Natural Language Programming in Medicine: Administering Evidence Based Clinical Workflows with Autonomous Agents Powered by Generative Large Language Models
This addresses the challenge of using LLMs for clinical decision-making in healthcare, though it is incremental by building on existing methods like RAG and expert oversight.
The study evaluated generative large language models (LLMs) as autonomous agents in a simulated medical center, finding that proprietary models like GPT-4, enhanced with Retrieval Augmented Generation (RAG), improved guideline adherence and response accuracy in clinical cases.
Generative Large Language Models (LLMs) hold significant promise in healthcare, demonstrating capabilities such as passing medical licensing exams and providing clinical knowledge. However, their current use as information retrieval tools is limited by challenges like data staleness, resource demands, and occasional generation of incorrect information. This study assessed the potential of LLMs to function as autonomous agents in a simulated tertiary care medical center, using real-world clinical cases across multiple specialties. Both proprietary and open-source LLMs were evaluated, with Retrieval Augmented Generation (RAG) enhancing contextual relevance. Proprietary models, particularly GPT-4, generally outperformed open-source models, showing improved guideline adherence and more accurate responses with RAG. The manual evaluation by expert clinicians was crucial in validating models' outputs, underscoring the importance of human oversight in LLM operation. Further, the study emphasizes Natural Language Programming (NLP) as the appropriate paradigm for modifying model behavior, allowing for precise adjustments through tailored prompts and real-world interactions. This approach highlights the potential of LLMs to significantly enhance and supplement clinical decision-making, while also emphasizing the value of continuous expert involvement and the flexibility of NLP to ensure their reliability and effectiveness in healthcare settings.