Answering real-world clinical questions using large language model based systems

TL;DR

This study evaluates various large language models for answering clinical questions, finding that specialized, purpose-built systems significantly outperform general-purpose models in relevance, reliability, and ability to handle novel queries.

Contribution

The paper demonstrates that combining retrieval-augmented generation and agentic LLMs enhances clinical question answering, highlighting the need for purpose-built healthcare LLM systems.

Findings

General-purpose LLMs rarely produced relevant, evidence-based answers (2%-10%).

RAG-based and agentic LLMs achieved 24%-58% relevance and evidence quality.

Only agentic ChatRWD answered novel questions effectively (65%).

Abstract

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.