The Predictive Modeling of Middle-aged Hypertension using Integrated Method of Decision Tree and Neural Network

Haewon Byeon, Sung-Hyoun Cho
2015 Asia-pacific Journal of Multimedia services convergent with Art Humanities and Sociology  
The purpose of present study was to analyze the factors that affects the middle-aged hypertension in Korea. Data were from the A Study on the Seoul Welfare Panel Study 2010. Subjects were 2,564 persons (1,177 male; 1,387 female) aged 40-59 in South Korea. Dependent variable was defined as prevalence ratio of hypertension. Explanatory variables were included as gender level of education, household income, smoking, drinking, self-reported health status, and physical activity. A prediction model
more » ... s developed by the use of a Decision Tree and Neural Network Algorithm. In the Prediction model, self reported health status, physical activity, education, smoking, household income were significantly associated with middle-aged hypertension in Korea. 1 506-706
doi:10.14257/ajmahs.2015.04.25 fatcat:7lpl6c2igreyfn63lzqx5wgw5m