In this study, we developed a probabilistic model to analyze patient accessibility to hospitals by using a geographic information system (GIS). In the consideration of patient accessibility, we do not have correct patient addresses because of the laws related to protection of a patient's personal information. Thus, we use a representational place in the city or the ZIP code of the area. However, this may lead to a decline in the accuracy of the analysis. In this study, we used a 500-m mesh map and obtained the population gender and age group data from the national census data, in order to estimate the patient accessibility to medical facilities in small areas. We calculated the probability that a patient lives in each mesh on the basis of the population gender and five-year age group data. We selected the appropriate mesh on the basis of this probability and investigated the time distance from the estimated mesh to each hospital by using a GIS. As a result, we calculated the time distance and its distribution by using the proposed method from limited available information. Further, we found that in the target cities, the average time distance to hospital calculated using the proposed method was longer than that calculated by using a previous method; the percentage of patients who took more time than the city average to reach a hospital by using the proposed method. This method is very useful when planning the geographical resource allocation of medical services.

In this study, we developed the Patient Access Area Model by using a Geographic information system (GIS), and, in order to evaluate the balance of medical supply and demand in the future in small areas, simulated patients’ access to hospitals. We set the accessible area by patients’ transit time for each hospital. The patients living in each 500 meters mesh were allowed to enter hospitals only within the access area. The hospitals have its limit to admit patients based on their actual numbers of beds. We distributed inpatients from each mesh across hospitals. For the evaluation of demand, if patients could not be distributed to the hospitals within the accessible area, we defined the situation as “over-demand.” As a result, although it was expected that over 9000 inpatients will not receive inpatient care in a southwest area region in the studied prefecture, most of the over-demand is in the densely regions along large traffic lines in 2030. Using this model, we can know demand for local health resources more clearly. This method is very useful to plan geographical resource allocation in medical services.

We propose a method which visualizes irregular multidimensional time-series data as a sequence of probabilistic prototypes for detecting exceptions from medical test data. Conventional visualization methods often require iterative analysis and considerable skill thus are not totally supported by a wide range of medical experts. Our PrototypeLines displays summarized information based on a probabilistic mixture model by using hue only thus is considered to exhibit novelty. The effectiveness of the summarization is pursued mainly through use of a novel information criterion. We report our endeavor with chronic hepatitis data, especially discoveries of interesting exceptions by a nonexpert and an untrained expert.

The hepatitis temporal database collected at Chiba university hospital between 1982--2001 was recently given to challenge the KDD research. The database is large where each patient corresponds to 983 tests represented as sequences of irregular timestamp points with different lengths. This paper presents a temporal abstraction approach to mining knowledge from this hepatitis database. Exploiting hepatitis background knowledge and data analysis, we introduce new notions and methods for abstracting short-term changed and long-term changed tests. The abstracted data allow us to apply different machine learning methods for finding knowledge part of which is considered as new and interesting by medical doctors.