• 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.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.2
• /
• pp.137-148
• /
• 2011

In this paper, we systematically investigate regional differences of the dead due to injuries in cities, towns and counties about transportation accidents, suicides and fall accidents, which have recently been an important issue of health problems in Korea, The data are from the Annual Report on the Cause of Death Statistics in Korea in 2008. They include the deaths over the age 19 from transportation accidents, suicides and fall accidents with the criterion of the International Statistical Classification of Diseases. Poisson HGLM is applied to estimate the mortality rate under the assumption that the number of deaths follow a Poisson distribution, by considering regions as random effects and by adjusting age, sex and standardized residence tax as fixed effects. Using the results of random effects prediction, the regional differences in cities, counties and towns are marked in disease mapping. The results showed that there were significant regional differences of mortality rates for transportation accidents and suicides, but no significant differences for fall accidents.

• The Korean Journal of Applied Statistics
• /
• v.28 no.2
• /
• pp.325-334
• /
• 2015

Elderly suicide rates tend to be high in Korea. Suicide by the elderly is no longer a personal problem; consequently, further research on risk and regional factors is necessary. Disease mapping in epidemiology estimates spatial patterns for disease risk over a geographical region. In this study, we use a simultaneous conditional autoregressive model for spatial correlations between neighboring areas to estimate standard mortality ratios and mapping. The method is illustrated with cause of death data from 2006 and 2010 to analyze regional patterns of elderly suicide in Korea. By considering spatial correlations, the Bayesian spatial models, mean educational attainment and percentage of the elderly who live alone was the significant regional characteristic for elderly suicide. Gibbs sampling and grid method are used for computation.

• The Korean Journal of Applied Statistics
• /
• v.33 no.4
• /
• pp.379-393
• /
• 2020

A terminal event such as death may censor an intermediate event such as relapse, but not vice versa in semi-competing risks data, which is often seen in medicine, public health, and epidemiology. We propose a Weibull regression model with a normal frailty to analyze semi-competing risks data when all three transition times of the illness-death model are possibly interval-censored. We construct the conditional likelihood separately depending on the types of subjects: still alive with or without the intermediate event, dead with or without the intermediate event, and dead with the intermediate event missing. Optimal parameter estimates are obtained from the iterative quasi-Newton algorithm after the marginalization of the full likelihood using the adaptive importance sampling. We illustrate the proposed method with extensive simulation studies and PAQUID (Personnes Agées Quid) data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.6
• /
• pp.2672-2679
• /
• 2012

The study was done to provide basic data of medical quality evaluation after developing the comorbidity disease mortality measurement modeled on the severity-adjustment method of AMI. This study analyzed 699,701 cases of Hospital Discharge Injury Data of 2005 and 2008, provided by the Korea Centers for Disease Control and Prevention. We used logistic regression to compare the risk-adjustment model of the Charlson Comorbidity Index with the predictability and compatibility of our severity score model that is newly developed for calibration. The models severity method included age, sex, hospitalization path, PCI presence, CABG, and 12 variables of the comorbidity disease. Predictability of the newly developed severity models, which has statistical C level of 0.796(95%CI=0.771-0.821) is higher than Charlson Comorbidity Index. This proves that there are differences of mortality, prevalence rate by method of mortality model calibration. In the future, this study outcome should be utilized more to achieve an improvement of medical quality evaluation, and also models will be developed that are considered for clinical significance and statistical compatibility.

• The Korean Journal of Applied Statistics
• /
• v.31 no.4
• /
• pp.529-538
• /
• 2018

Tuberculosis causes high morbidity and mortality. However, Korea still has the highest tuberculosis (TB) incidence and mortality among OECD countries despite decreasing incidence and mortality due to the development of modern medicine. Korea has now implemented various policy projects to prevent and control tuberculosis. This study analyzes the effects of public-private mix (PPM) tuberculosis control program on treatment outcomes and identifies the factors that affecting the success of TB treatment. We analyzed 130,000 new tuberculosis patient cohort from 2012 to 2015 using data of tuberculosis patient reports managed by the Disease Control Headquarters. A cumulative incidence function (CIF) compared the cumulative treatment success rates for each factor. We compared the results of the analysis using two popular types of competition risk models (cause-specific Cox's proportional hazards model and subdistribution hazard model) that account for the main event of interest (treatment success) and competing events (death).

• The Journal of the Korea Contents Association
• /
• v.18 no.10
• /
• pp.145-157
• /
• 2018

In this study, we analyzed the effect of the income level of cancer, stroke, and myocardial infarction on mortality by using National Health Insurance Service(NHIS) Cohort 2.0 DB. Patients who newly developed the disease in 2007 were observed till 2015. The analysis used the Cox probability proportional risk model and the competing risk model. The income level used information at the time of the onset of the disease in 2007, categorized into low / mid / high. The results showed that there were differences in the risks of death and secondary disease in patients with cancer, stroke, or myocardial infarction according to the income level. In addition to the need for a social safety net to lower the incidence of early deaths in low-income families, it seems necessary to continue to strengthen universal protection for serious diseases similar to the current policy.

• Environmental and Resource Economics Review
• /
• v.17 no.4
• /
• pp.845-873
• /
• 2008

This study estimates the VSL(value of a statistical life) as well as the WTP(willingness to pay) for mortality risk reduction using sample selection model with data on liver cancer examination which is associated with little possibility of multi-purpose(i.e. joint production) in averting behavior. The marginal benefits of mortality risk reduction are estimated by applying for household production function model with medical expense and the time required for medical examination of liver cancer. Individuals are more likely to take liver cancer test if they are male, older, higher educated, those with spouse, smoker, more income of household, and more anxious about their health. The costs of liver cancer examination are statistically significantly affected with expected signs by size of mortality risk reduction, sex, period of eduction, those with spouse, and household income. The marginal effect of mortality risk reduction owing to taking liver cancer examination is estimated at 321,097 won. The costs of liver cancer examination are increased by 905 won with more one year of education period and by 1,743 won with more one million won in household income. On liver cancer examination, male spends more 12,310 won than female and those with spouse pay more 7,969 won than those without spouse. Therefore the VSL from mortality risk reduction due to liver cancer examination is 321.10 million won at mean size of mortality risk reduction and mean cost of liver cancer examination. The results of sensitivity tests on costs and effects of liver cancer test shows that the VSLs are estimated in a range from 160.55 million won to 642.19 million won.

• Korea journal of population studies
• /
• v.22 no.1
• /
• pp.123-151
• /
• 1999

미국사회에서 노인의 거주지 적응양식은 인종간에 차이가 크다. 일반적으로 소수인종노인은 백인 노인에 비하여 자녀와 함께 사는 경향이 강하다. 이에 대하여 문화적 입장에서는 소수인종은 백인에 비하여 가족부양규범이 강하다고 주장한다. 다른 한편 경제적 입장에서는 소수인종은 그들의 생애를 지배하는 빈곤 때문에 규모의 경제를 통하여 가계비용을 줄이기 위하여 확대가족을 유지할 수밖에 없다고 주장한다. 본 연구는 노인이 질병과 빈곤에 적응하는 방식에 있어 인종간 차이를 검토함으로써 기존의 경제학적 논의와 문화적 논의의 적합성을 검정하는데 목적을 두고 있다. 이를 위하여 노인의 거주지 적응에 대한 문화적 영향과 관련하여 두가지 가설을 검정하고 있다. 첫째, 소수인종 노인은 백인노인에 비하여 빈곤과 질병상황에서 가족으로부터 더 오랜기간 보호를 받는지를 검토한다. 둘째, 소수인종 노인은 백인노인에 비하여 건강이 악화될 때 더욱 신속하게 가족으로부터 보호를 받을 수 있는지를 검토한다. 분석을 위해서 1984년에서 1990년기간 동안 실시된 "고령화에 대한 종단적 조사(Longitudinal Survey on Aging)"를 이용하여 마르코비안 다중생명표 모형과 사건분석을 수행하였다. 본 연구결과에 따르면 소수인종 노인은 가족부양규범의 문화적 이점을 그다지 크게 다지고 있지 않다. 인종간 사망력과 시설입소의 차이를 통제할 때, 소수인종 노인은 백인노인에 비하여 보다 흔하게 자녀동거에서 단독거주형태로 혹은 그 반대방향으로 거주지 변화를 경험하고 있다. 백인 노인은 소수인종에 비하여 질병상태와 관련하여 자녀와 동거하는 경향이 더 강하다. 사망력과 시설입소의 인종간 차이를 통제할 때 소수인종노인이 백인노인보다 쉽게 자녀동거에서 단독거주로 이행하는데 이는 소수인종에서 가족부양체계가 불안정함을 의미한다. 또한 빈곤시에 소수인종 노인은 백인노인에 비하여 쉽게 자녀와 떨어져 살게 된다. 이러한 결과는 소수인종 노인에 대한 가족의 지원은 그 가족의 경제적 제약속에서 매우 안정적이지 못함을 시사한다. 못함을 시사한다.

• Journal of the Korea Society for Simulation
• /
• v.23 no.4
• /
• pp.31-39
• /
• 2014

Seasonal influenza epidemics cause 3 to 5 millions severe illness and 250,000 to 500,000 deaths worldwide each year. To prepare better controls on severe influenza epidemics, many studies have been proposed to achieve near real-time surveillance of the spread of influenza. Korea CDC publishes clinical data of influenza epidemics on a weekly basis typically with a 1-2-week reporting lag. To provide faster detection of epidemics, recently approaches using unofficial data such as news reports, social media, and search queries are suggested. Collection of such data is cheap in cost and is realized in near real-time. This research aims to develop regression models for early detecting the outbreak of the seasonal influenza epidemics in Korea with keyword query information provided from the Naver (Korean representative portal site) trend services for PC and mobile device. We selected 20 key words likely to have strong correlations with influenza-like illness (ILI) based on literature review and proposed a logistic regression model and a multiple regression model to predict the outbreak of ILI. With respect of model fitness, the multiple regression model shows better results than logistic regression model. Also we find that a mobile-based regression model is better than PC-based regression model in estimating ILI percentages.