• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.139-153
• /
• 2017

Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.

• Radiation Oncology Journal
• /
• v.19 no.3
• /
• pp.224-229
• /
• 2001

Purpose : The aim of this study is to analyze the treatment failure patterns and the risk factors for locoregional or distant failure of uterine cervical carcinoma treated with radiation therapy. Materials and methods . A retrospective analysis was undertaken of 154 patients treated with curative radiation therapy in Gyeongsang National University Hospital from April 1989 through December 1997. According to FIGO classification, 12 patients were stage IB, 24 were IIA, 98 were IIB, 1 were IIIA, 17 were IIIB, 2 were IVA. Results : Overall treatment failure rate was $42.1\%$ (65/154), and that of complete responder was $31.5\%$ (41/130). Among 65 failures, 25 failed locoregionally, another 25 failed distantly, and 15 failed locoregionally and distantly. Multivariate analysis confirmed tumor size (>4 cm) as risk factor for locoregional failure, and tumor size (>4 cm), pelvic lymph node involvement as risk factors for distant failure. Conclusion : On the basis of results of our study and recent published data of prospective randomized study for locally advanced uterine cervical carcinoma, we concluded that uterine cervical carcinoma with size more than 4 cm or pelvic lymph node involvement should be treated with concurrent chemoradiation.

• Korean Journal of Social Welfare Studies
• /
• v.48 no.3
• /
• pp.171-208
• /
• 2017

The purpose of this study is to classify the underlying and parsimonious types of child maltreatment and examine whether the effects of risk factors on child maltreatment recurrence differ by type of maltreatment. We utilized the multiyear national administrative data from the National Child Maltreatment Information System collected by Child Protection Agency in Korea. Of 26,921 child maltreatment victims reported and substantiated on or after January 1, 2012, 1,447 children who had recurrence of child maltreatment until December 31, 2015 were selected as maltreatment recurrence group and 4,580 children who had not experienced maltreatment since first substantiation were assigned as maltreatment non-recurrence group. Latent class analysis(LCA) and latent transition analysis(LTA) were used to group children with similar maltreatment subtypes into discrete classes of child maltreatment recurrence. Logistic regression is employed to examine the association between the child maltreatment predominant types and risk factors for recurrence. Results of LCA and LTA showed four latent classes representing predominant type of child maltreatment: 'physical abuse predominant type', 'emotional abuse predominant type', 'sexual abuse predominant type', and 'neglect type'. Significant differences in the effect of risk factors among latent classes were found in child's age and gender, perpetrator's gender, family poverty, biological parent as the perpetrator, domestic violence toward partner, perpetrator's alcoholic problem, insufficient parenting skills, and out-of-home care service, Based on these findings, results suggested how the typology can be used to guide decision about who to target in prevention and intervention programs, and which features of risk factors to target. Practice and policy implications as well as further research tasks were discussed in the lights of searching for useful and important strategies to prevent recurrence of child maltreatment.

• Korean Journal of Psychosomatic Medicine
• /
• v.30 no.2
• /
• pp.127-136
• /
• 2022

Objectives : The study aimed to identify factors associated with suicidal attempt in Korean adults experiencing thoughts of suicide. Methods : This study analyzed outcomes of suicidal behavior in the Korea National Health and Nutrition Examination Survey (KNHANES) 2015, 2017, and 2019. This survey was administered by the Korea Centers for Disease Control and Prevention (KCDC). The suicidal idea group was divided into individuals who had attempted suicide (n=92) and those who had not (n=831). Complex samples crosstabs analysis was conducted to compare the two groups' sociodemographic, psychiatric, and clinical characteristics. In addition, factors related to attempted suicide were investigated using complex samples logistic regression analysis. Results : The attempted suicide group had significantly higher rates of depression, recent psychiatric counseling, and suicidal plan (p<0.001) than the non-attempting group. In addition, the groups differed significantly in the frequency of binge drinking and smoking (p<0.05). Adjusted multivariate analysis revealed that the presence of a suicidal plan (Odds ratio [OR]=8.46, 95% Confidential Intervals [CI]=4.72-15.00), daily binge drinking (OR=3.14, 95% CI=1.26-7.84), psychiatric counseling within the past year (OR=3.03, 95% CI=1.75-5.23), low income level (OR=2.89, 95% CI=1.17-7.10), and history of depression (OR=2.39, 95% CI=1.29-4.42) were significantly associated with suicidal attempt. Conclusions : Factors associated with suicidal attempt among suicidal ideators in the general Korean population were identified across all sociodemographic, psychiatric, and clinical variables. Assessment of and intervention in suicidal plan, binge drinking, income level, and depression might prevent progression to suicidal attempt among those contemplating suicide.

• Journal of Nutrition and Health
• /
• v.56 no.6
• /
• pp.702-713
• /
• 2023

Purpose: Depression is a prevalent mental health concern globally including South Korea. Given the growing interest in the relationship between diet and mental health, this study aimed to investigate the association between seafood consumption and depression among Korean adults. Methods: A cross-sectional analysis was conducted using data from the Korea National Health and Nutrition Examination Survey (KNHANES, 2014-2020). The study included 18,149 participants (7,541 men and 10,608 women) aged 19 years and older who completed the Patient Health Questionnaire (PHQ-9). Seafood intake levels were assessed using a oneday 24-hour dietary recall, and participants were categorized into three tertiles by gender. Depression status was determined using the PHQ-9 scores and the self-report of the doctor's diagnosis and treatment. Multivariable logistic regression analysis was performed to assess the association between seafood consumption and depression in both genders. Results: Participants with a higher seafood intake had a significantly lower nutritional density of total fat, while the nutritional density of omega-3 polyunsaturated fatty acids was significantly higher. The prevalence of depression was significantly lower in the highest tertile of seafood consumption compared to the lowest tertile in both men (p < 0.001) and women (p < 0.001). After adjusting for confounding factors, the highest tertile of seafood consumption demonstrated a decreased risk of depression compared to the lowest tertile in men (odds ratio [OR], 0.71; 95% confidence interval [CI], 0.51-0.99; p-trend = 0.020) and women (OR, 0.73; 95% CI, 0.59-0.91; p-trend = 0.004). Conclusion: The findings of this study suggest that consuming seafood rich in omega-3 fatty acids may potentially reduce the risk of depression in the adult population.

• Journal of the Korean Society of Radiology
• /
• v.81 no.2
• /
• pp.395-408
• /
• 2020

Purpose To evaluate the value of clinicopathologic factors and imaging features of primary breast cancer in predicting early recurrence after the primary treatment. Materials and Methods We enrolled 480 patients who had been followed-up after breast-conserving surgery and adjuvant therapy from January 2010 to December 2014 at our hospital. Early recurrence was defined as recurrence within 3 years after completion of primary treatment, and univariate and multivariate logistic regression analyses were performed to determine the clinicopathologic and imaging predictive factors of early recurrence. Results In the univariate analysis, among the clinicopathologic factors, advanced stage (p = 0.021), high histologic grade (p < 0.001), estrogen receptor negative (p = 0.002), high Ki-67 proliferation index (p = 0.017), and triple-negative breast cancer (p = 0.019), and among the imaging features, multifocality (p < 0.001), vessels in the rim on Doppler ultrasonography (US) (p = 0.012), and rim enhancement (p < 0.001) on magnetic resonance imaging of the breast were significantly associated with early recurrence. In the multivariate analysis, advanced stage [odds ratio (OR) = 3.47; 95% confidence interval (CI) 1.12-10.73; p = 0.031] and vessels in the rim on Doppler US (OR = 3.32; 95% CI 1.38-8.02; p = 0.008) were the independent predictive factors of early recurrence. Conclusion Vascular findings in the rim of the primary breast cancer on Doppler US before treatment is a radiologic independent predictive factor of early recurrence after the primary treatment.

• Journal of agricultural medicine and community health
• /
• v.24 no.2
• /
• pp.269-289
• /
• 1999

This study was conducted to examine the relationship among health concern, health practice and ADL of elderly staying at home in a rural community and their affecting factors. Data were collected through direct interviews made with 480 old people aged more than sixty-five from November 15, 1998 to December 20, 1998. Out of 189 male and 291 female, the high-level group that showed high health concern accounted for 44.4%, the medium-level group for 13.1%, and the low-level group for 42.5%, in the health practice, the high-level group accounted for 3.8%, the medium-level group for 18.8%, and the low-level group for 77.5%. In the self-rated health status, the high-level group accounted for 29.0%, the medium-level group for 31.0%, and the low-level group for 40.0%, and in the ADL, the high ADL group accounted for 91.5%, and the low-level ADL group for 8.5%. The result of the chi-square test showed that for male, there was a significant relation between the health concern and the health practice index score. In the relation between the health practice index score and the self-rated health status, there was significant positive relationship between health practice index and self-rated health status, and in the relation between the health practice Index score and the ADL, old people with higher health practices showed good ADL(but not significant). Old people with good ADL also showed good self-rated health status. In the multiple regression analysis where the health practice was used as a dependent variable, the health concern was added to the sociodemographic variables as an independent variables, a formula was formed for male old people only and ones with high concern in health showed good health practice. In the multiple logistic regression analysis where the sociodemographic variables to which the health practices was added were used as an independent variable and the ADL as a dependent variable, the ADL appeared to be not good if for male old people the living costs were born by their sons and daughters and as for female old people their ages increased, but it was good if old people had sources of health information such as hospitals or health centers. The self-rated health status was worse, for male old people, if they had short living costs or diseases and for female old people, if they had spouses, living costs born by their sons and daughters or diseases, but it was better, for male old people, if they had periodical gatherings or carried out health practices a lot, and for female old people, if they had sources of health information such as hospitals or health centers or carried out health practices a lot. In view of the results stated above, the higher the old people had health concern, the more they carried out health practices, and the more they carried out health practices, the better they had ADL and self-rated health status that served as the level of health. Further, the better ADL, the better self-rated health status.

• Journal of agricultural medicine and community health
• /
• v.30 no.2
• /
• pp.167-182
• /
• 2005

Objectives: This study was performed to investigate the prevalence of knee osteoarthritis according to the criteria of diagnosing knee osteoarthritis in rural women and the factors related with this disease. Methods: The data obtained from 200 women older than 40 years of age residing in 5 Ri's in Goryeong-gun. Gyeongsanbuk-do by random cluster sampling from September to October 2002. Knee osteoarthritis was determined positive according to the Kellgren and Lawrence classification and knee pain. Results: Among these subjects, 71.0% showed more than grade 2 in radiologic finding and the rate of knee pain according to the survey was 67.0%. The rate of subjects meeting the criteria of knee osteoarthritis was 54.0%. According to univariate analysis, the prevalence of knee osteoarthritis increased with age and those farming people and people working in household industry was significantly high at 58.9% compared with others. The prevalence of knee osteoarthritis showed a significant relationship with the family history and past history of knee injury and knee surgery(p<0.01), and diabetes mellitus(p<0.05). The score of ADL was significantly different in the subjects with knee osteoarthritis compared with normal group(p<0.05). When the presence of knee osteoarthritis and the period of the life style of seating down on the floor were compared, a significant difference was present between the osteoarthritis group and normal group. As for metabolic factors, the blood sugar level, bone density, and body mass index(BMI) were significantly different in the osteoarthritis group compared with normal group. When multiple logistic regression analysis was performed with the presence of knee osteoarthritis as the dependent variable, the prevalence of knee osteoarthritis was significantly affected by older age, subjects farming or working in household industry, the history of knee injury, the history of surgery, higher blood sugar level, and higher BMI. Conclusions: These subjects need an intervention through self-care programs such as exercise for preventing osteoarthritis, weight control programs, other exercise programs strengthening knee joints, and guidelines when working in vinyl houses.

• Clinical and Experimental Pediatrics
• /
• v.50 no.6
• /
• pp.536-542
• /
• 2007

Purpose : We investigated the effects of restricted fluid in the first 7 days of life on the risk of bronchopulmonary dysplasia (BPD) or patent ductus arteriosus (PDA) in very low birth weight (VLBW) infants. Methods : Eighty three VLBW infants who lived more than 28 days were selected. The amount of daily maintenance fluid was determined by calculation of insensible water loss (IWL) and urine output (UO). Seventy to 80 percent of calculated amount was given to the ventilated infants. Subjects were grouped into low (<25th%), moderate (25-75th%), and high (>75th%) fluid groups for the first 24 hours, 3 days and 7 days. Chi square tests analyzed proportions of subjects with or without morbidities across fluid groups. Multivariate logistic regression was used to analyze the effect of fluid intake on BPD or PDA, controlling for factors that are significantly associated with BPD or PDA by univariate analysis. Results : Rates of BPD and PDA were not significantly associated with fluid groups on each time period. The result was the same after controlling for factors that are significantly associated with BPD or PDA by univariate analysis. For the first 3 and 7 days, fluid intakes were positively related with maximal weight loss, urine output and mechanical ventilation duration. Conclusion : In VLBW infants, when given based on needs reflected from IWL and UO versus intake, relatively low fluid intakes in the first week of life do not decrease the risk of BPD or PDA, and vice versa. We suggest that calculation of daily fluid based on IWL and UO is appropriate for VLBW infants.

• Tuberculosis and Respiratory Diseases
• /
• v.56 no.6
• /
• pp.600-610
• /
• 2004

Background : The plasma B-type natriuretic peptide(BNP) concentration increases with the degree of pulmonary hypertension in patients with chronic respiratory disease. The aim of this study was to examine the prognostic role of BNP in the acute exacerbation of chronic obstructive lung disease (COPD). Method : We selected 67 patients who were admitted our hospital because of an acute exacerbation of COPD. Their BNP levels were checked on admission at the Emergency Department. Their medical records were analyzed retrospectively. The patients were divided into two groups according to their in-hospital mortality. The patients' medical history, comobidity, exacerbation type, blood gas analysis, pulmonary function, APACHE II severity score and plasma BNP level were compared. Results : Multiple logistic regression analysis identified three independent predictors of mortality: $FEV_1$, APACHE II score and plasma BNP level. The decedents group showed a lower $FEV_1$($28{\pm}7$ vs. $37{\pm}15%$, p=0.005), a higher APACHE II score($22.4{\pm}6.1$ vs. $15.8{\pm}4.7$, p=0.000) and a higher BNP level ($201{\pm}116$ vs. $77{\pm}80pg/mL$, p=0.000) than the sSurvivors group. When the BNP cut-off level was set to 88pg/mL using the receiver operating characteristic curve, the sensitivity was 90% and the specificity was 75% in differentiating between the survivors and decedents. On Fisher's exact test, the odds ratio for mortality was 21.2 (95% CI 2.49 to 180.4) in the patients with a BNP level > 88pg/mL. Conclusion : The plasma BNP level might be a predictor of mortality in an acute exacerbation of COPD as well as the $FEV_1$ and APACHE II score.