基于医患对话的临床发现识别与阴阳性判别  

Clinical Findings Recognition and Yin&Yang Status Inference Based on Doctor-Patient Dialogue

作　　者：林浩楠 谭红叶[1,2] 冯慧敏 LIN Haonan;TAN Hongye;FENG Huimin(School of Computer and Information Technology,Shanxi University,Taiyuan 030006,China;Key Laboratory of Ministry of Education Intelligence and Chinese Information Processing,Shanxi University,Taiyuan 030006,China)

机构地区：[1]山西大学计算机与信息技术学院,太原030006 [2]山西大学计算智能与中文信息处理教育部重点实验室,太原030006

出　　处：《计算机科学》2024年第S02期76-82,共7页Computer Science

基　　金：国家自然科学基金面上项目(62076155)。

摘　　要：临床发现识别与阴阳性判别是智慧医疗领域的重要任务之一,旨在识别医患对话等医疗文本中的疾病与症状,并判断其阴阳性状态。该任务的现有研究主要不足有:(1)缺乏对医患对话语义信息、对话结构等特征的建模,导致模型准确率不高;(2)将该任务分为识别与判别两阶段进行,引起错误累积问题。针对以上不足,提出结合对话信息的统一生成模型,通过构建静态-动态融合图对医患对话语义、结构等信息建模,增强模型的对话理解能力;使用生成式语言模型将临床发现识别与阴阳性判别两个子任务统一为一个序列生成任务,以缓解错误累积问题,并且通过识别阴阳性指示词,辅助模型提高阴阳性判别准确率。在CHIP2021评测数据集CHIP-MDCFNPC上的实验结果表明:所提方法在F1指标上达到了71.83%,比基线模型平均提升了2.82%。Clinical findings recognition and Yin&Yang status inference are import tasks in the field of intelligent healthcare.The goal is to identify clinical findings such as diseases and symptoms from doctor-patient dialogue record,then determine their Yin&Yang status.The main weakness of existing research is as follow:(1)Lack of modeling of semantic information and dialogue structure in doctor-patient dialogues,leading to low model accuracy.(2)Implementing it as a two-stage process,it will cause error accumulation.This paper proposes a unified generative method that incorporates dialogue information.It achieves this by constructing a static-dynamic fusion graph to model semantic and structural information in doctor-patient dialogues,enhancing the model’s understanding of conversations.And utilizes a generative language model to unify clinical findings recognition and Yin&Yang status inference into a sequence generation task,mitigating the problem of error accumulation.Additionally,it improves the accuracy of Yin&Yang statue inference by identifying Yin&Yang statue indicator words.Experimental results on the CHIP2021 evaluation dataset CHIP-MDCFNPC show that the proposed method achieves an F1 score of 71.83%,which is 2.82% higher than the baseline model on average.

关 键 词：医患对话 临床发现识别 阴阳性判别 对话建模 统一生成模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]