Abstract

Info

Title:: Development and validation of a Web-crawler-based medical records information aggregation tool

Author(s):: LIU Hongjia1; 2; WANG Jing3; HUANG Yuliang1; 2; LI Chenguang1; 2; WU Hao1; 2; MA Wenjun4; CAO Wentian4; ZHANG Yibao1; 2; 1. Institute of Medical Technology, Peking University Health Science Center, Beijing 100191, China 2. Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing 100142, China 3. Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou 310202, China 4. School of Physics, Peking University, Beijing 100871, China

Keywords:: Keywords: Web crawler automatic analysis big data hospital information system

Abstract:: Abstract: Objective To develop and validate a Web-crawler-based medical records information aggregation tool for the clinical and research practices in Department of Radiation Oncology. Methods Based on Selenium framework and Python programming language, a Web-crawler-based medical records information aggregation tool was designed. The benefits of the proposed tool for clinical workflow were analyzed under two scenarios, namely the data preparation for retrospective study and the aggregate report of routine clinical examination results of newly-admitted patients. Moreover, the efficiency and accuracy between automatic and manual methods were also compared. Results Compared with manual method, the automatic information aggregation tool had superior efficiency and accuracy. For the first scenario, automatic method identified 110 radiation pneumonia cases out of 3 541 cases at the time cost of about 54 s per case, while manual methods also identified the same number of radiation pneumonia cases but cost about 90 s per case. For the other scenario, automatic method cost about 10 s per case and manual method cost 75 s per case. Conclusion The Web-crawler-based medical records information aggregation tool can implement special functions such as data retrieval and subtotal for clinical and scientific researches under low access rights, with the advantages of security, efficiency, accuracy, cross-platform and easy-to-extend application.