COLLEGE OF MEDICINE AND HEALTH
Medicine, Nursing and Allied Health Professions

Profile

Loading content
 Lauric Ferrat

Lauric Ferrat

Postdoctoral Research Fellow

 

Overview

Lauric Ferrat is an applied mathematician. With a background in the development of mathematical models of biological processes and applications in medicine, his research focuses on machine learning and statistical tools.

In July 2018, he joined the University of Exeter Medical School as a postdoctoral research fellow, working on the prediction of type one diabetes in children using genetic, environmental and clinical risk factors. His main collaborators at RILD are Dr Richard Oram and Prof. Mike Weedon, and he works in close collaboration with Profs Jonathan Fielsend (University of Exeter), Kendra Vehik (University South Florida) and William Hagopian (Pacific Northwest Diabetes Research Institute). Lauric is also undertaking research into the prediction of the onset of celiac disease, and supports his collaborators in their other projects.

He completed his engineering diploma at the National School for Statistics and Information Analysis in France, specialising in advanced statistical engineering. Lauric has always been interested in applying his knowledge to the health care sector. After internships in both the pharmaceutical industry and at the EHESP School of Public Health in France, he began his PhD with Professor John Terry. His PhD project focused on the analysis of mathematical models using statistical and machine learning techniques.

Qualifications

  • PhD Applied Mathematics – University of Exeter
  • Engineer diploma - ENSAI

Grants/Funding:

JDRF 2019-2021 Improved, cost effective prediction of type 1 diabetes in early life using combined prediction models (CI 380,760.47)
 

Research

Research interests

My research interests are in development and application of machine learning and statistical techniques with practical clinical use.

I am particularly interested by

  • Prediction modelling.
  • Optimization of cohort design.
  • Translation from research to clinical practice

Research projects

Current Projects:

  • Improved, cost effective prediction of type 1 diabetes in early life using combined prediction models;
  • Identification and follow up optimisation for children with high type 1 diabetes risk;
  • Improved, cost effective prediction of celiac disease in early life using combined prediction models.

 

 

Publications

Key publications | Publications by category | Publications by year

Publications by category


Journal articles

Ferrat LA, Vehik K, Sharp SA, Lernmark A, Rewers MJ, She J-X, Ziegler A-G, Toppari J, Akolkar B, Krischer JP, et al (2020). A combined risk score enhances prediction of type 1 diabetes among susceptible children. NATURE MEDICINE, 26(8), 1247-+. Author URL.  Full text.
Carr ALJ, Perry DJ, Lynam AL, Chamala S, Flaxman CS, Sharp SA, Ferrat LA, Jones AG, Beery ML, Jacobsen LM, et al (2020). Histological validation of a type 1 diabetes clinical diagnostic model for classification of diabetes. Diabetic Medicine Full text.
Lynam AL, Dennis JM, Owen KR, Oram RA, Jones AG, Shields BM, Ferrat LA (2020). Logistic regression has similar performance to optimised machine learning algorithms in a clinical setting: application to the discrimination between type 1 and type 2 diabetes in young adults. Diagnostic and Prognostic Research, 4(1). Full text.
Ferrat LA, Goodfellow M, Terry JR (2018). Classifying dynamic transitions in high dimensional neural mass models: a random forest approach. PLoS Comput Biol, 14(3). Abstract.  Author URL.  Full text.

Conferences

Ferrat LA, Vehik K, Sharp SA, Lernmark A, Ziegler A, Rewers M, She J-X, Toppari J, Akolkar B, Krischer J, et al (2019). A Combined Method Improves Risk Prediction for Childhood Type 1 Diabetes in the TEDDY Study.  Author URL.
Oram RA, Sharp SA, Pihoker C, Ferrat LA, Imperatore G, Saydah S, Williams AH, Wagenknecht LE, Lawrence JM, Weedon MN, et al (2019). A T1D Genetic Risk Score Combined with Clinical Features and Autoantibodies Enables Accurate Diabetes Classification in a Racial/Ethnically Diverse Population: the Search for Diabetes in Youth Study.  Author URL.

Publications by year


2020

Ferrat LA, Vehik K, Sharp SA, Lernmark A, Rewers MJ, She J-X, Ziegler A-G, Toppari J, Akolkar B, Krischer JP, et al (2020). A combined risk score enhances prediction of type 1 diabetes among susceptible children. NATURE MEDICINE, 26(8), 1247-+. Author URL.  Full text.
Carr ALJ, Perry DJ, Lynam AL, Chamala S, Flaxman CS, Sharp SA, Ferrat LA, Jones AG, Beery ML, Jacobsen LM, et al (2020). Histological validation of a type 1 diabetes clinical diagnostic model for classification of diabetes. Diabetic Medicine Full text.
Lynam AL, Dennis JM, Owen KR, Oram RA, Jones AG, Shields BM, Ferrat LA (2020). Logistic regression has similar performance to optimised machine learning algorithms in a clinical setting: application to the discrimination between type 1 and type 2 diabetes in young adults. Diagnostic and Prognostic Research, 4(1). Full text.

2019

Ferrat LA, Vehik K, Sharp SA, Lernmark A, Ziegler A, Rewers M, She J-X, Toppari J, Akolkar B, Krischer J, et al (2019). A Combined Method Improves Risk Prediction for Childhood Type 1 Diabetes in the TEDDY Study.  Author URL.
Oram RA, Sharp SA, Pihoker C, Ferrat LA, Imperatore G, Saydah S, Williams AH, Wagenknecht LE, Lawrence JM, Weedon MN, et al (2019). A T1D Genetic Risk Score Combined with Clinical Features and Autoantibodies Enables Accurate Diabetes Classification in a Racial/Ethnically Diverse Population: the Search for Diabetes in Youth Study.  Author URL.

2018

Ferrat LA, Goodfellow M, Terry JR (2018). Classifying dynamic transitions in high dimensional neural mass models: a random forest approach. PLoS Comput Biol, 14(3). Abstract.  Author URL.  Full text.

Lauric_Ferrat Details from cache as at 2020-10-19 08:23:49

Refresh publications

Teaching

Supervision / Group

Back | Edit Profile