• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.19
• /
• pp.8057-8062
• /
• 2014

Purpose: The aim of the study was to evaluate the correlation of ultrasound features with breast cancer molecular status. Materials and Methods: A retrospective review was performed of ultrasound findings in 263 patients diagnosed with breast invasive ductal carcinoma for comparison with immunohistochemistric results were obtained from each lesion. Relationships between ultrasound findings and molecular status were investigated by using multiple regression analysis by means of stepwise logistic regression. Differences in ultrasound criteria were assessed among women with different molecular status. Results: ER positivity was associated with small size, lobulate, angular or spiculated margin contours, absence of calcification, posterior tumor shadowing and low elasticity score; PR positivity was associated with small size, lobulate or angular or spiculated margin contours and absence of calcification; HER2 positivity was associated with presence of calcification and absence of any echogenic halo. The calculated models of predicted molecular status were accurate and discriminating with AUCs of 0.78, 0.74, and 0.74, respectively. Conclusions: Breast cnacer ultrasound features show some correlation with the molecular status. These models may help to expand the scope of ultrasound in predicting tumor biology.

• Genomics & Informatics
• /
• v.17 no.4
• /
• pp.47.1-47.12
• /
• 2019

The achievements of genome-wide association studies have suggested ways to predict diseases, such as type 2 diabetes (T2D), using single-nucleotide polymorphisms (SNPs). Most T2D risk prediction models have used SNPs in combination with demographic variables. However, it is difficult to evaluate the pure additive contribution of genetic variants to classically used demographic models. Since prediction models include some heritable traits, such as body mass index, the contribution of SNPs using unmatched case-control samples may be underestimated. In this article, we propose a method that uses propensity score matching to avoid underestimation by matching case and control samples, thereby determining the pure additive contribution of SNPs. To illustrate the proposed propensity score matching method, we used SNP data from the Korea Association Resources project and reported SNPs from the genome-wide association study catalog. We selected various SNP sets via stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and the elastic-net (EN) algorithm. Using these SNP sets, we made predictions using SLR, LASSO, and EN as logistic regression modeling techniques. The accuracy of the predictions was compared in terms of area under the receiver operating characteristic curve (AUC). The contribution of SNPs to T2D was evaluated by the difference in the AUC between models using only demographic variables and models that included the SNPs. The largest difference among our models showed that the AUC of the model using genetic variants with demographic variables could be 0.107 higher than that of the corresponding model using only demographic variables.

• Physical Therapy Korea
• /
• v.14 no.3
• /
• pp.81-89
• /
• 2007

The purpose of this study was to utilize the K-MBI (Korean Modified Barthel Index) and subscales of K-MBI in predicting the length of hospital stay (LOS) and the discharge destinations for stroke patients. The study population consisted of 97 stroke patients (57 men and 40 women) admitted to the Seoul National University at the Bundang Hospital. All participants were assessed by K-MBI at admission and discharge after rehabilitation therapy and the information available was investigated at admission. The data were analyzed by using the Mann-Whitney U test, the stepwise multiple regression and the logistic regression. The median LOS was 30 days (mean, 32.8 days; range, 22 to 43 days). The K-MBI score at initiation of rehabilitation therapy (p<.001), the type of stroke and living habits before a stroke were the main explanatory indicators for LOS (p<.05). Within the parameters of K-MBI measured at initiation for rehabilitation, feeding and chair/bed transfer were the explanatory factors for LOS prediction (p<.01). Confidence in the prediction of LOS was 20%. Significant predictors of discharge destination in a logistic regression model were the discharge K-MBI score, sex and hemiplegic side. Dressing in items of discharge K-MBI was the significant predictor of discharge destination. The K-MBI score was the most important factor to predict LOS and discharge destination. Knowledge of these predictors can contribute to more appropriate treatment and discharge planning.

• Genomics & Informatics
• /
• v.14 no.4
• /
• pp.138-148
• /
• 2016

The success of genome-wide association studies (GWASs) has enabled us to improve risk assessment and provide novel genetic variants for diagnosis, prevention, and treatment. However, most variants discovered by GWASs have been reported to have very small effect sizes on complex human diseases, which has been a big hurdle in building risk prediction models. Recently, many statistical approaches based on penalized regression have been developed to solve the "large p and small n" problem. In this report, we evaluated the performance of several statistical methods for predicting a binary trait: stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN). We first built a prediction model by combining variable selection and prediction methods for type 2 diabetes using Affymetrix Genome-Wide Human SNP Array 5.0 from the Korean Association Resource project. We assessed the risk prediction performance using area under the receiver operating characteristic curve (AUC) for the internal and external validation datasets. In the internal validation, SLR-LASSO and SLR-EN tended to yield more accurate predictions than other combinations. During the external validation, the SLR-SLR and SLR-EN combinations achieved the highest AUC of 0.726. We propose these combinations as a potentially powerful risk prediction model for type 2 diabetes.

• Research in Community and Public Health Nursing
• /
• v.18 no.1
• /
• pp.136-145
• /
• 2007

Purpose: This study was attempted to illuminate danger signals through an extensive analysis of factors influencing adolescents' illicit drug use. On this basis, it built predictive factors of adolescents' illicit drug use. Method: A questionnaire was distributed to 1,238 subjects living in Seoul, and of them 1,082 answers were analyzed using the SAS 8.2 program. Also logistic regression analysis was conducted based on the stepwise selection method for constructing the predictive factors. Results: The findings of this study are as follows. Individual-related factors were psycho-somatic symptoms, self-esteem, fortune delinquent experience, and sexual-violence delinquent experience. Home-related factors were insincerity, threatening and the assessment of the parent (rearer)-adolescent communication type. Society-related factors were affection of friends and friends' attitude toward delinquency. Conclusion: These findings of this study suggest that a broad intervention program should be provided to nurture wholesome youth culture related to illicit drug use. It is also recommended that a variety of individual, home and society-related programs should be developed for drug users.

• Research in Community and Public Health Nursing
• /
• v.17 no.2
• /
• pp.253-262
• /
• 2006

Purpose: This study was done to evaluate the predictive factors of smoking cessation intention of smoking adolescents at H. district in Chungchungnam-do. Method: A convenience sample was recruited from a public health center at H. district in Chungchungnam-do. A total of 100 smoking adolescents were enrolled in this study. A self-report survey method was used to identify the predictive factors related to smoking cessation. Result: A forward stepwise logistic regression analysis identified four factors associated with smoking cessation intention of smoking adolescents: accompanied friends during the smoking cessation program (OR=20.14), preparation for smoking cessation (OR=5.12), smoking cessation knowledge after the smoking cessation program (OR=1.41), and the number of cigarettes (OR=0.15). Conclusion: Based on this study results, the effective programs in reducing adolescent smoking rates should include components to accompany peers, increase the knowledge of smoking impact, and the benefit of smoking cessation.

• Korean Journal of Adult Nursing
• /
• v.27 no.5
• /
• pp.583-593
• /
• 2015

Purpose: This study was conducted to identify factors influencing depression in the elderly male in Korea. Methods: The initial data were collected from the $5^{th}$ Korea national health and nutrition examination survey (KNHANES-V). The data of 1,210 adults with the age over 65 years were finally analysed using t or ${\chi}^2$ test, stepwise multiple logistic regression. Research variables utilized in this study were 29 factors including demographic and health-related characteristics, physical and economic activities, and life habits. Results: Seven factors were found to be associated with depression in the elderly male including stress level, uncontrolled drinking experience, physical discomfort days in recent two weeks, the level of activities in daily life, diabetes mellitus, economic activity status, and sleeping hours. Conclusion: These results can be used in developing appropriate depression prevention program considering the characteristics of the elderly male.

• Imaging Science in Dentistry
• /
• v.50 no.2
• /
• pp.117-124
• /
• 2020

Purpose: The purpose of this study was to evaluate possible differences in the location of the inferior alveolar canal in male and female Egyptians. Materials and Methods: This cross-sectional retrospective study involved the evaluation of 210 CBCT scans of Egyptian individuals (18-70 years old). The inferior alveolar canal was localized by measuring 8 linear dimensions: 2 for the vertical localization of the mental foramen (superior and inferior to the mental foramen), 4 at the first molar bifurcation for the vertical and horizontal localization of the inferior alveolar canal (superior, inferior, buccal, and lingual to the inferior alveolar canal), and 2 for the horizontal localization of the mandibular foramen (anterior and posterior to the mandibular foramen). The measurements were statistically analyzed via comparative analysis, stepwise logistic regression, and receiver operating characteristic (ROC) curve analysis. Results: Six of the 8 measured distances differed to a statistically significant extent between the sexes. Regression analysis suggested a logistic function with a concordance index of 84%. The diagnostic accuracy capabilities of the linear measurements as sex predictors were calculated using ROC analysis, and the 6 best predictors for sex determination were selected and ranked from highest to lowest predictive power. Moreover, combining these 6 predictors increased the predictive power to 84%. Conclusion: The location of the inferior alveolar canal in the Egyptian population varies significantly by sex; accordingly, this anatomic landmark could be used as a reliable indicator of sexual dimorphism.

• Journal of Biomedical Engineering Research
• /
• v.33 no.3
• /
• pp.148-154
• /
• 2012

Hemorrhagic shock is a primary cause of deaths resulting from injury in the world. Although many studies have tried to diagnose accurately hemorrhagic shock in the early stage, such attempts were not successful due to compensatory mechanisms of humans. The objective of this study was to construct a survival prediction model of rats in acute hemorrhagic shock using a random forest (RF) model. Heart rate (HR), mean arterial pressure (MAP), respiration rate (RR), lactate concentration (LC), and peripheral perfusion (PP) measured in rats were used as input variables for the RF model and its performance was compared with that of a logistic regression (LR) model. Before constructing the models, we performed 5-fold cross validation for RF variable selection, and forward stepwise variable selection for the LR model to examine which variables were important for the models. For the LR model, sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (ROC-AUC) were 0.83, 0.95, 0.88, and 0.96, respectively. For the RF models, sensitivity, specificity, accuracy, and AUC were 0.97, 0.95, 0.96, and 0.99, respectively. In conclusion, the RF model was superior to the LR model for survival prediction in the rat model.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.2
• /
• pp.65-70
• /
• 2015

In the PCB(Printed Circuit Board) manufacturing industry, the yield is an important management factor because it affects the product cost and quality significantly. In real situation, it is very hard to ensure a high yield in a manufacturing shop because products called chips are made through hundreds of nano-scale manufacturing processes. Therefore, in order to improve the yield, it is necessary to analyze main fault process and equipment that cause low PCB yield. This paper proposes a systematic approach to discover fault-causing processes and equipment by using a logistic regression and a stepwise variable selection procedure. We tested our approach with lot trace records of real work-site. A lot trace record consists of the equipment sequence that the lot passed through and the number of faults for each fault type in the lot. We demonstrated that the test results reflected the real situation of a PCB manufacturing line.