From Retrieving Information to Reasoning with AI: Exploring Different Interaction Modalities to Support Human-AI Coordination in Clinical Decision-Making

TL;DR

This study explores how clinicians perceive various interaction modalities with AI tools, revealing preferences and limitations in using LLMs for decision support, emphasizing the need for tailored interaction methods.

Contribution

It provides qualitative insights into clinicians' use and perceptions of different AI interaction modalities, highlighting the importance of diverse approaches for effective clinical decision support.

Findings

Clinicians mainly used LLMs for information retrieval and confirmation.

Interaction preferences varied based on individual cognitive styles.

No single modality was universally preferred or most effective.

Abstract

LLMs are popular among clinicians for decision-support because of simple text-based interaction. However, their impact on clinicians' performance is ambiguous. Not knowing how clinicians use this new technology and how they compare it to traditional clinical decision-support systems (CDSS) restricts designing novel mechanisms that overcome existing tool limitations and enhance performance and experience. This qualitative study examines how clinicians (n=12) perceive different interaction modalities (text-based conversation with LLMs, interactive and static UI, and voice) for decision-support. In open-ended use of LLM-based tools, our participants took a tool-centric approach using them for information retrieval and confirmation with simple prompts instead of use as active deliberation partners that can handle complex questions. Critical engagement emerged with changes to the interaction setup. Engagement also differed with individual cognitive styles. Lastly, benefits and drawbacks of interaction with text, voice and traditional UIs for clinical decision-support show the lack of a one-size-fits-all interaction modality.