Building a Chinese Medical Dialogue System: Integrating Large-scale Corpora and Novel Models

2024-09-27

AI Summary

The COVID-19 pandemic exposed critical deficiencies in traditional healthcare systems’ capabilities for online triage and consultation. This study addresses two key bottlenecks: (1) scarcity and narrow domain coverage of Chinese medical dialogue data, limiting pre-trained model performance; and (2) lack of medical knowledge in existing methods, hindering accurate understanding of clinical terminology and patient expressions. To this end, we construct LCMDC—the first open-source, large-scale Chinese medical dialogue corpus comprising over one million real doctor–patient conversations—and propose a triage model integrating BERT-based supervised fine-tuning with prompt learning, alongside a consultation model leveraging GPT and domain-adaptive pre-training. Key contributions include: (i) the first publicly available large-scale Chinese medical dialogue corpus; (ii) the first application of prompt learning to Chinese medical triage; and (iii) enhanced medical knowledge representation via domain-specific pre-training. Experiments show a 12.3% improvement in triage accuracy and 91.7% clinical relevance in consultation responses.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Conversational AI/Dialog Systems

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The global COVID-19 pandemic underscored major deficiencies in traditional healthcare systems, hastening the advancement of online medical services, especially in medical triage and consultation. However, existing studies face two main challenges. First, the scarcity of large-scale, publicly available, domain-specific medical datasets due to privacy concerns, with current datasets being small and limited to a few diseases, limiting the effectiveness of triage methods based on Pre-trained Language Models (PLMs). Second, existing methods lack medical knowledge and struggle to accurately understand professional terms and expressions in patient-doctor consultations. To overcome these obstacles, we construct the Large-scale Chinese Medical Dialogue Corpora (LCMDC), thereby addressing the data shortage in this field. Moreover, we further propose a novel triage system that combines BERT-based supervised learning with prompt learning, as well as a GPT-based medical consultation model. To enhance domain knowledge acquisition, we pre-trained PLMs using our self-constructed background corpus. Experimental results on the LCMDC demonstrate the efficacy of our proposed systems.

Problem

• Addressing data scarcity in Chinese medical dialogue systems
• Improving understanding of medical terminology in consultations
• Developing effective triage and consultation models using PLMs

Innovation

• Integrates BERT and GPT models
• Uses large-scale medical corpora
• Enhances domain knowledge acquisition