Prediction Model for Intention of Mental Health Promotion Program among Korean Elderly Persons Using CART Algorithm

Abstract

The aim of the present study was to analyze the factors that affects the intention of mental health promotion program among Korean elderly persons. Data were from the A Study on the Seoul Welfare Panel Study 2010. Subjects were 2,111 persons aged 60 and older living in the community. Dependent variable was defined as intention of mental health promotion program. Explanatory variables were included as age, gender, education level, employment status, household income, marital status, drinking, self-reported health status, subjective family relationship, subjective relationship with friends, depression, and physical activity. A prediction model was developed by the use of a CART (Classification And Regression Tree) algorithm of data-mining approach. In the CART algorithm analysis, subjective health status, smoking, level Received (July 07, 2015), Review Request(July 08, 2015), Review Result(July 24, 2015) Accepted(August 13, 2015), Published(October 31, 2015) 506-706 Dept. Speech Language Pathology & Audiology, Nambu University, Chumdan 23, Gwansangu, Gwangju, Korea email: byeon@nambu.ac.kr (Corresponding Author) 506-706 Dept. Physical Therapy, Nambu University, Chumdan 23, Gwansangu, Gwangju, Korea email: geriatricpt1@naver.com Prediction Model for Intention of Mental Health Promotion Program among Korean Elderly Persons Using CART Algorithm Copyright c 2015 HSST 204 of education, marital status, drinking, employment status, subjective family relationship, depression, and subjective relationship with friends were significantly associated with intention of mental health promotion program in Korean elderly. Based on this result, systematic programs are required in order to maintain the mental health of the elderly.