The Benefits and Risks of LLMs for Facilitating Medical Decision-Making Among Laypersons

We explored the potential of Large Language Models (LLMs) to facilitate laypersons' selection of treatment goals within a complex medical decision-making context. Using ChatGPT-4o, we developed an LLM-enhanced tool to guide users through goal elicitation, clarification, and revision. Our findings demonstrate that LLM features can effectively support these key aspects of decision-making. However, the absence of human interaction, the lack of patient- and context-specific treatment information, and the risk of information overload due to unconstrained access to LLM-generated content present significant risks. To balance the benefits and risks, we propose that LLM-enhanced facilitation tools for asynchronous, independent use should be clinician-initiated, constrain broad information search, and focus on creating a safe space for the exploration of laypersons' preferences and goals regarding the difficult challenges in balancing treatment and tradeoffs for quality of life.