In-Kyung Jeong

Spatial scan statistics are widely used for count data to detect geographical disease clusters of high or low incidence, mortality or prevalence and to evaluate their statistical significance. Some data are ordinal or continuous in nature, however, so that it is necessary to dichotomize the data to use a traditional scan statistic for count data. There is then a loss of information and the choice of cut-off point is often arbitrary. In this paper, we propose a spatial scan statistic for ordinal

As a geographical cluster detection analysis tool, the spatial scan statistic has been developed for different types of data such as Bernoulli, Poisson, ordinal, exponential and normal. Another interesting data type is multinomial. For example, one may want to find clusters where the disease-type distribution is statistically significantly different from the rest of the study region when there are different types of disease. In this paper, we propose a spatial scan statistic for such data, which

We aimed to use deep learning to detect tuberculosis in chest radiographs in annual workers’ health examination data and compare the performances of convolutional neural networks (CNNs) based on images only (I-CNN) and CNNs including demographic variables (D-CNN). The I-CNN and D-CNN models were trained on 1000 chest X-ray images, both positive and negative, for tuberculosis. Feature extraction was conducted using VGG19, InceptionV3, ResNet50, DenseNet121, and InceptionResNetV2. Age, weight, hei

There are several different proposed data mining methods for the postmarketing surveillance of drug safety. Adverse events are often classified into a hierarchical structure. Our objective was to compare the performance of several of these different data mining methods for adverse drug events data with a hierarchical structure. We generated datasets based on the World Health Organization's Adverse Reaction Terminology (WHO-ART) hierarchical structure. We evaluated different data mining methods f

The spatial scan statistic proposed by Kulldorff (Commun. Statist.-Theory Methods 1997; 26:1481-1496) is one of the most widely used methods for detecting spatial clusters and evaluating their statistical significance. However, it is not fully capable of adjusting for all types of confounding covariates. In this article, a generalized linear models (GLM) approach to construct spatial scan statistics, which is readily in a form for covariate adjustment, is proposed. Using GLM, spatial scan statis

Background Although emerging evidence suggests that periodontitis might increase the risk of cancer, comorbidity and lifestyle behaviors, such as smoking and body mass index (BMI), may have confounded this reported association. This study aimed to investigate whether chronic periodontitis is associated with cancer risk using a large, nationwide database. Methods We conducted a population-based, retrospective cohort study using data from the Korean National Health Insurance Cohort Database obtain

The spatial scan statistic is an important tool for spatial cluster detection. There have been numerous studies on scanning window shapes. However, little research has been done on the maximum scanning window size or maximum reported cluster size. Recently, Han et al. proposed to use the Gini coefficient to optimize the maximum reported cluster size. However, the method has been developed and evaluated only for the Poisson model. We adopt the Gini coefficient to be applicable to the spatial scan

In a recent report, Roehle et al (2008) described the global microRNA (miRNA) expression signature of B-cell lymphomas. In that study, the authors were also able to investigate the impact of miRNAs expression on the survival of diffuse large B-cell lymphomas (DLBCL). However, although several miRNAs segregated with outcome in their series, expression of the oncogenic MIRN155 played no role on the overall or event-free survival of DLBCL patients. MiRNAs are abundant non-protein coding RNAs that a

Bayesian signal detection methods, including the multiitem gamma Poisson shrinker (MGPS), assume a Poisson distribution for the number of reports. However, the database of the adverse event reporting system often has a large number of zero-count cells. A zero-inflated Poisson (ZIP) distribution can be more appropriate in this situation than a Poisson distribution. Few studies have considered ZIP-based models for Bayesian signal detection. In addition, most studies on Bayesian signal detection me

BACKGROUND: Spatial scan statistics are widely used for spatial cluster detection, and several parametric models exist. For continuous data, a normal-based scan statistic can be used. However, the performance of the model has not been fully evaluated for non-normal data. METHODS: We propose a nonparametric spatial scan statistic based on the Wilcoxon rank-sum test statistic and compared the performance of the method with parametric models via a simulation study under various scenarios. RESULTS:

BACKGROUND: Restless leg syndrome (RLS) is associated with poor sleep quality, depression or anxiety, poor dietary patterns, microvasculopathy, and hypoxia, all of which are known risk factors for dementia. However, the relationship between RLS and incident dementia remains unclear. This retrospective cohort study aimed to explore the possibility that RLS could be deemed as a non-cognitive prodromal feature of dementia. METHODS: This was a retrospective cohort study using the Korean National Hea

Spatial scan statistics with circular or elliptic scanning windows are commonly used for cluster detection in various applications, such as the identification of geographical disease clusters from epidemiological data. It has been pointed out that the method may have difficulty in correctly identifying non-compact, arbitrarily shaped clusters. In this paper, we evaluated the Gini coefficient for detecting irregularly shaped clusters through a simulation study. The Gini coefficient, the use of wh

Class imbalance is a major problem in classification, wherein the decision boundary is easily biased toward the majority class. A data-level solution (resampling) is one possible solution to this problem. However, several studies have shown that resampling methods can deteriorate the classification performance. This is because of the overgeneralization problem, which occurs when samples produced by the oversampling technique that should be represented in the minority class domain are introduced