Risk Prediction of Chronic Kidney Disease Progression in Type 2 Diabetes Mellitus Across Diverse Populations - PubMed
5 days ago
- #Risk Prediction
- #Type 2 Diabetes Mellitus
- #Chronic Kidney Disease
- Chronic kidney disease (CKD) is a common complication of type 2 diabetes mellitus (T2DM), with limited predictive tools for individualized prognosis, especially in Asian populations.
- Deep learning-based prognostic models were developed using a 17-year longitudinal dataset from 569,680 individuals across 165 healthcare facilities in Hong Kong.
- The models integrated clinical, biochemical, and prescription history data to predict CKD progression at 2-, 5-, and 10-year intervals with high accuracy (AUCs: 87.1%, 85.3%, 84.7%).
- Key predictors identified include serum creatinine, sex, age, and angiotensin prescription history.
- External validation in UK Biobank and China Health and Retirement Longitudinal Study (CHARLS) cohorts confirmed model generalizability (AUCs: 74.6% to 82.0%).
- The models offer a scalable and interpretable framework for early risk stratification and personalized intervention for T2DM-related CKD progression.