• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.53-64
• /
• 2021

Depression is one of the most important psychiatric disorders worldwide. Most depression-related data mining and machine learning studies have been conducted to predict the presence of depression or to derive individual risk factors. However, since depression is caused by a combination of various factors, it is necessary to identify the complex relationship between the factors in order to establish effective anti-depression and management measures. In this study, we propose a methodology for identifying and interpreting patterns of depression expressions using the method of deriving random forest rules, where the random forest rule consists of the condition for the manifestation of the depressive pattern and the prediction result of depression when the condition is met. The analysis was carried out by subdividing into 4 groups in consideration of the different depressive patterns according to gender and age. Depression rules derived by the proposed methodology were validated by comparing them with the results of previous studies. Also, through the AUC comparison test, the depression diagnosis performance of the derived rules was evaluated, and it was not different from the performance of the existing PHQ-9 summing method. The significance of this study can be found in that it enabled the interpretation of the complex relationship between depressive factors beyond the existing studies that focused on prediction and deduction of major factors.

• Journal of muscle and joint health
• /
• v.20 no.2
• /
• pp.112-121
• /
• 2013

Purpose: This purpose of study was to examine the degree of the depression and to identify the affecting factors on the depression of Korean female university students. Methods: A cross-sectional descriptive study design was used. Data were collected from 448 female university students. Participants completed a self-reported questionnaire including general characteristics, depression, well-being, stress, self-efficacy, social support, coping, self-esteem, and temperament. Results: The mean of Beck's Depression Inventory was 11.07. The affecting factors on the depression of female university students were stress, well-being, self-esteem, health status and major. The proportion of variance explained by these affecting factors was 50.0%. Conclusion: Depression among female university students were associated with various factors. Considering these factors, intervention programs should be developed to reduce depression of female university students.

• Journal of Preventive Medicine and Public Health
• /
• v.55 no.5
• /
• pp.444-454
• /
• 2022

Objectives: We aimed to identify the factors related to depression and quality of life in patients with hypertension by using multilevel regression analysis. Methods: In 2019, 229 043 participants in the Korean Community Health Survey were selected as the study group. Individual factors were identified using data from the 2019 Community Health Survey. Regional factors were identified using data from the National Statistical Office of Korea. Multilevel regression analysis was conducted to find individual and local factors affecting depression and quality of life in patients with hypertension and to determine any associated interactions. Results: As individual factors in patients with hypertension, women, those with lower education-levels, recipients of basic livelihood benefits, and those with poor dietary conditions showed stronger associations with depression and quality of life. As regional factors and individual-level variables in patients with hypertension, lower gross regional personal income, fewer doctors at medical institutions, and lower rates of participation in volunteer activities presented stronger associations with depression and quality of life. In addition, the associations of depression with gross regional personal income, the number of doctors at medical institutions, and dietary conditions were significantly stronger in patients with hypertension than in patients without hypertension. The associations of gender and employment status with quality of life were also significantly greater. Conclusions: Policy interventions are needed to adjust health behaviors, prevent depression, and improve quality of life for patients with hypertension, especially for those with the risk factors identified in this study.

• Women's Health Nursing
• /
• v.16 no.2
• /
• pp.95-104
• /
• 2010

Purpose: This study examined the influencing factors on antenatal depression among pregnant women. Methods: This was a cross sectional descriptive study with 255 pregnant women who visited a general hospital in a metropolitan city for their regularly scheduled check-up. Measurement tools employed were the Korean version of Beck Depression Inventory (BDI), the food habits, and the Pittsburg Sleep Quality Index (PSQI). Socio-demographic variables and the status of high risk pregnancy were identified. Influencing factors on antenatal depression were identified using a stepwise multiple regression analysis. Results: The mean score of antenatal depression was $7.2{\pm}5.0$; 18.4% with mild depression, 5.9% had moderate depression, with 0.8% identified with severe depression on BDI scale. Influencing factors on antenatal depression accounted for 47.8% of the total variance which consisted of quality of sleep, marital satisfaction, food habits, gestation periods, sexual satisfaction, high risk pregnancy, and age. Conclusion: Findings show that antenatal depression should be monitored on a regular basis during early pregnancy and in high risk pregnancy if possible, and quality of sleep and food habits should be incorporated in the management of antenatal depression.

• Korean Journal of Adult Nursing
• /
• v.27 no.3
• /
• pp.262-272
• /
• 2015

Purpose: This study was conducted to examine the mutual reciprocal relationship between elders' ego integrity and depression including physical and psycho-social predictors of both variables. The study also investigated the significant predictors of elders' ego integrity and depression. Methods: Data were collected using a structured questionnaire from 137 elders. Results: Perceived health status, self-esteem, family interaction, and depression were significant predictors of ego integrity, whereas pain, self-esteem, and ego integrity were significant factors of depression. The results also showed that ego integrity and depression had reciprocal relationship with each other. Conclusion: Psycho-social factors might be more important to improve ego integrity and to alleviate depression in elderly subjects than physical factors.

• Journal of Korean Public Health Nursing
• /
• v.28 no.1
• /
• pp.71-86
• /
• 2014

Purpose: This study was conducted in order to identify factors that predict suicidal ideation and depression according to gender among Korean adults. Method: From the data base of the fifth Korean National Health and Nutritional Examination Survey(KNHANESV-1, 2010), data on 4,894 adults aged 19~64 were used. Data were analyzed by application of the Rao-Scott Chi-Square test and logistic analysis with SAS 9.2. Results: Overall, 8.5% of men and 18.1% of women had suicidal ideation during the last year; 7.5% of men and 17.0% of women had depression during the last two weeks. Risk factors for suicidal ideation include perceived high stress(OR male 3.649, female 2.941), depression(OR male 10.109, female 6.033), poor cognition of health status(OR male 8.115, female 6.664), low economic status(OR male 1.898), and low educational status(OR female 1.631). Risk factors for depression include perceived high stress(OR male 2.678, female 3.686), suicidal ideation(OR male 9.925, female 6.022), non-employed(OR female 1.525), married(OR female 2.392), and physical discomfort(OR female 1.545). Conclusions: Based on the above mentioned results, risk factors of suicidal ideation and depression differed according to gender. Development of various policies and appropriate intervention programs according to gender, that lessen the risk of suicidal ideation and depression for adults is needed.

• Journal of Korean Public Health Nursing
• /
• v.28 no.2
• /
• pp.333-346
• /
• 2014

Purpose: This study was conducted in order to identify factors that influence depression for low-income elderly who live at home from the International Classification of Functioning model (ICF). Methods: The subjects were 205 elderly people living at home in two public health centers located in metropolitan cities. Subjects were divided according to their depression scores, which were measured using the GDS-short form, including normal, risk, and depression groups. Each variable was consistent with factors of the ICF model, including health condition, individual factors, environmental factors, body function, activities, and participation. Data were collected using structured questionnaires. ANOVA, $x^2$, Pearson's correlation coefficient, and Multinomial logistic regression with IBM SPSS 21.0 were used for analysis of the data. Results: Statistically significant differences were observed among normal, risk, and depression groups regarding personal factors. Gender, education level, numbers of diseases, perceived health, life satisfaction, and social support were identified as the variables that had a significant impact on depression of low-income elderly living at home. Conclusion: Results of this study indicate that there is a need for construction and implementation of strategies that strengthen life satisfaction and social support in order to lower depression of low-income elderly.

• Journal of Korean Academy of Nursing
• /
• v.42 no.1
• /
• pp.136-147
• /
• 2012

Purpose: This study was conducted to compare the degree of depression between men and women and to identify factors influencing their depression. Methods: Participants in this cross-sectional descriptive study were 263 persons over 65 years old (men: 103, women: 160). Data were collected through face to face interviews using questionnaires and were done in two urban areas in 2010. Research instruments utilized in this study were SGDS, MMSE-K, SRH, FILE, sleep pattern scale, family and friend support scale, and social support scale. Multivariate regression analysis was performed to identify factors influencing depression in elders. Results: The proportions of participants with depression were significantly different between men and women (52.4% vs. 67.5%). Regression model for depression in elderly men significantly accounted for 54%; disease stress (32%), economic stress (10%), perceived health status (4%), and family support, educational level, age, and hypertension. Regression model for depression in elderly women significantly accounted for 47%; disease stress (25%), perceived social loneliness (8%), friend support (5%), family stress (4%), and sleep satisfaction, and family support. Conclusion: Results demonstrate that depression is an important health problem for elders, and show gender differences for factors influencing depression. These results could be used in the developing depression prevention programs.

• Journal of Korean Academy of Nursing
• /
• v.33 no.5
• /
• pp.609-617
• /
• 2003

Purpose: The purpose of this study is to understand the depression of patients for Fibromyalgia Syndrome(FMS) and to identify the factors influencing depression. Method: The instruments used here are Beck Depression Inventory in depression, the Korean Rheumatology Health Association' instruments in Self-Efficacy. Also, Pain and Fatigue was measured by Visual Graphic Rating Scale. The subject of study is 76 outpatients diagnosing FMS from rheumatism specialists at C hospital in D city. The data has been collected from Sep. 1st to Sep. 30th in 2001. For the analysis of collected data, frequency analysis, independent t-test, analysis of variance, Pearson's correlation and multiple regression analysis were used for statistical analysis with SAS statistical program. Result: General characteristics showing statistically significant difference in depression were age, education, occupation, gender, exercise and sleep in the patients with FMS. Depression for the patients with FMS has negative correlation coefficients with Self-efficacy and ADL, and positive correlation coefficients with Pain and Fatigue. The suitable regression form resulting from the multiple regression analysis to investigate the influencing factors of depression for the partients with FMS was expressed by y =50.067 - 0.278x$_1$ + 1.320x$_2$ (x$_1$: Self-Efficacy x$_2$: Fatigue) and $R^2$ =0.427. Conclusion: The factors influencing on depression of patients for FMS was Self-Efficacy, ADL, Pain, and Fatigue. Further study needs to be done identify methods of overcoming and presentation of depression in FMS.

• Women's Health Nursing
• /
• v.20 no.1
• /
• pp.38-47
• /
• 2014

Purpose: This study aimed to identify related factors of prenatal depression by stress-vulnerability and stress-coping models for pregnant women. Methods: A cross-sectional survey design with a convenience sampling was used. A total of 107 pregnant women who visited a general hospital in a metropolitan city were recruited from August to October, 2013. A structured questionnaire included the Korean version of Beck Depression Inventory II, and the instruments measuring Self-Esteem, Marital Satisfaction, Pregnancy Stress, Stressful Life Events, and Coping. The data were analyzed using descriptive statistics, t-test, Parson's correlation analysis, and stepwise multiple regression. Results: The mean score of prenatal depression was $11.95{\pm}6.2$, then showing 19.6% with mild depression, 15.0% with moderate depression, and 0.9% with severe depression on BDI II scale. Prenatal depression had positive correlation with pregnancy stress (r=.55, p<.01), stressful life events (r=.26, p<.01) and negative correlation with self- esteem (r=-.38, p<.01), marital satisfaction (r=-.40, p<.01), and coping (r=-.21, p<.05). Factors of pregnancy stress, self-esteem, stressful life events, and planned pregnancy explained 38% of the total variance of prenatal depression. Conclusion: These findings show that health providers need to assess prenatal depression and to control the influencing factors.