• 시스템엔지니어링학술지
• /
• 제17권2호
• /
• 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.

• 한국직업건강간호학회지
• /
• 제11권1호
• /
• 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.

• 디지털융복합연구
• /
• 제13권1호
• /
• pp.353-366
• /
• 2015

본 연구의 목적은 심정지 발생의 지역별 변이요인을 규명하는 것이다. 분석을 위하여 244개 행정구역별로 건강상태 및 심정지발생에 관한 지표를 수집하여 분석용 데이터 셋을 구축하였다. 지표 선정을 위해 질병관리본부의 2010년 심정지 조사자료와 지역사회 건강조사자료를 이용하였다. 자료 분석은 다중회귀분석, 지리적 가중회귀분석, 의사결정나무분석 기법을 이용하였다. 의사결정나무를 이용하여 심정지 발생의 지역별 변이를 설명하는 최종 모형을 설정하였다. 최종 모형인 의사결정나무에 근거한 지역별 변이요인은 인구밀도, 고혈압 평생의사 경험진단율, 스트레스 인지율, 고지혈증 평생의사 경험진단율, 우울증 경험률, 건강검진 수검율, 고위험음주율, 현재 흡연율로 나타났다. 심정지 발생을 감소시키기 위한 지역별 보건정책의 수립은 지역의 건강상태, 건강행위 및 사회경제적 요인 등에 근거하여 이루어질 필요가 있다.

• 디지털융복합연구
• /
• 제11권10호
• /
• pp.593-608
• /
• 2013

상해상병으로 청구되는 건수가 증가함에 따라 조사 대상을 보다 정교하게 선정하여 상해요인 조사 대상을 줄이면서 환수율 및 환수금액을 올릴 수 있는 방안을 마련할 필요가 있다. 이를 위해서 2006~2011년까지의 상해요인 조사자료를 수집하여 의사결정나무 모형을 활용하여 지역가입자 상해상병 진료건에 대한 부당환수 조사대상 선정모형을 개발하였다. 최종 개발된 모형결과에 따르면, 조사대상 유형은 18개로 분류되었고, 이러한 분류결과는 실제 조사가 시행될 시, 모형을 적용하지 않았을 때 보다 최고 12.8배 높은 부당환수결정율을 나타낼 수 있을 것으로 분석되었다. 또한, 본 연구에서 개발된 조사 대상자 선정 모형을 실제 업무에 적용하기 위해서는 조사물량 대비 국민건강보험공단의 조사인력 및 운영 계획을 보다 면밀히 검토해야만 모형 적용의 효과성이 극대화 될 수 있을 것으로 판단된다.

• 디지털융복합연구
• /
• 제13권8호
• /
• pp.419-429
• /
• 2015

본 연구는 고지혈증 유병률의 지역 간 변이 정도와 위험 요인을 규명하여 지역별 특성에 맞는 고지혈증 관리 사업을 지원하기 위한 기초자료를 제공하기 위해 수행되었다. 이를 위해 질병관리본부의 2012년도 시군구 지역사회건강조사 249건의 자료를 이용하여 단순 상관관계 분석, 단계적 회귀분석, 의사결정나무 등의 기법으로 분석하였다. 249개 시군구 지역의 고지혈증 유병률은 9.2%였고, 변동계수는 28.3%였다. 남동부 해안지역에 비해 수도권과 내륙지방의 고지혈증 유병률이 높았다. 의사결정나무 모형이 회귀모형에 비해 예측력이 좋았는데, 지역의 임금근로자 비율, 스트레스 인지율, 고혈압, 협심증, 관절염 유병률이 높은 지역일수록 고지혈증 유병률이 높은 것으로 나타났다. 따라서 사회 역학적 관점에서 지역사회의 개입이 가능한 지점을 중심으로 고지혈증 유병률을 감소시키기 위한 전략 마련이 필요하다.

• 정보관리학회지
• /
• 제23권2호
• /
• pp.245-263
• /
• 2006

학술잡지 구입 예산의 구입비용 상승에 따른 압력으로 지난 수십년간 학술잡지의 선택에 영향을 미치는 요인들에 대한 연구가 활발히 진행되어 왔지만, 학술잡지의 선택에 대한 만족할만한 이론적 틀이 제시되지 못하였다. 이에 따라 본 연구에서는 의학도서관에서 의학분야의 학술잡지의 선택에 영향을 미치는 요인들을 확인하여 이러한 이론적 틀을 제시할 수 있는 근거를 마련코자 한다. 본 연구는 상관관계 분석과 로지스틱회귀분석을 통해 학술잡지선택의 분산을 설명하고, 나아가 예측하는 통계적 모델들을 여러 변수조합을 이용해 제시한다. 또한 이러한 모델의 실제적 적용과 향후 연구방향을 논의한다.

• 대한간호학회지
• /
• 제43권1호
• /
• 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.

• 한국직업건강간호학회지
• /
• 제18권2호
• /
• 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
• /
• 제4권2호
• /
• 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
• /
• 제22권1호
• /
• 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.