Available online Apr 30, 2026.

[ Original ] Volume 32, Issue 2, 2026, Pages 247-260

---

Abstract

Cardiovascular disease remains the leading cause of mortality among older adults globally, yet a substantial proportion remains undiagnosed until acute events occur. This study develops a machine learning decision support framework that estimates the likelihood of undiagnosed cardiovascular risk in adults aged 60 years and above by integrating routinely captured clinical records with demographic, behavioural, and psychosocial indicators. The framework translates model outputs into clear, context-aware guidance that facilitates timely screening and preventive intervention. Comparative testing demonstrates that ensemble learners, particularly gradient boosting, deliver superior discrimination compared to baseline models while maintaining clinical interpretability. The approach is positioned to complement public health initiatives and primary care pathways by offering a feasible mechanism for earlier detection and improved cardiovascular outcomes in aging populations.

Keywords

Undiagnosed-cardiovascular-disease, Older-adults, Machine-learning, Risk-stratification, Clinical-decision-support, Primary-care, Health-equity, Nigeria, Ensemble-methods, Gradient-boosting,

---

View more