Improving Clinical Note Generation from Complex Doctor-Patient Conversation

2024-08-26

arXiv.org

AI Summary

Clinical documentation consumes substantial time, severely impeding physician–patient interaction. To address this critical efficiency bottleneck, we propose an end-to-end framework for generating structured clinical notes directly from doctor–patient dialogues. Our contributions are threefold: (1) We introduce CliniKnote—the first high-quality, human-annotated dialogue–note paired dataset; (2) We design K-SOAP, an enhanced structured format extending SOAP with a dedicated Keyword layer to support fine-grained clinical semantic modeling; (3) We develop a format-constrained decoding strategy coupled with medical expert-in-the-loop data curation, overcoming key limitations of standard LLM fine-tuning. Evaluated on real-world, complex clinical dialogues, our method achieves state-of-the-art performance across accuracy, completeness, and clinical utility metrics, while significantly improving generation efficiency over baselines.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Writing clinical notes and documenting medical exams is a critical task for healthcare professionals, serving as a vital component of patient care documentation. However, manually writing these notes is time-consuming and can impact the amount of time clinicians can spend on direct patient interaction and other tasks. Consequently, the development of automated clinical note generation systems has emerged as a clinically meaningful area of research within AI for health. In this paper, we present three key contributions to the field of clinical note generation using large language models (LLMs). First, we introduce CliniKnote, a comprehensive dataset consisting of 1,200 complex doctor-patient conversations paired with their full clinical notes. This dataset, created and curated by medical experts with the help of modern neural networks, provides a valuable resource for training and evaluating models in clinical note generation tasks. Second, we propose the K-SOAP (Keyword, Subjective, Objective, Assessment, and Plan) note format, which enhances traditional SOAP~cite{podder2023soap} (Subjective, Objective, Assessment, and Plan) notes by adding a keyword section at the top, allowing for quick identification of essential information. Third, we develop an automatic pipeline to generate K-SOAP notes from doctor-patient conversations and benchmark various modern LLMs using various metrics. Our results demonstrate significant improvements in efficiency and performance compared to standard LLM finetuning methods.

Problem

• Automate clinical note generation from doctor-patient conversations
• Reduce time spent on manual note writing by clinicians
• Enhance SOAP notes with keyword section for quick reference

Innovation

• CliniKnote dataset with 1200 doctor-patient conversations
• K-SOAP note format with keyword section
• Automatic pipeline for K-SOAP note generation