Development and Validation of a Machine Learning Algorithm for Predicting Diabetes Retinopathy in Patients With Type 2 Diabetes: Algorithm Development Study

• Published in: JMIR medical informatics Vol. 13; p. e58107
• Main Authors: Kim, Sunyoung, Park, Jaeyu, Son, Yejun, Lee, Hojae, Woo, Selin, Lee, Myeongcheol, Lee, Hayeon, Sang, Hyunji, Yon, Dong Keon, Rhee, Sang Youl
• Format: Journal Article
• Language: English
• Published: Canada JMIR Publications 07.02.2025
• Subjects: Adult; Aged; Algorithms; Diabetes; Diabetes Mellitus, Type 2 - complications; Diabetic Retinopathy; Diabetic Retinopathy - diagnosis; Diabetic Retinopathy - etiology; Electronic Health Records; Female; Humans; Machine Learning; Male; Middle Aged; Original Paper; Republic of Korea - epidemiology; Risk Assessment - methods; Risk Factors; ROC Curve; Tools, Programs and Algorithms; Republic of Korea; diabetes retinopathy; retinal; type 2 diabetes; comorbidities; prediction; ophthalmology; machine learning; algorithm
• ISSN: 2291-9694; 2291-9694
• DOI: 10.2196/58107

Diabetic retinopathy (DR) is the leading cause of preventable blindness worldwide. Machine learning (ML) systems can enhance DR in community-based screening. However, predictive power models for usability and performance are still being determined. This study used data from 3 university hospitals in South Korea to conduct a simple and accurate assessment of ML-based risk prediction for the development of DR that can be universally applied to adults with type 2 diabetes mellitus (T2DM). DR was predicted using data from 2 independent electronic medical records: a discovery cohort (one hospital, n=14,694) and a validation cohort (2 hospitals, n=1856). The primary outcome was the presence of DR at 3 years. Different ML-based models were selected through hyperparameter tuning in the discovery cohort, and the area under the receiver operating characteristic (ROC) curve was analyzed in both cohorts. Among 14,694 patients screened for inclusion, 348 (2.37%) were diagnosed with DR. For DR, the extreme gradient boosting (XGBoost) system had an accuracy of 75.13% (95% CI 74.10-76.17), a sensitivity of 71.00% (95% CI 66.83-75.17), and a specificity of 75.23% (95% CI 74.16-76.31) in the original dataset. Among the validation datasets, XGBoost had an accuracy of 65.14%, a sensitivity of 64.96%, and a specificity of 65.15%. The most common feature in the XGBoost model is dyslipidemia, followed by cancer, hypertension, chronic kidney disease, neuropathy, and cardiovascular disease. This approach shows the potential to enhance patient outcomes by enabling timely interventions in patients with T2DM, improving our understanding of contributing factors, and reducing DR-related complications. The proposed prediction model is expected to be both competitive and cost-effective, particularly for primary care settings in South Korea.