In order to realize the ideal state of the future system of medical care provision in the region, clarification and specialization of clinical functions are being promoted with the aim of effectively utilizing and optimizing medical resources. The Clinical Function Reporting System requires medical institutions to report their clinical functions along with data representing the actual conditions of medical care, and encourages them to voluntarily grasp the current situation and plan for the future. In this study, we analyzed published clinical function report data using topic models cultivated in the field of natural language processing, and attempted to extract patterns of medical care activities that characterize clinical functions. As a result, the functional units that compose the clinical function could be extracted as topics, indicating the possibility of quantitative analysis of clinical function. In the midst of the promotion of a community healthcare plan toward 2025, proper analysis based on objective data is of paramount importance in forming consensus among stakeholders and encouraging constructive discussion. This research is considered to play a part in the analysis method.

　In order to prevent malfunctions of medical equipment caused by radio transmitters and other devices using radio waves, setting the separation distance according to the transmission output has been advised. Mobile phones are wireless transmitters that are used commonly within medical institutions and have many opportunities for unintentional proximity to medical devices. In order to suppress the output of the 4G handset, we set the parameters of the indoor base station system (IMCS) appropriately and measured the output of the 4G handset. It was found that the output of 10 mW in burst in the operating room and ICU setting that is well below the average power of 80 mW in burst of PHS. As PHS has a limited impact on medical devices and is used in medical institutions, it is consdered that the 4G mobile phone can be used in the operating room and ICU without affecting the medical equipment by setting the parameters of the 4G IMCS appropriately.

　Because medical records are stored in each medical facility, even records about one disease of one patient are fragmented. To solve this problem, it is desirable to build a Personal Health Record (PHR). PHR requires a powerful center system on the cloud, which will be a cost burden. If a private sector run this business, designing of its business model becomes a key issue. We have considered an architecture of PHR centered on a medical information bank, where individuals entrust their personal medical data to the medical information bank that promotes data usage. We classified the data usage into medical use (primary use), non-medical health service use, and secondary use for research. We proposed a business model in which the medical information bank receive payment from beneficiaries depending of the type of the data usage. We tried the PHR service for obstetric patients at Osaka University Hospital. This service was well received by the patients. Based on this experience, we aim to develop PHR project.

　Standardization and structuring of data are necessary for analyzing medical data between medical institutions. An interface and repository are developed for data linkage of the electronic medical record, have simplified the work of integrating data. In this paper, we propose an analysis method that can determine the priority of clinical intervention by prioritizing and visualizing time series of patient condition during the hospitalization period. Time series analysis of long-term hospitalizations and discharge destination was performed using DPC and clinical pathway data stored in the institutions using machine learning and the directed graphs. Long-term hospitalization was AUC=0.913, rolling over, changing clothes, respiratory status, and circulatory status were extracted. The discharge destination was AUC=0.773, oral care, and meal were extracted. The directed graph showed the relationship between the time-series variables, and was confirmed to be useful for the analysis of clinical process.