Development and Validation of a New Risk Prediction Model for New-Onset Diabetes: Multicohort Study

Abstract

Background: In this study, we aimed to propose a novel risk prediction model based on machine learning techniques with a high accuracy for diabetes mellitus. Methods: Upon analyzing their demographic and biochemical data, we classified the 2013–16 Korea National Health and Nutrition Examination Survey (KNHANES), the 2017–18 KNHANES, and the Korean Genome and Epidemiology Study (KoGES), as the derivation, internal validation, and external validation sets, respectively. We constructed a new diabetes index using logistic regression (LR) and calculated the probability of diabetes in the validation sets. We used the area under the receiver operating characteristic curve (AUROC) and Cox regression analysis to measure the performance of the internal and external validation sets, respectively. Findings: Based on literature review, we identified candidate risk factors, of which 20 were selected using backward stepwise LR. We constructed a gender-specific diabetes prediction model, having a resultant AUROC of 0.93 and 0.94 for men and women, respectively. Thereafter, we calculated the probability of diabetes in non-diabetic KoGES subjects at baseline. Based on this probability, we classified participants into five groups and analyzed cumulative incidence from the KoGES dataset. Group 5 demonstrated significantly worse outcomes than those in other groups. Interpretation: Our novel model for predicting diabetes, based on two large-scale population-based cohort studies, showed high sensitivity and selectivity. Therefore, our prediction model can be used to classify individuals at high risk of diabetes, in whom lifestyle modifications may be employed for the prevention of the disease. Funding Statement: This research was supported by the Basic Science Research Program, through the National Research Foundation of Korea (NRF), and funded by the Ministry of Education (2020R1C1C1004999 to C.M.O). Declaration of Interests: The authors declare no conflict of interest. Ethics Approval Statement: The Institutional Review Board of Gwangju Institute of Science and Technology (South Korea) approved the study protocol (IRB No. 20200414-EX-01-02). All research procedures were performed in accordance to the relevant guidelines and regulations. All participants volunteered and provided written informed consent prior to enrolment, and their records were anonymized before being accessed by the authors.