Earticle

본 연구는 독거노인의 우울발생을 예측하는 요인을 탐색하는 목적으로 하는 연구로 2020년 한국 노인실 태조사 원시자료를 활용하였다. 연구 대상자는 65세 이상의 독거노인으로 최종 분석에서 3,117명이 선정되었다. 독거노인의 우울발생에 영향을 미치는 요인들의 병합 및 관계조합을 확인하고자 데이터마 이닝 기법 중 의사결정 나무분석 알고리즘을 통해 분석을 실시하였다. 연구결과 독거노인의 우울을 예측하는 가장 높은 변수 관계 조합은 주관적 건강상태에 있어 부정적으로 평가하는 경우, 장애요인과 관련하여 장애가 있다고 응답한 독거노인 집단에서 우울 발생 가능성이 가장 높게 예측되었다. 이어, 성별 요인에서는 남성 독거노인, 기초생활수급권 유무에 있어 비수급 독거노인인 경우 우울 발생이 유의미하게 예측됨을 확인 하였다. 연구 결과를 바탕으로 독거노인의 우울을 감소하고 관리할 수 있는 실천적 제언을 제공하였다.

The purpose of this study is to explore the factors predicting the occurrence of depression in elderly individuals living alone. people were selected in the final analysis 3,117 elderly people aged 65 or older who are living alone from the raw data of the 2020 National Survey of Older Koreans. A decision tree analysis algorithm, one of the data mining techniques, was used to identify the combinations and relationships of factors affecting the occurrence of depression in elderly individuals living alone. The results of the study indicated that the highest probability of depression was predicted in elderly individuals living alone who gave a negative evaluation of their subjective health status and reported having a disability. Additionally, Men were identified as a significant influencing factor in gender factorsr and Non-basic living security were identified as significant influencing factors. Based on the study results, suggestions for managing depression in elderly individuals living alone were provided.

｢금융소비자 보호에 관한 법률｣의 통과와 더불어 소비자 지향적인 금융정보 제공 및 교육에 대한 정책적 노력 이 지속되는 가운데, 금융소비자들의 정보탐색 행동에 대한 관심이 높아지고 있다. 본 연구는 미국 Survey of Consumer Finances의 2016년 자료를 활용하여 저축 및 투자 의사결정에서의 정보탐색의 특성을 살펴보고 이 를 결정하는 요인 및 요인의 상대적 중요도를 파악하고자 하였다. 이를 위해 자기 주도형의 정보탐색과 전문가 활용형의 정보탐색을 구분하고 데이터 마이닝 기법 중 하나인 의사결정나무를 활용하여 각각의 의사결정모델을 수립하고 결정요인 및 규칙을 도출하였다. 연구의 주요 결과는 다음과 같다. 미디어 및 인터넷 등을 통해 자기 주도적으로 정보탐색을 하는 소비자는 전체의 23.9%를 차지하며, 54세 이 하, 히스패닉, 미혼, 고졸 미만, 무직인 소비자 집단에서 높은 비중을 차지하였다. 재무설계사, 회계사, 은행원 등 전문가를 활용하는 소비자들은 전체의 21.3%로 65세 이상, 백인, 기혼, 고교 졸업, 자영업자에서 상대적으 로 높은 분포를 나타냈다. 자기 주도형 탐색을 결정하는 요인으로는 이용 정보원천 수, 금융자산, 위험감수성향, 은퇴자금 만족도, 필요 비상자금 수준, 순자산, 인종 및 민족, 부채, 연령 등이 있다. 자기 주도형 탐색을 가장 많이 포함할 확률은 단수 의 정보원천을 이용하며, 준비된 은퇴자금 만족도가 낮은 편이고, 백인 또는 아시아 및 기타민족 소비자이며 가 계부채를 적게 보유한 그룹에서 가장 높게 나타났다. 한편 전문가 활용형 탐색의 결정요인은 이용 정보원천 수, 금융자산, 비 금융자산, 자택소유여부, 연령, 주택담보대출 여부, 은퇴자금 만족도 등이 있다. 전문가 집단을 활 용하여 정보탐색을 할 확률은 단수의 정보원천을 이용하며 금융자산 수준이 높고 위험감수성향이 낮은 소비자에 게서 가장 높게 나타났다. 두 유형의 정보탐색 의사결정모델에서 모두 이용정보의 원천 수는 가장 중요한 결정요인인 것으로 나타났으나, 자기 주도형 대비 전문가 활용형 탐색에서는 응답자 가계의 재무적 상태를 나타내는 요인들이 상대적으로 더욱 중요한 것으로 나타났다.

Analyzing the 2016 Survey of Consumer Finances, this study describes how financial consumers search information on their decisions of saving and investment. Two types of search behaviors, self-directed and expert-utilized search are examined to identify the factors that determine search behaviors and their relative importance using a decision tree analysis. Consisting of 23.9% of the sample, those who did self-directed search exhibit higher proportions in Hispanic, non-married, under high school graduate, and not working. Presenting 21.3% of the sample, those who did expert-utilized search show higher proportions in males, aged 65 and older, White, married, high school graduate, and self-employed relative to their comparative groups. The factors determining self-directed search are the number of information sources they used, financial asset, risk tolerance, satisfaction of retirement preparedness, emergency fund, net worth, race and ethnicity, debt, and age. Those who use a single information source, less satisfy their retirement preparedness, White, Asian and others, and have less debt show the highest probability of being a self-directed consumer. The factors determining the model of expert-utilized search are the number of information sources, financial asset, non-financial asset, homeownership, age, debt secured by primary residence, satisfaction of retirement preparedness. Those who use a single information source, have more financial assets, and are less risk-tolerate show the highest probability of being an expert-utilized consumer. While the number of information sources is the most significant determinant for both models, factors relating to financial resources have more explanatory power in the expert-utilized model than the self-directed model.

한국 사회에서는 결혼 중심의 가족형성 규범이 약화되면서 비혼 동거가 확산되고 있다. 비혼 동거는 결혼 전 단계로서의 동거와 결혼 대안적 동거로 이중적 특성을 보이며, 한국의 비혼 동거는 한국적 특성을 보이면서도 국제적 흐름의 경향에서 크게 벗어나 있지 않아 지속적인 확산을 예측해 볼 수 있다. 본 연구는 비혼 동거 이후 법률혼 이행 여부가 개인의 태도와 사회경제적 요인의 복합적 영향을 받을 수 있다는 점에 주목하였다. 2023년 가족실태조사 자료를 활용하여 현재 비혼 동거 중인 집단의 법률혼 계획을 의사결정나무 분석으로 검토하였다. 분석 결과, 비혼 동거 중인 집단의 55.5%가 법률혼을 계획하고 있었다. 생활 비 지출 결정권이 낮고, 가족을 경제적 생계 공동체로 인식하며, 배우자를 노년기 동반자로 인식할수록 법률혼 이행 가능성이 높게 예측되었다. 이는 법률혼 전환이 단순한 혼인 가치관을 넘어, 경제적 협력 구조와 장기적 관계 안정성 인식에 의해 결정됨을 시사한다. 본 연구는 한국 비혼 동거의 제도 이행 요인을 실증적으로 제시함으로써, 향후 정책 설계 및 사회적 논의에 기초자료를 제공한다.

In Korean society, the traditional marriage-centered norm in family formation has weakened, resulting in a rise in unmarried cohabitation. Cohabitation exhibits dual characteristics both as a premarital stage and as an alternative form to marriage, and although it reflects certain Korea-specific features, its trajectory remains broadly aligned with global trends, suggesting continued growth. This study focuses on the possibility that the transition from cohabitation to legal marriage is influenced by a complex interplay of individual attitudes and socioeconomic factors. Using data from the 2023 Korean Family Survey, we conducted a decision tree analysis to examine legal marriage intentions among individuals currently in unmarried cohabitation. The findings show that 55.5% of cohabiting individuals reported plans to enter legal marriage. The likelihood of transitioning to legal marriage increased when individuals had lower decision-making authority over living expenses, perceived family as an economic livelihood-sharing unit, and viewed their partner as a long-term companion in later life. These results indicate that legal marriage intentions are shaped not only by attitudes toward marriage, but also by perceptions of economic cooperation and expectations of long-term relational stability. By empirically identifying the determinants of institutional transition among unmarried cohabitors in Korea, this study provides foundational evidence for future policy development and public discourse.

오늘날은 가히 웰빙과 LOHAS 시대를 넘어 힐링시대라 할 만큼 모두들 스스로의 치료(self therapy)에 관심 이 많다. 이에 따라 민간요법과 관련된 분야의 활발한 산업화 그리고 질병치료가 아닌 건강증진 등에 대한 관심이 증대되면서 다양한 분야에서 대체의학이나 대체요법에 대한 연구가 수행되고 있다. 이렇듯 민간요법을 통한 건강증 진 및 인간의 자연치유력에 대한 관심이 증대되고 있는 시점에서, 민간요법에 대한 인식을 구성하는 요인들을 탐색 해 보는 것은 매우 의미 있는 일이다. 이에 본 연구에서는 선행연구를 토대로 인식 속성 관련 설문문항을 개발하여 요인분석 등을 이용하여 민간요법을 구성하는 요인에 대해 탐색해 보고, 인구통계학적인 특성들에 따라 인식 속성에 어떠한 차이가 있는지를 통계적 검정해 보았다. 그 결과 24개로 구성된 민간요법 관련 측정 변수들은 4개의 요인, 즉, 건강증진요인, 안전요인, 심리요인 그리고 대안요인 등으로 분류되었다. 그리고 전체적으로 30세 이하의 젊은 층 보다는 40~60대의 중장년층 그리고 학력이 높을수록 민간요법에 대한 사용경험이 높으며, 성별로는 큰 차이가 없음 을 알 수 있었다.

Nowaday, beyond the time of wellbeing and LOHAS, many people have great interest in self therapy, so it is called healing era. As the folk medicine fields are actively industrialized and the interest in health improvement, not disease cure, is increased, many researches about the alternative medicine and therapy in various fields are being performed. In the times of the interest in health improvement and spontaneous, natural healing ability of human body is getting increase, it is very meaningful to search the factors which consist of recognition to folk medicine. So in this study, we developed the questionaries on the basis of previous studies, researched the factors affecting the recognition to folk medicine using factor analysis, and tested statistically the difference of recognition character according to demo-statistical traits. As the result, the twenty-four measurable variables related to folk medicine are sorted to four factors, ie, health improvement factor, safety factor, psycholocial factor, and substitutional factor. And overall, the middle and senior ages, the forties to sixties, and higher-educated peoples have more experiences in folk medicine than the younger ages, below thirties and lower-educated peoples. The distiction of sex makes little differences.

실증자료 분석을 통해, 지난 제18대 대통령 선거에서 대북정책과 같은 포괄적인 북한요인이 후보를 선택하는데 영향력을 발휘했는지 그 여부를 검증하는데 본 연구의 목적이 있다. 로지스틱 회귀분석(Logistic Regression) 결과 ‘후보선택’에 영향을 미치는 요인은 ‘대북정책, 연령, 권역, 경제과제, 직업, 가구소득’ 순으로 나타났다. 의사결정나무분석(Decision Tree Analysis) 결과 ‘후보선택’에 영향을 미치는 요인은 세 가지 분석기법에서 공통적으로 ‘지지정당, 대북정책’으로 분석되었다. 새누리당 지지층은 박근혜, 민주통합당 지지층은 문재인을 지지했다. 그러나 무당파층에서는 ‘유연한 대북정책’을 선호하는 응답자는 문재인 후보, ‘강경한 대북정책’을 선호하는 응답자는 박근혜 후보를 지지했다. 이와 같은 연구결과는 북한의 직접적인 개입이 없었던 제18대 대통령선거에서도, 여전히 북한요인이 후보선택의 중요한 요인으로 작용하였다는 것을 보여주는 것이라 하겠다.

The purpose of this study is to empirically analyze the effect of North Korean Factors on Voter's Choice of Candidate in the 18th Presidential Election by employing t-test, ANOVA, logistic regression, and decision tree analysis. The results of the Logistics Regression using survey data show that the determining factors on choice of candidate during the 18th Presidential Election were political issue preference (about North Korean policies), age, area, economic issues, job, income. The results of the decision tree analysis show that the most influential factors on choice of candidate were party identification and political issue preference (about North Korean policies). Voters who supported political parties(partisan) simply chose the candidate who belonged to their political party. On the other hand, those who did not support political parties (non-partisan) chose the candidate who claimed to back the same issues (about North Korean policies) they preferred.

Abstract : In this study, previous studies the existing advocacy organizations identified as factors affecting the properties(the state agency supervision of the firm, participation in decision-making), self-efficacy, political efficacy variables perform advocacy activities focusing on the impact of youth leaders. To evaluate the predictive model is during the month of June 2009 and 7 national youth-related agencies and organizations working in the purposive sampling to target youth leaders called for a total of 159 were analyzed. The results are part of the leaders of youth organizations in the state supervision of the firm on average 3.86 (SD = .95) was higher than the average level of participation in decision-making 2. 78 (SD = 1.20) was found to be less than the normal level. In addition, self-efficacy of youth leaders averaged 3. 51 points (SD = .901) was higher than the average, self-efficacy areas of expertise average 3.46 points (SD = .94) an average 3.57 points to practice skills areas (SD = .84) than the more narrowly was found to be low. Youth leaders' political efficacy and the average score of 3.42 points (SD = .98) was performed advocacy activities averaged 3.03 (SD = 1.00) than the normal level was found. Perform advocacy activities of youth leaders around the state and the institutions supervision firm to participate in decisions, self-efficacy and a statistically significant positive correlation was found to perform advocacy activities of youth leaders in the models predicting self-efficacy and decision-making authority on the rights of the variables was found to be very important. Based on these findings, perform advocacy activities in youth leadership development plan and proposed recommendations.

Purpose: Body image distortion (BID) in adolescents is a crucial problem that causes both abnormal eating habits and unhealthy weight control behaviors. COVID-19 has had a negative impact on adolescents’ psychological and behavioral status, and this might influence the onset of BID in adolescents. This study aimed to develop a prediction model for BID in Korean adolescents using decision tree analysis. Methods: The decision tree analysis was used to develop a prediction model for BID in Korean adolescents using the data of 2021 Korea Youth Risk Behavior Survey Web-based (KYRBS). Results: In the present study, about one-third of the study subjects (31%, n=6,316) showed BID. The BID rate was higher in females (37.2%, node1) than in males (21.2%, node2). Female students with severe GAD-7 level and smartphone use on the weekend over 12h showed the highest rate of BID (66.9%). As to males, the BID rate was the highest (33.1%) among middle school male students who did strength training once a week or none. Conclusion: In order to reduce BID, there is a need to develop a customized BID education and management programs.

본 연구의 목적은 우리나라 27개 시군구 지역 주민 2,700명을 대상으로 한 설문조사 결과를 통 하여 삶의 만족도에 대한 영향요인들의 결합조건을 의사결정나무 분석 모형으로 분석해 보고, 주민 들의 삶의 만족수준을 제고시킬 수 있는 정책적 시사점을 얻고자 하는 데 있다. 본 연구로부터 얻 은 시사점을 정리하면 다음과 같다. 첫째, 전국적 차원에서 볼 때, 끝마디로 조건들이 결정되는 삶 의 만족 영향요인들의 조합은 모두 25개이며 가장 중요한 영향변수는 인구이고, 재정자립도 등 다 양한 조건들의 결합들이 주민들의 삶의 만족수준에 영향을 미친다는 것을 볼 수 있다. 이러한 사실 은 다양하게 결합되는 조건들에 대한 차별적 정책 조합을 통하여 중앙정부나 지방정부가 실질적으 로 주민들의 만족수준을 높일 수 있는 정보로 활용할 수 있다는 점이다. 둘째, 대도시는 16개 노드, 중소도시는 14개 노드, 그리고 농촌군의 경우에도 14개 노드로 구분되어 지역유형별로 주민들을 노드별 특성을 고려하여 분류하고 이 분류에 맞게 차등적 삶의 만족 수준 제고 정책을 수행할 수 있 다는 점이다. 이를 통하여 주민들의 삶의 만족수준을 제고시킬 수 있는 차등적 관리방안을 제시할 수 있다는 점에서 본 연구의 시사점을 찾을 수 있다.

This article aims at identifying multiple combinations of the factors affecting local residents’ satisfaction with their daily lives in their local area by using decision-tree analysis method, to examine which domain of the factors affects their life satisfaction most, and to look at the characteristics underlying the more satisfied groups and the less satisfied groups. For this purpose, this article utilizes decision tree analysis method which has seldom been used in the field of happiness studies. The conclusions of this study are summarized as follows. First, it is discovered that the total number of significant nodes explaining residents’ life satisfaction at national level is 25, and the most important factor affecting life satisfaction is population size of local government through which local residents are served. Second, it is also found that metropolitan cities, small and medium sized cities, and rural ares are classified into 16 nodes, 14 nodes and 14 nodes, respectively. This paper puts forward policy implications for central government and local government to be able to reflect the research results into their policy processes.

The electric vehicle (EV) industry in China is rapidly developing along with environmental protection issues. The voluntary choice of consumers and the will of the government to promote are essential for the overall social diffusion of EVs. Therefore, this study aims to identify the factors that influence the purchase intention of Chinese consumers for EVs. Product quality, policy awareness, social influence, environmental concern, personal innovation, and perceived usefulness, which were derived from previous studies, were used as significant variables. Decision tree analysis (DTA) was conducted on the complicated consumer purchasing behavior. The result indicates that perceived usefulness, social influence, and policy awareness significantly influenced the high EV purchase intention group. In addition, high levels of personal innovation led to relatively high levels of purchase intention for the group with low levels of perceived usefulness and social influence. Although the Chinese government actively implemented policies to promote the purchase of EVs, the study found that policy awareness was not a decisive factor that influenced purchase intention for EVs. Finally, academic and practical suggestions are discussed.

본 연구는 질병관리청에서 제공하는 2021년 청소년건강행태조사 데이터를 활용하여 의사결정나무 분석 법으로 코로나19 시대 중 ‧ 고등학생의 성별에 따른 체질량지수를 예측하는 모델을 구현하고자 하였다. 예측 모형에서 체질량지수는 성별에 따라 유의미한 차이가 있었고, 남자 중학생의 경우에 고강도 신체활 동을 전혀 하지 않으면서 주말 동안의 스마트폰 사용 시간이 11시간 이상인 경우 비만율이 37.4%로 가장 높게 나타났다. 남자 고등학생은 고강도 신체활동을 하지 않거나 일주일에 1번 정도 하면서 학업 성적이 중간-낮음의 수준인 경우 비만 비율이 36.2%로 가장 높았다. 여중생의 경우 학업성적이 낮으면서 불안장애수준이 심각하거나 반대로 완전히 낮은 경우 비만 비율이 18.4%로 가장 높았다. 여고생의 경우 는 코로나19에 따른 경제적 상황에 크게 변화가 있으면서 주말 동안의 스마트폰 사용 시간이 9.8시간 이상인 경우에 비만율이 20.5%로 가장 높았다. 코로나19 상황 이후 비만 청소년 관리를 위하여 개인적 특성 및 상황을 고려한 맞춤형 관리프로그램의 개발과 적용이 시급하다.

This study built a prediction model for BMI by sex of middle and high school students in the COVID-19 era by using 2021 Korea Youth Risk Behavior Survey. This study used data from 30,015 middle school and 24,833 high school students. The data was analyzed by using decision tree analysis. For male middle school students, if they did not engage in strenuous physical activity and spent more than 11 hours on a smartphone during the weekend, the obesity rate was the highest at 37.4%. Male high school students, those who did 0-1time strenuous physical activity a week and had medium-low level academic performance showed the highest level of obesity(36.2%). Middle school girls, when the academic performance was low and the anxiety disorder level was severe or conversely, the obesity rate was the highest at 18.4%. High school girls, the obesity rate was the highest at 20.5% when there was a significant change in the economic situation due to COVID-19 and the time spent on smartphone over the weekend was 9.8 hours or more. It is needed to develop a customized management and counseling program for obese adolescents.

의사결정나무 알고리즘은 데이터마이닝 기법중 하나인데 관심이 되는 데이터들에 대하여 분류 및 예측을 가능하게 해준다. 이 기법은 데이터 형태의 특성을 분석할 수 있고 산업재해 형태의 차이점을 찾아내는데 사용될 수 있다. 본 연구에서는 산업재해 데이터의 특성을 파악하고자 C4.5 알고리즘을 사용하였다. 본 연구에서 분석을 위하여 사용된 데이터는 강원도에서 발생한 2년 동안의 산업재해 관련 데이터로서 연구에 적용된 데이터의 수는 19,909개로 구성되어 있다. 본 연구의 목적을 위하여 한 개의 목표변수와 여덟 개의 독립변수가 산업재해 형태에 따라 세분화 되었다. 분석 후 데이터는 222개의 전체 나뭇가지와 151개의 줄기가지로 분류되었다. 또한 본 연구에서는 재해자들의 위험도 관리와 감소를 위하여 이익도표를 제공하였다.

.

Purpose: This study was performed to analyze the levels of blood pressure and to identify good or poor blood pressure control (BPC) groups among hypertension patients. The study was based on the Korea National Health and Nutrition Examination Survey (KNHANES VI and VII) conducted from 2013 to 2016. Methods: The sociodemographic and clinical data of 4,151 Korean hypertension patients aged 20-79 years and who were taking antihypertensive medications was extracted from the KNHANES VI and VII database. Descriptive statistics for complex samples and a decision-tree analysis were performed using the SPSS WIN 24.0 program. Results: The mean age was 62.46±0.21 years. The mean systolic blood pressure (SBP) was 128.07±0.28mmHg, and the diastolic blood pressure (DBP) was 76.99±0.21mmHg. 71.9% of participants showed normal blood pressure (SBP <140mmHg and DBP <90mmHg). From the decision-trees analysis, the characteristics of participants related to good BPC group were presented with 9 different pathways same as those from the poor BPC group. Good or poor BPC groups were classified according to the patients’ characteristics such as age, living status, occupation, education, hypertension diagnosis period, numbers of comorbidity, perceived health status, total cholesterol, high density lipoprotein-cholesterol, alcohol drinking per month, and depressive mood. Total cholesterol level (<201mg/dL or ≥201mg/dL cutoff point) was the most significant predictor of the participants’ BPC group. Conclusion: This decision-tree model with the 18 different pathways can form a basis for the screening of hypertension patients with good or poor BPC in either clinical or community settings.

Purpose: This study aims to identify predicting factors influencing Chinese students’ intentions to quit smoking. Methods: Secondary data for this study came from a study on the change in smoking cessation among Asian students. Data on their intention to quit smoking was collected from October 2020 to January 2021 through an online survey. The study participants included 190 Chinese international students aged 19 to 29 who were smokers. Descriptive statistics, chi-squared test, independent-test, and decision-making trees were used for analysis. Results: 73.2% (139 students) of Chinese international students in Korea intended to quit smoking; 97.8% of the groups intending to quit smoking had previously attempted to quit. The decision tree ultimately had seven sections. The attempt to quit smoking was the most significant predictor of smoking cessation intention. Stop smoking attempts, intent to participate in a nonsmoking programs, smoking parents, stop-smoking self attempts, and smoking after studying abroad were factors predicting intention to quit smoking. Conclusion: The factors influencing Chinese students’ intention to quit smoking differed depending on their previous smoking cessation experience. Intention to participate in a smoking cessation program, parent smoking, and recent attempts to quit smoking were factors predicting intention to quit in those with previous smoking cessation experience. A program tailored to their needs should be developed to improve the smoking cessation intention of Chinese international students depending on their history of smoking cessation.

Purpose: This study aimed to identify frailty determinants by age group. Methods: The participants were 9,955 older adults from the 2023 National Survey of the Living Conditions of Older Koreans. They were divided into three groups: young old (65~74 years), advanced old (75~84 years), and very advanced old (85+ years). The data were analyzed using IBM SPSS Statistics 29.0 and a decision tree. Results: Frailty prevalence increased with age: 2.0% in the young old, 7.0% in the advanced old, and 11.3% in the very advanced old group. Major predictors differed by group: activities of daily living in the young old, instrumental activities of daily living in the advanced old, and depression in the very advanced old. The primary causes of frailty gradually changed as people aged, moving from physical to psychological and social influences. Conclusion: These findings suggest the need for age-specific frailty management programs. Programs should emphasize physical activity for the young old and socio-psychological support for the very advanced old to support healthy aging.

Purpose: The aim of this study was to assess lipid levels and to identify groups with poor lipid control group among patients with dyslipidemia. Methods: Data from 1,399 Korean patients with dyslipidemia older than 20 years were extracted from the Korea National Health and Nutrition Examination Survey. Complex sample analysis and decision-tree analysis were conducted with using SPSS for Windows version 27.0. Results: The mean levels of total cholesterol (TC), triglyceride (TG), low density lipoprotein-cholesterol (LDL-C), and high density lipoprotein cholesterol were 211.38±1.15 mg/dL, 306.61±1.15 mg/dL, 118.48±1.08 mg/dL, and 42.39±1.15 mg/dL, respectively. About 61% of participants showed abnormal lipid control. Poor glycemic control groups (TC ≥ 200 mg/dL or TG ≥ 150 mg/dL or LDL-C ≥ 130 mg/dL) were identified through seven different pathways via decision-tree analysis. Poor lipid control groups were categorized based on patients’ characteristics such as gender, age, education, dyslipidemia medication adherence, perception of dyslipidemia, diagnosis of myocardial infarction or angina, diabetes mellitus, perceived health status, relative hand grip strength, hemoglobin A1c, aerobic exercise per week, and walking days per week. Dyslipidemia medication adherence was the most significant predictor of poor lipid control. Conclusion: The findings demonstrated characteristics that are predictive of poor lipid control and can be used to detect poor lipid control in patients with dyslipidemia.

자살 시도는 장기적인 계획에 의해 실행될 수도 있고 급성 위기 상황에서 충동적으로 실행될 수도 있다. 효과적인 자살 예방과 개입을 위해서는 이러한 자살 시도의 행동 특성을 예측하는 차별적인 요인을 밝히는 것이 중요하다. 본 연구에서는 자살 시도 이전 계획 수준과 자살시도 당일 충동성을 예측하는 심리사회적 요인을 각각 알아보았다. 특히, 의사결정나무분석을 이용하여 자살 시도의 계획 수준 및 충동성을 예측하는 요인들 간의 상호작용 효과를 알아보는 것을 주요 목적으로 하였다. 이를 위해 성별과 연령대를 층화 표집하여 자살 시도 경험이 있는 성인 300명을 모집하였다. 온라인 설문조사를 통해 자살 행동 이전 계획 수준 및 자살 시도 당일 충동성을 측정하였고, 주요 예측변인으로 우울, 절망감, 부정 긴급성, 인지적 유연성, 스트레스 경험을 측정하였다. 의사결정나무분석 결과, 자살 시도 이전의 계획 수준은우울과 부정 긴급성의 상호작용이 예측하였다. 구체적으로 우울 수준이 높을수록 자살 시도 계획 수준이 높았고, 우울 수준이 낮은 경우에는 부정 긴급성이 높을수록 자살 시도 계획 수준이 높게 나타났다. 자살 시도 당일 충동성은 우울, 인지적 유연성(통제, 대안)과 절망감의 상호작용이 예측하였다. 첫째, 우울 수준이 낮을수록 자살 시도 당일 충동성이 높았다. 둘째, 우울 수준이 낮은 경우 통제와 대안 수준이 높을수록 자살 시도 당일 충동성이 높았고, 셋째, 우울, 통제, 대안 수준이 모두 낮을 경우에는 절망감이 높을수록 자살 시도 당일 충동성이 높게 나타났다. 본 연구 결과는 자살 시도 이전 계획 수준이 높은 자살 시도자와 급성 위기 상황에서 충동적으로 자살 시도를 하는사람들을 위한 차별화된 개입 전략이 필요함을 시사한다.

Suicide attempt is usually made as a result of distal planning and/or proximal impulsivity during an acute crisis. The aim of this study was to examine the interaction effects of psychosocial factors that predict the planning level and impulsivity of suicide attempt. Using stratified sampling by age and sex, 300 adults with a history of suicide attempt were recruited. Planning level and impulsivity of the most recent suicide attempt were assessed, and the following were assessed and used as the main predictors: depression, hopelessness, negative urgency, cognitive flexibility, and stress experience. Using decision tree analysis, the results indicated that the interaction between depression and negative urgency predicted the planning level of suicide attempt. Specifically, the higher the level of depression, the higher the planning level of a suicide attempt. In cases of low levels of depression, a higher level of negative urgency predicted the planning level. The psychosocial factors that predicted impulsivity of suicide attempt were the interaction of depression, cognitive flexibility (control and alternatives), and hopelessness. First, the lower the level of depression, the greater the impulsivity of a suicide attempt. Second, when depression levels were low, higher levels of control and alternatives predicted the impulsivity. Third, when the levels of depression, control, and alternatives were low, hopelessness predicted the impulsivity. The results of this study suggest that differential intervention strategies are needed for individuals planning suicide and those who may act impulsively during an acute crisis.

Purpose: The aim of this study is to explore levels of suicidal ideation and identify subgroups of high suicidal risk among the depressed elderly in Korea. Methods: A descriptive cross-sectional design was adopted on secondary data from the 6th (1st year) Korean national health and nutrition examination survey (KNHANES). A total of 239 depressed elders aged 60 or over who participated in the KNHANES. The prevalence of suicidal ideation and its related factors, including sociodemographic, physical, psychological characteristics and quality of life (EQ-5D index) were examined. Descriptive statistics and a decision tree analysis were performed using the SPSS/WIN 23.0 and SPSS Modeler 14.2 programs. Results: Of the depressed elderly, 28.9% had suicidal ideation. Three groups with high suicidal ideation were identified. Predictive factors included perceived stress level, household income level, quality of life and restriction of activity. In the highest risk group were those depressed elderly with moderate and low levels of stress, less than .71 of EQ-5D index and restriction of activity, and 80.0% of these participants had suicidal ideation. The accuracy of the model was 80.8%, its sensitivity 85.9%, and its specificity 68.1%. Conclusion: Multi-dimensional intervention should be designed to decrease suicide among the depressed elderly, particularly focusing on subgroups with high risk factors. This research is expected to contribute itself to the policy design and solution building in the future as it suggests policy implications in preventing the suicide of the depressed elderly.

Purpose: This study aimed to construct a model to predict whether the elderly population over 65 years of age will experience falls according to multi-drug therapy and related factors. Methods: Decision tree analysis was used to analyze data from the 2020 national survey of the living condition and welfare needs of older Koreans. Results: The fall experience rate was 23.7%, which was the highest in the case of diet management due to disease while taking multi-drug therapy. In contrast, those who did not receive multi-drug therapy had good subjective health rates, and those who did not have arthritis showed the lowest fall experience rate (5.5%). Conclusion: The elderly population has a high prevalence of chronic diseases, and the number of people using multi-drug therapy is increasing accordingly. For this reason, healthcare providers should carefully prescribe medication for older adults. In addition, it is necessary to develop and apply a customized fall management program that reflects the demographic and health-related factors, which include diet, disease types, and health levels, with multi-drug therapy.

본 연구의 목적은 학교폭력에 영향을 미치는 생태체계적 요인들 간의 상호작용을 통해 학교폭력 주변인 행동유형을 예측하기 위함이다. 이를 위해 전국 중․고등학생 1,984명을 대상으로 생태체계적 이론에 근거한 16개 요인에 관한 질문지를 활용하여 조사하고, 가해동조자, 방관자, 피해방어자를 예측하는 다양한 요인들 간의 상호작용을 분석하기 위해 데이터마이닝의 의사결정나무분석을 적용하였다. 그 결과는 다음과 같다. 첫째, 가해동조자 의사결정나무모형에서는 폭력적 매체의 영향과 지각된 사회의 폭력용인도, 공감, 또래집단화 간의 상호작용을 통해 가장 많은 가해동조자를 예측하였다. 둘째, 방관자 의사결정나무모형에서는 교사와의 상호작용과 학교폭력 예방 안전체계, 갈등 해결전략, 폭력적 매체의 영향 간의 상호작용을 통해 가장 많은 방관자를 예측하였다. 셋째, 피해방어자 의사결정나무모형에서는 교사와의 상호작용과 폭력적 매체의 영향, 지각된 사회의 폭력용인도, 사회불안 간의 상호작용을 통해 가장 많은 피해방어자를 예측하였다. 본 연구의 결과를 토대로 학교폭력 예방과 감소를 위해 학교폭력 주변인의 중요성과 이들에 대한 상담 및 교육의 실천적 방안을 논의하고, 추후 연구의 방향을 제안하였다.

The purpose of this study was to predict the behavioral types among school violence bystanders, focusing on the interactions between ecological systemic factors affecting school violence. For this, 1,984 middle and high school students were surveyed using a questionnaire that consisted of 16 factors derived from the ecological systemic theory. The interactions between these factors predicting behavioral types (i.e., the bully-follower, outsider, and victim-defender) were analyzed using the data mining's decision tree analysis. Results are as follows. First, in the decision tree model of bully-follower, the bully-followers were most often predicted by the following factors: strong influence of violent media, perceived social tolerance to violence as being more tolerant, low level of empathy, and interactions with peer groups. Second, in the decision tree model of outsider, the outsiders were most often predicted when there were: less frequent interactions with teachers, not well-established school violence prevention safety systems existing, lack of conflict resolution strategies, and less influence of violent media. Third, in the decision tree model of victim-defender, the victim-defenders were most often predicted by the following factors: more frequent interactions with teachers, less influence of violent media, perceived social tolerance to violence as being more intolerant, and low level of social anxiety. Based on the results of this study, to prevent and reduce school violence, we discussed the importance of studying school violence bystanders and developing counseling and educational approaches for them. Directions for future research were also suggested.