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

doi:10.1016/j.ijmedinf.2025.105810

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

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

22 Downloads (Pure)

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 language	English
Article number	105810
Number of pages	10
Journal	INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS
Volume	196
DOIs	https://doi.org/10.1016/j.ijmedinf.2025.105810
Publication status	Published - Apr 2025

Keywords

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

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.ijmedinf.2025.105810Licence: CC BY-NC

Final published versionFinal published version, 1.73 MBLicence: CC BY-NC

Cite this

Pinero de Plaza, M. A., Lambrakis, K., Marmolejo-Ramos, F., Beleigoli, A., Archibald, M., Yadav, L., McMillan, P., Clark, R., Lawless, M., Morton, E., Hendriks, J., Kitson, A., Visvanathan, R., Chew, D. P., & Barrera Causil, C. J. (2025). Human-centred AI for emergency cardiac care: Evaluating RAPIDx AI with PROLIFERATE_AI. INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 196, Article 105810. https://doi.org/10.1016/j.ijmedinf.2025.105810

@article{ad361100f896414d96e6ac9e932b7a68,

title = "Human-centred AI for emergency cardiac care: Evaluating RAPIDx AI with PROLIFERATE_AI",

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.",

keywords = "Adoption, Artificial intelligence, Cardiac biomarkers, Decision support, Emergency medicine, Human-centred evaluation, Usability",

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

year = "2025",

month = apr,

doi = "10.1016/j.ijmedinf.2025.105810",

language = "English",

volume = "196",

journal = "INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS",

issn = "1386-5056",

publisher = "Elsevier Ireland Ltd",

}

Pinero de Plaza, MA, Lambrakis, K, Marmolejo-Ramos, F , Beleigoli, A, Archibald, M, Yadav, L, McMillan, P, Clark, R , Lawless, M, Morton, E, Hendriks, J , Kitson, A, Visvanathan, R, Chew, DP & Barrera Causil, CJ 2025, 'Human-centred AI for emergency cardiac care: Evaluating RAPIDx AI with PROLIFERATE_AI', INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, vol. 196, 105810. https://doi.org/10.1016/j.ijmedinf.2025.105810

TY - JOUR

T1 - Human-centred AI for emergency cardiac care

T2 - Evaluating RAPIDx AI with PROLIFERATE_AI

AU - Pinero de Plaza, Maria Alejandra

AU - Lambrakis, Kristina

AU - Marmolejo-Ramos, Fernando

AU - Beleigoli, Alline

AU - Archibald, Mandy

AU - Yadav, Lalit

AU - McMillan, Penelope

AU - Clark, Robyn

AU - Lawless, Michael

AU - Morton, Erin

AU - Hendriks, Jeroen

AU - Kitson, Alison

AU - Visvanathan, Renuka

AU - Chew, Derek P.

AU - Barrera Causil, Carlos Javier

PY - 2025/4

Y1 - 2025/4

N2 - 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.

AB - 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.

KW - Adoption

KW - Artificial intelligence

KW - Cardiac biomarkers

KW - Decision support

KW - Emergency medicine

KW - Human-centred evaluation

KW - Usability

UR - http://www.scopus.com/inward/record.url?scp=85216572413&partnerID=8YFLogxK

UR - http://purl.org/au-research/grants/NHMRC/1191914

U2 - 10.1016/j.ijmedinf.2025.105810

DO - 10.1016/j.ijmedinf.2025.105810

M3 - Article

AN - SCOPUS:85216572413

SN - 1386-5056

VL - 196

JO - INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS

JF - INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS

M1 - 105810

ER -

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

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Consumers' Choice Poster - Sponsored by The Heart Foundation

CSIRO On Prime Innovation Reward 2024

Healthcare Innovator Award 2024

Aged & Extended Care Unit Academic Meeting - Monday 17/2/25: Advancing Human-Centred AI in Emergency Care: A Multimethod Evaluation of RAPIDx AI Using the PROLIFERATE_AI Framework

Research to Value | Flinders University & CSIRO | Guest Speaker

Global Impact and Recognition of the PROLIFERATE_AI Method

Freeing transdisciplinarity from the project straightjacket: reframing the problem

From Promise to Practice: How Health Researchers Understand and Promote Transdisciplinary Collaboration

From Utility to Meaning: Reframing Health System Evaluation through Multilevel, Predictive and Biographical Models

Cite this

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

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Prizes

Activities

Research output

Cite this