From EMR Data to Clinical Insight: An LLM-Driven Framework for Automated Pre-Consultation Questionnaire Generation

TL;DR

This paper introduces a multi-stage LLM-driven framework that extracts, structures, and synthesizes EMR data to automatically generate comprehensive pre-consultation questionnaires, improving clinical information collection efficiency.

Contribution

The paper presents a novel multi-stage framework that explicitly builds clinical knowledge from EMRs for questionnaire generation, addressing limitations of direct LLM approaches.

Findings

Outperforms baseline methods in information coverage and diagnostic relevance

Achieves higher understandability and faster generation times

Validated by clinical experts on real-world EMR data

Abstract

Pre-consultation is a critical component of effective healthcare delivery. However, generating comprehensive pre-consultation questionnaires from complex, voluminous Electronic Medical Records (EMRs) is a challenging task. Direct Large Language Model (LLM) approaches face difficulties in this task, particularly regarding information completeness, logical order, and disease-level synthesis. To address this issue, we propose a novel multi-stage LLM-driven framework: Stage 1 extracts atomic assertions (key facts with timing) from EMRs; Stage 2 constructs personal causal networks and synthesizes disease knowledge by clustering representative networks from an EMR corpus; Stage 3 generates tailored personal and standardized disease-specific questionnaires based on these structured representations. This framework overcomes limitations of direct methods by building explicit clinical knowledge. Evaluated on a real-world EMR dataset and validated by clinical experts, our method demonstrates superior performance in information coverage, diagnostic relevance, understandability, and generation time, highlighting its practical potential to enhance patient information collection.