• Journal of agricultural medicine and community health
• /
• v.23 no.2
• /
• pp.229-242
• /
• 1998

Face-to-face interviews were carried out to investigate the relationship between social networks and hypertension in 958 rural residents(males=440, females=518) aged 60-64 of a community-dwelling sample of Dalsung County from April to September in 1996. Eight elements of social network were measured : marital status, regular religious attendance, membership in groups, number of friends, relatives, siblings, children, grandchildren. Hypertensives were defined as meeting at least one of following criteria : hypertension history, systolic blood pressure more than 160 mmHg, diastolic blood pressure more than 95 mmHg. In univariate logistic regression for males, having 1-4 friends vs. none showed odds ratio 0.43 (95% Confidence interval CI 0.19-0.96) and having 2-3, 4 and more than 5 children had reduced prevalence of hypertension with odds ratios 0.21 (95% CI 0.06-0.72), 0.14 (95% CI 0.04-0.49), 0.24 (95% CI 0.07-0.82), respectively when compared with persons without children. In females, there was no elements of social network statistically significant. Having 5-9 grandchildren vs. none showed a marginally significant odds ratio 0.42. In multivariate logistic regression models for males with adjustment for age, education, body mass index, smoking and drinking, number of friends and children showed increased odds ratios and number of close relatives gained a statistically significant odds ratios (0.44-0.50). In females, the adjustment yielded little changes of odds ratios except number of grandchildren which gained a statistically significance. These results suggest that only a certain elements of social network may be associated with reduced risk of hypertension and they may be different between genders in rural resident aged 60-64.

• KDI Journal of Economic Policy
• /
• v.30 no.2
• /
• pp.99-128
• /
• 2008

Nearly all Koreans are insured through National Health Insurance(NHI). While NHI coverage is nearly universal, it is not complete. Coverage is largely limited to minimal level of hospital and physician expenses, and copayments are required in each case. As a result, Korea's public insurance system covers roughly 50% of overall individual health expenditures, and the remaining 50% consists of copayments for basic services, spending on services that are either not covered or poorly covered by the public system. In response to these gaps in the public system, 64% of the Korean population has supplemental private health insurance. Expansion of private health insurance raises negative externality issue. Like public financing schemes in other countries, the Korean system imposes cost-sharing on patients as a strategy for controlling utilization. Because most insurance policies reimburse patients for their out-of-pocket payments, supplemental insurance is likely to negate the impact of the policy, raising both total and public sector health spending. So far, most empirical analysis of supplemental health insurance to date has focused on the US Medigap programme. It is found that those with supplements apparently consume more health care. Two reasons for higher health care consumption by those with supplements suggest themselves. One is the moral hazard effect: by eliminating copayments and deductibles, supplements reduce the marginal price of care and induce additional consumption. The other explanation is that supplements are purchased by those who anticipate high health expenditures - adverse effect. The main issue addressed has been the separation of the moral hazard effect from the adverse selection one. The general conclusion is that the evidence on adverse selection based on observable variables is mixed. This article investigates the extent to which private supplementary insurance affect use of health care services by public health insurance enrollees, using Korean administrative data and private supplements related data collected through all relevant private insurance companies. I applied a multivariate two-part model to analyze the effects of various types of supplements on the likelihood and level of public health insurance spending and estimated marginal effects of supplements. Separate models were estimated for inpatients and outpatients in public insurance spending. The first part of the model estimated the likelihood of positive spending using probit regression, and the second part estimated the log of spending for those with positive spending. Use of a detailed information of individuals' public health insurance from administration data and of private insurance status from insurance companies made it possible to control for health status, the types of supplemental insurance owned by theses individuals, and other factors that explain spending variations across supplemental insurance categories in isolating the effects of supplemental insurance. Data from 2004 to 2006 were used, and this study found that private insurance increased the probability of a physician visit by less than 1 percent and a hospital admission by about 1 percent. However, supplemental insurance was not found to be associated with a bigger health care service utilization. Two-part models of health care utilization and expenditures showed that those without supplemental insurance had higher inpatient and outpatient expenditures than those with supplements, even after controlling for observable differences.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.147-168
• /
• 2017

There have been many studies on accurate stock market forecasting in academia for a long time, and now there are also various forecasting models using various techniques. Recently, many attempts have been made to predict the stock index using various machine learning methods including Deep Learning. Although the fundamental analysis and the technical analysis method are used for the analysis of the traditional stock investment transaction, the technical analysis method is more useful for the application of the short-term transaction prediction or statistical and mathematical techniques. Most of the studies that have been conducted using these technical indicators have studied the model of predicting stock prices by binary classification - rising or falling - of stock market fluctuations in the future market (usually next trading day). However, it is also true that this binary classification has many unfavorable aspects in predicting trends, identifying trading signals, or signaling portfolio rebalancing. In this study, we try to predict the stock index by expanding the stock index trend (upward trend, boxed, downward trend) to the multiple classification system in the existing binary index method. In order to solve this multi-classification problem, a technique such as Multinomial Logistic Regression Analysis (MLOGIT), Multiple Discriminant Analysis (MDA) or Artificial Neural Networks (ANN) we propose an optimization model using Genetic Algorithm as a wrapper for improving the performance of this model using Multi-classification Support Vector Machines (MSVM), which has proved to be superior in prediction performance. In particular, the proposed model named GA-MSVM is designed to maximize model performance by optimizing not only the kernel function parameters of MSVM, but also the optimal selection of input variables (feature selection) as well as instance selection. In order to verify the performance of the proposed model, we applied the proposed method to the real data. The results show that the proposed method is more effective than the conventional multivariate SVM, which has been known to show the best prediction performance up to now, as well as existing artificial intelligence / data mining techniques such as MDA, MLOGIT, CBR, and it is confirmed that the prediction performance is better than this. Especially, it has been confirmed that the 'instance selection' plays a very important role in predicting the stock index trend, and it is confirmed that the improvement effect of the model is more important than other factors. To verify the usefulness of GA-MSVM, we applied it to Korea's real KOSPI200 stock index trend forecast. Our research is primarily aimed at predicting trend segments to capture signal acquisition or short-term trend transition points. The experimental data set includes technical indicators such as the price and volatility index (2004 ~ 2017) and macroeconomic data (interest rate, exchange rate, S&P 500, etc.) of KOSPI200 stock index in Korea. Using a variety of statistical methods including one-way ANOVA and stepwise MDA, 15 indicators were selected as candidate independent variables. The dependent variable, trend classification, was classified into three states: 1 (upward trend), 0 (boxed), and -1 (downward trend). 70% of the total data for each class was used for training and the remaining 30% was used for verifying. To verify the performance of the proposed model, several comparative model experiments such as MDA, MLOGIT, CBR, ANN and MSVM were conducted. MSVM has adopted the One-Against-One (OAO) approach, which is known as the most accurate approach among the various MSVM approaches. Although there are some limitations, the final experimental results demonstrate that the proposed model, GA-MSVM, performs at a significantly higher level than all comparative models.

• Tuberculosis and Respiratory Diseases
• /
• v.66 no.4
• /
• pp.300-308
• /
• 2009

Background: The quality of care for patients with community acquired pneumonia needs to be improved; the factors affecting this care need to be analyzed. The objectives of this study were used to measure the performance of care processes of for patients with pneumonia and to determine those patient and hospital characteristics are associated with quality care. Methods: The analysis was performed using data from 21 hospitals that had over 500 beds for 1,001 patients, who were sampled randomly. All patients were born before 31 December 1989, and discharged between the two months' August 2006 and October 2006. Performance process indicators were measured by respective hospital, and multivariate logistic regression was used to calculate associations between patients and hospital characteristics using 4 process indicators. Results: Performance rates in timely assessment of oxygenation assessments and blood cultures, correct administration of antibiotic medications, and blood culture performed prior to initial antibiotics were 69.4%, 79.1%, 82.5% and 60.5%, respectively. Age had a positive affect on oxygenation assessment within 24 hours. Bed number, number of nurses per bed, annual number of emergency department visits, average percentage of beds filled, location and arrival time, and site were factors associated with process indicators. Conclusion: It is necessary to make up for the weak points in the process of care for patients with community acquired pneumonia, by enforcing quality assurance. To reduce performance rate variation among hospitals, improvement in care protocols is required for hospitals that have poor quality of care levels.

• Korean Journal of Psychosomatic Medicine
• /
• v.21 no.2
• /
• pp.106-113
• /
• 2013

Objectives: The purpose of this study was to examine the characteristics and the psychosocial factors associated to the referral to psychiatric care in the suicide attempters visiting emergency center. Methods: We conducted a systematic chart review of 377 suicidal attempters visiting emergency center of the Korea University Ansan Hospital between January 2008 and December 2011. We gathered a data contain 20 items including psychosocial characteristics and factors related to suicide and factors related to psychiatric treatment. Multivariate logistic regression models were fitted to data to estimate the unique effects of sex, drunken status, companion, suicidal methods, place of suicide and current use of psychiatric medication on the referral to psychiatric care. Results: The female gender(OR=1.63, 95% CI=0.99-2.69), suicidal attempts at home(OR=3.40, 95% I= 1.21-9.56) and drunken state at visit(OR=2.34, 95% CI=1.10-5.01) are the factors that predict the risk of the non-referral of the patients to psychiatric intervention. Place of suicidal attempt was the most important factor do play a role in determining whether referral to psychiatric care will take place or not. Current use of psychiatric medication showed a trend toward significance(p=0.08, OR=1.67, 95% CI=0.95-2.95). Conclusions: These results suggest that when deciding whether to adapt or to refuse the referral to psychiatric care, the factors such as suicidal intent, lethality of suicide methods, familiar factors and alcohol may contribute onto the referral to psychiatric care. Additional research is required to investigate an association of these factors with referral to psychiatric care.

• Journal of Nutrition and Health
• /
• v.47 no.2
• /
• pp.113-123
• /
• 2014

Purpose: Vitamin D has been known to play an important role in the central nervous system and brain functions in the human body, and cumulative evidence has shown that vitamin D deficiency might be linked with various mental health conditions. Epidemiologic studies have shown that vitamin D deficiency may be associated with higher risk of depression in the US and European populations. However, limited information is available regarding the association between vitamin D status and depression in the Korean population. The objective of this study was to examine the associations between vitamin D levels and prevalence of depression. Methods: We conducted a cross-sectional analysis using nationally representative data from the 2008-2010 Korean National Health and Nutrition Examination Survey from which serum 25-hydroxyvitamin D concentrations were available. A total of 18,735 adults who had available demographic, dietary, and lifestyle information were included in our analysis. We defined "depression" with a diagnosis by a physician. "Depressed condition" was defined as having feelings of sadness or depression without diagnosis by a physician. Results: The prevalence of depression was 1.63% and 5.43% in Korean men and women, respectively; 12.5% of men and 26.1% of women were defined as the group having depressed conditions. In multivariate logistic regression models, no significant associations were observed between vitamin D status and prevalence of depression or depressed conditions in Korean men and women. Conclusion: We found no association between vitamin D insufficiency and depression/depressed conditions in Korean adults. Future large prospective studies and randomized controlled trials are needed to confirm this relationship.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.103-128
• /
• 2021

Recently, investors' interest and the influence of stock-related information dissemination are being considered as significant factors that explain stock returns and volume. Besides, companies that develop, distribute, or utilize innovative new technologies such as artificial intelligence have a problem that it is difficult to accurately predict a company's future stock returns and volatility due to macro-environment and market uncertainty. Market uncertainty is recognized as an obstacle to the activation and spread of artificial intelligence technology, so research is needed to mitigate this. Hence, the purpose of this study is to propose a machine learning model that predicts the volatility of a company's stock price by using the internet search volume of artificial intelligence-related technology keywords as a measure of the interest of investors. To this end, for predicting the stock market, we using the VAR(Vector Auto Regression) and deep neural network LSTM (Long Short-Term Memory). And the stock price prediction performance using keyword search volume is compared according to the technology's social acceptance stage. In addition, we also conduct the analysis of sub-technology of artificial intelligence technology to examine the change in the search volume of detailed technology keywords according to the technology acceptance stage and the effect of interest in specific technology on the stock market forecast. To this end, in this study, the words artificial intelligence, deep learning, machine learning were selected as keywords. Next, we investigated how many keywords each week appeared in online documents for five years from January 1, 2015, to December 31, 2019. The stock price and transaction volume data of KOSDAQ listed companies were also collected and used for analysis. As a result, we found that the keyword search volume for artificial intelligence technology increased as the social acceptance of artificial intelligence technology increased. In particular, starting from AlphaGo Shock, the keyword search volume for artificial intelligence itself and detailed technologies such as machine learning and deep learning appeared to increase. Also, the keyword search volume for artificial intelligence technology increases as the social acceptance stage progresses. It showed high accuracy, and it was confirmed that the acceptance stages showing the best prediction performance were different for each keyword. As a result of stock price prediction based on keyword search volume for each social acceptance stage of artificial intelligence technologies classified in this study, the awareness stage's prediction accuracy was found to be the highest. The prediction accuracy was different according to the keywords used in the stock price prediction model for each social acceptance stage. Therefore, when constructing a stock price prediction model using technology keywords, it is necessary to consider social acceptance of the technology and sub-technology classification. The results of this study provide the following implications. First, to predict the return on investment for companies based on innovative technology, it is most important to capture the recognition stage in which public interest rapidly increases in social acceptance of the technology. Second, the change in keyword search volume and the accuracy of the prediction model varies according to the social acceptance of technology should be considered in developing a Decision Support System for investment such as the big data-based Robo-advisor recently introduced by the financial sector.