Machine Learning-based Predictive Analytics for Early Detection of Chronic Diseases

Abstract

Chronic diseases remain a major cause of mortality and long-term disability, and proactive identification of high-risk individuals is difficult because early clinical changes are often subtle, incomplete, and distributed across heterogeneous hospital records. This study proposes a machine-learning-based predictive analytics framework for early detection of chronic disease risk using electronic health records, laboratory profiles, demographic factors, medication history, and derived clinical indicators. The study used 48,320 adult patient records collected from four tertiary hospitals between 2014 and 2023, with leakage-controlled preprocessing, multistage missing-data handling, correlation and SHAP-assisted feature selection, and stratified model development. Logistic Regression, Random Forest, XGBoost, Multilayer Perceptron, and TabNet were evaluated against clinical risk-score baselines using AUROC, PR-AUC, F1-score, recall, calibration, Brier score, and stability under missingness and imbalance. XGBoost achieved the strongest internal performance with AUROC of 0.942, PR-AUC of 0.901, F1-score of 0.901, and Brier score of 0.108. External validation on 12,950 patients from an unseen hospital produced AUROC of 0.931, confirming limited performance degradation and improved generalizability. SHAP analysis identified creatinine, HbA1c, age, systolic blood pressure, and triglycerides as dominant contributors, supporting clinically interpretable early-risk alerts for preventive care.