• The Korean Journal of Applied Statistics
• /
• v.28 no.2
• /
• pp.335-342
• /
• 2015

Joint hierarchical generalized linear models proposed by Molas et al. (2013) extend the simple longitudinal model into multiple models fitted jointly. It can easily handle the correlation of multivariate longitudinal data. In this paper, we apply this method to analyze KoGES cohort dataset. Fixed unknown parameters, random effects and variance components are estimated based on a standard framework of h-likelihood theory. Furthermore, based on the conditional Akaike information criterion the correlated covariance structure of random-effect model is selected rather than an independent structure.

• Clinical and Experimental Pediatrics
• /
• v.64 no.9
• /
• pp.489-493
• /
• 2021

Background: There is evidence of destructive effects of oxytocin use during labor on neurodevelopment. Purpose: This meta-analysis pooled all observational studies to determine the association between labor induction and the risk of attention-deficit/hyperactivity disorder (ADHD) among children. Methods: All observational studies (case-control and cohort) were reviewed until September 2020 after searches of the PubMed, Scopus, and Web of Science databases, the gray literature, and conference proceedings. The pooled odds ratios (ORs), relative ratios (RRs), and 95% confidence intervals (CI (swere calculated as random effect estimates of association among studies. Results: All observational studies were reviewed, including 4 cohort studies including 2,885,743 participants and 3 case-control studies including 51,135 participants (10,961 with ADHD and 40,174 in control groups) with a sample size of 2,936,878 participants. The pooled estimates of OR and RR did not indicate a significant association between labor induction and ADHD among children (OR, 1.13; 95% CI, 0.90-1.35) and (RR, 1.10; 95% CI, 0.96-1.24). Conclusions: The findings showed that labor induction is not associated with an increased risk of ADHD among children. However, more studies are needed to investigate the relationship between labor induction and ADHD.

• The Journal of Health Technology Assessment
• /
• v.6 no.2
• /
• pp.133-141
• /
• 2018

Objectives: In the past, the pharmaceutical drug heparin was mostly used as the anticoagulant for continuous renal replacement therapy (CRRT), but the duration time is long to have the risk of a bleeding adverse effect, and in that case the drug therapy Nafamostat mesilate was utilized instead, as it is more safe in this case, with a short half-life and is increasing in use to permit lower concerns for bleeding incidents. However, there are insufficient number of large-scale studies on the comparison of Nafamostat mesilate and heparin. Methods: In this study, a systematic review are used to compare the bleeding risk of Nafamostat mesilate and Heparin, as subjected to patients and procedures for measuring risks performed with a CRRT, and the filter life span is to be evaluated as well in this patients. Results: As a result of literature review search, a total of 6 studies were included in systematic review. The reducing risk of bleeding and filter life span was analyzed. The retrospective cohort studies confirm that Nafamostat mesilate is less at risk of bleeding than heparin. And a cohort study confirms that Nafamostat mesilate is longer filter lifespan than heparin and randomized controlled trial studies show that Nafamostat mesilate is longer filter lifespan than not using the anticoagulants. Conclusion: Nafamostat mesilate is considered to be a good therapeutic option because it has a longer filter life span as well as the advantage of reducing bleeding.

• Genomics & Informatics
• /
• v.20 no.3
• /
• pp.34.1-34.11
• /
• 2022

Multilevel analysis is an appropriate and powerful tool for analyzing hierarchical structure data widely applied from public health to genomic data. In practice, however, we may lose the information on multiple nesting levels in the multilevel analysis since data may fail to capture all levels of hierarchy, or the top or intermediate levels of hierarchy are ignored in the analysis. In this study, we consider a multilevel linear mixed effect model (LMM) with single imputation that can involve all data hierarchy levels in the presence of missing top or intermediate-level clusters. We evaluate and compare the performance of a multilevel LMM with single imputation with other models ignoring the data hierarchy or missing intermediate-level clusters. To this end, we applied a multilevel LMM with single imputation and other models to hierarchically structured cohort data with some intermediate levels missing and to simulated data with various cluster sizes and missing rates of intermediate-level clusters. A thorough simulation study demonstrated that an LMM with single imputation estimates fixed coefficients and variance components of a multilevel model more accurately than other models ignoring data hierarchy or missing clusters in terms of mean squared error and coverage probability. In particular, when models ignoring data hierarchy or missing clusters were applied, the variance components of random effects were overestimated. We observed similar results from the analysis of hierarchically structured cohort data.

• Clinical and Experimental Pediatrics
• /
• v.65 no.3
• /
• pp.131-135
• /
• 2022

Purpose: There is inconsistent evidence about the association between fetal nuchal cord and the risk of autism spectrum disorder (ASD). We performed a meta-analysis to investigate whether fetal nuchal cord is associated with an increased risk of ASD in offspring. Methods: Three main English databases were searched until January 2021. The Newcastle-Ottawa Scale was used to assess study quality. Study heterogeneity was determined using the I 2 statistic, while publication bias was assessed using Begg and Egger tests. Results are presented as odds ratios (ORs) and relative ratios with 95% confidence intervals (CI) and were determined by a random-effects model. Results: Five articles (1 cohort, 4 case-control; 3,088 total children) were included in the present meta-analysis. Fetal nuchal cord was not a risk factor for ASD (OR, 1.11; 95% CI, 0.66-1.57). There was homogeneity among studies that reported a risk of ASD (I²=0.0%). Conclusion: Our results showed that fetal nuchal cord is not a risk factor for ASD. Future large cohort studies should confirm this finding.

• Safety and Health at Work
• /
• v.13 no.4
• /
• pp.482-486
• /
• 2022

Background: This study aimed to estimate the annual prevalence and incidence of urolithiasis stratified by work status based on a large nationwide sample. Methods: This study used data from the National Health Insurance Service-National Sample Cohort from 2002 to 2015. The prevalence and incidence of urolithiasis were estimated based on work status and gender stratification. The risk of urolithiasis among workers was calculated using age-standardized incidence ratio with stratification of work type. Results: The prevalence of urolithiasis was significantly higher in workers than in non-workers, especially men, during the follow-up period. The total estimated number of urolithiasis cases was 41,086 and the overall incidence of urolithiasis was 0.3%. The age-standardized incidence ratio of urolithiasis was significantly higher among the total workers (1.14; 95% confidence interval, 1.13-1.16), self-employed workers (1.08; 95% confidence interval, 1.06-1.11), and paid workers (1.19; 95% confidence interval, 1.17-1.21) than among the non-working population. Conclusions: Workers, especially paid workers and men, were vulnerable to urolithiasis. Further studies are required to investigate the effects of working conditions on urolithiasis.

• Korean Circulation Journal
• /
• v.52 no.11
• /
• pp.808-813
• /
• 2022

Studies showing that coronavirus disease 2019 (COVID-19) is associated with an increased risk of cardiovascular disease continue to be published. However, studies on how long the overall cardiovascular risk increases after COVID-19 and the magnitude of its long-term effects have only been confirmed recently. This is partly because the distinction between cardiovascular risk as an acute complication of COVID-19 or post-acute cardiovascular manifestations is ambiguous. Long-COVID has arisen as an important topic in the second half of the pandemic. This term indicates that symptoms persist for more than two 2 months; following three months of SARS-CoV-2 infection and cannot be explained by other medical conditions. Despite the agreement of these international organizations and experts, it is difficult to define whether there is sufficient medical evidence to prove the existence of long-COVID. However, the Korean government and Korea Disease Control and Prevention Agency (KDCA) are preparing a new platform to assess the long-term impact of COVID-19. Using this data, a prospective cohort of 10,000 confirmed COVID-19 cases will be established. This cohort will be linked with claims data from the National Health Insurance Services (NHIS) and it is expected that increased real-world evidence of long-COVID will be accumulated.

• Clinical Endoscopy
• /
• v.55 no.2
• /
• pp.248-255
• /
• 2022

Background/Aims: Endoscopic submucosal dissection (ESD) is the preferred technique for treating early gastric cancer (EGC). However, very few studies have been conducted in South America. This study aimed to assess the efficacy and safety of ESD for EGC. Methods: We analyzed data from a prospective cohort from 2013 to 2020. A total of 152 superficial gastric neoplasms that fulfilled the absolute or expanded criteria for ESD were included. Outcomes were en bloc, R0, and curative resection rates, incidence of adverse events, and length of procedure. Results: The age of the enrolled patients was 68.4±11.3 years. The number of included patients based on the absolute and expanded indications was 150 and 2, respectively. En bloc, R0, and curative resections were achieved in 98.0%, 96.1%, and 89.5% of the cases, respectively. Bleeding and perforation were reported in 5.9% and 6.6% of the cases, respectively. Histopathological examination revealed low-grade dysplasia, high-grade dysplasia, well-differentiated adenocarcinoma, and poorly differentiated adenocarcinoma in 13, 20, 117, and 2 cases, respectively. Conclusions: Our study shows that ESD performed by properly trained endoscopists in reference centers is safe and effective, with comparable therapeutic outcomes to those reported in the Eastern series.

• 대한예방의학회:학술대회논문집
• /
• 2004.10a
• /
• pp.81.1-81.1
• /
• 2004

• Communications for Statistical Applications and Methods
• /
• v.27 no.3
• /
• pp.301-311
• /
• 2020

Schwarz's Bayesian information criterion (BIC) is one of the most popular criteria for model selection, that was derived under the assumption of independent and identical distribution. For correlated data in longitudinal studies, Jones (Statistics in Medicine, 30, 3050-3056, 2011) modified the BIC to select the best linear mixed effects model based on the effective sample size where the number of parameters in covariance structure was not considered. In this paper, we propose an extended Jones' modified BIC by considering covariance parameters. We conducted simulation studies under a variety of parameter configurations for linear mixed effects models. Our simulation study indicates that our proposed BIC performs better in model selection than Schwarz's BIC and Jones' modified BIC do in most scenarios. We also illustrate an example of smoking data using a longitudinal cohort of cancer patients.