Predicting the implementation impact of RAPIDx AI  in South Australian emergency departments

Maria Alejandra  Pinero de Plaza; Kristina Lambrakis; Carlos Javier Barrera Causil; Fernando Marmolejo Ramos; Derek Chew; Alline Beleigoli; Michael Lawless; Mandy Archibald; Alexandra Mudd; Penelope McMillan; Erin Morton; Rachel Ambagtsheer; Ehsan Khan; Robyn Clark; Renuka Visvanathan; Lalit Yadav; Alison Kitson

Predicting the implementation impact of RAPIDx AI in South Australian emergency departments

Maria Alejandra Pinero de Plaza, Kristina Lambrakis, Carlos Javier Barrera Causil, Fernando Marmolejo Ramos, Derek Chew, Alline Beleigoli, Michael Lawless, Mandy Archibald, Alexandra Mudd, Penelope McMillan, Erin Morton, Rachel Ambagtsheer, Ehsan Khan, Robyn Clark, Renuka Visvanathan, Lalit Yadav, Alison Kitson

Research output: Contribution to conference › Poster › peer-review

Abstract

Background: There were 75,900 presentations to Australian public hospital Emergency Departments (EDs) with a principal diagnosis of Coronary Heart Disease in 2020–21. RAPIDx AI is a randomised controlled trial to test whether computer algorithms in hospital EDs can help doctors provide better care for patients with symptoms that may be due to their heart.

Objective: To develop an evaluation and prediction method to measure stakeholders' perspectives about the implementation impact of RAPIDx AI. This methodological innovation is necessary because person-centred healthcare services require effective technology integration within clinical workflows to provide better patient care while considering the needs of all end-users involved and affected by such types of tech/practices/service changes.

Methods: We introduce an evaluation framework and method based on complexity science and participatory action research (PROLIFERATE). Using Bayesian statistics, we created a protocol and produced computer-simulated results to demonstrate the evaluation and prediction capabilities of the method concerning RAPIDx AI. Ethical approval was granted by the Southern Adelaide Human Research Ethics Committee (SACHREC): OfR no.272.20

Results: Our methodological innovation is informed by 95% probability prediction and credible intervals on these domains of stakeholders' perspectives: Comprehension, Emotional response; Uptake barriers; Motivation and Optimisation. Computer-simulated responses to a PROLIFERATE online survey predicted an Average Impact for RAPIDx AI. The simulation results imply that motivational and emotional knowledge-translation strategies must be implemented for clinicians and the community to improve RAPIDx AI sustainability. (PROLIFERATE constructs benchmarked at 50%—algorithm and data analysis developed in R.)

Conclusion: PROLIFERATE considers the non-linear characteristics of complex and adaptive workflows of acute care environments from an end-user perspective. It can monitor real-world clinical settings, research outcomes, and technological products by assessing their fitness via person-centred parameters and a transdisciplinary approach.

Original language	English
Pages	1
Number of pages	1
Publication status	Published - 28 Oct 2022
Event	South Australian Cardiovascular Showcase - Adelaide - SAHMRI, Adelaide , Australia Duration: 28 Oct 2022 → 28 Oct 2022 Conference number: 2 https://sahmri.org.au/news/events/heart-and-vascular-health/sahmri-to-host-state-heart-health-showcase

Other

Other	South Australian Cardiovascular Showcase
Abbreviated title	SA Cardiovascular Showcase
Country/Territory	Australia
City	Adelaide
Period	28/10/22 → 28/10/22
Internet address	https://sahmri.org.au/news/events/heart-and-vascular-health/sahmri-to-host-state-heart-health-showcase

Keywords

artificial intelligence (AI)
Evaluation
Participatory Action Research
Implementation Science
Bayesian analysis
Heart disease
Emergency Care

UN SDGs

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

Cite this

Pinero de Plaza, M. A., Lambrakis, K., Barrera Causil, C. J., Marmolejo Ramos, F., Chew, D., Beleigoli, A., Lawless, M., Archibald, M., Mudd, A., McMillan, P., Morton, E., Ambagtsheer, R., Khan, E., Clark, R., Visvanathan, R., Yadav, L., & Kitson, A. (2022). Predicting the implementation impact of RAPIDx AI in South Australian emergency departments. 1. Poster session presented at South Australian Cardiovascular Showcase, Adelaide , Australia.

@conference{183f251a2cf6477fae97c769c425e5b7,

title = "Predicting the implementation impact of RAPIDx AI in South Australian emergency departments",

abstract = "Background: There were 75,900 presentations to Australian public hospital Emergency Departments (EDs) with a principal diagnosis of Coronary Heart Disease in 2020–21. RAPIDx AI is a randomised controlled trial to test whether computer algorithms in hospital EDs can help doctors provide better care for patients with symptoms that may be due to their heart.Objective: To develop an evaluation and prediction method to measure stakeholders' perspectives about the implementation impact of RAPIDx AI. This methodological innovation is necessary because person-centred healthcare services require effective technology integration within clinical workflows to provide better patient care while considering the needs of all end-users involved and affected by such types of tech/practices/service changes.Methods: We introduce an evaluation framework and method based on complexity science and participatory action research (PROLIFERATE). Using Bayesian statistics, we created a protocol and produced computer-simulated results to demonstrate the evaluation and prediction capabilities of the method concerning RAPIDx AI. Ethical approval was granted by the Southern Adelaide Human Research Ethics Committee (SACHREC): OfR no.272.20Results: Our methodological innovation is informed by 95% probability prediction and credible intervals on these domains of stakeholders' perspectives: Comprehension, Emotional response; Uptake barriers; Motivation and Optimisation. Computer-simulated responses to a PROLIFERATE online survey predicted an Average Impact for RAPIDx AI. The simulation results imply that motivational and emotional knowledge-translation strategies must be implemented for clinicians and the community to improve RAPIDx AI sustainability. (PROLIFERATE constructs benchmarked at 50%—algorithm and data analysis developed in R.)Conclusion: PROLIFERATE considers the non-linear characteristics of complex and adaptive workflows of acute care environments from an end-user perspective. It can monitor real-world clinical settings, research outcomes, and technological products by assessing their fitness via person-centred parameters and a transdisciplinary approach. ",

keywords = "artificial intelligence (AI), Evaluation, Participatory Action Research, Implementation Science, Bayesian analysis, Heart disease, Emergency Care",

author = "{Pinero de Plaza}, {Maria Alejandra} and Kristina Lambrakis and {Barrera Causil}, {Carlos Javier} and {Marmolejo Ramos}, Fernando and Derek Chew and Alline Beleigoli and Michael Lawless and Mandy Archibald and Alexandra Mudd and Penelope McMillan and Erin Morton and Rachel Ambagtsheer and Ehsan Khan and Robyn Clark and Renuka Visvanathan and Lalit Yadav and Alison Kitson",

year = "2022",

month = oct,

day = "28",

language = "English",

pages = "1",

note = "South Australian Cardiovascular Showcase, SA Cardiovascular Showcase ; Conference date: 28-10-2022 Through 28-10-2022",

url = "https://sahmri.org.au/news/events/heart-and-vascular-health/sahmri-to-host-state-heart-health-showcase",

}

Pinero de Plaza, MA, Lambrakis, K, Barrera Causil, CJ, Marmolejo Ramos, F, Chew, D , Beleigoli, A , Lawless, M , Archibald, M , Mudd, A, McMillan, P, Morton, E, Ambagtsheer, R, Khan, E, Clark, R, Visvanathan, R, Yadav, L & Kitson, A 2022, 'Predicting the implementation impact of RAPIDx AI in South Australian emergency departments', South Australian Cardiovascular Showcase, Adelaide , Australia, 28/10/22 - 28/10/22 pp. 1.

TY - CONF

T1 - Predicting the implementation impact of RAPIDx AI in South Australian emergency departments

AU - Pinero de Plaza, Maria Alejandra

AU - Lambrakis, Kristina

AU - Barrera Causil, Carlos Javier

AU - Marmolejo Ramos, Fernando

AU - Chew, Derek

AU - Beleigoli, Alline

AU - Lawless, Michael

AU - Archibald, Mandy

AU - Mudd, Alexandra

AU - McMillan, Penelope

AU - Morton, Erin

AU - Ambagtsheer, Rachel

AU - Khan, Ehsan

AU - Clark, Robyn

AU - Visvanathan, Renuka

AU - Yadav, Lalit

AU - Kitson, Alison

N1 - Conference code: 2

PY - 2022/10/28

Y1 - 2022/10/28

N2 - Background: There were 75,900 presentations to Australian public hospital Emergency Departments (EDs) with a principal diagnosis of Coronary Heart Disease in 2020–21. RAPIDx AI is a randomised controlled trial to test whether computer algorithms in hospital EDs can help doctors provide better care for patients with symptoms that may be due to their heart.Objective: To develop an evaluation and prediction method to measure stakeholders' perspectives about the implementation impact of RAPIDx AI. This methodological innovation is necessary because person-centred healthcare services require effective technology integration within clinical workflows to provide better patient care while considering the needs of all end-users involved and affected by such types of tech/practices/service changes.Methods: We introduce an evaluation framework and method based on complexity science and participatory action research (PROLIFERATE). Using Bayesian statistics, we created a protocol and produced computer-simulated results to demonstrate the evaluation and prediction capabilities of the method concerning RAPIDx AI. Ethical approval was granted by the Southern Adelaide Human Research Ethics Committee (SACHREC): OfR no.272.20Results: Our methodological innovation is informed by 95% probability prediction and credible intervals on these domains of stakeholders' perspectives: Comprehension, Emotional response; Uptake barriers; Motivation and Optimisation. Computer-simulated responses to a PROLIFERATE online survey predicted an Average Impact for RAPIDx AI. The simulation results imply that motivational and emotional knowledge-translation strategies must be implemented for clinicians and the community to improve RAPIDx AI sustainability. (PROLIFERATE constructs benchmarked at 50%—algorithm and data analysis developed in R.)Conclusion: PROLIFERATE considers the non-linear characteristics of complex and adaptive workflows of acute care environments from an end-user perspective. It can monitor real-world clinical settings, research outcomes, and technological products by assessing their fitness via person-centred parameters and a transdisciplinary approach.

AB - Background: There were 75,900 presentations to Australian public hospital Emergency Departments (EDs) with a principal diagnosis of Coronary Heart Disease in 2020–21. RAPIDx AI is a randomised controlled trial to test whether computer algorithms in hospital EDs can help doctors provide better care for patients with symptoms that may be due to their heart.Objective: To develop an evaluation and prediction method to measure stakeholders' perspectives about the implementation impact of RAPIDx AI. This methodological innovation is necessary because person-centred healthcare services require effective technology integration within clinical workflows to provide better patient care while considering the needs of all end-users involved and affected by such types of tech/practices/service changes.Methods: We introduce an evaluation framework and method based on complexity science and participatory action research (PROLIFERATE). Using Bayesian statistics, we created a protocol and produced computer-simulated results to demonstrate the evaluation and prediction capabilities of the method concerning RAPIDx AI. Ethical approval was granted by the Southern Adelaide Human Research Ethics Committee (SACHREC): OfR no.272.20Results: Our methodological innovation is informed by 95% probability prediction and credible intervals on these domains of stakeholders' perspectives: Comprehension, Emotional response; Uptake barriers; Motivation and Optimisation. Computer-simulated responses to a PROLIFERATE online survey predicted an Average Impact for RAPIDx AI. The simulation results imply that motivational and emotional knowledge-translation strategies must be implemented for clinicians and the community to improve RAPIDx AI sustainability. (PROLIFERATE constructs benchmarked at 50%—algorithm and data analysis developed in R.)Conclusion: PROLIFERATE considers the non-linear characteristics of complex and adaptive workflows of acute care environments from an end-user perspective. It can monitor real-world clinical settings, research outcomes, and technological products by assessing their fitness via person-centred parameters and a transdisciplinary approach.

KW - artificial intelligence (AI)

KW - Evaluation

KW - Participatory Action Research

KW - Implementation Science

KW - Bayesian analysis

KW - Heart disease

KW - Emergency Care

UR - https://sahmri.org.au/news/events/heart-and-vascular-health/sahmri-to-host-state-heart-health-showcase

UR - https://twitter.com/MariaAPinero/status/1585745933618544641?s=20&t=RMnWB4bvZes07P_PFyfCDg

M3 - Poster

SP - 1

T2 - South Australian Cardiovascular Showcase

Y2 - 28 October 2022 through 28 October 2022

ER -

Predicting the implementation impact of RAPIDx AI in South Australian emergency departments

Abstract

Other

Keywords

UN SDGs

Other files and links

Fingerprint

ACvA CV Champion

The Vice-President & Executive Dean’s Awards 2021

The Vice-President & Executive Dean’s Awards 2022

A Human-Machine Evaluation of AI in Cardiac Emergencies

CLINICA SUMMIT 2022

New Ways to Solve Complex Problems and PROLIFERATE

Co-designing, measuring, and optimizing innovations and solutions within complex adaptive health systems

Holding the suspension bridge of ongoing high-quality care

Implementation and prospective evaluation of the Country Heart Attack Prevention model of care to improve attendance and completion of cardiac rehabilitation for patients with cardiovascular diseases living in rural Australia: a study protocol

Cite this

Predicting the implementation impact of RAPIDx AI in South Australian emergency departments

Abstract

Other

Keywords

UN SDGs

Other files and links

Fingerprint

Prizes

Activities

Research output

Cite this