Uncertainty-aware hybrid optimization for robust cardiovascular disease detection: A clinical translation framework

Cardiovascular disease causes 17.9 million deaths annually, yet current AI systems achieve ∼82 % accuracy without uncertainty quantification—limiting clinical utility where prediction confidence directly guides life-saving treatment decisions. We developed an uncertainty-aware hybrid optimization framework for robust CVD detection that provides clinicians with both risk predictions and confidence intervals, enabling personalized decision-making under real-world clinical conditions. Our clinical translation framework integrates multiple complementary AI models (Gaussian processes, gradient-boosted trees, Transformers) through uncertainty-guided optimization. Key clinical innovations include: (1) real-time uncertainty calibration responding to data quality variations, (2) dynamic model weighting adapting to individual patient characteristics, and (3) interpretable confidence intervals supporting clinical decision protocols. Clinical validation on 12,458 CVD patients from MIMIC-III and UK Biobank demonstrated clinically significant improvements: +1.4 % AUC (0.853 vs 0.839, p < 0.01) translating to 50 additional correct diagnoses per 10,000 patients, +1.5 % balanced accuracy, and 20 % better uncertainty calibration. The framework maintained robust performance (>80 % AUC) under realistic clinical noise while providing reliable confidence intervals across all risk levels. This framework delivers immediate clinical utility through real-time inference (<2s), FHIR-compliant EHR integration, and physician-validated uncertainty interpretation. Implementation prevents an estimated 50 missed diagnoses and 23 unnecessary procedures per 10,000 patients screened annually. Our uncertainty-aware framework represents the first clinically ready AI system providing both accurate CVD risk assessment and trustworthy confidence measures, directly addressing physician adoption barriers and supporting personalized cardiovascular care. • Uncertainty-aware hybrid optimization enhances cardiovascular risk prediction. • Improves AUC (+1.4 %) and reduces calibration error by 20 % under clinical noise. • Real-time inference (<2 s) supports seamless hospital deployment. • Robust across missing data and multi-institutional patient cohorts. • Provides interpretable, confidence-aware outputs for physician decision support.