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

Maria Alejandra Pinero de Plaza*, Kristina Lambrakis, Fernando Marmolejo-Ramos, Alline Beleigoli, Mandy Archibald, Lalit Yadav, Penelope McMillan, Robyn Clark, Michael Lawless, Erin Morton, Jeroen Hendriks, Alison Kitson, Renuka Visvanathan, Derek P. Chew, Carlos Javier Barrera Causil

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

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.
Original languageEnglish
Article number105810
Number of pages10
JournalInternational Journal of Medical Informatics
Volume196
DOIs
Publication statusPublished - 1 Apr 2025

Keywords

  • Adoption
  • Artificial intelligence
  • Cardiac biomarkers
  • Decision support
  • Emergency medicine
  • Human-centred evaluation
  • Usability

Fingerprint

Dive into the research topics of 'Human-centred AI for emergency cardiac care: Evaluating RAPIDx AI with PROLIFERATE_AI'. Together they form a unique fingerprint.

Cite this