AI-derived ACS checklists for cardiology training: implementation barriers and ethical considerations using the CURACO framework

Abstract Background/Introduction Acute coronary syndrome management requires rapid, systematic clinical decision-making, yet resident doctors often experience uncertainty in managing these time-sensitive presentations. Traditional checklist implementations focus primarily on clinical confidence without addressing patient empowerment, healthcare equity, or systematic integration of safety, understanding, research, authenticity, ethics, and technology. Current approaches lack holistic frameworks ensuring both clinical excellence and patient-centred care delivery. Purpose To conduct a pilot evaluation of whether AI-generated ACS checklists enhanced through CURACO principles (Clinical safety, Understanding, Research-informed care, Authentic patient-centred approaches, Conscientious ethics, and Optimised technology) improve resident doctors' confidence while incorporating patient empowerment and equity considerations. Methods We developed AI-generated ACS management checklists at our hospital, derived from ESC guidelines and enhanced using CURACO principles to ensure safety-first protocols, patient understanding components, research-informed guidelines, authentic care approaches, ethical considerations, and optimised technology integration. We surveyed resident doctors (n=15) rotating through cardiology between August 2024-February 2025 using 5-point Likert scales to assess confidence across ACS management domains before and after implementation. Paired t-tests analysed pre- and post-implementation confidence scores. Results All domains showed significant confidence improvements after implementation (p<0.001). ECG interpretation confidence improved dramatically, with 66.7% reporting maximum confidence post-implementation versus 6.7% pre-implementation. Troponin management confidence increased to 73.3% maximum confidence versus 33.3% pre-implementation. Risk stratification confidence for invasive management increased from 0% to 93.3% for high confidence scores. Documentation confidence increased from 13.3% to 86.7%. The CURACO-enhanced approach demonstrated additional benefits: 100% agreed the checklist helped standardise their approach while maintaining patient-centred focus. Patient understanding components were valued by 80% of users, creating a more holistic approach than traditional implementations. Conclusion Implementation of CURACO-enhanced AI-generated ACS checklists significantly improved resident confidence across all domains while incorporating patient empowerment and systematic excellence principles. This pilot demonstrates that AI-derived interventions can be transformed through systematic integration of safety, understanding, research, authenticity, ethics, and technology. The CURACO framework provides foundation for developing clinical tools serving both clinical excellence and patient-centred care. These findings justify progression to larger-scale studies with patient outcomes and multi-centre validation