Fujita Katsuhide, Akiyama Masanori, Toyama Nobuyuki, Kamemori Yasuko
Facility of Engineering, Tokyo University of Agriculture and Technology, Tokyo, Japan.
Stud Health Technol Inform. 2013;192:137-41.
The analysis of medical incident reports is indispensable for patient safety. Most incident reports are composed from freely written descriptions, but an analysis of such free descriptions is not sufficient in the medical field. In this study, we aim to conduct new findings using incident information, to clarify improvements that should be made to solve the root cause of an accident, and to ensure safe medical treatment through such improvements. We employed natural language processing (NLP) and network analysis to identify effective classes of medical incident reports. Network analysis can find various relationships that are not only direct but also indirect. After that, we compared the clustering results between Jichi Medical University and Osaka City University Hospital. By finding the common and different parts in medical incident report' s classes, we could show new perspectives on proposing a common reporting systems in Japan for improving patient safety.
医疗事故报告分析对于患者安全而言不可或缺。大多数事故报告由自由撰写的描述构成，但在医学领域，对这类自由描述进行分析是不够的。在本研究中，我们旨在利用事故信息得出新发现，以阐明为解决事故根源应做出的改进，并通过此类改进确保医疗安全。我们采用自然语言处理（NLP）和网络分析来识别医疗事故报告的有效类别。网络分析不仅可以发现直接关系，还能发现各种间接关系。之后，我们比较了自治医科大学和大阪市立大学医院的聚类结果。通过找出医疗事故报告类别中的相同点和不同点，我们能够为在日本建立一个通用报告系统以提高患者安全提供新的视角。
