Human-Algorithmic Interaction Using a Large Language Model-Augmented Artificial Intelligence Clinical Decision Support System

要旨

Integration of artificial intelligence (AI) into clinical decision support systems (CDSS) poses a socio-technological challenge that is impacted by usability, trust, and human-computer interaction (HCI). AI-CDSS interventions have shown limited benefit in clinical outcomes, which may be due to insufficient understanding of how health-care providers interact with AI systems. Large language models (LLMs) have the potential to enhance AI-CDSS, but haven't been studied in either simulated or real-world clinical scenarios. We present findings from a randomized controlled trial deploying AI-CDSS for the management of upper gastrointestinal bleeding (UGIB) with and without an LLM interface within realistic clinical simulations for physician and medical student participants. We find evidence that LLM augmentation improves ease-of-use, that LLM-generated responses with citations improve trust, and HCI varies based on clinical expertise. Qualitative themes from interviews suggest the perception of LLM-augmented AI-CDSS as a team-member used to confirm initial clinical intuitions and help evaluate borderline decisions.

著者
Niroop Channa. Rajashekar
Yale School of Medicine, New Haven, Connecticut, United States
Yeo Eun Shin
Yale Medicine, New Haven, Connecticut, United States
Yuan Pu
Yale School of Medicine, New Haven, Connecticut, United States
Sunny Chung
Yale School of Medicine, New Haven, Connecticut, United States
Kisung You
CUNY Baruch College, New York, New York, United States
Mauro Giuffre
Yale School of Medicine, New Haven, Connecticut, United States
Colleen E. Chan
Yale University , New Haven, Connecticut, United States
Theo Saarinen
University of California, Berkeley, Berkeley, California, United States
Allen Hsiao
Yale School of Medicine, New Haven, Connecticut, United States
Jasjeet Sekhon
Yale University, New Haven, Connecticut, United States
Ambrose H. Wong
Yale University, New Haven, Connecticut, United States
Leigh V. Evans
Yale School of Medicine, New Haven, Connecticut, United States
Rene F.. Kizilcec
Cornell University, Ithaca, New York, United States
Loren Laine
Yale School of Medicine, New Havent, Connecticut, United States
Terika McCall
Yale School of Public Health, New Haven, Connecticut, United States
Dennis Shung
Yale School of Medicine, New Haven, Connecticut, United States
論文URL

https://doi.org/10.1145/3613904.3642024

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Health and AI B

315
5 件の発表
2024-05-16 01:00:00
2024-05-16 02:20:00