• The Journal of Korean Medicine
• /
• v.29 no.1
• /
• pp.7-14
• /
• 2008

Purpose : The purpose of study was to develop generalized validity evaluation methods and terms for Sasang type diagnostic tests. Methods : A generalized statistical evaluation model for Sasang typology was suggested and generalized validity evaluation indices were proposed with this model. Results : The usefulness of validity evaluations, such as sensitivity and specificity values, were confirmed by the systematic review of the data from previously reported studies. Conclusion :Major obstacles in the multi-facet analysis and systematic review for Sasang type diagnostic tests were discussed with this test validity study.

• Journal of Veterinary Science
• /
• v.23 no.6
• /
• pp.89.1-89.7
• /
• 2022

It is challenging to diagnose metastatic tumors whose cellular morphology is different from the primary. We characterized canine primary pulmonary adenocarcinoma (PAC) and its xenografted tumors by histological and immunohistochemical analyses for critical diagnostic and cancer stem cell (CSC) markers. To generate a tumor xenograft model, we subsequently transplanted the tissue pieces from the PAC into athymic nude mice. Immunohistochemical examination was performed for diagnostic (TTF-1, Napsin A, and SP-A) and CSC markers (CD44 and CD133). The use of CSC markers together with diagnostic markers can improve the detection and diagnosis of canine primary and metastatic adenocarcinomas.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.10
• /
• pp.112-122
• /
• 1996

In order to monitior machine tool condition and diagnose alarm states due to electrical and mechanical faults, and expert system using diagnostic parameters of NC machine tools was developed. A model-based knowledge base was constructed via searching and comparing procedures of diagnostic parameters and state parameters of the machine tool. Diagnostic monitoring results generate through a successive type inference engine were graphically displayed on the screen of the console. The validity and reliability of the expert system was rcrified on a vertical machining center equipped with FANUC OMC through a series of experiments.

• Korean Journal of Radiology
• /
• v.22 no.7
• /
• pp.1213-1224
• /
• 2021

Objective: To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. Materials and Methods: Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. Results: Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. Conclusion: CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.

• Communications for Statistical Applications and Methods
• /
• v.2 no.2
• /
• pp.266-276
• /
• 1995

We have considered the study of local influence for smoothing parameter estimates in nonparametric regression model. Practically, generalized cross validation(GCV) does not work well in the presence of data perturbation. Thus we have proposed local influence measures for GCV estimates and examined effects of diagnostic by above measures.

• Proceedings of the KSMRM Conference
• /
• 1997.10a
• /
• pp.12-12
• /
• 1997

• Communications for Statistical Applications and Methods
• /
• v.21 no.3
• /
• pp.253-260
• /
• 2014

The intraclass correlation model has a long history of applications in several fields of research. Case deletion diagnostic methods for the intraclass correlation model are proposed. Based on the likelihood equations, we derive a formula for a case deletion diagnostic method which enables us to investigate the influence of observations on the maximum likelihood estimates of the model parameters. Using the Taylor series expansion we develop an approximation to the likelihood distance. Numerical examples are provided for illustration.

• Korean Journal of Radiology
• /
• v.2 no.1
• /
• pp.21-27
• /
• 2001

Objective: To identify and evaluate the lateral border zone by comparing the size and distribution of the abnormal signal area demonstrated by MR imaging with the infarct area revealed by pathological examination in a reperfused myocardial infarction cat model. Materials and Methods: In eight cats, the left anterior descending coronary artery was occluded for 90 minutes, and this was followed by 90 minutes of reperfusion. ECG-triggered breath-hold turbo spin-echo T2-weighted MR images were initially obtained along the short axis of the heart before the administration of contrast media. After the injection of Gadomer-17 and Gadophrin-2, contrast-enhanced T1-weighted MR images were obtained for three hours. The size of the abnormal signal area seen on each image was compared with that of the infarct area after TTC staining. To assess ultrastructural changes in the myocardium at the infarct area, lateral border zone and normal myocardium, electron microscopic examination was performed. Results: The high signal area seen on T2-weighted images and the enhanced area seen on Gadomer-17-enhanced T1WI were larger than the enhanced area on Gadophrin-2-enhanced T1WI and the infarct area revealed by TTC staining; the difference was expressed as a percentage of the size of the total left ventricle mass (T2= 39.2 %; Gadomer-17 =37.25 % vs Gadophrin-2 = 29.6 %; TTC staining = 28.2 %; p < 0.05). The ultrastructural changes seen at the lateral border zone were compatible with reversible myocardial damage. Conclusion: In a reperfused myocardial infarction cat model, the presence and size of the lateral border zone can be determined by means of Gadomer-17- and Gadophrin-2-enhanced MR imaging.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2008.06a
• /
• pp.279-280
• /
• 2008

Accelerated aging tests were conducted under laboratory conditions on two generator stator bars. Electrical stress is applied in No. 1 model stator bar. Electrical and thermal stresses are applied in No. 2 model stator bar. As aging times increased from 0 to 4780h, diagnostic tests were performed on No. 1 and No. 2 model stator bars. Diagnostic tests included AC current, dissipation factor(tan$\delta$) and partial discharge magnitude. The ${\Delta}tan{\delta}$ and $\Deta$I of No. 1 and No. 2 model stator bars increased with increased in aging time.

• Korean Journal of Radiology
• /
• v.24 no.2
• /
• pp.155-165
• /
• 2023

Objective: Little is known about the effects of using different expert-determined reference standards when evaluating the performance of deep learning-based automatic detection (DLAD) models and their added value to radiologists. We assessed the concordance of expert-determined standards with a clinical gold standard (herein, pathological confirmation) and the effects of different expert-determined reference standards on the estimates of radiologists' diagnostic performance to detect malignant pulmonary nodules on chest radiographs with and without the assistance of a DLAD model. Materials and Methods: This study included chest radiographs from 50 patients with pathologically proven lung cancer and 50 controls. Five expert-determined standards were constructed using the interpretations of 10 experts: individual judgment by the most experienced expert, majority vote, consensus judgments of two and three experts, and a latent class analysis (LCA) model. In separate reader tests, additional 10 radiologists independently interpreted the radiographs and then assisted with the DLAD model. Their diagnostic performance was estimated using the clinical gold standard and various expert-determined standards as the reference standard, and the results were compared using the t test with Bonferroni correction. Results: The LCA model (sensitivity, 72.6%; specificity, 100%) was most similar to the clinical gold standard. When expert-determined standards were used, the sensitivities of radiologists and DLAD model alone were overestimated, and their specificities were underestimated (all p-values < 0.05). DLAD assistance diminished the overestimation of sensitivity but exaggerated the underestimation of specificity (all p-values < 0.001). The DLAD model improved sensitivity and specificity to a greater extent when using the clinical gold standard than when using the expert-determined standards (all p-values < 0.001), except for sensitivity with the LCA model (p = 0.094). Conclusion: The LCA model was most similar to the clinical gold standard for malignant pulmonary nodule detection on chest radiographs. Expert-determined standards caused bias in measuring the diagnostic performance of the artificial intelligence model.