Human-centred AI for emergency cardiac care: Evaluating RAPIDx AI with PROLIFERATE_AI

Background: Chest pain diagnosis in emergency care is hindered by overlapping cardiac and non-cardiac symptoms, causing diagnostic uncertainty. Artificial Intelligence, such as RAPIDx AI, aims to enhance accuracy through clinical and biochemical data integration, but its adoption relies on addressing usability, explainability, and seamless workflow integration without disrupting care. Objective: Evaluate RAPIDx AI's integration into clinical workflows, address usability barriers, and optimise its adoption in emergencies. Methods: The PROLIFERATE_AI framework was implemented across 12 EDs (July 2022-January 2024) with 39 participants: 15 experts co-designed a survey via Expert Knowledge Elicitation (EKE), applied to 24 ED clinicians to assess RAPIDx AI usability and adoption. Bayesian inference, using priors, estimated comprehension, emotional engagement, usage, and preference, while Monte Carlo simulations quantified uncertainty and variability, generating posterior means and 95% bootstrapped confidence intervals. Qualitative thematic analysis identified barriers and optimisation needs, with data triangulated through the PROLIFERATE_AI scoring system to rate RAPIDx AI's performance by user roles and demographics. Results: Registrars exhibited the highest comprehension (median: 0.466, 95 % CI: 0.41-0.51) and preference (median: 0.458, 95 % CI: 0.41-0.48), while residents/interns scored the lowest in comprehension (median: 0.198, 95 % CI: 0.17-0.26) and emotional engagement (median: 0.112, 95 % CI: 0.09-0.14). Registered nurses showed strong emotional engagement (median: 0.379, 95 % CI: 0.35-0.45). Novice users faced usability and workflow integration barriers, while experienced clinicians suggested automation and streamlined workflows. RAPIDx AI scored "Good Impact," excelling with trained users but requiring targeted refinements for novices. Conclusion: RAPIDx AI enhances diagnostic accuracy and efficiency for experienced users, but usability challenges for novices highlight the need for targeted training and interface refinements. The PROLIFERATE_AI framework offers a robust methodology for evaluating and scaling AI solutions, addressing the evolving needs of sociotechnical systems.