摘要：It is well recognized that there are many kinds of diseases that are affected by meteorological factors. This study aims at investing the relation between the onset of cerebral infarction (CI) and climatic elements. Databases of medical emergency transfers in Nagoya during the winter seasons of 2002-2004 were reviewed. We applied a bi-directional self-organizing map (SOM), cluster analysis and decision tree to estimate the effects of climatic elements on the onset of CI. We classified climatic elements into three patterns, such as “rainy weather”, “west high and east low pressure” and “fair weather” by applying SOM. The risk of CI was estimated more clearly over each pattern. The meteorological variances are associated with the onset of CI. This fact was more accurately observed by classification of climatic patterns based on SOM. This study also suggests that effective warning is possible for the onset of CI, if we classify weather patterns.
