From EMR Data to Clinical Insight: An LLM-Driven Framework for Automated Pre-Consultation Questionnaire Generation
This work addresses the problem of inefficient patient information collection in healthcare by automating questionnaire generation, though it is incremental as it builds on existing LLM methods with structured clinical knowledge.
The paper tackles the challenge of generating comprehensive pre-consultation questionnaires from Electronic Medical Records (EMRs) by proposing a multi-stage LLM-driven framework that extracts atomic assertions, constructs personal causal networks, and synthesizes disease knowledge, resulting in superior performance in information coverage, diagnostic relevance, understandability, and generation time as validated on a real-world dataset.
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.