• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.1
• /
• pp.1-6
• /
• 2023

This study developed models using decision forest, support vector machine, and logistic regression methods to predict and prevent suicidal ideation among Korean adolescents. The study sample consisted of 51,407 individuals after removing missing data from the raw data of the 18th (2022) Youth Health Behavior Survey conducted by the Korea Centers for Disease Control and Prevention. Analysis was performed using the MS Azure program with Two-Class Decision Forest, Two-Class Support Vector Machine, and Two-Class Logistic Regression. The results of the study showed that the decision forest model achieved an accuracy of 84.8% and an F1-score of 36.7%. The support vector machine model achieved an accuracy of 86.3% and an F1-score of 24.5%. The logistic regression model achieved an accuracy of 87.2% and an F1-score of 40.1%. Applying the logistic regression model with SMOTE to address data imbalance resulted in an accuracy of 81.7% and an F1-score of 57.7%. Although the accuracy slightly decreased, the recall, precision, and F1-score improved, demonstrating excellent performance. These findings have significant implications for the development of prediction models for suicidal ideation among Korean adolescents and can contribute to the prevention and improvement of youth suicide.

• Korean Journal of Artificial Intelligence
• /
• v.9 no.1
• /
• pp.9-14
• /
• 2021

This paper predicted a model that indicates whether to buy a car based on primary health insurance customer data. Currently, automobiles are being used to land transportation and living, and the scope of use and equipment is expanding. This rapid increase in automobiles has caused automobile insurance to emerge as an essential business target for insurance companies. Therefore, if the car insurance sales are predicted and sold using the information of existing health insurance customers, it can generate continuous profits in the insurance company's operating performance. Therefore, this paper aims to analyze existing customer characteristics and implement a predictive model to activate advertisements for customers interested in such auto insurance. The goal of this study is to maximize the profits of insurance companies by devising communication strategies that can optimize business models and profits for customers. This study was conducted through the Microsoft Azure program, and an automobile insurance purchase prediction model was implemented using Health Insurance Cross-sell Prediction data. The program algorithm uses Two-Class Logistic Regression and Two-Class Boosted Decision Tree at the same time to compare two models and predict and compare the results. According to the results of this study, when the Threshold is 0.3, the AUC is 0.837, and the accuracy is 0.833, which has high accuracy. Therefore, the result was that customers with health insurance could induce a positive reaction to auto insurance purchases.

• The Korean Journal of Health Service Management
• /
• v.9 no.2
• /
• pp.81-88
• /
• 2015

The purpose of this study was to compare the risk-adjusted in-hospital mortality for craniotomies between logistic regression and multilevel analysis. By using patient sample data from the Health Insurance Review & Assessment Service, in-patients with a craniotomy were selected as the survey target. The sample data were collected from a total number of 2,335 patients from 90 hospitals. The sample data were analyzed with SAS 9.3. From the results of the existing logistic regression analysis and multilevel analysis, the values from the multilevel analysis represented a better model than that of logistic regression. The intra-class correlation (ICC) was 18.0%. It was found that risk-adjusted in-hospital mortality for craniotomies may vary in every hospital. The agreement by kappa coefficient between the two methods was good for the risk-adjusted in-hospital mortality for craniotomies, but the factors influencing the outcome for that were different.

• The Korean Journal of Applied Statistics
• /
• v.21 no.4
• /
• pp.589-602
• /
• 2008

This article studies on disability pensioners' characteristic with multinomial logit and logistic regression model. Seven factors are examined on whether each factor is reflected in degree of disability in the disability pension. By incorporating multinomial logit and logistic regression model, effectiveness and characteristic of the seven factors are investigated on the degree of disability. Result shows all the seven factors are significant on the degree of disability, while among the seven, five factors, age, sex, type of coverage, type of category, insured duration show a trend in degree of disability and the other two, cause of disability and class of standard monthly income are not effective on trend in degree of disability. Results from analyses might be useful for disability pension management.

• Nutrition Research and Practice
• /
• v.14 no.1
• /
• pp.45-54
• /
• 2020

BACKGROUND/OBJECTIVES: This study aimed to examine differences in weight control practices, beliefs, self-efficacy, and eating behaviors of weight class athletes according to weight control level. SUBJECTS/METHODS: Subjects were weight class athletes from colleges in Gyeong-gi Province. Subjects (n = 182) responded to a questionnaire assessing study variables by self-report, and data on 151 athletes were used for statistical analysis. Subjects were categorized into High vs. Normal Weight Loss (HWL, NWL) groups depending on weight control level. Data were analyzed using t-test, ANCOVA, x²-test, and multiple logistic regressions. RESULTS: Seventy-three percent of subjects were in the HWL group. The two groups showed significant differences in weight control practices such as frequency (P < 0.01), duration and magnitude of weight loss, methods, and satisfaction with weight control (P < 0.001). Multiple logistic regression showed that self-efficacy (OR: 0.846, 95% CI: 0.730, 0.980), eating behaviors during training period (OR: 1.285, 95% CI: 1.112, 1.485), and eating behaviors during the weight control period (OR: 0.731, 95% CI: 0.620, 0.863) were associated with weight control level. Compared to NWL athletes, HWL athletes agreed more strongly on the disadvantages of rapid weight loss (P < 0.05 - P < 0.01), perceived less confidence in controlling overeating after matches (P < 0.001), and making weight within their weight class (P < 0.05). HWL athletes showed more inappropriate eating behaviors than NWL athletes, especially during the weight control period (P < 0.05 - P < 0.001). CONCLUSIONS: Self-efficacy was lower and eating behaviors during pre-competition period were more inadequate in HWL athletes. Education programs should include strategies to help athletes apply appropriate methods for weight control, increase self-efficacy, and adopt desirable eating behaviors.

• Journal of the Korean Home Economics Association
• /
• v.49 no.9
• /
• pp.59-72
• /
• 2011

This study examined whether there are underlying latent classes of growth trajectories of maternal depression in the Korean population. Data from the first phase of the Panel Study of Korean Children (PSKC) of the Institute of Child Care and Education (KICCE) were used for this study. The final sample of participants included 1,471 mothers, who completed three interviews: at birth, at one month, and at four months. A two-class model consisting of depression (12.3%) and non-depression (87.7%) was considered the best-fitting solution using Mplus 3.13. The changes in postnatal depression in the Korean population within four weeks after childbirth, which is the period of "postpartum onset", seem to be important. Logistic regression analysis showed that duration of breast-feeding and planned pregnancy effects were significantly associated with trajectory class membership.

• The Korean Journal of Health Service Management
• /
• v.13 no.1
• /
• pp.31-42
• /
• 2019

Objectives: The purpose of this study is to analyze the relationship between the change gap in the perception of subjective hierarchy and medical expenditure and the factors influencing medical expenditure. Methods: An analysis based on the the data extracted from the Panel Study of Korea Health Panel for 2012-2013 (n=9,359) is conducted. Further in this study, data analysis included a chi-square test and logistic regression using SPSS version. 22.0 to analyze the factors influencing the turnover intention of industrial workers. Results: Model I showed decreases in medical expenditure by 1.247, 1.391, and 1.441 times in social classes one, two, and Model II showed an increase in medical expenditure by age, spouse, number of family members living together, insurance type, income class, economic activities, subjective health status, chronic illness and change on subjective recognition of social class. Conclusions: The study concludes that the state and community require psychological, social, and cultural support, in addition to individual efforts, to reduce medical expenditure.

• Korean Journal of Clinical Pharmacy
• /
• v.32 no.1
• /
• pp.13-19
• /
• 2022

Background: The use of combination therapy and fixed-dose combination therapy is increasing for the treatment of type 2 diabetes. Sodium glucose cotransporter-2 inhibitor (SGLT2i) is a drug class used in combination with metformin. Methods: Type 2 diabetes patients on SGLT2i/metformin combination therapy were extracted from the 2019 Health Insurance Review & Assessment Service-National Patients Sample. On July 1, 2019, SGLT2i and metformin fixed-dose combination (SGLT2i/metformin FDC) and two-pill combination (TPC) groups were identified, and a chi-square test and multiple logistic regression were performed. Results: Of total 2,992 patients, 1,077 (36%) were prescribed SGLT2i/metformin FDC and 1,915 (64%) were prescribed TPC. We found that the most common comorbidities were in the order of dyslipidemia, gastrointestinal disease, and hypertension. Multiple logistic regression analysis showed that the use of SGLT2i/metformin FDC was lower than TPC in patients with diabetic neuropathy (OR=0.76, p=0.008). Clinic (OR=2.09, p<0.001) and general hospital (OR=1.40, p=0.019) showed higher tendency to prescribe SGLT2i/metformin FDC compared to tertiary hospital. The tendency of prescribing SGLT2i/metformin FDC was lower in Kyeonggi (OR=0.79, p=0.037), Gyeongsang (OR=0.77, p=0.025) and Chungcheong (OR=0.68, p=0.007) than Seoul. Conclusion: Factors related to the use of SGLT2i/metformin FDC in patients with type 2 diabetes were complication, medical institution and region. The tendency to prescribe SGLT2i/metformin FDC was relatively higher in clinics than in tertiary general hospitals and in Seoul than in other regions.

• Communications for Statistical Applications and Methods
• /
• v.16 no.6
• /
• pp.1005-1012
• /
• 2009

The area under the curve(AUC) is commonly used as a measure of the receiver operating characteristic(ROC) curve which displays the performance of a set of binary classifiers for all feasible ratios of the costs associated with true positive rate(TPR) and false positive rate(FPR). In the bipartite ranking problem where one has to compare two different observations and decide which one is "better", the AUC measures the quantity that ranking score of a randomly chosen sample in one class is larger than that of a randomly chosen sample in the other class and hence, the function which maximizes an AUC of bipartite ranking problem is different to the function which maximizes (minimizes) accuracy (misclassification error rate) of binary classification problem. In this paper, we develop a way to construct the unified framework for AUC maximizer including support vector machines based on maximizing large margin and logistic regression based on estimating posterior probability. Moreover, we develop an efficient algorithm for the proposed unified framework. Numerical results show that the propose unified framework can treat various methodologies successfully.

• Research in Community and Public Health Nursing
• /
• v.33 no.1
• /
• pp.74-83
• /
• 2022

Purpose: The purpose of this study was to identify latent classes of health-related quality of life trajectories in middle-aged women and investigate predictors for latent classes. Methods: This study utilized data from the 2^nd, the 4^th to the 7^th Korean Longitudinal Survey of Women & Families. The subjects included 1,351 women aged 40~45 years. The data was analyzed using latent class growth analysis and logistic regression. Results: Two trajectories were identified for health-related quality of life in middle-aged women; 'persistently good' and 'increasing' groups. Predictors for the 'increasing' group were lower economic status, higher depression, and lower perceived health status. Conclusion: This study showed that characteristics of the individual, symptom status, and health perceptions were associated with health-related quality of life in middle-aged women. It is necessary to provide effective intervention for latent classes of health-related quality of life trajectories based on physical, mental, and social factors.