Answering real-world clinical questions using large language model based systems
This addresses the problem of limited and untrustworthy clinical evidence for healthcare decisions, offering a potential solution through specialized LLM systems, though it is incremental as it builds on existing RAG and agentic methods.
The study evaluated five LLM-based systems on answering 50 clinical questions, finding that general-purpose LLMs like ChatGPT-4 rarely produced relevant, evidence-based answers (2-10%), while RAG-based and agentic systems achieved higher rates, with ChatRWD reaching 58% and answering novel questions 65% of the time.
Evidence to guide healthcare decisions is often limited by a lack of relevant and trustworthy literature as well as difficulty in contextualizing existing research for a specific patient. Large language models (LLMs) could potentially address both challenges by either summarizing published literature or generating new studies based on real-world data (RWD). We evaluated the ability of five LLM-based systems in answering 50 clinical questions and had nine independent physicians review the responses for relevance, reliability, and actionability. As it stands, general-purpose LLMs (ChatGPT-4, Claude 3 Opus, Gemini Pro 1.5) rarely produced answers that were deemed relevant and evidence-based (2% - 10%). In contrast, retrieval augmented generation (RAG)-based and agentic LLM systems produced relevant and evidence-based answers for 24% (OpenEvidence) to 58% (ChatRWD) of questions. Only the agentic ChatRWD was able to answer novel questions compared to other LLMs (65% vs. 0-9%). These results suggest that while general-purpose LLMs should not be used as-is, a purpose-built system for evidence summarization based on RAG and one for generating novel evidence working synergistically would improve availability of pertinent evidence for patient care.