Clinician preimplementation perspectives of a decision-support tool for the prediction of cardiac arrhythmia based on machine learning: near-live feasibility and qualitative study

Publikation: Bidrag til tidsskriftTidsskriftartikelfagfællebedømt

Standard

Clinician preimplementation perspectives of a decision-support tool for the prediction of cardiac arrhythmia based on machine learning : near-live feasibility and qualitative study. / Matthiesen, Stina; Diederichsen, Søren Zöga; Hansen, Mikkel Klitzing Hartmann; Villumsen, Christina; Lassen, Mats Christian Højbjerg; Jacobsen, Peter Karl; Risum, Niels; Winkel, Bo Gregers; Philbert, Berit T.; Svendsen, Jesper Hastrup; Andersen, Tariq Osman.

I: JMIR Human Factors, Bind 8, Nr. 4, e26964, 2021.

Publikation: Bidrag til tidsskriftTidsskriftartikelfagfællebedømt

Harvard

Matthiesen, S, Diederichsen, SZ, Hansen, MKH, Villumsen, C, Lassen, MCH, Jacobsen, PK, Risum, N, Winkel, BG, Philbert, BT, Svendsen, JH & Andersen, TO 2021, 'Clinician preimplementation perspectives of a decision-support tool for the prediction of cardiac arrhythmia based on machine learning: near-live feasibility and qualitative study', JMIR Human Factors, bind 8, nr. 4, e26964. https://doi.org/10.2196/26964

APA

Matthiesen, S., Diederichsen, S. Z., Hansen, M. K. H., Villumsen, C., Lassen, M. C. H., Jacobsen, P. K., Risum, N., Winkel, B. G., Philbert, B. T., Svendsen, J. H., & Andersen, T. O. (2021). Clinician preimplementation perspectives of a decision-support tool for the prediction of cardiac arrhythmia based on machine learning: near-live feasibility and qualitative study. JMIR Human Factors, 8(4), [e26964]. https://doi.org/10.2196/26964

Vancouver

Matthiesen S, Diederichsen SZ, Hansen MKH, Villumsen C, Lassen MCH, Jacobsen PK o.a. Clinician preimplementation perspectives of a decision-support tool for the prediction of cardiac arrhythmia based on machine learning: near-live feasibility and qualitative study. JMIR Human Factors. 2021;8(4). e26964. https://doi.org/10.2196/26964

Author

Matthiesen, Stina ; Diederichsen, Søren Zöga ; Hansen, Mikkel Klitzing Hartmann ; Villumsen, Christina ; Lassen, Mats Christian Højbjerg ; Jacobsen, Peter Karl ; Risum, Niels ; Winkel, Bo Gregers ; Philbert, Berit T. ; Svendsen, Jesper Hastrup ; Andersen, Tariq Osman. / Clinician preimplementation perspectives of a decision-support tool for the prediction of cardiac arrhythmia based on machine learning : near-live feasibility and qualitative study. I: JMIR Human Factors. 2021 ; Bind 8, Nr. 4.

Bibtex

@article{6fa2705175fb4569b273cb4512bfcffb,
title = "Clinician preimplementation perspectives of a decision-support tool for the prediction of cardiac arrhythmia based on machine learning: near-live feasibility and qualitative study",
abstract = "Background: Artificial intelligence (AI), such as machine learning (ML), shows great promise for improving clinical decision-making in cardiac diseases by outperforming statistical-based models. However, few AI-based tools have been implemented in cardiology clinics because of the sociotechnical challenges during transitioning from algorithm development to real-world implementation. Objective: This study explored how an ML-based tool for predicting ventricular tachycardia and ventricular fibrillation (VT/VF) could support clinical decision-making in the remote monitoring of patients with an implantable cardioverter defibrillator (ICD). Methods: Seven experienced electrophysiologists participated in a near-live feasibility and qualitative study, which included walkthroughs of 5 blinded retrospective patient cases, use of the prediction tool, and questionnaires and interview questions. All sessions were video recorded, and sessions evaluating the prediction tool were transcribed verbatim. Data were analyzed through an inductive qualitative approach based on grounded theory. Results: The prediction tool was found to have potential for supporting decision-making in ICD remote monitoring by providing reassurance, increasing confidence, acting as a second opinion, reducing information search time, and enabling delegation of decisions to nurses and technicians. However, the prediction tool did not lead to changes in clinical action and was found less useful in cases where the quality of data was poor or when VT/VF predictions were found to be irrelevant for evaluating the patient. Conclusions: When transitioning from AI development to testing its feasibility for clinical implementation, we need to consider the following: Expectations must be aligned with the intended use of AI; trust in the prediction tool is likely to emerge from real-world use; and AI accuracy is relational and dependent on available information and local workflows. Addressing the sociotechnical gap between the development and implementation of clinical decision-support tools based on ML in cardiac care is essential for succeeding with adoption. It is suggested to include clinical end-users, clinical contexts, and workflows throughout the overall iterative approach to design, development, and implementation.",
keywords = "Artificial intelligence, Cardiac arrhythmia, Clinical decision support systems, Implantable cardioverter defibrillator, Machine learning, Preimplementation, Qualitative study, Remote follow-up, Short-term prediction, Sociotechnical",
author = "Stina Matthiesen and Diederichsen, {S{\o}ren Z{\"o}ga} and Hansen, {Mikkel Klitzing Hartmann} and Christina Villumsen and Lassen, {Mats Christian H{\o}jbjerg} and Jacobsen, {Peter Karl} and Niels Risum and Winkel, {Bo Gregers} and Philbert, {Berit T.} and Svendsen, {Jesper Hastrup} and Andersen, {Tariq Osman}",
note = "Publisher Copyright: {\textcopyright} 2021 JMIR Human Factors. All rights reserved.",
year = "2021",
doi = "10.2196/26964",
language = "English",
volume = "8",
journal = "JMIR Human Factors",
issn = "2292-9495",
publisher = "JMIR Publications Inc.",
number = "4",

}

RIS

TY - JOUR

T1 - Clinician preimplementation perspectives of a decision-support tool for the prediction of cardiac arrhythmia based on machine learning

T2 - near-live feasibility and qualitative study

AU - Matthiesen, Stina

AU - Diederichsen, Søren Zöga

AU - Hansen, Mikkel Klitzing Hartmann

AU - Villumsen, Christina

AU - Lassen, Mats Christian Højbjerg

AU - Jacobsen, Peter Karl

AU - Risum, Niels

AU - Winkel, Bo Gregers

AU - Philbert, Berit T.

AU - Svendsen, Jesper Hastrup

AU - Andersen, Tariq Osman

N1 - Publisher Copyright: © 2021 JMIR Human Factors. All rights reserved.

PY - 2021

Y1 - 2021

N2 - Background: Artificial intelligence (AI), such as machine learning (ML), shows great promise for improving clinical decision-making in cardiac diseases by outperforming statistical-based models. However, few AI-based tools have been implemented in cardiology clinics because of the sociotechnical challenges during transitioning from algorithm development to real-world implementation. Objective: This study explored how an ML-based tool for predicting ventricular tachycardia and ventricular fibrillation (VT/VF) could support clinical decision-making in the remote monitoring of patients with an implantable cardioverter defibrillator (ICD). Methods: Seven experienced electrophysiologists participated in a near-live feasibility and qualitative study, which included walkthroughs of 5 blinded retrospective patient cases, use of the prediction tool, and questionnaires and interview questions. All sessions were video recorded, and sessions evaluating the prediction tool were transcribed verbatim. Data were analyzed through an inductive qualitative approach based on grounded theory. Results: The prediction tool was found to have potential for supporting decision-making in ICD remote monitoring by providing reassurance, increasing confidence, acting as a second opinion, reducing information search time, and enabling delegation of decisions to nurses and technicians. However, the prediction tool did not lead to changes in clinical action and was found less useful in cases where the quality of data was poor or when VT/VF predictions were found to be irrelevant for evaluating the patient. Conclusions: When transitioning from AI development to testing its feasibility for clinical implementation, we need to consider the following: Expectations must be aligned with the intended use of AI; trust in the prediction tool is likely to emerge from real-world use; and AI accuracy is relational and dependent on available information and local workflows. Addressing the sociotechnical gap between the development and implementation of clinical decision-support tools based on ML in cardiac care is essential for succeeding with adoption. It is suggested to include clinical end-users, clinical contexts, and workflows throughout the overall iterative approach to design, development, and implementation.

AB - Background: Artificial intelligence (AI), such as machine learning (ML), shows great promise for improving clinical decision-making in cardiac diseases by outperforming statistical-based models. However, few AI-based tools have been implemented in cardiology clinics because of the sociotechnical challenges during transitioning from algorithm development to real-world implementation. Objective: This study explored how an ML-based tool for predicting ventricular tachycardia and ventricular fibrillation (VT/VF) could support clinical decision-making in the remote monitoring of patients with an implantable cardioverter defibrillator (ICD). Methods: Seven experienced electrophysiologists participated in a near-live feasibility and qualitative study, which included walkthroughs of 5 blinded retrospective patient cases, use of the prediction tool, and questionnaires and interview questions. All sessions were video recorded, and sessions evaluating the prediction tool were transcribed verbatim. Data were analyzed through an inductive qualitative approach based on grounded theory. Results: The prediction tool was found to have potential for supporting decision-making in ICD remote monitoring by providing reassurance, increasing confidence, acting as a second opinion, reducing information search time, and enabling delegation of decisions to nurses and technicians. However, the prediction tool did not lead to changes in clinical action and was found less useful in cases where the quality of data was poor or when VT/VF predictions were found to be irrelevant for evaluating the patient. Conclusions: When transitioning from AI development to testing its feasibility for clinical implementation, we need to consider the following: Expectations must be aligned with the intended use of AI; trust in the prediction tool is likely to emerge from real-world use; and AI accuracy is relational and dependent on available information and local workflows. Addressing the sociotechnical gap between the development and implementation of clinical decision-support tools based on ML in cardiac care is essential for succeeding with adoption. It is suggested to include clinical end-users, clinical contexts, and workflows throughout the overall iterative approach to design, development, and implementation.

KW - Artificial intelligence

KW - Cardiac arrhythmia

KW - Clinical decision support systems

KW - Implantable cardioverter defibrillator

KW - Machine learning

KW - Preimplementation

KW - Qualitative study

KW - Remote follow-up

KW - Short-term prediction

KW - Sociotechnical

U2 - 10.2196/26964

DO - 10.2196/26964

M3 - Journal article

C2 - 34842528

AN - SCOPUS:85120160021

VL - 8

JO - JMIR Human Factors

JF - JMIR Human Factors

SN - 2292-9495

IS - 4

M1 - e26964

ER -

ID: 286992302