• Clinical and Experimental Pediatrics
• /
• v.60 no.9
• /
• pp.290-295
• /
• 2017

Purpose: Airway pathology in children with atopic asthma can be reflected by the concave shape of the maximal expiratory flow-volume (MEFV) curve and high fractional exhaled nitric oxide (FeNO) values. We evaluated the capacity of the curvilinearity of the MEFV curve, FeNO, and their combination to distinguish subjects with atopic asthma from healthy individuals. Methods: FeNO and angle ${\beta}$, which characterizes the general configuration of the MEFV curve, were determined in 119 steroid-naïve individuals with atopic asthma aged 8 to 16 years, and in 92 age-matched healthy controls. Receiver operating characteristic (ROC) curve analyses were performed to determine the cutoff points of FeNO and angle ${\beta}$ that provided the best combination of sensitivity and specificity for asthma detection. Results: Asthmatic patients had a significantly smaller angle ${\beta}$ and higher FeNO compared with healthy controls (both, P<0.001). For asthma detection, the best cutoff values of angle ${\beta}$ and FeNO were observed at $189.3^{\circ}$ and 22 parts per billion, respectively. The area under the ROC curve for the combination of angle ${\beta}$ and FeNO improved to 0.91 (95% confidence interval [CI], 0.87-0.95) from 0.80 (95% CI, 0.75-0.86; P<0.001) for angle ${\beta}$ alone and 0.86 (95% CI, 0.82-0.91; P=0.002) for FeNO alone. In addition, the combination enhanced sensitivity with no significant decrease in specificity. Conclusion: These data suggest that the combined use of the curvilinearity of the MEFV curve and FeNO is a useful tool to differentiate between children with and without atopic asthma.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.4
• /
• pp.2567-2570
• /
• 2013

Background: This study analyzed Surveillance, Epidemiology and End Results (SEER) data to assess if socio-economic factors (SEFs) impact on endometrial cancer survival. Materials and Methods: Endometrial cancer patients treated from 2004-2007 were included in this study. SEER cause specific survival (CSS) data were used as end points. The areas under the receiver operating characteristic (ROC) curve were computed for predictors. Time to event data were analyzed with Kaplan-Meier method. Univariate and multivariate analyses were used to identify independent risk factors. Results: This study included 64,710 patients. The mean follow up time (S.D.) was 28.2 (20.8) months. SEER staging (ROC area of 0.81) was the best pretreatment predictor of CSS. Histology, grade, race/ethnicity and county level family income were also significant pretreatment predictors. African American race and low income neighborhoods decreased the CSS by 20% and 3% respectively at 5 years. Conclusions: This study has found significant endometrial survival disparities due to SEFs. Future studies should focus on eliminating socio-economic barriers to good outcomes.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.7
• /
• pp.928-933
• /
• 2018

Nowadays, gastropathy is a common disease. As endoscopic equipment are developed and used widely, it is possible to provide a large number of endoscopy images. Computer-aided Diagnosis (CADx) systems aim at helping physicians to identify possibly malignant abnormalities more accurately. In this paper, we present a CADx system to detect and classify the abnormalities of gastric lesions which include bleeding, ulcer, neuroendocrine tumor and cancer. We used an Inception module based deep learning model. And we used data augmentation for learning. Our preliminary results demonstrated promising potential for automatically labeled region of interest for endoscopy doctors to focus on abnormal lesions for subsequent targeted biopsy, with Az values of Receiver Operating Characteristic(ROC) curve was 0.83. The proposed CADx system showed reliable performance.

• Communications for Statistical Applications and Methods
• /
• v.25 no.3
• /
• pp.307-319
• /
• 2018

High-throughput technologies enable the simultaneous evaluation of thousands of genes that could discriminate different subclasses of complex diseases. Ranking genes according to differential expression is an important screening step for follow-up analysis. Many statistical measures have been proposed for this purpose. A good ranked list should provide a stable rank (at least for top-ranked gene), and the top ranked genes should have a high power in differentiating different disease status. However, there is a lack of emphasis in the literature on ranking genes based on these two criteria simultaneously. To achieve the above two criteria simultaneously, we proposed to apply a previously reported metric, the modified area under the receiver operating characteristic cure, to gene ranking. The proposed ranking method is found to be promising in leading to a stable ranking list and good prediction performances of top ranked genes. The findings are illustrated through studies on both synthesized data and real microarray gene expression data. The proposed method is recommended for ranking genes or other biomarkers for high-dimensional omics studies.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.622-624
• /
• 2002

생체인식 기술은 급속도로 발전하고 있지만 개개의 생체 정보를 이용한 단일 생체인식 기술은 생체 방식에 따라 각각의 문제점이 노출되고 있는 상황이다. 이에 두 가지 이상의 생체 정보를 결합하여 단일 생체인식 기술의 문제점을 극복하고 보다 좋은 인식률을 확보하기 위해 다중 생체인식 시스템(Multi-Modal Bio-metries System)이라는 복합 시스템이 제안 되었다. 이 논문에서는 생체인식 산업의 특성 및 개인 인증 방법으로 사용중인 단일 생체인식 시스템의 문제점을 알아보고 그 해결방안으로 다중 생체인식 시스템의 확률단계(Probability Level)에서 더 좋은 성능을 보여주기 위해 각각의 시스템에 가중치(Weight)를 부여 할 경우, EER(Equal Error Rate)이 단일 생체인식 시스템에 보다 가중치를 부여 했을 때 낮아짐과 동시에 ROC 커브도 (Receiver Operating Characteristic Curve) 좋아짐을 보였다.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1489-1502
• /
• 2019

This work introduces a novel unweighted combination method (UCSS) for business failure perdition (BFP). With considering features of BFP in the age of big data, UCSS integrates the quantitative and qualitative analysis by utilizing soft set theory (SS). We adopt the conventional expert system (ES) as the basic qualitative classifier, the logistic regression model (LR) and the support vector machine (SVM) as basic quantitative classifiers. Unlike other traditional combination methods, we employ soft set theory to integrate the results of each basic classifier without weighting. In this way, UCSS inherits the advantages of ES, LR, SVM, and SS. To verify the performance of UCSS, it is applied to real datasets. We adopt ES, LR, SVM, combination models utilizing the equal weight approach (CMEW), neural network algorithm (CMNN), rough set and D-S evidence theory (CMRD), and the receiver operating characteristic curve (ROC) and SS (CFBSS) as benchmarks. The superior performance of UCSS has been verified by the empirical experiments.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.2
• /
• pp.103-109
• /
• 2015

In this paper, a novel method for the classification of term and preterm birth is proposed based on time-frequency analysis of electrohysterogram (EHG) using multivariate empirical mode decomposition (MEMD). EHG is a promising study for preterm birth prediction, because it is low-cost and accurate compared to other preterm birth prediction methods, such as tocodynamometry (TOCO). Previous studies on preterm birth prediction applied prefilterings based on Fourier analysis of an EHG, followed by feature extraction and classification, even though Fourier analysis is suboptimal to biomedical signals, such as EHG, because of its nonlinearity and nonstationarity. Therefore, the proposed method applies prefiltering based on MEMD instead of Fourier-based prefilters before extracting the sample entropy feature and classifying the term and preterm birth groups. For the evaluation, the Physionet term-preterm EHG database was used where the proposed method and Fourier prefiltering-based method were adopted for comparative study. The result showed that the area under curve (AUC) of the receiver operating characteristic (ROC) was increased by 0.0351 when MEMD was used instead of the Fourier-based prefilter.

• Communications for Statistical Applications and Methods
• /
• v.30 no.1
• /
• pp.21-35
• /
• 2023

Metabolic syndrome is a serious disease that can eventually lead to various complications, such as stroke and cardiovascular disease. In this study, we aimed to identify the risk factors related to metabolic syndrome for its prevention and recognition and propose a nomogram that visualizes and predicts the probability of the incidence of metabolic syndrome. We conducted an analysis using data from the Korea National Health and Nutrition Survey (KNHANES VII) and identified 10 risk factors affecting metabolic syndrome by using the Rao-Scott chi-squared test, considering the characteristics of the complex sample. A naïve Bayesian classifier was used to build a nomogram for metabolic syndrome. We then predicted the incidence of metabolic syndrome using the nomogram. Finally, we verified the nomogram using a receiver operating characteristic curve and a calibration plot.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.105-108
• /
• 2021

Generative adversarial networks (GANs) have reached a great result at creating the synthesis image, especially in the face generation task. Unlike other deep learning tasks, the input of GANs is usually the random vector sampled by a probability distribution, which leads to unstable training and unpredictable output. One way to solve those problems is to employ the label condition in both the generator and discriminator. CelebA and FFHQ are the two most famous datasets for face image generation. While CelebA contains attribute annotations for more than 200,000 images, FFHQ does not have attribute annotations. Thus, in this work, we introduce a method to learn the attributes from CelebA then predict both soft and hard labels for FFHQ. The evaluated result from our model achieves 0.7611 points of the metric is the area under the receiver operating characteristic curve.

• The Korean Journal of Health Service Management
• /
• v.11 no.2
• /
• pp.105-115
• /
• 2017

Objectives : The aim of this study was to suggest the optimal cut off for best, very good, good, slightly bad, and bad grades. Methods : The subjects were recruited from 4 areas of South Korea and 487 questionnaires were analyzed. The nominal and continuous self-rated health questions were used to reveal the optimal cut off and the Short Form-12 Health Survey questionnaire (SF-12) was additionally used. Frequency, Pearson's correlation coefficient, and ROC-curve analysis were used; the significance level was <.05. Results : Subjects assigned 15(3.1%), 90(18.5%), 237(48.7%), 130(26.7%), and 15(3.1%) to best, very good, good, slightly bad and bad groups respectively. The self-rated health score was associated with total Component (r=.563, p<.001), Physical Component (r=.520, p<.001) and Mental Component of SF-12 (r=.303, p<.001). The optimal cut off was 80.5, 70.5, 53.5, and 40.5 for best, very good or more, good or more, and under slightly bad respectively and area under curve was 0.898, 0.908, 0.945, and 0.908 accordingly. Conclusions : This study suggests that the self-rated health score and grade could be integrated with the optimal cut off.