome-wide association studies (GWAS) can be used to infer causal relationships between phenotypes, using a strategy known as 2-sample Mendelian randomization (2SMR) and bypassing the need for individual-level data. However, 2SMR methods are evolving rapidly and GWAS results are often insufficiently curated, undermining efficient implementation of the approach. We therefore developed MR-Base (http://www.mrbase.org): a platform that integrates a curated database of complete GWAS results (no restrictions according to statistical significance) with an application programming interface, web app and R packages that automate 2SMR. The software includes several sensitivity analyses for assessing the impact of horizontal pleiotropy and other violations of assumptions. The database currently comprises 11 billion single nucleotide polymorphism-trait associations from 1673 GWAS and is updated on a regular basis. Integrating data with software ensures more rigorous application of hypothesis-driven analyses and allows millions of potential causal relationships to be efficiently evaluated in phenome-wide association studies.
Abstract.
Author URL.
Hartwig FP, Smith GD, Schmidt AF, Bowden J (2018). The median and the mode as robust meta-analysis methods in the presence of small study effects.
Abstract:
The median and the mode as robust meta-analysis methods in the presence of small study effects
AbstractMeta-analyses based on systematic literature reviews are commonly used to obtain a quantitative summary of the available evidence on a given topic. Despite its attractive simplicity, and its established position at the summit of the evidence-based medicine hierarchy, the reliability of any meta-analysis is largely constrained by the quality of its constituent studies. One major limitation is small study effects, whose presence can often easily be detected, but not so easily adjusted for. Here, robust methods of estimation based on the median and mode are proposed as tools to increase the reliability of findings in a meta-analysis. By re-examining data from published meta-analyses, and by conducting a detailed simulation study, we show that these two simple methods offer notable robustness to a range of plausible bias mechanisms, without making any explicit modelling assumptions. In conclusion, when performing a meta-analysis with suspected small study effects, we recommend reporting the mean, median and modal pooled estimates as a simple but informative sensitivity analyses.
Abstract.
Schmitz S, Maguire Á, Morris J, Ruggeri K, Haller E, Kuhn I, Leahy J, Homer N, Khan A, Bowden J, et al (2018). The use of single armed observational data to closing the gap in otherwise disconnected evidence networks: a network meta-analysis in multiple myeloma.
BMC Med Res Methodol,
18(1).
Abstract:
The use of single armed observational data to closing the gap in otherwise disconnected evidence networks: a network meta-analysis in multiple myeloma.
BACKGROUND: Network meta-analysis (NMA) allows for the estimation of comparative effectiveness of treatments that have not been studied in head-to-head trials; however, relative treatment effects for all interventions can only be derived where available evidence forms a connected network. Head-to-head evidence is limited in many disease areas, regularly resulting in disconnected evidence structures where a large number of treatments are available. This is also the case in the evidence of treatments for relapsed or refractory multiple myeloma. METHODS: Randomised controlled trials (RCTs) identified in a systematic literature review form two disconnected evidence networks. Standard Bayesian NMA models are fitted to obtain estimates of relative effects within each network. Observational evidence was identified to fill the evidence gap. Single armed trials are matched to act as each other's control group based on a distance metric derived from covariate information. Uncertainty resulting from including this evidence is incorporated by analysing the space of possible matches. RESULTS: Twenty five randomised controlled trials form two disconnected evidence networks; 12 single armed observational studies are considered for bridging between the networks. Five matches are selected to bridge between the networks. While significant variation in the ranking is observed, daratumumab in combination with dexamethasone and either lenalidomide or bortezomib, as well as triple therapy of carfilzomib, ixazomib and elozumatab, in combination with lenalidomide and dexamethasone, show the highest effects on progression free survival, on average. CONCLUSIONS: the analysis shows how observational data can be used to fill gaps in the existing networks of RCT evidence; allowing for the indirect comparison of a large number of treatments, which could not be compared otherwise. Additional uncertainty is accounted for by scenario analyses reducing the risk of over confidence in interpretation of results.
Abstract.
Author URL.
Bowden J, Del Greco M F, Minelli C, Davey Smith G, Sheehan N, Thompson J (2017). A framework for the investigation of pleiotropy in two-sample summary data Mendelian randomization.
Stat Med,
36(11), 1783-1802.
Abstract:
A framework for the investigation of pleiotropy in two-sample summary data Mendelian randomization.
Mendelian randomization (MR) uses genetic data to probe questions of causality in epidemiological research, by invoking the Instrumental Variable (IV) assumptions. In recent years, it has become commonplace to attempt MR analyses by synthesising summary data estimates of genetic association gleaned from large and independent study populations. This is referred to as two-sample summary data MR. Unfortunately, due to the sheer number of variants that can be easily included into summary data MR analyses, it is increasingly likely that some do not meet the IV assumptions due to pleiotropy. There is a pressing need to develop methods that can both detect and correct for pleiotropy, in order to preserve the validity of the MR approach in this context. In this paper, we aim to clarify how established methods of meta-regression and random effects modelling from mainstream meta-analysis are being adapted to perform this task. Specifically, we focus on two contrastin g approaches: the Inverse Variance Weighted (IVW) method which assumes in its simplest form that all genetic variants are valid IVs, and the method of MR-Egger regression that allows all variants to violate the IV assumptions, albeit in a specific way. We investigate the ability of two popular random effects models to provide robustness to pleiotropy under the IVW approach, and propose statistics to quantify the relative goodness-of-fit of the IVW approach over MR-Egger regression. © 2017 the Authors. Statistics in Medicine Published by JohnWiley & Sons Ltd.
Abstract.
Author URL.
Wason J, Stallard N, Bowden J, Jennison C (2017). A multi-stage drop-the-losers design for multi-arm clinical trials.
Stat Methods Med Res,
26(1), 508-524.
Abstract:
A multi-stage drop-the-losers design for multi-arm clinical trials.
Multi-arm multi-stage trials can improve the efficiency of the drug development process when multiple new treatments are available for testing. A group-sequential approach can be used in order to design multi-arm multi-stage trials, using an extension to Dunnett's multiple-testing procedure. The actual sample size used in such a trial is a random variable that has high variability. This can cause problems when applying for funding as the cost will also be generally highly variable. This motivates a type of design that provides the efficiency advantages of a group-sequential multi-arm multi-stage design, but has a fixed sample size. One such design is the two-stage drop-the-losers design, in which a number of experimental treatments, and a control treatment, are assessed at a prescheduled interim analysis. The best-performing experimental treatment and the control treatment then continue to a second stage. In this paper, we discuss extending this design to have more than two stages, which is shown to considerably reduce the sample size required. We also compare the resulting sample size requirements to the sample size distribution of analogous group-sequential multi-arm multi-stage designs. The sample size required for a multi-stage drop-the-losers design is usually higher than, but close to, the median sample size of a group-sequential multi-arm multi-stage trial. In many practical scenarios, the disadvantage of a slight loss in average efficiency would be overcome by the huge advantage of a fixed sample size. We assess the impact of delay between recruitment and assessment as well as unknown variance on the drop-the-losers designs.
Abstract.
Author URL.
Galbraith S, Bowden J, Mander A (2017). Accelerated longitudinal designs: an overview of modelling, power, costs and handling missing data.
Stat Methods Med Res,
26(1), 374-398.
Abstract:
Accelerated longitudinal designs: an overview of modelling, power, costs and handling missing data.
Longitudinal studies are often used to investigate age-related developmental change. Whereas a single cohort design takes a group of individuals at the same initial age and follows them over time, an accelerated longitudinal design takes multiple single cohorts, each one starting at a different age. The main advantage of an accelerated longitudinal design is its ability to span the age range of interest in a shorter period of time than would be possible with a single cohort longitudinal design. This paper considers design issues for accelerated longitudinal studies. A linear mixed effect model is considered to describe the responses over age with random effects for intercept and slope parameters. Random and fixed cohort effects are used to cope with the potential bias accelerated longitudinal designs have due to multiple cohorts. The impact of other factors such as costs and the impact of dropouts on the power of testing or the precision of estimating parameters are examined. As duration-related costs increase relative to recruitment costs the best designs shift towards shorter duration and eventually cross-sectional design being best. For designs with the same duration but differing interval between measurements, we found there was a cutoff point for measurement costs relative to recruitment costs relating to frequency of measurements. Under our model of 30% dropout there was a maximum power loss of 7%.
Abstract.
Author URL.
Gage SH, Jones HJ, Burgess S, Bowden J, Davey Smith G, Zammit S, Munafò MR (2017). Assessing causality in associations between cannabis use and schizophrenia risk: a two-sample Mendelian randomization study.
Psychol Med,
47(5), 971-980.
Abstract:
Assessing causality in associations between cannabis use and schizophrenia risk: a two-sample Mendelian randomization study.
BACKGROUND: Observational associations between cannabis and schizophrenia are well documented, but ascertaining causation is more challenging. We used Mendelian randomization (MR), utilizing publicly available data as a method for ascertaining causation from observational data. METHOD: We performed bi-directional two-sample MR using summary-level genome-wide data from the International Cannabis Consortium (ICC) and the Psychiatric Genomics Consortium (PGC2). Single nucleotide polymorphisms (SNPs) associated with cannabis initiation (p < 10-5) and schizophrenia (p < 5 × 10-8) were combined using an inverse-variance-weighted fixed-effects approach. We also used height and education genome-wide association study data, representing negative and positive control analyses. RESULTS: There was some evidence consistent with a causal effect of cannabis initiation on risk of schizophrenia [odds ratio (OR) 1.04 per doubling odds of cannabis initiation, 95% confidence interval (CI) 1.01-1.07, p = 0.019]. There was strong evidence consistent with a causal effect of schizophrenia risk on likelihood of cannabis initiation (OR 1.10 per doubling of the odds of schizophrenia, 95% CI 1.05-1.14, p = 2.64 × 10-5). Findings were as predicted for the negative control (height: OR 1.00, 95% CI 0.99-1.01, p = 0.90) but weaker than predicted for the positive control (years in education: OR 0.99, 95% CI 0.97-1.00, p = 0.066) analyses. CONCLUSIONS: Our results provide some that cannabis initiation increases the risk of schizophrenia, although the size of the causal estimate is small. We find stronger evidence that schizophrenia risk predicts cannabis initiation, possibly as genetic instruments for schizophrenia are stronger than for cannabis initiation.
Abstract.
Author URL.
Telomeres Mendelian Randomization Collaboration, Haycock PC, Burgess S, Nounu A, Zheng J, Okoli GN, Bowden J, Wade KH, Timpson NJ, Evans DM, et al (2017). Association Between Telomere Length and Risk of Cancer and Non-Neoplastic Diseases: a Mendelian Randomization Study.
JAMA Oncol,
3(5), 636-651.
Abstract:
Association Between Telomere Length and Risk of Cancer and Non-Neoplastic Diseases: a Mendelian Randomization Study.
IMPORTANCE: the causal direction and magnitude of the association between telomere length and incidence of cancer and non-neoplastic diseases is uncertain owing to the susceptibility of observational studies to confounding and reverse causation. OBJECTIVE: to conduct a Mendelian randomization study, using germline genetic variants as instrumental variables, to appraise the causal relevance of telomere length for risk of cancer and non-neoplastic diseases. DATA SOURCES: Genomewide association studies (GWAS) published up to January 15, 2015. STUDY SELECTION: GWAS of noncommunicable diseases that assayed germline genetic variation and did not select cohort or control participants on the basis of preexisting diseases. of 163 GWAS of noncommunicable diseases identified, summary data from 103 were available. DATA EXTRACTION AND SYNTHESIS: Summary association statistics for single nucleotide polymorphisms (SNPs) that are strongly associated with telomere length in the general population. MAIN OUTCOMES AND MEASURES: Odds ratios (ORs) and 95% confidence intervals (CIs) for disease per standard deviation (SD) higher telomere length due to germline genetic variation. RESULTS: Summary data were available for 35 cancers and 48 non-neoplastic diseases, corresponding to 420 081 cases (median cases, 2526 per disease) and 1 093 105 controls (median, 6789 per disease). Increased telomere length due to germline genetic variation was generally associated with increased risk for site-specific cancers. The strongest associations (ORs [95% CIs] per 1-SD change in genetically increased telomere length) were observed for glioma, 5.27 (3.15-8.81); serous low-malignant-potential ovarian cancer, 4.35 (2.39-7.94); lung adenocarcinoma, 3.19 (2.40-4.22); neuroblastoma, 2.98 (1.92-4.62); bladder cancer, 2.19 (1.32-3.66); melanoma, 1.87 (1.55-2.26); testicular cancer, 1.76 (1.02-3.04); kidney cancer, 1.55 (1.08-2.23); and endometrial cancer, 1.31 (1.07-1.61). Associations were stronger for rarer cancers and at tissue sites with lower rates of stem cell division. There was generally little evidence of association between genetically increased telomere length and risk of psychiatric, autoimmune, inflammatory, diabetic, and other non-neoplastic diseases, except for coronary heart disease (OR, 0.78 [95% CI, 0.67-0.90]), abdominal aortic aneurysm (OR, 0.63 [95% CI, 0.49-0.81]), celiac disease (OR, 0.42 [95% CI, 0.28-0.61]) and interstitial lung disease (OR, 0.09 [95% CI, 0.05-0.15]). CONCLUSIONS AND RELEVANCE: it is likely that longer telomeres increase risk for several cancers but reduce risk for some non-neoplastic diseases, including cardiovascular diseases.
Abstract.
Author URL.
Hemani G, Bowden J, Haycock P, Zheng J, Davis O, Flach P, Gaunt T, Smith GD (2017). Automating Mendelian randomization through machine learning to construct a putative causal map of the human phenome.
Abstract:
Automating Mendelian randomization through machine learning to construct a putative causal map of the human phenome
AbstractA major application for genome-wide association studies (GWAS) has been the emerging field of causal inference using Mendelian randomization (MR), where the causal effect between a pair of traits can be estimated using only summary level data. MR depends on SNPs exhibiting vertical pleiotropy, where the SNP influences an outcome phenotype only through an exposure phenotype. Issues arise when this assumption is violated due to SNPs exhibiting horizontal pleiotropy. We demonstrate that across a range of pleiotropy models, instrument selection will be increasingly liable to selecting invalid instruments as GWAS sample sizes continue to grow. Methods have been developed in an attempt to protect MR from different patterns of horizontal pleiotropy, and here we have designed a mixture-of-experts machine learning framework (MR-MoE 1.0) that predicts the most appropriate model to use for any specific causal analysis, improving on both power and false discovery rates. Using the approach, we systematically estimated the causal effects amongst 2407 phenotypes. Almost 90% of causal estimates indicated some level of horizontal pleiotropy. The causal estimates are organised into a publicly available graph database (http://eve.mrbase.org), and we use it here to highlight the numerous challenges that remain in automated causal inference.
Abstract.
Bowden J, Burgess S, Smith GD (2017). Difficulties in Testing the Instrument Strength Independent of Direct Effect Assumption in Mendelian Randomization.
JAMA Cardiol,
2(8), 929-930.
Author URL.
Ware JJ, Tanner J-A, Taylor AE, Bin Z, Haycock P, Bowden J, Rogers PJ, Davey Smith G, Tyndale RF, Munafò MR, et al (2017). Does coffee consumption impact on heaviness of smoking?.
Addiction,
112(10), 1842-1853.
Abstract:
Does coffee consumption impact on heaviness of smoking?
BACKGROUND AND AIMS: Coffee consumption and cigarette smoking are strongly associated, but whether this association is causal remains unclear. We sought to: (1) determine whether coffee consumption influences cigarette smoking causally, (2) estimate the magnitude of any association and (3) explore potential mechanisms. DESIGN: We used Mendelian randomization (MR) analyses of observational data, using publicly available summarized data from the Tobacco and Genetics (TAG) consortium, individual-level data from the UK Biobank and in-vitro experiments of candidate compounds. SETTING: the TAG consortium includes data from studies in several countries. The UK Biobank includes data from men and women recruited across England, Wales and Scotland. PARTICIPANTS: the TAG consortium provided data on n ≤ 38 181 participants. The UK Biobank provided data on 8072 participants. MEASUREMENTS: in MR analyses, the exposure was coffee consumption (cups/day) and the outcome was heaviness of smoking (cigarettes/day). In our in-vitro experiments we assessed the effect of caffeic acid, quercetin and p-coumaric acid on the rate of nicotine metabolism in human liver microsomes and cDNA-expressed human CYP2A6. FINDINGS: Two-sample MR analyses of TAG consortium data indicated that heavier coffee consumption might lead to reduced heaviness of smoking [beta = -1.49, 95% confidence interval (CI) = -2.88 to -0.09]. However, in-vitro experiments found that the compounds investigated are unlikely to inhibit significantly the rate of nicotine metabolism following coffee consumption. Further MR analyses in UK Biobank found no evidence of a causal relationship between coffee consumption and heaviness of smoking (beta = 0.20, 95% CI = -1.72 to 2.12). CONCLUSIONS: Amount of coffee consumption is unlikely to have a major causal impact upon amount of cigarette smoking. If it does influence smoking, this is not likely to operate via effects of caffeic acid, quercetin or p-coumaric acid on nicotine metabolism. The observational association between coffee consumption and cigarette smoking may be due to smoking impacting on coffee consumption or confounding.
Abstract.
Author URL.
Tillmann T, Vaucher J, Okbay A, Pikhart H, Peasey A, Kubinova R, Pajak A, Tamosiunas A, Malyutina S, Hartwig FP, et al (2017). Education and coronary heart disease: mendelian randomisation study.
BMJ,
358Abstract:
Education and coronary heart disease: mendelian randomisation study.
Objective To determine whether educational attainment is a causal risk factor in the development of coronary heart disease.Design Mendelian randomisation study, using genetic data as proxies for education to minimise confounding.Setting The main analysis used genetic data from two large consortia (CARDIoGRAMplusC4D and SSGAC), comprising 112 studies from predominantly high income countries. Findings from mendelian randomisation analyses were then compared against results from traditional observational studies (164 170 participants). Finally, genetic data from six additional consortia were analysed to investigate whether longer education can causally alter the common cardiovascular risk factors.Participants The main analysis was of 543 733 men and women (from CARDIoGRAMplusC4D and SSGAC), predominantly of European origin.Exposure A one standard deviation increase in the genetic predisposition towards higher education (3.6 years of additional schooling), measured by 162 genetic variants that have been previously associated with education.Main outcome measure Combined fatal and non-fatal coronary heart disease (63 746 events in CARDIoGRAMplusC4D).Results Genetic predisposition towards 3.6 years of additional education was associated with a one third lower risk of coronary heart disease (odds ratio 0.67, 95% confidence interval 0.59 to 0.77; P=3×10-8). This was comparable to findings from traditional observational studies (prevalence odds ratio 0.73, 0.68 to 0.78; incidence odds ratio 0.80, 0.76 to 0.83). Sensitivity analyses were consistent with a causal interpretation in which major bias from genetic pleiotropy was unlikely, although this remains an untestable possibility. Genetic predisposition towards longer education was additionally associated with less smoking, lower body mass index, and a favourable blood lipid profile.Conclusions This mendelian randomisation study found support for the hypothesis that low education is a causal risk factor in the development of coronary heart disease. Potential mechanisms could include smoking, body mass index, and blood lipids. In conjunction with the results from studies with other designs, these findings suggest that increasing education may result in substantial health benefits.
Abstract.
Author URL.
Lane JM, Liang J, Vlasac I, Anderson SG, Bechtold DA, Bowden J, Emsley R, Gill S, Little MA, Luik AI, et al (2017). Genome-wide association analyses of sleep disturbance traits identify new loci and highlight shared genetics with neuropsychiatric and metabolic traits.
Nat Genet,
49(2), 274-281.
Abstract:
Genome-wide association analyses of sleep disturbance traits identify new loci and highlight shared genetics with neuropsychiatric and metabolic traits.
Chronic sleep disturbances, associated with cardiometabolic diseases, psychiatric disorders and all-cause mortality, affect 25-30% of adults worldwide. Although environmental factors contribute substantially to self-reported habitual sleep duration and disruption, these traits are heritable and identification of the genes involved should improve understanding of sleep, mechanisms linking sleep to disease and development of new therapies. We report single- and multiple-trait genome-wide association analyses of self-reported sleep duration, insomnia symptoms and excessive daytime sleepiness in the UK Biobank (n = 112,586). We discover loci associated with insomnia symptoms (near MEIS1, TMEM132E, CYCL1 and TGFBI in females and WDR27 in males), excessive daytime sleepiness (near AR-OPHN1) and a composite sleep trait (near PATJ (INADL) and HCRTR2) and replicate a locus associated with sleep duration (at PAX8). We also observe genetic correlation between longer sleep duration and schizophrenia risk (rg = 0.29, P = 1.90 × 10-13) and between increased levels of excessive daytime sleepiness and increased measures for adiposity traits (body mass index (BMI): rg = 0.20, P = 3.12 × 10-9; waist circumference: rg = 0.20, P = 2.12 × 10-7).
Abstract.
Author URL.
Hartwig FP, Borges MC, Horta BL, Bowden J, Davey Smith G (2017). Inflammatory Biomarkers and Risk of Schizophrenia: a 2-Sample Mendelian Randomization Study.
JAMA Psychiatry,
74(12), 1226-1233.
Abstract:
Inflammatory Biomarkers and Risk of Schizophrenia: a 2-Sample Mendelian Randomization Study.
IMPORTANCE: Positive associations between inflammatory biomarkers and risk of psychiatric disorders, including schizophrenia, have been reported in observational studies. However, conventional observational studies are prone to bias, such as reverse causation and residual confounding, thus limiting our understanding of the effect (if any) of inflammatory biomarkers on schizophrenia risk. OBJECTIVE: to evaluate whether inflammatory biomarkers have an effect on the risk of developing schizophrenia. DESIGN, SETTING, AND PARTICIPANTS: Two-sample mendelian randomization study using genetic variants associated with inflammatory biomarkers as instrumental variables to improve inference. Summary association results from large consortia of candidate gene or genome-wide association studies, including several epidemiologic studies with different designs, were used. Gene-inflammatory biomarker associations were estimated in pooled samples ranging from 1645 to more than 80 000 individuals, while gene-schizophrenia associations were estimated in more than 30 000 cases and more than 45 000 ancestry-matched controls. In most studies included in the consortia, participants were of European ancestry, and the prevalence of men was approximately 50%. All studies were conducted in adults, with a wide age range (18 to 80 years). EXPOSURES: Genetically elevated circulating levels of C-reactive protein (CRP), interleukin-1 receptor antagonist (IL-1Ra), and soluble interleukin-6 receptor (sIL-6R). MAIN OUTCOMES AND MEASURES: Risk of developing schizophrenia. Individuals with schizophrenia or schizoaffective disorders were included as cases. Given that many studies contributed to the analyses, different diagnostic procedures were used. RESULTS: the pooled odds ratio estimate using 18 CRP genetic instruments was 0.90 (random effects 95% CI, 0.84-0.97; P = .005) per 2-fold increment in CRP levels; consistent results were obtained using different mendelian randomization methods and a more conservative set of instruments. The odds ratio for sIL-6R was 1.06 (95% CI, 1.01-1.12; P = .02) per 2-fold increment. Estimates for IL-1Ra were inconsistent among instruments, and pooled estimates were imprecise and centered on the null. CONCLUSIONS AND RELEVANCE: Under mendelian randomization assumptions, our findings suggest a protective effect of CRP and a risk-increasing effect of sIL-6R (potentially mediated at least in part by CRP) on schizophrenia risk. It is possible that such effects are a result of increased susceptibility to early life infection.
Abstract.
Author URL.
Richmond RC, Wade KH, Corbin L, Bowden J, Hemani G, Timpson NJ, Davey Smith G (2017). Investigating the role of insulin in increased adiposity: Bi-directional Mendelian randomization study.
Abstract:
Investigating the role of insulin in increased adiposity: Bi-directional Mendelian randomization study
AbstractInsulin may serve as a key causal agent which regulates fat accumulation in the body. Here we assessed the causal relationship between fasting insulin and adiposity using publicly-available results from two large-scale genome-wide association studies for body mass index and fasting insulin levels in a two-sample, bidirectional Mendelian Randomized approach. This approach is only valid on the condition that the two instruments are independent of one another. In analysis excluding overlapping loci, there was an increase of 0.20 (0.17, 0.23) log pmol/L fasting insulin per SD increase in BMI (P= 2.80 x 10−36), while there was a null effect of fasting insulin on BMI, with a 0.01 (−0.39, 0.38) SD decrease in BMI per log pmol/L increase in fasting insulin (P= 0.98). Furthermore, a high degree of heterogeneity in the causal estimates was obtained from the insulin-related variants, which may be attributed to varying mechanisms of action of the insulin-associated variants. Results were largely consistent when an Egger regression technique and weighted median and mode estimators were applied. Findings suggest that the positive correlation between adiposity and fasting insulin levels are at least in part explained by the causal effect of adiposity on increasing insulin, rather than vice versa.
Abstract.
Willems SM, Wright DJ, Day FR, Trajanoska K, Joshi PK, Morris JA, Matteini AM, Garton FC, Grarup N, Oskolkov N, et al (2017). Large-scale GWAS identifies multiple loci for hand grip strength providing biological insights into muscular fitness.
Nature Communications,
8Abstract:
Large-scale GWAS identifies multiple loci for hand grip strength providing biological insights into muscular fitness
Hand grip strength is a widely used proxy of muscular fitness, a marker of frailty, and predictor of a range of morbidities and all-cause mortality. To investigate the genetic determinants of variation in grip strength, we perform a large-scale genetic discovery analysis in a combined sample of 195,180 individuals and identify 16 loci associated with grip strength (P
Abstract.
Thompson JR, Minelli C, Bowden J, Del Greco FM, Gill D, Jones EM, Shapland CY, Sheehan NA (2017). Mendelian randomization incorporating uncertainty about pleiotropy.
Stat Med,
36(29), 4627-4645.
Abstract:
Mendelian randomization incorporating uncertainty about pleiotropy.
Mendelian randomization (MR) requires strong assumptions about the genetic instruments, of which the most difficult to justify relate to pleiotropy. In a two-sample MR, different methods of analysis are available if we are able to assume, M1 : no pleiotropy (fixed effects meta-analysis), M2 : that there may be pleiotropy but that the average pleiotropic effect is zero (random effects meta-analysis), and M3 : that the average pleiotropic effect is nonzero (MR-Egger). In the latter 2 cases, we also require that the size of the pleiotropy is independent of the size of the effect on the exposure. Selecting one of these models without good reason would run the risk of misrepresenting the evidence for causality. The most conservative strategy would be to use M3 in all analyses as this makes the weakest assumptions, but such an analysis gives much less precise estimates and so should be avoided whenever stronger assumptions are credible. We consider the situation of a two-sample design when we are unsure which of these 3 pleiotropy models is appropriate. The analysis is placed within a Bayesian framework and Bayesian model averaging is used. We demonstrate that even large samples of the scale used in genome-wide meta-analysis may be insufficient to distinguish the pleiotropy models based on the data alone. Our simulations show that Bayesian model averaging provides a reasonable trade-off between bias and precision. Bayesian model averaging is recommended whenever there is uncertainty about the nature of the pleiotropy.
Abstract.
Author URL.
Bowden J (2017). Misconceptions on the use of MR-Egger regression and the evaluation of the InSIDE assumption.
Int J Epidemiol,
46(6), 2097-2099.
Author URL.
Zheng J, Baird D, Borges M-C, Bowden J, Hemani G, Haycock P, Evans DM, Smith GD (2017). Recent Developments in Mendelian Randomization Studies.
Curr Epidemiol Rep,
4(4), 330-345.
Abstract:
Recent Developments in Mendelian Randomization Studies.
PURPOSE OF REVIEW: Mendelian randomization (MR) is a strategy for evaluating causality in observational epidemiological studies. MR exploits the fact that genotypes are not generally susceptible to reverse causation and confounding, due to their fixed nature and Mendel's First and Second Laws of Inheritance. MR has the potential to provide information on causality in many situations where randomized controlled trials are not possible, but the results of MR studies must be interpreted carefully to avoid drawing erroneous conclusions. RECENT FINDINGS: in this review, we outline the principles behind MR, as well as assumptions and limitations of the method. Extensions to the basic approach are discussed, including two-sample MR, bidirectional MR, two-step MR, multivariable MR, and factorial MR. We also consider some new applications and recent developments in the methodology, including its ability to inform drug development, automation of the method using tools such as MR-Base, and phenome-wide and hypothesis-free MR. SUMMARY: in conjunction with the growing availability of large-scale genomic databases, higher level of automation and increased robustness of the methods, MR promises to be a valuable strategy to examine causality in complex biological/omics networks, inform drug development and prioritize intervention targets for disease prevention in the future.
Abstract.
Author URL.
Hartwig FP, Davey Smith G, Bowden J (2017). Robust inference in summary data Mendelian randomization via the zero modal pleiotropy assumption.
Int J Epidemiol,
46(6), 1985-1998.
Abstract:
Robust inference in summary data Mendelian randomization via the zero modal pleiotropy assumption.
BACKGROUND: Mendelian randomization (MR) is being increasingly used to strengthen causal inference in observational studies. Availability of summary data of genetic associations for a variety of phenotypes from large genome-wide association studies (GWAS) allows straightforward application of MR using summary data methods, typically in a two-sample design. In addition to the conventional inverse variance weighting (IVW) method, recently developed summary data MR methods, such as the MR-Egger and weighted median approaches, allow a relaxation of the instrumental variable assumptions. METHODS: Here, a new method - the mode-based estimate (MBE) - is proposed to obtain a single causal effect estimate from multiple genetic instruments. The MBE is consistent when the largest number of similar (identical in infinite samples) individual-instrument causal effect estimates comes from valid instruments, even if the majority of instruments are invalid. We evaluate the performance of the method in simulations designed to mimic the two-sample summary data setting, and demonstrate its use by investigating the causal effect of plasma lipid fractions and urate levels on coronary heart disease risk. RESULTS: the MBE presented less bias and lower type-I error rates than other methods under the null in many situations. Its power to detect a causal effect was smaller compared with the IVW and weighted median methods, but was larger than that of MR-Egger regression, with sample size requirements typically smaller than those available from GWAS consortia. CONCLUSIONS: the MBE relaxes the instrumental variable assumptions, and should be used in combination with other approaches in sensitivity analyses.
Abstract.
Author URL.
Burgess S, Bowden J, Fall T, Ingelsson E, Thompson SG (2017). Sensitivity Analyses for Robust Causal Inference from Mendelian Randomization Analyses with Multiple Genetic Variants.
Epidemiology,
28(1), 30-42.
Abstract:
Sensitivity Analyses for Robust Causal Inference from Mendelian Randomization Analyses with Multiple Genetic Variants.
Mendelian randomization investigations are becoming more powerful and simpler to perform, due to the increasing size and coverage of genome-wide association studies and the increasing availability of summarized data on genetic associations with risk factors and disease outcomes. However, when using multiple genetic variants from different gene regions in a Mendelian randomization analysis, it is highly implausible that all the genetic variants satisfy the instrumental variable assumptions. This means that a simple instrumental variable analysis alone should not be relied on to give a causal conclusion. In this article, we discuss a range of sensitivity analyses that will either support or question the validity of causal inference from a Mendelian randomization analysis with multiple genetic variants. We focus on sensitivity analyses of greatest practical relevance for ensuring robust causal inferences, and those that can be undertaken using summarized data. Aside from cases in which the justification of the instrumental variable assumptions is supported by strong biological understanding, a Mendelian randomization analysis in which no assessment of the robustness of the findings to violations of the instrumental variable assumptions has been made should be viewed as speculative and incomplete. In particular, Mendelian randomization investigations with large numbers of genetic variants without such sensitivity analyses should be treated with skepticism.
Abstract.
Author URL.
Zhao Q, Wang J, Bowden J, Small DS (2017). Two-sample instrumental variable analyses using heterogeneous samples.
Abstract:
Two-sample instrumental variable analyses using heterogeneous samples
Instrumental variable analysis is a widely used method to estimate causal
effects in the presence of unmeasured confounding. When the instruments,
exposure and outcome are not measured in the same sample, Angrist and Krueger
(1992) suggested to use two-sample instrumental variable (TSIV) estimators that
use sample moments from an instrument-exposure sample and an instrument-outcome
sample. However, this method is biased if the two samples are from
heterogeneous populations so that the distributions of the instruments are
different. In linear structural equation models, we derive a new class of TSIV
estimators that are robust to heterogeneous samples under the key assumption
that the structural relations in the two samples are the same. The widely used
two-sample two-stage least squares estimator belongs to this class. It is
generally not asymptotically efficient, although we find that it performs
similarly to the optimal TSIV estimator in most practical situations. We then
attempt to relax the linearity assumption. We find that, unlike one-sample
analyses, the TSIV estimator is not robust to misspecified exposure model.
Additionally, to nonparametrically identify the magnitude of the causal effect,
the noise in the exposure must have the same distributions in the two samples.
However, this assumption is in general untestable because the exposure is not
observed in one sample. Nonetheless, we may still identify the sign of the
causal effect in the absence of homogeneity of the noise.
Abstract.
Author URL.
Bowden J, Trippa L (2017). Unbiased estimation for response adaptive clinical trials.
Stat Methods Med Res,
26(5), 2376-2388.
Abstract:
Unbiased estimation for response adaptive clinical trials.
Bayesian adaptive trials have the defining feature that the probability of randomization to a particular treatment arm can change as information becomes available as to its true worth. However, there is still a general reluctance to implement such designs in many clinical settings. One area of concern is that their frequentist operating characteristics are poor or, at least, poorly understood. We investigate the bias induced in the maximum likelihood estimate of a response probability parameter, p, for binary outcome by the process of adaptive randomization. We discover that it is small in magnitude and, under mild assumptions, can only be negative - causing one's estimate to be closer to zero on average than the truth. A simple unbiased estimator for p is obtained, but it is shown to have a large mean squared error. Two approaches are therefore explored to improve its precision based on inverse probability weighting and Rao-Blackwellization. We illustrate these estimation strategies using two well-known designs from the literature.
Abstract.
Author URL.
Lawlor D, Richmond R, Warrington N, McMahon G, Davey Smith G, Bowden J, Evans DM (2017). Using Mendelian randomization to determine causal effects of maternal pregnancy (intrauterine) exposures on offspring outcomes: Sources of bias and methods for assessing them.
Wellcome Open Res,
2Abstract:
Using Mendelian randomization to determine causal effects of maternal pregnancy (intrauterine) exposures on offspring outcomes: Sources of bias and methods for assessing them.
Mendelian randomization (MR), the use of genetic variants as instrumental variables (IVs) to test causal effects, is increasingly used in aetiological epidemiology. Few of the methodological developments in MR have considered the specific situation of using genetic IVs to test the causal effect of exposures in pregnant women on postnatal offspring outcomes. In this paper, we describe specific ways in which the IV assumptions might be violated when MR is used to test such intrauterine effects. We highlight the importance of considering the extent to which there is overlap between genetic variants in offspring that influence their outcome with genetic variants used as IVs in their mothers. Where there is overlap, and particularly if it generates a strong association of maternal genetic IVs with offspring outcome via the offspring genotype, the exclusion restriction assumption of IV analyses will be violated. We recommend a set of analyses that ought to be considered when MR is used to address research questions concerned with intrauterine effects on post-natal offspring outcomes, and provide details of how these can be undertaken and interpreted. These additional analyses include the use of genetic data from offspring and fathers, examining associations using maternal non-transmitted alleles, and using simulated data in sensitivity analyses (for which we provide code). We explore the extent to which new methods that have been developed for exploring violation of the exclusion restriction assumption in the two-sample setting (MR-Egger and median based methods) might be used when exploring intrauterine effects in one-sample MR. We provide a list of recommendations that researchers should use when applying MR to test the effects of intrauterine exposures on postnatal offspring outcomes and use an illustrative example with real data to demonstrate how our recommendations can be applied and subsequent results appropriately interpreted.
Abstract.
Author URL.
Robertson DS, Prevost AT, Bowden J (2016). Accounting for selection and correlation in the analysis of two-stage genome-wide association studies.
Biostatistics,
17(4), 634-649.
Abstract:
Accounting for selection and correlation in the analysis of two-stage genome-wide association studies.
The problem of selection bias has long been recognized in the analysis of two-stage trials, where promising candidates are selected in stage 1 for confirmatory analysis in stage 2. To efficiently correct for bias, uniformly minimum variance conditionally unbiased estimators (UMVCUEs) have been proposed for a wide variety of trial settings, but where the population parameter estimates are assumed to be independent. We relax this assumption and derive the UMVCUE in the multivariate normal setting with an arbitrary known covariance structure. One area of application is the estimation of odds ratios (ORs) when combining a genome-wide scan with a replication study. Our framework explicitly accounts for correlated single nucleotide polymorphisms, as might occur due to linkage disequilibrium. We illustrate our approach on the measurement of the association between 11 genetic variants and the risk of Crohn's disease, as reported in Parkes and others (2007. Sequence variants in the autophagy gene IRGM and multiple other replicating loci contribute to Crohn's disease susceptibility. Nat. Gen. 39: (7), 830-832.), and show that the estimated ORs can vary substantially if both selection and correlation are taken into account.
Abstract.
Author URL.
Parashar D, Bowden J, Starr C, Wernisch L, Mander A (2016). An optimal stratified Simon two-stage design.
Pharm Stat,
15(4), 333-340.
Abstract:
An optimal stratified Simon two-stage design.
In Phase II oncology trials, therapies are increasingly being evaluated for their effectiveness in specific populations of interest. Such targeted trials require designs that allow for stratification based on the participants' molecular characterisation. A targeted design proposed by Jones and Holmgren (JH) Jones CL, Holmgren E: 'An adaptive Simon two-stage design for phase 2 studies of targeted therapies', Contemporary Clinical Trials 28 (2007) 654-661.determines whether a drug only has activity in a disease sub-population or in the wider disease population. Their adaptive design uses results from a single interim analysis to decide whether to enrich the study population with a subgroup or not; it is based on two parallel Simon two-stage designs. We study the JH design in detail and extend it by providing a few alternative ways to control the familywise error rate, in the weak sense as well as the strong sense. We also introduce a novel optimal design by minimising the expected sample size. Our extended design contributes to the much needed framework for conducting Phase II trials in stratified medicine. © 2016 the Authors Pharmaceutical Statistics Published by John Wiley & Sons Ltd.
Abstract.
Author URL.
Bowden J, Del Greco M F, Minelli C, Davey Smith G, Sheehan NA, Thompson JR (2016). Assessing the suitability of summary data for two-sample Mendelian randomization analyses using MR-Egger regression: the role of the I2 statistic.
Int J Epidemiol,
45(6), 1961-1974.
Abstract:
Assessing the suitability of summary data for two-sample Mendelian randomization analyses using MR-Egger regression: the role of the I2 statistic.
BACKGROUND: : MR-Egger regression has recently been proposed as a method for Mendelian randomization (MR) analyses incorporating summary data estimates of causal effect from multiple individual variants, which is robust to invalid instruments. It can be used to test for directional pleiotropy and provides an estimate of the causal effect adjusted for its presence. MR-Egger regression provides a useful additional sensitivity analysis to the standard inverse variance weighted (IVW) approach that assumes all variants are valid instruments. Both methods use weights that consider the single nucleotide polymorphism (SNP)-exposure associations to be known, rather than estimated. We call this the `NO Measurement Error' (NOME) assumption. Causal effect estimates from the IVW approach exhibit weak instrument bias whenever the genetic variants utilized violate the NOME assumption, which can be reliably measured using the F-statistic. The effect of NOME violation on MR-Egger regression has yet to be studied. METHODS: an adaptation of the I2 statistic from the field of meta-analysis is proposed to quantify the strength of NOME violation for MR-Egger. It lies between 0 and 1, and indicates the expected relative bias (or dilution) of the MR-Egger causal estimate in the two-sample MR context. We call it IGX2. The method of simulation extrapolation is also explored to counteract the dilution. Their joint utility is evaluated using simulated data and applied to a real MR example. RESULTS: in simulated two-sample MR analyses we show that, when a causal effect exists, the MR-Egger estimate of causal effect is biased towards the null when NOME is violated, and the stronger the violation (as indicated by lower values of IGX2 ), the stronger the dilution. When additionally all genetic variants are valid instruments, the type I error rate of the MR-Egger test for pleiotropy is inflated and the causal effect underestimated. Simulation extrapolation is shown to substantially mitigate these adverse effects. We demonstrate our proposed approach for a two-sample summary data MR analysis to estimate the causal effect of low-density lipoprotein on heart disease risk. A high value of IGX2 close to 1 indicates that dilution does not materially affect the standard MR-Egger analyses for these data. CONCLUSIONS: : Care must be taken to assess the NOME assumption via the IGX2 statistic before implementing standard MR-Egger regression in the two-sample summary data context. If IGX2 is sufficiently low (less than 90%), inferences from the method should be interpreted with caution and adjustment methods considered.
Abstract.
Author URL.
Corbin LJ, Richmond RC, Wade KH, Burgess S, Bowden J, Smith GD, Timpson NJ (2016). BMI as a Modifiable Risk Factor for Type 2 Diabetes: Refining and Understanding Causal Estimates Using Mendelian Randomization.
Diabetes,
65(10), 3002-3007.
Abstract:
BMI as a Modifiable Risk Factor for Type 2 Diabetes: Refining and Understanding Causal Estimates Using Mendelian Randomization.
This study focused on resolving the relationship between BMI and type 2 diabetes. The availability of multiple variants associated with BMI offers a new chance to resolve the true causal effect of BMI on type 2 diabetes; however, the properties of these associations and their validity as genetic instruments need to be considered alongside established and new methods for undertaking Mendelian randomization (MR). We explore the potential for pleiotropic genetic variants to generate bias, revise existing estimates, and illustrate value in new analysis methods. A two-sample MR approach with 96 genetic variants was used with three different analysis methods, two of which (MR-Egger and the weighted median) have been developed specifically to address problems of invalid instrumental variables. We estimate an odds ratio for type 2 diabetes per unit increase in BMI (kg/m(2)) of between 1.19 and 1.38, with the most stable estimate using all instruments and a weighted median approach (1.26 [95% CI 1.17, 1.34]). TCF7L2(rs7903146) was identified as a complex effect or pleiotropic instrument, and removal of this variant resulted in convergence of causal effect estimates from different causal analysis methods. This indicated the potential for pleiotropy to affect estimates and differences in performance of alternative analytical methods. In a real type 2 diabetes-focused example, this study demonstrates the potential impact of invalid instruments on causal effect estimates and the potential for new approaches to mitigate the bias caused.
Abstract.
Author URL.
Haycock PC, Burgess S, Wade KH, Bowden J, Relton C, Davey Smith G (2016). Best (but oft-forgotten) practices: the design, analysis, and interpretation of Mendelian randomization studies.
Am J Clin Nutr,
103(4), 965-978.
Abstract:
Best (but oft-forgotten) practices: the design, analysis, and interpretation of Mendelian randomization studies.
Mendelian randomization (MR) is an increasingly important tool for appraising causality in observational epidemiology. The technique exploits the principle that genotypes are not generally susceptible to reverse causation bias and confounding, reflecting their fixed nature and Mendel’s first and second laws of inheritance. The approach is, however, subject to important limitations and assumptions that, if unaddressed or compounded by poor study design, can lead to erroneous conclusions. Nevertheless, the advent of 2-sample approaches (in which exposure and outcome are measured in separate samples) and the increasing availability of open-access data from large consortia of genome-wide association studies and population biobanks mean that the approach is likely to become routine practice in evidence synthesis and causal inference research. In this article we provide an overview of the design, analysis, and interpretation of MR studies, with a special emphasis on assumptions and limitations. We also consider different analytic strategies for strengthening causal inference. Although impossible to prove causality with any single approach, MR is a highly cost-effective strategy for prioritizing intervention targets for disease prevention and for strengthening the evidence base for public health policy.
Abstract.
Author URL.
Hartwig FP, Bowden J, Loret de Mola C, Tovo-Rodrigues L, Davey Smith G, Horta BL (2016). Body mass index and psychiatric disorders: a Mendelian randomization study.
Sci Rep,
6Abstract:
Body mass index and psychiatric disorders: a Mendelian randomization study.
Obesity is a highly prevalent risk factor for cardiometabolic diseases. Observational studies suggest that obesity is associated with psychiatric traits, but causal inference from such studies has several limitations. We used two-sample Mendelian randomization methods (inverse variance weighting, weighted median and MR-Egger regression) to evaluate the association of body mass index (BMI) with three psychiatric traits using data from the Genetic Investigation of Anthropometric Traits and Psychiatric Genomics consortia. Causal odds ratio estimates per 1-standard deviation increment in BMI ranged from 0.88 (95% CI: 0.62; 1.25) to 1.23 (95% CI: 0.65; 2.31) for bipolar disorder; 0.93 (0.78; 1.11) to 1.41 (0.87; 2.27) for schizophrenia; and 1.15 (95% CI: 0.92; 1.44) to 1.40 (95% CI: 1.03; 1.90) for major depressive disorder. Analyses removing potentially influential SNPs suggested that the effect estimates for depression might be underestimated. Our findings do not support the notion that higher BMI increases risk of bipolar disorder and schizophrenia. Although the point estimates for depression were consistent in all sensitivity analyses, the overall statistical evidence was weak. However, the fact that SNP-depression associations were estimated in relatively small samples reduced power to detect causal effects. This should be re-addressed when SNP-depression associations from larger studies become available.
Abstract.
Author URL.
Jackson D, Bowden J (2016). Confidence intervals for the between-study variance in random-effects meta-analysis using generalised heterogeneity statistics: should we use unequal tails?.
BMC Med Res Methodol,
16(1).
Abstract:
Confidence intervals for the between-study variance in random-effects meta-analysis using generalised heterogeneity statistics: should we use unequal tails?
BACKGROUND: Confidence intervals for the between study variance are useful in random-effects meta-analyses because they quantify the uncertainty in the corresponding point estimates. Methods for calculating these confidence intervals have been developed that are based on inverting hypothesis tests using generalised heterogeneity statistics. Whilst, under the random effects model, these new methods furnish confidence intervals with the correct coverage, the resulting intervals are usually very wide, making them uninformative. METHODS: We discuss a simple strategy for obtaining 95 % confidence intervals for the between-study variance with a markedly reduced width, whilst retaining the nominal coverage probability. Specifically, we consider the possibility of using methods based on generalised heterogeneity statistics with unequal tail probabilities, where the tail probability used to compute the upper bound is greater than 2.5 %. This idea is assessed using four real examples and a variety of simulation studies. Supporting analytical results are also obtained. RESULTS: Our results provide evidence that using unequal tail probabilities can result in shorter 95 % confidence intervals for the between-study variance. We also show some further results for a real example that illustrates how shorter confidence intervals for the between-study variance can be useful when performing sensitivity analyses for the average effect, which is usually the parameter of primary interest. CONCLUSIONS: We conclude that using unequal tail probabilities when computing 95 % confidence intervals for the between-study variance, when using methods based on generalised heterogeneity statistics, can result in shorter confidence intervals. We suggest that those who find the case for using unequal tail probabilities convincing should use the '1-4 % split', where greater tail probability is allocated to the upper confidence bound. The 'width-optimal' interval that we present deserves further investigation.
Abstract.
Author URL.
Bowden J, Davey Smith G, Haycock PC, Burgess S (2016). Consistent Estimation in Mendelian Randomization with Some Invalid Instruments Using a Weighted Median Estimator.
Genet Epidemiol,
40(4), 304-314.
Abstract:
Consistent Estimation in Mendelian Randomization with Some Invalid Instruments Using a Weighted Median Estimator.
Developments in genome-wide association studies and the increasing availability of summary genetic association data have made application of Mendelian randomization relatively straightforward. However, obtaining reliable results from a Mendelian randomization investigation remains problematic, as the conventional inverse-variance weighted method only gives consistent estimates if all of the genetic variants in the analysis are valid instrumental variables. We present a novel weighted median estimator for combining data on multiple genetic variants into a single causal estimate. This estimator is consistent even when up to 50% of the information comes from invalid instrumental variables. In a simulation analysis, it is shown to have better finite-sample Type 1 error rates than the inverse-variance weighted method, and is complementary to the recently proposed MR-Egger (Mendelian randomization-Egger) regression method. In analyses of the causal effects of low-density lipoprotein cholesterol and high-density lipoprotein cholesterol on coronary artery disease risk, the inverse-variance weighted method suggests a causal effect of both lipid fractions, whereas the weighted median and MR-Egger regression methods suggest a null effect of high-density lipoprotein cholesterol that corresponds with the experimental evidence. Both median-based and MR-Egger regression methods should be considered as sensitivity analyses for Mendelian randomization investigations with multiple genetic variants.
Abstract.
Author URL.
Bowden J, Seaman S, Huang X, White IR (2016). Gaining power and precision by using model-based weights in the analysis of late stage cancer trials with substantial treatment switching.
Stat Med,
35(9), 1423-1440.
Abstract:
Gaining power and precision by using model-based weights in the analysis of late stage cancer trials with substantial treatment switching.
In randomised controlled trials of treatments for late-stage cancer, it is common for control arm patients to receive the experimental treatment around the point of disease progression. This treatment switching can dilute the estimated treatment effect on overall survival and impact the assessment of a treatment's benefit on health economic evaluations. The rank-preserving structural failure time model of Robins and Tsiatis (Comm. Stat. 20:2609-2631) offers a potential solution to this problem and is typically implemented using the logrank test. However, in the presence of substantial switching, this test can have low power because the hazard ratio is not constant over time. Schoenfeld (Biometrika, 68:316-319) showed that when the hazard ratio is not constant, weighted versions of the logrank test become optimal. We present a weighted logrank test statistic for the late stage cancer trial context given the treatment switching pattern and working assumptions about the underlying hazard function in the population. Simulations suggest that the weighted approach can lead to large efficiency gains in either an intention-to-treat or a causal rank-preserving structural failure time model analysis compared with the unweighted approach. Furthermore, violation of the working assumptions used in the derivation of the weights only affects the efficiency of the estimates and does not induce bias or inflate the type I error rate. The weighted logrank test statistic should therefore be considered for use as part of a careful secondary, exploratory analysis of trial data affected by substantial treatment switching.
Abstract.
Author URL.
Veroniki AA, Jackson D, Viechtbauer W, Bender R, Bowden J, Knapp G, Kuss O, Higgins JPT, Langan D, Salanti G, et al (2016). Methods to estimate the between-study variance and its uncertainty in meta-analysis.
Res Synth Methods,
7(1), 55-79.
Abstract:
Methods to estimate the between-study variance and its uncertainty in meta-analysis.
Meta-analyses are typically used to estimate the overall/mean of an outcome of interest. However, inference about between-study variability, which is typically modelled using a between-study variance parameter, is usually an additional aim. The DerSimonian and Laird method, currently widely used by default to estimate the between-study variance, has been long challenged. Our aim is to identify known methods for estimation of the between-study variance and its corresponding uncertainty, and to summarise the simulation and empirical evidence that compares them. We identified 16 estimators for the between-study variance, seven methods to calculate confidence intervals, and several comparative studies. Simulation studies suggest that for both dichotomous and continuous data the estimator proposed by Paule and Mandel and for continuous data the restricted maximum likelihood estimator are better alternatives to estimate the between-study variance. Based on the scenarios and results presented in the published studies, we recommend the Q-profile method and the alternative approach based on a 'generalised Cochran between-study variance statistic' to compute corresponding confidence intervals around the resulting estimates. Our recommendations are based on a qualitative evaluation of the existing literature and expert consensus. Evidence-based recommendations require an extensive simulation study where all methods would be compared under the same scenarios.
Abstract.
Author URL.
Bowden J, Burgess S, Davey Smith G (2016). Response to Hartwig and Davies.
Int J Epidemiol,
45(5), 1679-1680.
Author URL.
Robertson DS, Prevost AT, Bowden J (2016). Unbiased estimation in seamless phase II/III trials with unequal treatment effect variances and hypothesis-driven selection rules.
Stat Med,
35(22), 3907-3922.
Abstract:
Unbiased estimation in seamless phase II/III trials with unequal treatment effect variances and hypothesis-driven selection rules.
Seamless phase II/III clinical trials offer an efficient way to select an experimental treatment and perform confirmatory analysis within a single trial. However, combining the data from both stages in the final analysis can induce bias into the estimates of treatment effects. Methods for bias adjustment developed thus far have made restrictive assumptions about the design and selection rules followed. In order to address these shortcomings, we apply recent methodological advances to derive the uniformly minimum variance conditionally unbiased estimator for two-stage seamless phase II/III trials. Our framework allows for the precision of the treatment arm estimates to take arbitrary values, can be utilised for all treatments that are taken forward to phase III and is applicable when the decision to select or drop treatment arms is driven by a multiplicity-adjusted hypothesis testing procedure. © 2016 the Authors. Statistics in Medicine Published by John Wiley & Sons Ltd.
Abstract.
Author URL.
Bowden J, Jackson C (2016). Weighing Evidence "Steampunk" Style via the Meta-Analyser.
Am Stat,
70(4), 385-394.
Abstract:
Weighing Evidence "Steampunk" Style via the Meta-Analyser.
The funnel plot is a graphical visualization of summary data estimates from a meta-analysis, and is a useful tool for detecting departures from the standard modeling assumptions. Although perhaps not widely appreciated, a simple extension of the funnel plot can help to facilitate an intuitive interpretation of the mathematics underlying a meta-analysis at a more fundamental level, by equating it to determining the center of mass of a physical system. We used this analogy to explain the concepts of weighing evidence and of biased evidence to a young audience at the Cambridge Science Festival, without recourse to precise definitions or statistical formulas and with a little help from Sherlock Holmes! Following on from the science fair, we have developed an interactive web-application (named the Meta-Analyser) to bring these ideas to a wider audience. We envisage that our application will be a useful tool for researchers when interpreting their data. First, to facilitate a simple understanding of fixed and random effects modeling approaches; second, to assess the importance of outliers; and third, to show the impact of adjusting for small study bias. This final aim is realized by introducing a novel graphical interpretation of the well-known method of Egger regression.
Abstract.
Author URL.
Jackson D, Bowden J, Baker R (2015). Approximate confidence intervals for moment-based estimators of the between-study variance in random effects meta-analysis.
Res Synth Methods,
6(4), 372-382.
Abstract:
Approximate confidence intervals for moment-based estimators of the between-study variance in random effects meta-analysis.
Moment-based estimators of the between-study variance are very popular when performing random effects meta-analyses. This type of estimation has many advantages including computational and conceptual simplicity. Furthermore, by using these estimators in large samples, valid meta-analyses can be performed without the assumption that the treatment effects follow a normal distribution. Recently proposed moment-based confidence intervals for the between-study variance are exact under the random effects model but are quite elaborate. Here, we present a much simpler method for calculating approximate confidence intervals of this type. This method uses variance-stabilising transformations as its basis and can be used for a very wide variety of moment-based estimators in both the random effects meta-analysis and meta-regression models.
Abstract.
Author URL.
Robertson DS, Prevost AT, Bowden J (2015). Correcting for bias in the selection and validation of informative diagnostic tests.
Stat Med,
34(8), 1417-1437.
Abstract:
Correcting for bias in the selection and validation of informative diagnostic tests.
When developing a new diagnostic test for a disease, there are often multiple candidate classifiers to choose from, and it is unclear if any will offer an improvement in performance compared with current technology. A two-stage design can be used to select a promising classifier (if one exists) in stage one for definitive validation in stage two. However, estimating the true properties of the chosen classifier is complicated by the first stage selection rules. In particular, the usual maximum likelihood estimator (MLE) that combines data from both stages will be biased high. Consequently, confidence intervals and p-values flowing from the MLE will also be incorrect. Building on the results of Pepe et al. (SIM 28:762-779), we derive the most efficient conditionally unbiased estimator and exact confidence intervals for a classifier's sensitivity in a two-stage design with arbitrary selection rules; the condition being that the trial proceeds to the validation stage. We apply our estimation strategy to data from a recent family history screening tool validation study by Walter et al. (BJGP 63:393-400) and are able to identify and successfully adjust for bias in the tool's estimated sensitivity to detect those at higher risk of breast cancer.
Abstract.
Author URL.
Bowden J, Davey Smith G, Burgess S (2015). Mendelian randomization with invalid instruments: effect estimation and bias detection through Egger regression.
Int J Epidemiol,
44(2), 512-525.
Abstract:
Mendelian randomization with invalid instruments: effect estimation and bias detection through Egger regression.
BACKGROUND: the number of Mendelian randomization analyses including large numbers of genetic variants is rapidly increasing. This is due to the proliferation of genome-wide association studies, and the desire to obtain more precise estimates of causal effects. However, some genetic variants may not be valid instrumental variables, in particular due to them having more than one proximal phenotypic correlate (pleiotropy). METHODS: We view Mendelian randomization with multiple instruments as a meta-analysis, and show that bias caused by pleiotropy can be regarded as analogous to small study bias. Causal estimates using each instrument can be displayed visually by a funnel plot to assess potential asymmetry. Egger regression, a tool to detect small study bias in meta-analysis, can be adapted to test for bias from pleiotropy, and the slope coefficient from Egger regression provides an estimate of the causal effect. Under the assumption that the association of each genetic variant with the exposure is independent of the pleiotropic effect of the variant (not via the exposure), Egger's test gives a valid test of the null causal hypothesis and a consistent causal effect estimate even when all the genetic variants are invalid instrumental variables. RESULTS: We illustrate the use of this approach by re-analysing two published Mendelian randomization studies of the causal effect of height on lung function, and the causal effect of blood pressure on coronary artery disease risk. The conservative nature of this approach is illustrated with these examples. CONCLUSIONS: an adaption of Egger regression (which we call MR-Egger) can detect some violations of the standard instrumental variable assumptions, and provide an effect estimate which is not subject to these violations. The approach provides a sensitivity analysis for the robustness of the findings from a Mendelian randomization investigation.
Abstract.
Author URL.
Villar SS, Bowden J, Wason J (2015). Multi-armed Bandit Models for the Optimal Design of Clinical Trials: Benefits and Challenges.
Stat Sci,
30(2), 199-215.
Abstract:
Multi-armed Bandit Models for the Optimal Design of Clinical Trials: Benefits and Challenges.
Multi-armed bandit problems (MABPs) are a special type of optimal control problem well suited to model resource allocation under uncertainty in a wide variety of contexts. Since the first publication of the optimal solution of the classic MABP by a dynamic index rule, the bandit literature quickly diversified and emerged as an active research topic. Across this literature, the use of bandit models to optimally design clinical trials became a typical motivating application, yet little of the resulting theory has ever been used in the actual design and analysis of clinical trials. To this end, we review two MABP decision-theoretic approaches to the optimal allocation of treatments in a clinical trial: the infinite-horizon Bayesian Bernoulli MABP and the finite-horizon variant. These models possess distinct theoretical properties and lead to separate allocation rules in a clinical trial design context. We evaluate their performance compared to other allocation rules, including fixed randomization. Our results indicate that bandit approaches offer significant advantages, in terms of assigning more patients to better treatments, and severe limitations, in terms of their resulting statistical power. We propose a novel bandit-based patient allocation rule that overcomes the issue of low power, thus removing a potential barrier for their use in practice.
Abstract.
Author URL.
Jama GM, Scarci M, Bowden J, Marciniak SJ (2015). Palliative treatment for symptomatic malignant pericardial effusion: a systematic review and quantitative synthesis. International Journal of Surgery, 18
Villar SS, Wason J, Bowden J (2015). Response-adaptive randomization for multi-arm clinical trials using the forward looking Gittins index rule.
Biometrics,
71(4), 969-978.
Abstract:
Response-adaptive randomization for multi-arm clinical trials using the forward looking Gittins index rule.
The Gittins index provides a well established, computationally attractive, optimal solution to a class of resource allocation problems known collectively as the multi-arm bandit problem. Its development was originally motivated by the problem of optimal patient allocation in multi-arm clinical trials. However, it has never been used in practice, possibly for the following reasons: (1) it is fully sequential, i.e. the endpoint must be observable soon after treating a patient, reducing the medical settings to which it is applicable; (2) it is completely deterministic and thus removes randomization from the trial, which would naturally protect against various sources of bias. We propose a novel implementation of the Gittins index rule that overcomes these difficulties, trading off a small deviation from optimality for a fully randomized, adaptive group allocation procedure which offers substantial improvements in terms of patient benefit, especially relevant for small populations. We report the operating characteristics of our approach compared to existing methods of adaptive randomization using a recently published trial as motivation.
Abstract.
Author URL.
Bowden J, Mander A (2014). A review and re-interpretation of a group-sequential approach to sample size re-estimation in two-stage trials.
Pharm Stat,
13(3), 163-172.
Abstract:
A review and re-interpretation of a group-sequential approach to sample size re-estimation in two-stage trials.
In this paper, we review the adaptive design methodology of Li et al. (Biostatistics 3:277-287) for two-stage trials with mid-trial sample size adjustment. We argue that it is closer in principle to a group sequential design, in spite of its obvious adaptive element. Several extensions are proposed that aim to make it even more attractive and transparent alternative to a standard (fixed sample size) trial for funding bodies to consider. These enable a cap to be put on the maximum sample size and for the trial data to be analysed using standard methods at its conclusion. The regulatory view of trials incorporating unblinded sample size re-estimation is also discussed.
Abstract.
Author URL.
Bowden J, Glimm E (2014). Conditionally unbiased and near unbiased estimation of the selected treatment mean for multistage drop-the-losers trials.
Biom J,
56(2), 332-349.
Abstract:
Conditionally unbiased and near unbiased estimation of the selected treatment mean for multistage drop-the-losers trials.
The two-stage drop-the-loser design provides a framework for selecting the most promising of K experimental treatments in stage one, in order to test it against a control in a confirmatory analysis at stage two. The multistage drop-the-losers design is both a natural extension of the original two-stage design, and a special case of the more general framework of Stallard & Friede () (Stat. Med. 27, 6209-6227). It may be a useful strategy if deselecting all but the best performing treatment after one interim analysis is thought to pose an unacceptable risk of dropping the truly best treatment. However, estimation has yet to be considered for this design. Building on the work of Cohen & Sackrowitz () (Stat. Prob. Lett. 8, 273-278), we derive unbiased and near-unbiased estimates in the multistage setting. Complications caused by the multistage selection process are shown to hinder a simple identification of the multistage uniform minimum variance conditionally unbiased estimate (UMVCUE); two separate but related estimators are therefore proposed, each containing some of the UMVCUEs theoretical characteristics. For a specific example of a three-stage drop-the-losers trial, we compare their performance against several alternative estimators in terms of bias, mean squared error, confidence interval width and coverage.
Abstract.
Author URL.
Bowden J, Brannath W, Glimm E (2014). Empirical Bayes estimation of the selected treatment mean for two-stage drop-the-loser trials: a meta-analytic approach.
Stat Med,
33(3), 388-400.
Abstract:
Empirical Bayes estimation of the selected treatment mean for two-stage drop-the-loser trials: a meta-analytic approach.
Point estimation for the selected treatment in a two-stage drop-the-loser trial is not straightforward because a substantial bias can be induced in the standard maximum likelihood estimate (MLE) through the first stage selection process. Research has generally focused on alternative estimation strategies that apply a bias correction to the MLE; however, such estimators can have a large mean squared error. Carreras and Brannath (Stat. Med. 32:1677-90) have recently proposed using a special form of shrinkage estimation in this context. Given certain assumptions, their estimator is shown to dominate the MLE in terms of mean squared error loss, which provides a very powerful argument for its use in practice. In this paper, we suggest the use of a more general form of shrinkage estimation in drop-the-loser trials that has parallels with model fitting in the area of meta-analysis. Several estimators are identified and are shown to perform favourably to Carreras and Brannath's original estimator and the MLE. However, they necessitate either explicit estimation of an additional parameter measuring the heterogeneity between treatment effects or a quite unnatural prior distribution for the treatment effects that can only be specified after the first stage data has been observed. Shrinkage methods are a powerful tool for accurately quantifying treatment effects in multi-arm clinical trials, and further research is needed to understand how to maximise their utility.
Abstract.
Author URL.
Jama GM, Scarci M, Bowden J, Marciniak SJ (2014). Palliative treatment for symptomatic malignant pericardial effusion†.
Interact Cardiovasc Thorac Surg,
19(6), 1019-1026.
Abstract:
Palliative treatment for symptomatic malignant pericardial effusion†.
Consensus has yet to emerge regarding the optimal choice of therapy in the management of malignant pericardial effusion. We review the literature to evaluate the existing evidence on the clinical effectiveness of surgical and interventional cardiological approaches. A formal literature search for all studies addressing the treatment of pericardial effusion in cancer patients was undertaken using predefined keywords. Abstracts were screened and reviewed, and data extracted. Data on intervention type, number of patients treated, number of patients surviving the procedure, effusion recurrences, need for further interventions and procedure-related complications were obtained from each study and collated in a quantitative synthesis. of 1181 articles identified, 59 contained sufficient quantitative information to be included in the synthesis. A total of 2322 patients with symptomatic pericardial effusion were identified, of which 1399 patients were reported to have underlying malignancy. Three surgical approaches were described in a total of 19 studies, with overall success rates ranging from 93.3 to 100% and associated complication rates ranging from 4.5 to 10.3%. The remaining 40 studies reported four non-surgical treatment modalities, with success rates of 55.1-90.4% and complication rates of 5.9-32%. Data from the literature suggest that surgical drainage of the pericardium is superior to non-surgical approaches for symptom relief, effusion recurrence and morbidity; however, the lack of randomized controlled trials means that selection bias remains an important limitation to the field and definitive adequately controlled trials should be a priority.
Abstract.
Author URL.
Jackson D, Baker R, Bowden J (2013). A sensitivity analysis framework for the treatment effect measure used in the meta-analysis of comparative binary data from randomised controlled trials.
Stat Med,
32(6), 931-940.
Abstract:
A sensitivity analysis framework for the treatment effect measure used in the meta-analysis of comparative binary data from randomised controlled trials.
The process of undertaking a meta-analysis involves a sequence of decisions, one of which is deciding which measure of treatment effect to use. In particular, for comparative binary data from randomised controlled trials, a wide variety of measures are available such as the odds ratio and the risk difference. It is often of interest to know whether important conclusions would have been substantively different if an alternative measure had been used. Here we develop a new type of sensitivity analysis that incorporates standard measures of treatment effect. Thus, rather than examining the implications of a variety of measures in an ad hoc manner, we can simultaneously examine an entire family of possibilities, including the odds ratio, the arcsine difference and the risk difference.
Abstract.
Author URL.
Parashar D, Bowden J, Starr C, Wernisch L, Mander A (2013). Adaptive enrichment in biomarker-stratified clinical trial design. Trials, 14(Suppl 1).
Choodari-Oskooei B, Parmar MK, Royston P, Bowden J (2013). Impact of lack-of-benefit stopping rules on treatment effect estimates of two-arm multi-stage (TAMS) trials with time to event outcome. Trials, 14(Suppl 1).
Choodari-Oskooei B, Parmar MKB, Royston P, Bowden J (2013). Impact of lack-of-benefit stopping rules on treatment effect estimates of two-arm multi-stage (TAMS) trials with time to event outcome.
Trials,
14Abstract:
Impact of lack-of-benefit stopping rules on treatment effect estimates of two-arm multi-stage (TAMS) trials with time to event outcome.
BACKGROUND: in 2011, Royston et al. described technical details of a two-arm, multi-stage (TAMS) design. The design enables a trial to be stopped part-way through recruitment if the accumulating data suggests a lack of benefit of the experimental arm. Such interim decisions can be made using data on an available 'intermediate' outcome. At the conclusion of the trial, the definitive outcome is analyzed. Typical intermediate and definitive outcomes in cancer might be progression-free and overall survival, respectively. In TAMS designs, the stopping rule applied at the interim stage(s) affects the sampling distribution of the treatment effect estimator, potentially inducing bias that needs addressing. METHODS: We quantified the bias in the treatment effect estimator in TAMS trials according to the size of the treatment effect and for different designs. We also retrospectively 'redesigned' completed cancer trials as TAMS trials and used the bootstrap to quantify bias. RESULTS: in trials in which the experimental treatment is better than the control and which continue to their planned end, the bias in the estimate of treatment effect is small and of no practical importance. In trials stopped for lack of benefit at an interim stage, the treatment effect estimate is biased at the time of interim assessment. This bias is markedly reduced by further patient follow-up and reanalysis at the planned 'end' of the trial. CONCLUSIONS: Provided that all patients in a TAMS trial are followed up to the planned end of the trial, the bias in the estimated treatment effect is of no practical importance. Bias correction is then unnecessary.
Abstract.
Author URL.
Villar SS, Bowden J, Wason J (2013). Revisiting the multi-armed bandit model for the optimal design of clinical trials: benefits and drawbacks. Trials, 14(Suppl 1).
Bowden J, Wason J (2012). Identifying combined design and analysis procedures in two-stage trials with a binary end point.
Stat Med,
31(29), 3874-3884.
Abstract:
Identifying combined design and analysis procedures in two-stage trials with a binary end point.
Two-stage trial designs provide the flexibility to stop early for efficacy or futility and are popular because they have a smaller sample size on average than a traditional trial has with the same type I and II error rates. This makes them financially attractive but also has the ethical benefit of reducing, in the long run, the number of patients who are given ineffective treatments. Designs that minimise the expected sample size are often referred to as 'optimal'. However, two-stage designs can impart a substantial bias into the parameter estimate at the end of the trial. In this paper, we argue that the expected performance of one's chosen estimation method should also be considered when deciding on a two-stage trial design. We review the properties of standard and bias-adjusted maximum likelihood estimators as well as mean and median unbiased estimators. We then identify optimal two-stage design and analysis procedures that balance projected sample size considerations with those of estimator performance. We make available software to implement this new methodology.
Abstract.
Author URL.
Vansteelandt S, Bowden J, Babanezhad M, Goetghebeur E (2012). On Instrumental Variables Estimation of Causal Odds Ratios.
Statistical Science,
26(3), 403-422.
Abstract:
On Instrumental Variables Estimation of Causal Odds Ratios
Inference for causal effects can benefit from the availability of an
instrumental variable (IV) which, by definition, is associated with the given
exposure, but not with the outcome of interest other than through a causal
exposure effect. Estimation methods for instrumental variables are now well
established for continuous outcomes, but much less so for dichotomous outcomes.
In this article we review IV estimation of so-called conditional causal odds
ratios which express the effect of an arbitrary exposure on a dichotomous
outcome conditional on the exposure level, instrumental variable and measured
covariates. In addition, we propose IV estimators of so-called marginal causal
odds ratios which express the effect of an arbitrary exposure on a dichotomous
outcome at the population level, and are therefore of greater public health
relevance. We explore interconnections between the different estimators and
support the results with extensive simulation studies and three applications.
Abstract.
Author URL.
Prevost AT, Bowden J (2011). Designing a preliminary adaptive study to inform a biomarker trial in Psoriasis. Trials, 12(Suppl 1).
Bowden J, Tierney JF, Simmonds M, Copas AJ, Higgins JP (2011). Individual patient data meta-analysis of time-to-event outcomes: one-stage versus two-stage approaches for estimating the hazard ratio under a random effects model.
Res Synth Methods,
2(3), 150-162.
Abstract:
Individual patient data meta-analysis of time-to-event outcomes: one-stage versus two-stage approaches for estimating the hazard ratio under a random effects model.
Meta-analyses of individual patient data (IPD) provide a strong and authoritative basis for evidence synthesis. IPD are particularly useful when the outcome of interest is the time to an event. Methodological developments now enable the meta-analysis of time-to-event IPD using a single model, allowing treatment effect and across-trial heterogeneity parameters to be estimated simultaneously. This differs from the standard approaches used with aggregate data, and also predominantly with IPD. Facilitated by a simulation study, we investigate what these new 'one-stage' random-effects models offer over standard 'two-stage' approaches. We find that two-stage approaches represent a robust, reliable and easily implementable way to estimate treatment effects and account for heterogeneity. Nevertheless, one-stage models can be used to provide a deeper insight into the data. Software for fitting one-stage Cox models with random effects using Restricted Maximum Likelihood methodology is made available, and its use demonstrated on an IPD meta-analysis assessing post-operative radio therapy for patients with non-small cell lung cancer. Copyright © 2011 John Wiley & Sons, Ltd.
Abstract.
Author URL.
Bowden J, Vansteelandt S (2011). Mendelian randomization analysis of case-control data using structural mean models.
Stat Med,
30(6), 678-694.
Abstract:
Mendelian randomization analysis of case-control data using structural mean models.
'Instrumental Variable' (IV) methods provide a basis for estimating an exposure's causal effect on the risk of disease. In Mendelian randomization studies, where genetic information plays the role of the IV, IV analyses are routinely performed on case-control data, rather than prospectively collected observational data. Although it is a well-appreciated fact that ascertainment bias may invalidate such analyses, ad hoc assumptions and approximations are made to justify their use. In this paper we attempt to explain and clarify why they may fail and show how they can be adjusted for improved performance. In particular, we propose consistent estimators of the causal relative risk and odds ratio if a priori knowledge is available regarding either the population disease prevalence or the population distribution of the IV (e.g. population allele frequencies). We further show that if no such information is available, approximate estimators can be obtained under a rare disease assumption. We illustrate this with matched case-control data from the recently completed EPIC study, from which we attempt to assess the evidence for a causal relationship between C-reactive protein levels and the risk of Coronary Artery Disease.
Abstract.
Author URL.
Simmonds MC, Tierney J, Bowden J, Higgins JP (2011). Meta-analysis of time-to-event data: a comparison of two-stage methods.
Res Synth Methods,
2(3), 139-149.
Abstract:
Meta-analysis of time-to-event data: a comparison of two-stage methods.
Meta-analysis is widely used to synthesise results from randomised trials. When the relevant trials collected time-to-event data, individual participant data are commonly sought from all trials. Meta-analyses of time-to-event data are typically performed using variants of the log-rank test, but modern statistical software allows for the use of maximum likelihood methods such as Cox proportional hazards models or interval-censored logistic regression. In this paper, the different approaches to the analysis of time-to-event data are examined and compared with show that log-rank test approaches are in fact first-order approximations to the maximum likelihood methods and that some methods assume proportional hazards, whereas others assume proportional odds. A simulation study is performed to compare the different methods, which shows that log-rank test approaches give biased estimates when the underlying hazard ratio or odds ratio is far from unity. It also shows that proportional hazards methods give biased results when hazards are not proportional, and proportional odds methods give biased results when odds are not proportional. Maximum likelihood models should, therefore, be preferred to log-rank test based methods for the meta-analysis of time-to-event data and any such meta-analysis should investigate whether proportional hazards or proportional odds assumptions are valid. Copyright © 2011 John Wiley & Sons, Ltd.
Abstract.
Author URL.
Bowden J, Tierney JF, Copas AJ, Burdett S (2011). Quantifying, displaying and accounting for heterogeneity in the meta-analysis of RCTs using standard and generalised Q statistics.
BMC Med Res Methodol,
11Abstract:
Quantifying, displaying and accounting for heterogeneity in the meta-analysis of RCTs using standard and generalised Q statistics.
BACKGROUND: Clinical researchers have often preferred to use a fixed effects model for the primary interpretation of a meta-analysis. Heterogeneity is usually assessed via the well known Q and I2 statistics, along with the random effects estimate they imply. In recent years, alternative methods for quantifying heterogeneity have been proposed, that are based on a 'generalised' Q statistic. METHODS: We review 18 IPD meta-analyses of RCTs into treatments for cancer, in order to quantify the amount of heterogeneity present and also to discuss practical methods for explaining heterogeneity. RESULTS: Differing results were obtained when the standard Q and I2 statistics were used to test for the presence of heterogeneity. The two meta-analyses with the largest amount of heterogeneity were investigated further, and on inspection the straightforward application of a random effects model was not deemed appropriate. Compared to the standard Q statistic, the generalised Q statistic provided a more accurate platform for estimating the amount of heterogeneity in the 18 meta-analyses. CONCLUSIONS: Explaining heterogeneity via the pre-specification of trial subgroups, graphical diagnostic tools and sensitivity analyses produced a more desirable outcome than an automatic application of the random effects model. Generalised Q statistic methods for quantifying and adjusting for heterogeneity should be incorporated as standard into statistical software. Software is provided to help achieve this aim.
Abstract.
Author URL.
Burgess S, Thompson SG, CRP CHD Genetics Collaboration, Burgess S, Thompson SG, Andrews G, Samani NJ, Hall A, Whincup P, Morris R, et al (2010). Bayesian methods for meta-analysis of causal relationships estimated using genetic instrumental variables.
Stat Med,
29(12), 1298-1311.
Abstract:
Bayesian methods for meta-analysis of causal relationships estimated using genetic instrumental variables.
Genetic markers can be used as instrumental variables, in an analogous way to randomization in a clinical trial, to estimate the causal relationship between a phenotype and an outcome variable. Our purpose is to extend the existing methods for such Mendelian randomization studies to the context of multiple genetic markers measured in multiple studies, based on the analysis of individual participant data. First, for a single genetic marker in one study, we show that the usual ratio of coefficients approach can be reformulated as a regression with heterogeneous error in the explanatory variable. This can be implemented using a Bayesian approach, which is next extended to include multiple genetic markers. We then propose a hierarchical model for undertaking a meta-analysis of multiple studies, in which it is not necessary that the same genetic markers are measured in each study. This provides an overall estimate of the causal relationship between the phenotype and the outcome, and an assessment of its heterogeneity across studies. As an example, we estimate the causal relationship of blood concentrations of C-reactive protein on fibrinogen levels using data from 11 studies. These methods provide a flexible framework for efficient estimation of causal relationships derived from multiple studies. Issues discussed include weak instrument bias, analysis of binary outcome data such as disease risk, missing genetic data, and the use of haplotypes.
Abstract.
Author URL.
Jackson D, Bowden J, Baker R (2010). How does the DerSimonian and Laird procedure for random effects meta-analysis compare with its more efficient but harder to compute counterparts?.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE,
140(4), 961-970.
Author URL.
Bowden J, Jackson D, Thompson SG (2010). Modelling multiple sources of dissemination bias in meta-analysis.
Stat Med,
29(7-8), 945-955.
Abstract:
Modelling multiple sources of dissemination bias in meta-analysis.
Asymmetry in the funnel plot for a meta-analysis suggests the presence of dissemination bias. This may be caused by publication bias through the decisions of journal editors, by selective reporting of research results by authors or by a combination of both. Typically, study results that are statistically significant or have larger estimated effect sizes are more likely to appear in the published literature, hence giving a biased picture of the evidence-base. Previous statistical approaches for addressing dissemination bias have assumed only a single selection mechanism. Here we consider a more realistic scenario in which multiple dissemination processes, involving both the publishing authors and journals, are operating. In practical applications, the methods can be used to provide sensitivity analyses for the potential effects of multiple dissemination biases operating in meta-analysis.
Abstract.
Author URL.
Jackson D, Bowden J (2009). A re-evaluation of the 'quantile approximation method' for random effects meta-analysis.
Stat Med,
28(2), 338-348.
Abstract:
A re-evaluation of the 'quantile approximation method' for random effects meta-analysis.
The quantile approximation method has recently been proposed as a simple method for deriving confidence intervals for the treatment effect in a random effects meta-analysis. Although easily implemented, the quantiles used to construct intervals are derived from a single simulation study. Here it is shown that altering the study parameters, and in particular introducing changes to the distribution of the within-study variances, can have a dramatic impact on the resulting quantiles. This is further illustrated analytically by examining the scenario where all trials are assumed to be the same size. A more cautious approach is therefore suggested, where the conventional standard normal quantile is used in the primary analysis, but where the use of alternative quantiles is also considered in a sensitivity analysis.
Abstract.
Author URL.
Bowden J, Dudbridge F (2009). Unbiased estimation of odds ratios: combining genomewide association scans with replication studies.
Genet Epidemiol,
33(5), 406-418.
Abstract:
Unbiased estimation of odds ratios: combining genomewide association scans with replication studies.
Odds ratios or other effect sizes estimated from genome scans are upwardly biased, because only the top-ranking associations are reported, and moreover only if they reach a defined level of significance. No unbiased estimate exists based on data selected in this fashion, but replication studies are routinely performed that allow unbiased estimation of the effect sizes. Estimation based on replication data alone is inefficient in the sense that the initial scan could, in principle, contribute information on the effect size. We propose an unbiased estimator combining information from both the initial scan and the replication study, which is more efficient than that based just on the replication. Specifically, we adjust the standard combined estimate to allow for selection by rank and significance in the initial scan. Our approach explicitly allows for multiple associations arising from a scan, and is robust to mis-specification of a significance threshold. We require replication data to be available but argue that, in most applications, estimates of effect sizes are only useful when associations have been replicated. We illustrate our approach on some recently completed scans and explore its efficiency by simulation.
Abstract.
Author URL.
Bowden J, Glimm E (2008). Unbiased estimation of selected treatment means in two-stage trials.
BIOMETRICAL JOURNAL,
50(4), 515-527.
Author URL.
Bowden J, Thompson JR, Burton PR (2007). A two-stage approach to the correction of ascertainment bias in complex genetic studies involving variance components.
Ann Hum Genet,
71(Pt 2), 220-229.
Abstract:
A two-stage approach to the correction of ascertainment bias in complex genetic studies involving variance components.
Correction for ascertainment bias is a vital part of the analysis of genetic epidemiology studies that needs to be undertaken whenever subjects are not recruited at random. Adjustment often requires extensive numerical integration, which can be very slow or even computationally infeasible, especially if the model includes many fixed and random effects. In this paper we propose a two-stage method for ascertainment bias correction. In the first stage we estimate parameters that pertain to the ascertained population, that is the population that would be selected into the sample if the ascertainment criterion were applied to everyone. In the second stage we convert the estimates for the ascertained population into general population parameter estimates. We illustrate the method with simulations based on a simple model and then describe how the method can be used with complex models. The two-stage approach avoids some of the integration required in direct adjustment, hence speeding up the process of model fitting.
Abstract.
Author URL.
Bowden J, Thompson JR, Burton P (2006). Using pseudo-data to correct for publication bias in meta-analysis.
STATISTICS IN MEDICINE,
25(22), 3798-3813.
Author URL.
Bowden J, Whittaker J (2005). A latent variable scorecard for neonatal baby frailty.
STATISTICAL MODELLING,
5(2), 159-172.
Author URL.
