基于自然语言处理的病历智能质控系统的研究与应用  

Research and application of intelligent quality control system for medical records based on natural language processing

作　　者：尹思艺 庞晓燕[2] 蔡秀军[2] 林辉[2] 乔凯[2] 王可心 徐哲 YIN Siyi;PANG Xiaoyan;CAI Xiujun;LIN Hui;QIAO Kai;WANG Kexin;XU Zhe(Data Operation Division,Medical Management Center,National Health Commission of the People's Republic of China,Beijing 100044,China;Office of Internet,Sir Run Run Shaw Hospital,Zhejiang University School of Medicine,Zhejiang,Hangzhou 310016,China;Department of Traditional Chinese Medicine,Beijing Liujiayao Medical Hospital,Beijing 100075,China;Departmentof Technology,Hangzhou Lantone Information Technology Limited Company Technology Department,Zhejiang,Hangzhou 310053,China)

机构地区：[1]国家卫生健康委医管中心数据运行处,北京100044 [2]浙江大学医学院附属邵逸夫医院互联网办公室,浙江杭州310016 [3]北京刘家窑中医院中西医科,北京100075 [4]杭州朗通信息技术有限公司技术部,浙江杭州310053

出　　处：《中国医药科学》2021年第16期1-4,共4页China Medicine And Pharmacy

摘　　要：目的探讨基于自然语言的病历内涵缺陷质控模型的研究与应用,探索有效的质控方法,规范病历书写流程,解决事后质控存在的缺陷和不足。方法通过医学自然语言处理、术语映射和前沿的深度学习等技术,实现对多元异构医疗数据的清洗归类和建模应用。结果通过上述方法提高了对病历文本的语义识别和理解能力,规范了病历书写流程,解决了病历书写格式混乱、病历内容缺陷和内涵质量低下等问题。结论基于自然语言处理及知识库的智能病历全流程质控系统可以实现对病历文本自然语言的识别和理解,能够对病历文书的完整性、时限性、逻辑性、合规性等方面进行内涵缺陷审核与评价。Objective To explore effective quality control methods,standardize medical record writing process and solve the defects and deficiencies of post-factum quality control by the research and application of quality control model based on natural language for medical record connotation defects.Methods Through medical natural language processing,terminology mapping and cutting-edge deep learning technologies,the cleaning and categorization and the modeling application of multiple heterogeneous medical data were realized.Results The above methods improved the semantic recognition and understanding of medical record text,standardized the medical record writing process and solvedsuch problems as confusing medical record writing format,defective medical record content and low connotation quality.Conclusion The intelligent whole process quality control system for medical records based on natural language processing and knowledge base can realize natural language recognition and understanding of medical record text.Besides,the system can audit and evaluate medical record documents in terms of completeness,timeliness,logic and compliance for connotation defects.

关 键 词：内涵质控 质控系统 自然语言处理 深度学习 

分 类 号：R197.323[医药卫生—卫生事业管理]