"It's the future, come on!": a think aloud study exploring clinicians' use of knowledge-based AI decision support

Area of Science:

• Healthcare technology
• Clinical decision support systems
• Artificial intelligence in medicine

Background:

• AI-based clinical decision support (CDS) is proposed to address healthcare capacity challenges.
• A significant implementation gap exists for AI CDS.
• Existing research often relies on abstract definitions or general participant understanding of AI, lacking specific context.

Purpose of the Study:

• To address the research gap by examining the practical experience of AI CDS.
• To explore barriers and enablers of AI CDS implementation through direct user experience.
• To provide insights into the practical application of AI CDS before widespread adoption.

Main Methods:

• Phenomenological perspective with think-aloud protocol and cognitive interviews.
• Recruited 14 participants (5 doctors, 9 physiotherapists).
• Participants used a prototype AI CDS for assessing serious pathology in low back pain patients; analysis used grounded theory.

Main Results:

• Three themes emerged: Attitudes, Workflow, and Patient Navigation.
• Clinicians identified barriers and enablers within their work context, noting potential for decision support.
• Workflow integration, design, prompts, and clinical reasoning were crucial; timesaving features and organizational support were facilitators.

Conclusions:

• Directly exploring clinicians' experiences offers valuable insights into practical AI CDS application.
• Participants remained solution-focused, regardless of initial attitudes towards AI.
• The study highlighted how AI CDS can influence clinical judgment and patient journey navigation.