Development of Data Mining Methods and Evaluation Systems in the Specific Health Checkup for Metabolic Syndrome Management

点击翻译按钮获取中文摘要

The metabolic syndrome has become a significant problem in the world, and health checkup and guidance targeted on it has started from 2008 in Japan. In order to support this large undertaking from the side of information technology, we introduce ideas based on Bayesian networks in data mining technology. The Bayesian network has emerged in recent years as a powerful technique for handling uncertainty in complex domains and is expected to be appropriate methods in the health checkup domain that require analyzing the results with medical knowledge. In this work, we constructed some Bayesian networks connecting the information of physical examination and questionnaire on daily life style. By applying these network models to the field data of subjects in the specific health checkup, the proposed method was found to provide better performance and show its usefulness.