Prediction of diabetic kidney disease risk using machine learning models: a population-based cohort study of Asian adults
Preprint
Abstract
Background: Machine learning (ML) techniques improve disease prediction by identifying the most relevant features in multi-dimensional data. We compared the accuracy of ML algorithms for predicting incident diabetic kidney disease (DKD). Methods: We utilized longitudinal data from 1365 Chinese, Malay and Indian participants aged 40-80 years with diabetes but free of DKD who participated in the baseline and 6-year follow-up visit of the Singapore Epidemiology of Eye Diseases Study (2004-2017). Incident DKD (11.9%) was defined as an estimated glomerular filtration rate (eGFR) 2 with at least 25% decrease in eGFR at follow-up from baseline. 339 features including participant characteristics, retinal imaging, genetic and blood metabolites were used as predictors. Performances of several ML models were compared to each other and to logic regression (LR) model based on established features of DKD (age, sex, ethnicity, duration of diabetes, systolic blood pressure, HbA1c, and body mass index) using area under the receiver operating characteristic curve (AUC). Results: ML model, Elastic Net (EN) had the best AUC (95% confidence interval) of 0.851 (0.847-0.856), which was 7.0% relatively higher than by LR 0.795 (0.790-0.801). Sensitivity and specificity of EN were 88.2% and 65.9% vs. 73.0% and 72.8% by LR. The top-15 predictors included age, ethnicity, antidiabetic medication, hypertension, diabetic retinopathy, systolic blood pressure, HbA1c, eGFR and metabolites related to lipids, lipoproteins, fatty acids and ketone bodies. Conclusions: Our results showed ML together with feature selection improves prediction accuracy of DKD risk in an asymptomatic stable population and identifies novel risk factors including metabolites. Funding Support: This study was supported by the National Medical Research Council, NMRC/OFLCG/001/2017 and NMRC/HCSAINV/MOH-001019-00. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Conflicts of interest: None declared.Keywords
All Related Versions
- Published version: eLife, 12.
This publication has 24 references indexed in Scilit:
- Chronic Kidney DiseaseThe Lancet, 2017
- Type 2 Diabetes Genetic Variants and Risk of Diabetic RetinopathyOphthalmology, 2016
- Development and Characterization of Genic SSR Markers from Indian Mulberry Transcriptome and Their Transferability to Related Species of MoraceaePLOS ONE, 2016
- Risk Prediction for Early CKD in Type 2 DiabetesClinical Journal of the American Society of Nephrology, 2015
- Evaluation and Management of Chronic Kidney Disease: Synopsis of the Kidney Disease: Improving Global Outcomes 2012 Clinical Practice GuidelineAnnals of Internal Medicine, 2013
- Chapter 2: Definition, identification, and prediction of CKD progressionKidney International Supplements, 2013
- Retinal Arteriolar Narrowing and Subsequent Development of CKD Stage 3: The Multi-Ethnic Study of Atherosclerosis (MESA)American Journal of Kidney Diseases, 2011
- Methodology of the Singapore Indian Chinese Cohort (SICC) Eye Study: Quantifying ethnic variations in the epidemiology of eye diseases in AsiansOphthalmic Epidemiology, 2009
- A New Equation to Estimate Glomerular Filtration RateAnnals of Internal Medicine, 2009
- Rationale and Methodology for a Population-Based Study of Eye Diseases in Malay People: The Singapore Malay Eye Study (SiMES)Ophthalmic Epidemiology, 2007