Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Dec 5, 2024
Open Peer Review Period: Dec 6, 2024 - Jan 31, 2025
Date Accepted: Jan 28, 2025
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Trust in AI-Based Clinical Decision Support Systems Among Healthcare Workers: A Systematic Review
ABSTRACT
Background:
Artificial intelligence-based Clinical Decision Support Systems (AI-CDSS) have offered personalized medicine and improved healthcare efficiency to healthcare workers. Despite opportunities, trust in these tools remains a critical factor for their successful integration. Existing research lacks synthesized insights and actionable recommendations for providing healthcare workers' trust in AI-CDSS.
Objective:
The study aims to identify and synthesize factors for guiding in designing systems that foster healthcare worker trust in AI-CDSS.
Methods:
We performed a systematic review of published studies from January 2020 to November 2024 that were retrieved from PubMed, Scopus, and Google Scholar, focusing on healthcare workers’ perceptions, experiences, and trust in AI-CDSS. Two independent reviewers utilized the Cochrane Collaboration Handbook and PRISMA 2020 guidelines to develop a data charter and synthesize the study data. The CASP tool was applied to assess the quality of the studies included and evaluate the risk of bias, ensuring a rigorous and systematic review process.
Results:
The review included 27 studies that met the inclusion criteria, across diverse healthcare workers predominantly in hospitalized settings. Qualitative methods dominated (n=16,59%), with sample sizes ranging from small focus groups to over 1,000 participants. Seven key themes were identified: System Transparency, Training and Familiarity, System Usability, Clinical Reliability, Credibility and Validation, Ethical Considerations, and Customization and Control through enablers and barriers that impact healthcare workers’ trust in AI-based CDSS.
Conclusions:
From seven thematic areas, enablers such as transparency, training, usability, and clinical reliability, while barriers include algorithmic opacity and ethical concerns. Recommendations emphasize the explainability of AI models, comprehensive training, stakeholder involvement, and human-centered design for healthcare worker trust in AI-CDSS.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.