Engaging Multidisciplinary Clinical Users in the Design of an Artificial Intelligence-Powered Graphical User Interface for Intensive Care Unit Instability Decision Support.
Journal
Applied clinical informatics
ISSN: 1869-0327
Titre abrégé: Appl Clin Inform
Pays: Germany
ID NLM: 101537732
Informations de publication
Date de publication:
08 2023
08 2023
Historique:
pmc-release:
04
10
2024
medline:
1
11
2023
pubmed:
5
10
2023
entrez:
4
10
2023
Statut:
ppublish
Résumé
Critical instability forecast and treatment can be optimized by artificial intelligence (AI)-enabled clinical decision support. It is important that the user-facing display of AI output facilitates clinical thinking and workflow for all disciplines involved in bedside care. Our objective is to engage multidisciplinary users (physicians, nurse practitioners, physician assistants) in the development of a graphical user interface (GUI) to present an AI-derived risk score. Intensive care unit (ICU) clinicians participated in focus groups seeking input on instability risk forecast presented in a prototype GUI. Two stratified rounds (three focus groups [only nurses, only providers, then combined]) were moderated by a focus group methodologist. After round 1, GUI design changes were made and presented in round 2. Focus groups were recorded, transcribed, and deidentified transcripts independently coded by three researchers. Codes were coalesced into emerging themes. Twenty-three ICU clinicians participated (11 nurses, 12 medical providers [3 mid-level and 9 physicians]). Six themes emerged: (1) analytics transparency, (2) graphical interpretability, (3) impact on practice, (4) value of trend synthesis of dynamic patient data, (5) decisional weight (weighing AI output during decision-making), and (6) display location (usability, concerns for patient/family GUI view). Nurses emphasized having GUI objective information to support communication and optimal GUI location. While providers emphasized need for recommendation interpretability and concern for impairing trainee critical thinking. All disciplines valued synthesized views of vital signs, interventions, and risk trends but were skeptical of placing decisional weight on AI output until proven trustworthy. Gaining input from all clinical users is important to consider when designing AI-derived GUIs. Results highlight that health care intelligent decisional support systems technologies need to be transparent on how they work, easy to read and interpret, cause little disruption to current workflow, as well as decisional support components need to be used as an adjunct to human decision-making.
Sections du résumé
BACKGROUND
Critical instability forecast and treatment can be optimized by artificial intelligence (AI)-enabled clinical decision support. It is important that the user-facing display of AI output facilitates clinical thinking and workflow for all disciplines involved in bedside care.
OBJECTIVES
Our objective is to engage multidisciplinary users (physicians, nurse practitioners, physician assistants) in the development of a graphical user interface (GUI) to present an AI-derived risk score.
METHODS
Intensive care unit (ICU) clinicians participated in focus groups seeking input on instability risk forecast presented in a prototype GUI. Two stratified rounds (three focus groups [only nurses, only providers, then combined]) were moderated by a focus group methodologist. After round 1, GUI design changes were made and presented in round 2. Focus groups were recorded, transcribed, and deidentified transcripts independently coded by three researchers. Codes were coalesced into emerging themes.
RESULTS
Twenty-three ICU clinicians participated (11 nurses, 12 medical providers [3 mid-level and 9 physicians]). Six themes emerged: (1) analytics transparency, (2) graphical interpretability, (3) impact on practice, (4) value of trend synthesis of dynamic patient data, (5) decisional weight (weighing AI output during decision-making), and (6) display location (usability, concerns for patient/family GUI view). Nurses emphasized having GUI objective information to support communication and optimal GUI location. While providers emphasized need for recommendation interpretability and concern for impairing trainee critical thinking. All disciplines valued synthesized views of vital signs, interventions, and risk trends but were skeptical of placing decisional weight on AI output until proven trustworthy.
CONCLUSION
Gaining input from all clinical users is important to consider when designing AI-derived GUIs. Results highlight that health care intelligent decisional support systems technologies need to be transparent on how they work, easy to read and interpret, cause little disruption to current workflow, as well as decisional support components need to be used as an adjunct to human decision-making.
Identifiants
pubmed: 37793618
doi: 10.1055/s-0043-1775565
pmc: PMC10550364
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
789-802Subventions
Organisme : NINR NIH HHS
ID : F31 NR019725
Pays : United States
Informations de copyright
Thieme. All rights reserved.
Déclaration de conflit d'intérêts
None declared.
Références
Crit Care Med. 2017 Oct;45(10):1751-1761
pubmed: 28749855
Ann Am Thorac Soc. 2017 Mar;14(3):384-391
pubmed: 28033032
Comput Inform Nurs. 2017 Jun;35(6):281-288
pubmed: 28005564
Cardiol Young. 2021 Nov;31(11):1770-1780
pubmed: 34725005
Crit Care Nurse. 2019 Oct;39(5):14-20
pubmed: 31575590
Aust Health Rev. 2020 Sep;44(5):661-665
pubmed: 31744594
J Clin Monit Comput. 2019 Dec;33(6):973-985
pubmed: 30767136
JAMA. 2018 Dec 4;320(21):2199-2200
pubmed: 30398550
Appl Clin Inform. 2020 Jan;11(1):34-45
pubmed: 31940670
Crit Care Explor. 2020 Jun 11;2(6):e0142
pubmed: 32696005
Artif Intell Med. 2009 May;46(1):5-17
pubmed: 18790621
J Hosp Med. 2017 Sep;12(9):743-746
pubmed: 28914280
Appl Clin Inform. 2021 Mar;12(2):208-221
pubmed: 33853140
Appl Clin Inform. 2020 Aug;11(4):680-691
pubmed: 33058103
NAM Perspect. 2021 Sep 08;2021:
pubmed: 34901780
Crit Care. 2020 Nov 25;24(1):661
pubmed: 33234161
AMA J Ethics. 2019 Feb 1;21(2):E146-152
pubmed: 30794124
JAMA. 2020 Feb 11;323(6):509-510
pubmed: 31845963
Nurs Open. 2021 Jul;8(4):1788-1796
pubmed: 33638617
Int J Med Inform. 2015 Feb;84(2):87-100
pubmed: 25453274
Jt Comm J Qual Patient Saf. 2020 Apr;46(4):207-216
pubmed: 32085952
BMJ Open. 2019 Dec 2;9(12):e031988
pubmed: 31796483
J Biomed Inform. 2017 Jul;71:211-221
pubmed: 28579532
Implement Sci. 2018 Jul 4;13(1):91
pubmed: 29973225
J Prim Care Community Health. 2019 Jan-Dec;10:2150132719829315
pubmed: 30767602
Int J Med Inform. 2022 Mar;159:104643
pubmed: 34973608
J Med Syst. 2017 Nov 20;42(1):5
pubmed: 29159719
Appl Clin Inform. 2022 Mar;13(2):339-354
pubmed: 35388447
Jt Comm J Qual Patient Saf. 2017 Dec;43(12):676-685
pubmed: 29173289
Aust Health Rev. 2019 Jan;43(6):656-661
pubmed: 30384880