A clinical logistic regression model for CVD risk stratification in older adults achieved an ROC-AUC of 0.9425 in development and retained discrimination (ROC-AUC 0.8355) in an external cohort.
Cohort (n=795)
Does an interpretable machine-learning framework accurately predict cardiovascular disease risk in older adults aged 65 years and older?
An interpretable machine-learning model trained on a small geriatric cohort demonstrated strong predictive performance for cardiovascular disease risk when externally validated in a larger independent cohort.
Cardiovascular disease (CVD) risk assessment in older adults requires models that are accurate, clinically interpretable, and able to retain performance in independent populations. This study developed an interpretable machine-learning framework for CVD risk stratification in individuals aged 65 years and older using routinely available clinical factors and a selected biochemical extension and then evaluated its performance in a substantially larger independent external cohort. Model development used a development cohort of 100 patients (Almaty, age ≥ 65) with leakage-free nested cross-validation and out-of-fold (OOF) probabilities. Three internally evaluated configurations were compared: a clinical logistic regression baseline (LR clinical), a biomarker-augmented logistic regression (LR selected), and a nonlinear random forest on the selected feature set (RF selected). Discrimination was assessed using ROC-AUC and PR-AUC; probabilistic accuracy using Brier score and log loss. Calibration was examined using OOF calibration curves with sigmoid calibration for selected models. Decision-analytic utility and exploratory operational thresholds were assessed using Decision Curve Analysis (DCA), yielding a three-tier scale with thresholds tₗow = 0. 23 and tₕigh = 0. 40. In nested cross-validation, LR clinical achieved ROC-AUC 0. 9425 ± 0. 0188 and PR-AUC 0. 9574 ± 0. 0092 with Brier 0. 1004 ± 0. 0215 and log loss 0. 3634 ± 0. 0652; LR selected performed worse, while RF selected showed competitive discrimination. External validation on an independent cohort (n = 695) showed retained discrimination (ROC-AUC 0. 8355; PR-AUC 0. 9376) with acceptable probabilistic accuracy (Brier 0. 1131; log loss 0. 3760), and recalibration (intercept + slope) slightly improved probability metrics. Explainability analyses (odds ratios, permutation importance, SHAP) consistently identified heredity, BMI, physical activity, and diabetes as influential model-associated factors, with clinically plausible directionality. The results suggest that an interpretable model trained on a small geriatric cohort can retain meaningful predictive performance on a substantially larger external cohort, supporting the potential value of transparent risk stratification in older adults, while broader prospective and multi-center validation remains necessary before routine clinical implementation.
Suleimenova et al. (2026) conducted a cohort in Cardiovascular disease (n=795). Machine-learning framework for CVD risk stratification was evaluated on Model discrimination (ROC-AUC and PR-AUC) and probabilistic accuracy. A clinical logistic regression model for CVD risk stratification in older adults achieved an ROC-AUC of 0.9425 in development and retained discrimination (ROC-AUC 0.8355) in an external cohort.