• The Journal of Bigdata
• /
• v.2 no.2
• /
• pp.115-128
• /
• 2017

Recently, Machine Learning Methods are widely used with high prediction performance. But if the limit of the data is solved by the statistical technique, It can, lead to higher prediction performance than the existing one. In this study, the SMOTE method is used to solve the imbalance problem in the longitudinal and imbalanced data. As a result, It, was confirmed that the prediction performance increases. Additionally, Although, studies on COPD have been actively conducted, only studies that are related to acute exacerbation have been conducted. So there are no studies on the prediction of acute exacerbation through multiple perspectives and predictive models for various factors. In this study, We examined the factors related to acute exacerbation of COPD and constructed a personalized specific disease prediction model.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.1
• /
• pp.101-109
• /
• 2015

SMRs (standardized mortality rates) for major diseases, accidents, cancer are considered in small areas of administrative units such as Eup/Myeon/Dong from years 2005 to 2008. Due to small sample issue in small areas, the precision of directly estimated crude SMR for each area can be low. In this study, we consider the HGLM (hierarchical generalized linear model) with MRF (Markov random field) to account for the spatial correlations among the small areas. The effects of covariates for cause of mortality by Dongs in Seoul and disease maps based on the estimated SMR are presented. The results suggest how we analyze and interpret the difference in mortalities by small areas such as Dongs by revealing the spatial patterns.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.11
• /
• pp.6369-6373
• /
• 2013

Background: Gastric cancer is one of the most common causes of cancer deaths all over the world and the most important reason for its high rate of death is its belated diagnosis at advanced stages of the disease. Events occur in patients which are regarded not only as themselves factors affecting patients' survival but also which can be affected by other factors. This study was designed and implemented aiming to identify these events and to investigate factors affecting their occurrence. Materials and Methods: Data from 330 patients with gastric cancer undergoing surgery at the Iran Cancer Institute from 1995-1999 were analyzed. The survival time of these patients was determined after surgery and the effects of various factors including demographic, diagnostic and clinical as well as medical, and post-surgical varuiables on the occurrence of death hazard without relapse, hazard of relapse, and death hazard with a relapse were assessed. Results: The median survival time for these patients was 16.3 months and the 5-year survival rate was 21.6%. Based on the results of multi-state model, age and distant metastases affected relapse whereas disease stage, type and extent of surgery, lymph nodes metastases, and number of renewed treatments affected death hazard without relapse. Moreover, age, type and extent of surgery, number of renewed treatments, and liver metastases were identified as factors affecting death hazard in patients with relapse. Conclusions: Most cancer studies pay heed to factors which have effect on death occurrence, but some events occur which should be taken into consideration to better describe the natural process of the disease and provide researchers with more accurate data.

• Journal of Korean society of Dental Hygiene
• /
• v.17 no.1
• /
• pp.145-153
• /
• 2017

Objectives: This paper aimed to contribute to better oral disease prevention and practice of health behavior for immigrant women in multi-cultural families, to define missing and filled permanent teeth index of immigrant women, data from the 6th Korea National Health and Nutrition Examination Survey from the Korea Centers for Disease Control and Prevention was used. Methods: For the immigrant women to be subjects, they needed to be born overseas, had acquired Korean citizenship as a married immigrant women, and the estimate of the number of subjects was 133,093 women. For analyzing data, SPSS 21statistical program was used. We used covariance analysis (ANCOVA) andgeneral linear models for finding the relation with the missing and filled permanent teeth index. The significance level was 0.05. Results: DMFT-index of immigrant women was 7.33 points. $R^2$ was 0.416; and increased with age, and $R^2$ was 0.126 points higher (p<0.01). In household income, 'lower' was 5.933 points lower than 'upper' (p<0.05), and in toothbrushing after lunch, 'yes' was 3.598 points lower than 'no' (p<0.01). In preventive treatment, 'yes' was 4.301 points lower than 'no' (p<0.05). Conclusions: The result of this paper is as follows: for maintaining oral health of immigrant women, we think that the government needs to develop an oral health policy and a customized education system suited to immigrant women for preventive management of dental disease in immigrant women. In addition, basic data will be provided for public dental health programs based on the result of the study.

• Health Policy and Management
• /
• v.19 no.4
• /
• pp.98-120
• /
• 2009

The purpose of this study is to elicit preference for drug listing decision criteria and to estimate the ICER threshold in South Korea using the discrete choice experiment (DCE) method. To collect the data, a DCE survey was administered to a subject sample either educated in the principle concepts of pharmacoeconomics or were decision makers within that field. Subjects chose between alternative drug profiles differing in four attributes: ICER, uncertainty, budget impact and severity of disease. The orthogonal and balanced designs were determined through computer algorithm to take the optimal set of drug profiles. The survey employed 15 hypothetical choice sets. A random effect probit model was used to analyze the relative importance of attributes and the probabilities of a recommendation response. Parameter estimates from the models indicated that three attributes (ICER, Impact, Severity of disease) influenced respondents' choice significantly(p${\pm}$0.001). In addition, each parameter displayed an expected sign. The Lower the ICER, the higher the probability of choosing that alternative. Respondents also preferred low levels of uncertainty and smaller impact on health service budget. They were also more likely to choose drugs for serious diseases rather than mild or moderate ones. Uncertainty however is not statistically significant. The ICER threshold, at which the probability of a recommendation was 0.5, was 29,000,000 KW/QALY in expert group and 46,500,000 KW/QALY in industry group. We also found that those in our sample were willing to accept high ICER to get medication for severe diseases. This study demonstrates that the cost-effectiveness, budget impact and severity of disease are the main reimbursement decision criteria in South Korea, and that DCE can be a useful tool in analyzing the decision making process where a variety of factors are considered and prioritized.

• Journal of Preventive Medicine and Public Health
• /
• v.51 no.2
• /
• pp.71-82
• /
• 2018

Objectives: Areca nut is widely consumed in many parts of the world, especially in South and Southeast Asia, where cardiovascular disease (CVD) is also a huge burden. Among the forms of CVD, acute coronary syndrome (ACS) is a major cause of mortality and morbidity. Research has shown areca nut chewing to be associated with diabetes, hypertension, oropharyngeal and esophageal cancers, and CVD, but little is known about mortality and re-hospitalization secondary to ACS among areca nut users and non-users. Methods: A prospective cohort was studied to quantify the effect of areca nut chewing on patients with newly diagnosed ACS by categorizing the study population into exposed and non-exposed groups according to baseline chewing status. Cox proportional hazards models were used to examine the associations of areca nut chewing with the risk of re-hospitalization and 30-day mortality secondary to ACS. Results: Of the 384 ACS patients, 49.5% (n=190) were areca users. During 1-month of follow-up, 20.3% (n=78) deaths and 25.1% (n=96) re-hospitalizations occurred. A higher risk of re-hospitalization was found (adjusted hazard ratio [aHR], 2.05; 95% confidence interval [CI], 1.29 to 3.27; p=0.002) in areca users than in non-users. Moreover, patients with severe disease were at a significantly higher risk of 30-day mortality (aHR, 2.77; 95% CI, 1.67 to 4.59; p<0.001) and re-hospitalization (aHR, 2.72; 95% CI, 1.73 to 4.26; p<0.001). Conclusions: The 30-day re-hospitalization rate among ACS patients was found to be significantly higher in areca users and individuals with severe disease. These findings suggest that screening for a history of areca nut chewing may help to identify patients at a high risk for re-hospitalization due to secondary events.

• Journal of Korean Biological Nursing Science
• /
• v.10 no.2
• /
• pp.176-183
• /
• 2008

Purpose: The purpose of this study was to identify the effect of Environmental Enrichment (EE) on improvement of motor function in animal models of Parkinson's Disease. Methods: Male C57BL6 mice weighing 25-30 g, at the age of 12 wks were used in this study. The animals were injected MPTP (1-methyl-4-phenyl-1,2,3,6-tetrahydropyridin, 20 mg/kg in saline, i.p.) 4 times a day at every 2 hr, and raised in EE cage for 14 days. On day 14, after behavior test, all mice were sacrificed for immunohistochemistry. All values were expressed as means$\pm$S.E.M. Statistical significance was evaluated using a one way ANOVA followed by Sheffe test. Results: There was a significant difference between the experimental group and the control group in the behavior test. Also EE significantly reduced of TH positive cell loss in Substantia nigra pars compacta as compared to the result of MPTP treatment. Conclusion: Based on these findings, it is reasonable to assume that the environmental enrichment prevents dopaminergic neuronal loss and improves disarrangement of motor function and behavioral disability induced by MPTP.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.1
• /
• pp.381-385
• /
• 2015

Background:Hepatocellular carcinoma (HCC) is the second most common malignancy in Egypt. Data mining is a method of predictive analysis which can explore tremendous volumes of information to discover hidden patterns and relationships. Our aim here was to develop a non-invasive algorithm for prediction of HCC. Such an algorithm should be economical, reliable, easy to apply and acceptable by domain experts. Methods: This cross-sectional study enrolled 315 patients with hepatitis C virus (HCV) related chronic liver disease (CLD); 135 HCC, 116 cirrhotic patients without HCC and 64 patients with chronic hepatitis C. Using data mining analysis, we constructed a decision tree learning algorithm to predict HCC. Results: The decision tree algorithm was able to predict HCC with recall (sensitivity) of 83.5% and precession (specificity) of 83.3% using only routine data. The correctly classified instances were 259 (82.2%), and the incorrectly classified instances were 56 (17.8%). Out of 29 attributes, serum alpha fetoprotein (AFP), with an optimal cutoff value of ${\geq}50.3ng/ml$ was selected as the best predictor of HCC. To a lesser extent, male sex, presence of cirrhosis, AST>64U/L, and ascites were variables associated with HCC. Conclusion: Data mining analysis allows discovery of hidden patterns and enables the development of models to predict HCC, utilizing routine data as an alternative to CT and liver biopsy. This study has highlighted a new cutoff for AFP (${\geq}50.3ng/ml$). Presence of a score of >2 risk variables (out of 5) can successfully predict HCC with a sensitivity of 96% and specificity of 82%.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.4
• /
• pp.2223-2227
• /
• 2016

Background: Breast cancer is the most common cancer among Iranian women. Since development of the disease in Iranian women occurs relatively early, the survival rate matters considerably. In different countries, survival of breast cancer patients varies considerably. Therefore, the one-year, three-year, five-year, and ten-year survival rates for breast cancer in Iran were assessed using a meta-analysis. Materials and Methods: This systematic review and meta-analysis was based on valid Iranian sources including SID, MAGIRAN and IRANMEDEX, along with reliable English databases, namely, PUBMED and SCOPUS. In domestic databases, a search was conducted based on key words of breast cancer and survival rate, and in international databases, with "breast cancer" and the equivalent of "neoplasm" of Mesh Word, "survival rate" and "Iran." Then all reviewed papers and theses which met the inclusion criteria were selected for investigation. To conduct the analysis STATA 11.2 software and random-effects models were used. Results: In 24 studies, 22,745 participants were included. The one-year, three-year, five-year and ten-year survival rates were 0.956, 0.808, 0.695 and 0.559, respectively. The minimum and maximum survival rates for 5-years were 0.48 and 0.87. The average age of the onset of the disease was 48.3. Conclusions: As in Iran, since the onset of the disease is at low age, in spite of the relatively high survival rate as compared to other cancers, prevention and screening programs at early age for early stage diagnosis seems necessary.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.5
• /
• pp.1771-1777
• /
• 2012

The impact of anatomic resection (AR) as compared to non-anatomic resection (NAR) for hepatocellular carcinoma (HCC) as a factor for preventing intra-hepatic and local recurrence after the initial surgical procedure remains controversial. A systematic review and meta-analysis of nonrandomized trials comparing anatomic resection with non-anatomic resection for HCC published from 1990 to 2010 in PubMed and Medline, Cochrane Library, Embase, and Science Citation Index were therefore performed. Intra-hepatic recurrence, including early and late, and local recurrence were considered as primary outcomes. As secondary outcomes, 5 year survival and 5 year disease-free survival were considered. Pooled effects were calculated utilizing either fixed effects or random effects models. Eleven non-randomized studies including 1,576 patients were identified and analyzed, with 810 patients in the AR group and 766 in the NAR group. Patients in the AR group were characterized by lower prevalence of cirrhosis, more favorable hepatic function, and larger tumor size and higher prevalence of macrovascular invasion compared with patients in the NAR group. Anatomic resection significantly reduced the risks of local recurrence and achieved a better 5 years disease-free survival. Also, anatomic resection was marginally effective for decreasing the early intra-hepatic recurrence. However, it was not advantageous in preventing late intra-hepatic recurrence compared with non-anatomic resection. No differences were found between AR and NAR with respect to postoperative morbidity, mortality, and hospitalization. Anatomic resection can be recommended as superior to non-anatomic resection in terms of reducing the risks of local recurrence, early intra-hepatic recurrence and achieving a better 5 year disease-free survival in HCC patients.