American Diabetes Association
3 files

Comparisons of Polyexposure, Polygenic, and Clinical Risk Scores in Risk Prediction of Type 2 Diabetes

Version 2 2021-03-11, 15:43
Version 1 2021-02-09, 23:55
posted on 2021-03-11, 15:43 authored by Yixuan He, Chirag M Lakhani, Danielle Rasooly, Arjun K Manrai, Ioanna Tzoulaki, Chirag J Patel

Establish a polyexposure score for T2D incorporating 12 non-genetic exposure and examine whether a polyexposure and/or a polygenic risk score improves diabetes prediction beyond traditional clinical risk factors.


We identified 356,621 unrelated individuals from the UK Biobank of white British ancestry with no prior diagnosis of T2D and normal HbA1c levels. Using self-reported and hospital admission information, we deployed a machine learning procedure to select the most predictive and robust factors out of 111 non-genetically ascertained exposure and lifestyle variables for the polyexposure risk score (PXS) in prospective T2D. We computed the clinical risk score (CRS) and polygenic risk score (PGS) by taking a weighted sum of eight established clinical risk factors and over six million SNPs, respectively.


In the study population, 7,513 had incident T2D. The C-statistics for the PGS, PXS, and CRS models were 0.709, 0.762, and 0.839, respectively. Hazard ratios (HR) associated with risk score values in the top 10% percentile versus the remaining population is 2.00, 5.90, and 9.97 for PGS, PXS, and CRS respectively. Addition of PGS and PXS to CRS improves T2D classification accuracy with a continuous net reclassification index of 15.2% and 30.1% for cases, respectively, and 7.3% and 16.9% for controls, respectively.


For T2D, the PXS provides modest incremental predictive value over established clinical risk factors. The concept of PXS merits further consideration in T2D risk stratification and is likely to be useful in other chronic disease risk prediction models.


Our analysis was conducted using the UK Biobank resource via application number 22881. We would like to thank all the volunteers who participated in this project. This work was supported by the Bioinformatics and Integrative Genomics training grant from the National Institutes of Health NHGRI under award number T32HG002295, the National Institutes of Health NIEHS under award numbers R00ES23504 and R21ES205052, NIAID under award numbers R01AI12725003, the National Science Foundation Graduate Research Fellowship under award number DGE1745303 (to Y.H.), the UK Biobank Early-Career Researcher Award (to Y.H.), and the National Science Foundation under award number 1636870.