Key result
Machine learning models fail to outperform clinician baseline accuracy for CAD prognosis.
Why the study?
Prior machine learning studies relying on multimodal clinical, imaging, and genetic data do not provide early screening or prognosis, leaving the feasibility of using lifestyle and medical history variables alone unclear.
Can machine learning models using lifestyle and medical history data accurately predict CAD prognosis compared to clinicians?
Observational (n=571)
Can machine learning models using lifestyle and medical history data accurately predict CAD prognosis compared to clinicians?
Machine learning models using only lifestyle and medical history data achieve moderate accuracy (up to 76%) for CAD prognosis, slightly lower than clinician baseline, highlighting their potential as complementary early screening tools.
Answers are grounded in this paper and cite their sources.
ML models approach clinician accuracy for CAD prognosis; leaves open their role as adjunct screening tools pending validation.
Coronary artery disease (CAD) remains a leading cause of morbidity and mortality worldwide, emphasizing the need for early and scalable risk stratification approaches. While recent Machine Learning (ML) studies have reported high diagnostic performance using multimodal clinical, laboratory, imaging, and genetic data, they do not provide early screening or prognosis. In this study, we investigate the extent to which CAD prognosis can be achieved using lifestyle and medical history variables alone. We pooled a cohort of 571 participants with and without CAD and evaluated multiple ML models, including Random Forest, CatBoost, AdaBoost, XGBoost, TabPFN, and k-Nearest Neighbors, using 10-fold cross-validation. Across models, predictive performance converged in a narrow range (72–76% accuracy), with the best-performing models reaching approximately 76% accuracy, compared to a clinician baseline of 78.8%. To enhance transparency and clinical interpretability, we further outline an explainability analysis for the top-performing model using SHAP-based approaches. Overall, this work highlights both the potential and the limitations of lifestyle-based ML models for CAD prognosis and supports their role as complementary tools for early screening and preventive cardiology.
No takes yet. Share an insight, caveat, or question.
Samaras et al. (2026) conducted an observational in Coronary artery disease (CAD) (n=571). Machine learning models using lifestyle and medical history variables vs. Clinician baseline was evaluated on Predictive accuracy for CAD prognosis. Machine learning models using lifestyle and medical history variables achieved up to 76% accuracy for CAD prognosis, compared to a clinician baseline of 78.8%.
Synapse has enriched 10 related papers. Consider them for comparative context: