文献类型：期刊文献

英文题名：QAnalysis: a question-answer driven analytic tool on knowledge graphs for leveraging electronic medical records for clinical research

作者：Ruan, Tong[1];Huang, Yueqi[1];Liu, Xuli[1];Xia, Yuhang[1];Gao, Ju[2]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[2]Shanghai Shuguang Hosp, Shanghai 200021, Peoples R China

年份：2019

卷号：19

外文期刊名：BMC MEDICAL INFORMATICS AND DECISION MAKING

收录：;WOS:【SCI-EXPANDED(收录号:WOS:000463058800001)】；

基金：This work is supported by National Natural Science Foundation of China (No. 61772201), The 863 plan of China Ministry of Science and Technology (No. 2015AA020107), The Science and Technology Innovation Project of Shanghai Science and Technology Commission (No. 16511101000) and National Science and Technology Support Program of China (No. 2015BAH12 F01-05). The funders had no role in the design of the study, collection, analysis and interpretation of data, or writing the manuscript.

语种：英文

外文关键词：Electronic medical record; Statistical question answering; Graph database; Context-free grammar

摘要：BackgroundWhile doctors should analyze a large amount of electronic medical record (EMR) data to conduct clinical research, the analyzing process requires information technology (IT) skills, which is difficult for most doctors in China.MethodsIn this paper, we build a novel tool QAnalysis, where doctors enter their analytic requirements in their natural language and then the tool returns charts and tables to the doctors. For a given question from a user, we first segment the sentence, and then we use grammar parser to analyze the structure of the sentence. After linking the segmentations to concepts and predicates in knowledge graphs, we convert the question into a set of triples connected with different kinds of operators. These triples are converted to queries in Cypher, the query language for Neo4j. Finally, the query is executed on Neo4j, and the results shown in terms of tables and charts are returned to the user.ResultsThe tool supports top 50 questions we gathered from two hospital departments with the Delphi method. We also gathered 161 questions from clinical research papers with statistical requirements on EMR data. Experimental results show that our tool can directly cover 78.20% of these statistical questions and the precision is as high as 96.36%. Such extension is easy to achieve with the help of knowledge-graph technology we have adopted. The recorded demo can be accessed from https://github.com/NLP-BigDataLab/QAnalysis-project.ConclusionOur tool shows great flexibility in processing different kinds of statistic questions, which provides a convenient way for doctors to get statistical results directly in natural language.