This study aims to clarify the applicability of neural network to represent hypertension model. From medical database, 599 cases were randomly chosen to the learning group. Input variables used in this study were sex, age, smoking and drinking habits, body mass index, systolic and diastolic blood pressure, total cholesterol, triglyceride, fasten plasma glucose and uric acid. These input variables were used directly and also used after transforming to the fuzzy memberships. For quantitative evaluation of risk factors, the output ratio (risk/standard) derived from neural network, odds ratio based on logistic regression, coefficient based on the covariance structure analysis are compared. The neural network was also able to represent the risk factors associated to the occurrences of hypertension.
