Experienced clinicians adapt decision support usage for complex cases
"It Feels Weird to Just Rely on AI": How Experienced Healthcare Professionals Work With Decision Support Systems in Clinical Practice
Human-Computer Interaction
Summary
Clinicians use computer programs called decision support systems (DSS) that help them make medical decisions. This paper explores how doctors actually use these systems in real hospitals, not just in labs or simple tests. The authors found that as doctors gain experience, they use these tools differently, especially for difficult cases. Doctors also talk with their colleagues about the computer's advice, and how well the system fits into their daily work affects how much they rely on it.
What this means in practice
- •For health it developers: Design DSS interfaces that adapt to clinician experience and support decision discussions for complex medical cases within existing workflows.
- •For hospital management teams: Organize clinical workflows to better integrate DSS tools, enhancing clinician trust and effective use during challenging patient care decisions.
Authors
Simon W. S. Fischer, Hanna Schraffenberger, Miranda L. van Hooff, Casper Reijnen, Serge Thill, Pim Haselager
Abstract
Decision support systems (DSS) assist with clinical decision-making. Little is known, however, about the decision-making process with DSS in clinical practice and the extent to which clinicians consider or rely on the predictions. Studies on human-AI decision-making usually focus on laypeople, simplified decision tasks, or one-shot interactions with prototypes that are not integrated into existing workflows. To gain insights from real-world practice, we conducted an online survey (n=12) and semi-structured interviews (n=10) with clinicians from two different medical cohorts each working with a DSS. Findings show, amongst other things, that the interaction with DSS changes as experience increases, the predictions become more important in complex cases, that decisions are discussed with colleagues, and that workflow integration affects decision-making. Our findings on human, technical, contextual, and organisational factors contribute to a socio-technical perspective on DSS reliance behaviour. We conclude by discussing the implications of our findings for the design of DSS.