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

Autor: He Y; Program in Bioinformatics and Integrative Genomics, Harvard Medical School, Boston, MA.; Department of Biomedical Informatics, Harvard Medical School, Boston, MA., Lakhani CM; Department of Biomedical Informatics, Harvard Medical School, Boston, MA., Rasooly D; Department of Biomedical Informatics, Harvard Medical School, Boston, MA.; Computational Health Informatics Program, Boston Children's Hospital, Boston, MA., Manrai AK; Department of Biomedical Informatics, Harvard Medical School, Boston, MA.; Computational Health Informatics Program, Boston Children's Hospital, Boston, MA., Tzoulaki I; Department of Epidemiology and Biostatistics, Imperial College London School of Public Health, London, U.K.; Department of Hygiene and Epidemiology, University of Ioannina Medical School, Ioannina, Greece., Patel CJ; Department of Biomedical Informatics, Harvard Medical School, Boston, MA chirag_patel@hms.harvard.edu.
Jazyk: angličtina
Zdroj: Diabetes care [Diabetes Care] 2021 Apr; Vol. 44 (4), pp. 935-943. Date of Electronic Publication: 2021 Feb 09.
DOI: 10.2337/dc20-2049
Abstrakt: Objective: To establish a polyexposure score (PXS) for type 2 diabetes (T2D) incorporating 12 nongenetic exposures and examine whether a PXS and/or a polygenic risk score (PGS) improves diabetes prediction beyond traditional clinical risk factors.
Research Design and Methods: We identified 356,621 unrelated individuals from the UK Biobank of White British ancestry with no prior diagnosis of T2D and normal HbA 1c 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 nongenetically ascertained exposure and lifestyle variables for the PXS in prospective T2D. We computed the clinical risk score (CRS) and PGS by taking a weighted sum of eight established clinical risk factors and >6 million single nucleotide polymorphisms, respectively.
Results: 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. Individuals in the top 10% of PGS, PXS, and CRS had 2.00-, 5.90-, and 9.97-fold greater risk, respectively, compared to the remaining population. Addition of PGS and PXS to CRS improved 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.
Conclusions: For T2D, the PXS provides modest incremental predictive value over established clinical risk factors. However, the concept of PXS merits further consideration in T2D risk stratification and is likely to be useful in other chronic disease risk prediction models.
(© 2021 by the American Diabetes Association.)
Databáze: MEDLINE
Externí odkaz: