• Journal of the Korean Society of Systems Engineering
• /
• v.17 no.2
• /
• pp.98-105
• /
• 2021

As the average life expectancy is rising, the population is aging and the number of chronic diseases is increasing. This has increased the importance of healthy life and health management, and interest in mobile health services is on the rise thanks to the development of ICT(Information and communication technologies) and the smartphone use expansion. In order to meet these interests, many mobile services related to daily health are being launched in the market. Therefore, in this study, the characteristics of users who actually use mobile health services were analyzed and a predictive model applied with machine learning modeling was developed. As a result of the study, we developed a prediction model to which the decision tree and ensemble methods were applied. And it was found that the mobile health service users' continued use can be induced by providing features that require frequent visit, suggesting achievable activity missions, and guiding the sensor connection for user's activity measurement.

• Korean Journal of Occupational Health Nursing
• /
• v.11 no.1
• /
• pp.63-80
• /
• 2002

Objectives: The objective of this study is to evaluate the job characteristics of container terminal workers by applying the Job Strain model, and to assess the relationship among the general characteristics, job characteristics and psychosocial distress. Methods: A self-administrated questionnaire survey was performed to the container terminal workers in Pusan. Among the 200 male workers who answered the questionnaires, white-collar workers and blue-collar workers were 100, respectively. Karaseks Job Content Questionnaire was utilized to evaluate the job characteristics and Psychosocial well-being index (PWI) was applied to measure the extent of their psychosocial stress. Results: In white-collar workers, the skill discretion, created skill, decision-making authority, decision-making latitude, psychological job demand, and supervisor support of the job characteristics were significantly high, while in blue-collar workers physical exertion was significantly high. The result of Psychosocial well-being index (PWI) reveals that blue-collar workers were more stressed than white-collar workers, especially, the indices of depression (factor 2), sleeping disturbance and anxiety (factor 3), General well-being and vitality (factor 4) were significantly increased; whereas, in white-collar workers, only the index of social performance and self-confidence (factor 1) was significantly increased. And PWI scores were significantly increased in the lower social support and psychological job demand. By the multiple logistic regression analysis for PWI, blue-collar workers had increased odds ratio of 2.66(95% CI;1.11-6.41) compared with white-collar workers. The unmarried workers increased odds ratio of 3.54(95% CI;1.18-10.62) compared with married workers. And workers who have not own house increased odds ratio of 2.35(95% CI;1.15-4.79) compared with workers who have own house. Particularly, odds ratio of work-shift in blue-collar workers was 11.10(2.14-57.64). Conclusion: Skill discretion, created skill, decision-making authority, decision-making latitude, psychological job demand, and supervisor support were increased in white-collar workers. Decreased skill discretion and increased physical exertion were found in blue-collar workers, which is supported the Job Strain model. Job stress of blue-collar workers was comparatively higher than that of white-collar workers, especially, skill discretion, decision-making authority, decision-making latitude, job insecurity, physical exertion were noticeable factors. Especially, sleeping, smoking, and work shifting turned out to be a main cause that increases stress. Therefore, in order to decrease the job stress, a health promotion program to change the health behaviors should be activated and an organized job stress management program should be introduced. Especially, working condition for blue-collar such as physical exertion and work-shift should be improved.

• Journal of Digital Convergence
• /
• v.13 no.1
• /
• pp.353-366
• /
• 2015

The purpose of this study was to examine how region-specific characteristics affect the occurrence of cardiac arrest. To analyze, we combined a unique data set including key indicators of health condition and cardiac arrest occurrence at the 244 small administrative districts. Our data came from two main sources in Korea Center For Disease Control and Prevention (KCDC): 2010 Out-of-Hospital Cardiac Arrest Surveillance and Community Health Survey. We analyzed data by using multiple regression, geographically weighted regression and decision tree. Decision tree model is selected as the final model to explain regional variations of cardiac arrest. Factors of regional variations of cardiac arrest occurrence are population density, diagnosis rates of hypertension, stress level, participating screening level, high drinking rate, and smoking rate. Taken as a whole, accounting for geographical variations of health conditions, health behaviors and other socioeconomic factors are important when regionally customized health policy is implemented to decrease the cardiac arrest occurrence.

• Journal of Digital Convergence
• /
• v.11 no.10
• /
• pp.593-608
• /
• 2013

According to increasing number of injury claims, the challenge is reducing investigation of cases of injuries by selecting them more delicately, while also increasing the redemption rates and the amount of restitution. In this regards, we developed the fraud detection model for injury claims of self-employed insured by using decision tree after collecting medical claim data from 2006 to 2011 of the National Health Insurance in Korea. As a result of this model, subject types were classified into 18 types. If applying these types to the actual survey compared with if not applying, the redumption collecting rate will be increasing by 12.8%. Also, the effectiveness of this model will be maximize when the number of claims handlers considering their survey volume and management plans are examined thoroughly.

• Journal of Digital Convergence
• /
• v.13 no.8
• /
• pp.419-429
• /
• 2015

We investigate how the regional prevalence of hyperlipidemia is affected by health-related and socioeconomic factors with a special emphasis on geographic variations. We focus on the likelihood of hyperlipidemia as function of various region-specific attributes. We analysis a data set at the level of 249 small administrative districts collected from 2012 Korean Community Health Survey by Korea Centers for Disease Control and Prevention. To estimate, we use several methods including correlation analysis, multiple regression and decision tree model. We find that the average prevalence of hyperlipidemia in 249 small districts is 9.6% and its coefficient of variation is 28.3%. Prevalence of hyperlipidemia in continental and capital regions is higher than in southeast coastal regions. Further findings using decision tree model suggest that variations of hyperlipidemia prevalence between regions is more likely to be associated with rate of employee, level of stress, prevalence of hypertension, angina pectoris, and osteoarthritis in their regions.

• Journal of the Korean Society for information Management
• /
• v.23 no.2
• /
• pp.245-263
• /
• 2006

Since the beginning of discussions on serial collection management, as budgets have waxed and waned over the ensuing decades, a number of key variables affecting selection/deselection have emerged but without the framework of a coherent and accepted theoretical model. This study is an effort to identify variables which affect the serial collection decision with special attention to selection/deselection in the context of an academic health science library. Based on results from correlation analyses and logistic regression analyses, the serial collection decision can be explained and predicted using various combinations of a reduced set of objective variables. Applications of the results to libraries are discussed, and further research is proposed.

• Journal of Korean Academy of Nursing
• /
• v.43 no.1
• /
• pp.1-10
• /
• 2013

Purpose: The purpose of this study was to develop a prediction model for the characteristics of older adults with depression using the decision tree method. Methods: A large dataset from the 2008 Korean Elderly Survey was used and data of 14,970 elderly people were analyzed. Target variable was depression and 53 input variables were general characteristics, family & social relationship, economic status, health status, health behavior, functional status, leisure & social activity, quality of life, and living environment. Data were analyzed by decision tree analysis, a data mining technique using SPSS Window 19.0 and Clementine 12.0 programs. Results: The decision trees were classified into five different rules to define the characteristics of older adults with depression. Classification & Regression Tree (C&RT) showed the best prediction with an accuracy of 80.81% among data mining models. Factors in the rules were life satisfaction, nutritional status, daily activity difficulty due to pain, functional limitation for basic or instrumental daily activities, number of chronic diseases and daily activity difficulty due to disease. Conclusion: The different rules classified by the decision tree model in this study should contribute as baseline data for discovering informative knowledge and developing interventions tailored to these individual characteristics.

• Korean Journal of Occupational Health Nursing
• /
• v.18 no.2
• /
• pp.141-152
• /
• 2009

Purpose: The purpose of this research was to describe the decision making of nurses in a VIP ward. Method: The methodology of collecting and analyzing the data was based on the grounded theory of Strauss and Corbin (1998). The data were collected through an in-depth interview, which were audio-taped and transcribed. The data were collected from 10 nurses from July to November 2007. Results: The core category on VIP ward nurses' decision making was named as "adjusting with flexibility and deepened insight". The causal condition was established by 'the patients who wanted to be treated specially'. The contextual conditions included 'caring patients from various departments', 'differences depending on the nurses' clinical experience', and 'client-centered atmosphere in the VIP ward'. The intervening conditions included 'problem solving styles of nurses', 'attitudes of patients and family members', 'nurse-doctor relationships', and 'accessibility to information'. It was confirmed that nurses changed their action-interaction strategies depending on the intervening conditions, thus resulted in the nurses' role conflict and the need to expand their consciousness. Conclusion: The result of this study indicates that nurse's decision making depends on their experiences and the nature of social context in which nursing occurs.

• Asian Journal of Business Environment
• /
• v.4 no.2
• /
• pp.5-11
• /
• 2014

Purpose - This study attempts to examine Islamic banking practices in Iran based on new scientific methods. Design, methodology, and approach - The study used financial ratios demonstrating healthy or non-healthy banks to assess the financial health of banks listed on the Tehran Stock Exchange. The assessment of these ratios with a decision tree as a non-parametric method for modeling is recommended to present this model. Information about the financial health of banks could affect the decisions of different groups of banks' financial report users including shareholders, auditors, stock exchanges, central banks, and so on. Results - The results of the study show that a decision tree is a strong approach for classifying Islamic banks in Iran. Conclusions - To date, several studies have been conducted in various countries on the topic of this study. Considering the importance of Islamic banking, this is one of the first studies in Iran the outcomes of the study may prove helpful to the Iranian economy.

• Journal of Preventive Medicine and Public Health
• /
• v.22 no.1 s.25
• /
• pp.57-64
• /
• 1989

A decision support system (DSS) was developed to support doctor's decision-making in diagnosing hearing loss. The final diagnosis encompassed 41 diseases with the problem of hearing loss. The system was developed by integrating model-oriented DSS technique and artificial intelligence technology. The system can be used as both diagnosis tool and teaching tool for medical students. Furthermore, the AI technology obtained from this study may also be used in developing DSS for hospital management.