Do Physicians Know How to Prompt? The Need for Automatic Prompt Optimization Help in Clinical Note Generation
This addresses the need for more reliable AI assistance in healthcare documentation, though it is incremental by building on existing LLM methods.
The study tackled the problem of inconsistent prompt quality in clinical note generation by introducing an Automatic Prompt Optimization (APO) framework, which improved GPT4's performance in standardizing outputs across note sections.
This study examines the effect of prompt engineering on the performance of Large Language Models (LLMs) in clinical note generation. We introduce an Automatic Prompt Optimization (APO) framework to refine initial prompts and compare the outputs of medical experts, non-medical experts, and APO-enhanced GPT3.5 and GPT4. Results highlight GPT4 APO's superior performance in standardizing prompt quality across clinical note sections. A human-in-the-loop approach shows that experts maintain content quality post-APO, with a preference for their own modifications, suggesting the value of expert customization. We recommend a two-phase optimization process, leveraging APO-GPT4 for consistency and expert input for personalization.