Asking the Right Questions: Benchmarking Large Language Models in the Development of Clinical Consultation Templates

TL;DR

This paper benchmarks large language models' ability to generate structured clinical consultation templates, revealing strengths in comprehensiveness but challenges in prioritization and specialty-specific performance, underscoring the need for improved evaluation methods.

Contribution

It introduces a multi-agent pipeline for evaluating LLMs in clinical template generation and highlights their potential and limitations in real-world medical communication.

Findings

Models like o3 achieve high comprehensiveness (up to 92.2%)

Models often generate excessively long templates and struggle with prioritization

Performance varies across medical specialties, with lower accuracy in psychiatry and pain medicine

Abstract

This study evaluates the capacity of large language models (LLMs) to generate structured clinical consultation templates for electronic consultation. Using 145 expert-crafted templates developed and routinely used by Stanford's eConsult team, we assess frontier models -- including o3, GPT-4o, Kimi K2, Claude 4 Sonnet, Llama 3 70B, and Gemini 2.5 Pro -- for their ability to produce clinically coherent, concise, and prioritized clinical question schemas. Through a multi-agent pipeline combining prompt optimization, semantic autograding, and prioritization analysis, we show that while models like o3 achieve high comprehensiveness (up to 92.2\%), they consistently generate excessively long templates and fail to correctly prioritize the most clinically important questions under length constraints. Performance varies across specialties, with significant degradation in narrative-driven fields such as psychiatry and pain medicine. Our findings demonstrate that LLMs can enhance structured clinical information exchange between physicians, while highlighting the need for more robust evaluation methods that capture a model's ability to prioritize clinically salient information within the time constraints of real-world physician communication.