• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.722-729
• /
• 2010

Prediction problems are widely used in medical domains. For example, computer aided diagnosis or prognosis is a key component in a CDSS (Clinical Decision Support System). SVMs with nonlinear kernels like RBF kernels, have shown superior accuracy in prediction problems. However, they are not preferred by physicians for medical prediction problems because nonlinear SVMs are difficult to visualize, thus it is hard to provide intuitive interpretation of prediction results to physicians. Nomogram was proposed to visualize SVM classification models. However, it cannot visualize nonlinear SVM models. Localized Radial Basis Function (LRBF) was proposed which shows comparable accuracy as the RBF kernel while the LRBF kernel is easier to interpret since it can be linearly decomposed. This paper presents a new tool named VRIFA, which integrates the nomogram and LRBF kernel to provide users with an interactive visualization of nonlinear SVM models, VRIFA visualizes the internal structure of nonlinear SVM models showing the effect of each feature, the magnitude of the effect, and the change at the prediction output. VRIFA also performs nomogram-based feature selection while training a model in order to remove noise or redundant features and improve the prediction accuracy. The area under the ROC curve (AUC) can be used to evaluate the prediction result when the data set is highly imbalanced. The tool can be used by biomedical researchers for computer-aided diagnosis and risk factor analysis for diseases.

• Journal of the Korea Society for Simulation
• /
• v.32 no.4
• /
• pp.19-26
• /
• 2023

The increase in the dropout rate of college students nationwide has a serious negative impact on universities and society as well as individual students. In order to proactive identify students at risk of dropout, this study built a decision tree, random forest, logistic regression, and deep learning-based dropout prediction model using academic data that can be easily obtained from each university's academic management system. Their performances were subsequently analyzed and compared. The analysis revealed that while the logistic regression-based prediction model exhibited the highest recall rate, its f-1 value and ROC-AUC (Receiver Operating Characteristic - Area Under the Curve) value were comparatively lower. On the other hand, the random forest-based prediction model demonstrated superior performance across all other metrics except recall value. In addition, in order to assess model performance over distinct prediction periods, we divided these periods into short-term (within one semester), medium-term (within two semesters), and long-term (within three semesters). The results underscored that the long-term prediction yielded the highest predictive efficacy. Through this study, each university is expected to be able to identify students who are expected to be dropped out early, reduce the dropout rate through intensive management, and further contribute to the stabilization of university finances.

• Korean Journal of Radiology
• /
• v.25 no.3
• /
• pp.243-256
• /
• 2024

Objective: We aimed to investigate whether 2-[¹⁸F]fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography (2-[¹⁸F]FDG PET/CT) can aid in evaluating the risk of malignancy in ampullary tumors detected by endoscopy. Materials and Methods: This single-center retrospective cohort study analyzed 155 patients (79 male, 76 female; mean age, 65.7 ± 12.7 years) receiving 2-[¹⁸F]FDG PET/CT for endoscopy-detected ampullary tumors 5-87 days (median, 7 days) after the diagnostic endoscopy between June 2007 and December 2020. The final diagnosis was made based on histopathological findings. The PET imaging parameters were compared with clinical data and endoscopic features. A model to predict the risk of malignancy, based on PET, endoscopy, and clinical findings, was generated and validated using multivariable logistic regression analysis and an additional bootstrapping method. The final model was compared with standard endoscopy for the diagnosis of ampullary cancer using the DeLong test. Results: The mean tumor size was 17.1 ± 7.7 mm. Sixty-four (41.3%) tumors were benign, and 91 (58.7%) were malignant. Univariable analysis found that ampullary neoplasms with a blood-pool corrected peak standardized uptake value in earlyphase scan (SUVe) ≥ 1.7 were more likely to be malignant (odds ratio [OR], 16.06; 95% confidence interval [CI], 7.13-36.18; P < 0.001). Multivariable analysis identified the presence of jaundice (adjusted OR [aOR], 4.89; 95% CI, 1.80-13.33; P = 0.002), malignant traits in endoscopy (aOR, 6.80; 95% CI, 2.41-19.20; P < 0.001), SUVe ≥ 1.7 in PET (aOR, 5.43; 95% CI, 2.00-14.72; P < 0.001), and PET-detected nodal disease (aOR, 5.03; 95% CI, 1.16-21.86; P = 0.041) as independent predictors of malignancy. The model combining these four factors predicted ampullary cancers better than endoscopic diagnosis alone (area under the curve [AUC] and 95% CI: 0.925 [0.874-0.956] vs. 0.815 [0.732-0.873], P < 0.001). The model demonstrated an AUC of 0.921 (95% CI, 0.816-0.967) in candidates for endoscopic papillectomy. Conclusion: Adding 2-[¹⁸F]FDG PET/CT to endoscopy can improve the diagnosis of ampullary cancer and may help refine therapeutic decision-making, particularly when contemplating endoscopic papillectomy.

• Journal of the Korean Society of Radiology
• /
• v.85 no.1
• /
• pp.147-160
• /
• 2024

Purpose To define an MRI scoring system for differentiating xanthogranulomatous cholecystitis (XGC) from wall-thickening type gallbladder cancer (GBC) and compare the diagnostic performance of the scoring system with the visual assessment of radiologists. Materials and Methods We retrospectively analyzed 23 and 35 patients who underwent abdominal MRI and were pathologically diagnosed with XGC and wall-thickening-type GBC after surgery, respectively. Three radiologists reviewed all MRI findings. We defined a scoring system using these MRI findings for differentiating XGC from wall-thickening type GBC and compared the area under the curve (AUC) of the scoring system with the visual assessment of radiologists. Results Nine MRI findings showed significant differences in differentiating the two diseases: diffuse gallbladder wall thickening (p < 0.001), mucosal uniformity (p = 0.002), intramural T2-high signal intensity (p < 0.001), mucosal retraction (p = 0.016), gallbladder stones (p < 0.001), T1-intermediate to high-signal intensity (p = 0.033), diffusion restriction (p = 0.005), enhancement pattern (p < 0.001), and phase of peak enhancement (p = 0.008). The MRI scoring system showed excellent diagnostic performance with an AUC of 0.972, which was significantly higher than the visual assessment of the reviewers. Conclusion The MRI scoring system showed better diagnostic performance than the visual assessment of radiologists to differentiate XGC from wall-thickening-type GBC.

• Korean Journal of Veterinary Research
• /
• v.35 no.4
• /
• pp.815-822
• /
• 1995

The toxicokinetics of rifapentine was studied after an oral administration to beagle dogs. High-performance liquid chromatography(HPLC) using column-switching technique was performed to determine the serum concentrations of rifapentine. The pharmacokinetic profiles of rifapentine were analysed using one-compartment open model. Following a single oral administration of 10mg/kg, pharmacokinetic parameters were determined as follows: maximum serum concentration($C_{max}$), $28.90{\mu}g/ml$; maximum concentration time($T_{max}$), 3.7hr; elimination half-life($t_{1/2}$, 4.7hr; area under the curve(AUC), $339.0{\mu}g{\cdot}hr/ml$; volume of disiribution/bioavailability (Vd/F), 0.21 l/kg; lag time, 24min; absorption rate constant($k_a$), $0.445hr^{-1}$; elimination rate constant($k_{el}$), $0.148hr^{-1}$. After 6 month multiple oral doses of 10mg/kg/day, parameters were as follows: $C_{max}$, $34.40{\mu}g/ml$; $T_{max}$, 2.6hr; $t_{1/2}$, 6.7hr; AUC, $391.3{\mu}g{\cdot}hr/ml$; Vd/F, 0.291/kg; $k_a$, $0.976hr^{-1}$; $k_{el}$, $0.104hr^{-1}$. The consistant kinetic parameters after a single and multiple oral administration show that there was no accumulation of rifapentine after 6 month oral administration. We also simulated the concentration of rifapentine after oral multiple administration of 10 and 50mg/kg/ day, based on the parameters obtained form the single administration. The measured serum concentrations of rifapentine were well fitted to the simulated results. The simulated results show that rifapentine readily reaches to steady-state after about 3 doses and the steady-state serum concentrations($C_{ss}$) are fluctuated in between $2.2{\sim}25.2{\mu}g/ml$, and $10.6{\sim}125.2{\mu}g/ml$ at the doses of 10 and 50mg/kg/day, respectively.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.4
• /
• pp.313-322
• /
• 2021

Purpose: To find diagnostic image features, to compare diagnostic performance of multiphase CT versus gadoxetic acid disodium-enhanced MRI (GAD-MRI), and to evaluate the impact of analyzing Liver Imaging Reporting and Data System (LI-RADS) imaging features, for distinguishing combined hepatocellular-cholangiocarcinoma (CHC) from hepatocellular carcinoma (HCC). Materials and Methods: Ninety-six patients with pathologically proven CHC (n = 48) or HCC (n = 48), diagnosed June 2008 to May 2018 were retrospectively analyzed in random order by three radiologists with different experience levels. In the first analysis, the readers independently determined the probability of CHC based on their own knowledge and experiences. In the second analysis, they evaluated imaging features defined in LI-RADS 2018. Area under the curve (AUC) values for CHC diagnosis were compared between CT and MRI, and between the first and second analyses. Interobserver agreement was assessed using Cohen's weighted κ values. Results: Targetoid LR-M image features showed better specificities and positive predictive values (PPV) than the others. Among them, rim arterial phase hyperenhancement had the highest specificity and PPV. Average sensitivity, specificity, and AUC values were higher for MRI than for CT in both the first (P = 0.008, 0.005, 0.002, respectively) and second (P = 0.017, 0.026, 0.036) analyses. Interobserver agreements were higher for MRI in both analyses (κ = 0.307 for CT, κ = 0.332 for MRI in the first analysis; κ = 0.467 for CT, κ = 0.531 for MRI in the second analysis), with greater agreement in the second analysis for both CT (P = 0.001) and MRI (P < 0.001). Conclusion: Rim arterial phase hyperenhancement on GAD-MRI can be a good indicator suggesting CHC more than HCC. GAD-MRI may provide greater accuracy than CT for distinguishing CHC from HCC. Interobserver agreement can be improved for both CT and MRI by analyzing LI-RADS imaging features.

• Journal of Pharmaceutical Investigation
• /
• v.39 no.2
• /
• pp.141-147
• /
• 2009

The purpose of this study was to evaluate the bioequivalence of two nateglinide tablets, $PASTIC^{(R)}$ tablet (ILDONG Pharm. Co., Ltd., Seoul, Korea, reference drug) and $GLUNATE^{(R)}$ tablet (ILHWA. Co., Ltd., Seoul, Korea, test drug), according to the guidelines of Korea Food and Drug Administration (KFDA). Thirty-five healthy male volunteers, $23.1{\pm}2.3$ years in age and $69.2{\pm}8.8\;kg$ in body weight, were divided into two groups and a randomized $2{\times}2$ cross-over study was employed. After a tablet containing 90 mg of nateglinide was orally administrated, blood was taken at predetermined time intervals over a period of 8 hr and concentrations of nateglinide in plasma were monitored using LC-MS/MS. Pharmacokinetic parameters such as AUCt (the area under the plasma concentration-time curve from time 0 to 8 hr), $C_{max}$ (maximum plasma drug concentration) and $TC_{max}$ (time to reach $CC_{max}$) were calculated and analysis of variance (ANOVA) test was utilized for the statistical analysis of the parameters using logarithmically transformed $AUC_t$ and $C_{max}$ and untransformed $T_{max}$. The 90% confidence intervals of the $AUC_t$ ratio and the $C_{max}$ ratio for $GLUNATE^{(R)}/PASTIC^{(R)}$ were ${\log}1.0782{\sim}{\log}1.1626$ and ${\log}0.9621{\sim}{\log}1.1679$, respectively. Since these values were within the acceptable bioequivalence intervals of ${\log}0.80{\sim}{\log}1.25$, recommended by KFDA, it was concluded that $GLUNATER^{(R)}$ tablet was bioequivalent to $PASTIC^{(R)}$ tablet, in terms of both rate and extent of absorption.

• Korean Journal of Food Science and Technology
• /
• v.53 no.1
• /
• pp.72-77
• /
• 2021

Silkworms have traditionally been used to produce silk and textiles. However, steamed and freeze-dried mature silkworm larval powder (SMSP) contain large amounts of amino acids, vitamins, and essential minerals. In this study, we investigated the potential of SMSP as a hangover-relieving agent. Thirty individuals who met the selection criteria and exclusion criteria were included in the study and subsequently underwent a double-blind, randomized, placebo-controlled, cross-design human application test. Importantly, the test product containing SMSP (CKDHC) was proven to alleviate hangovers through a significant reduction in the plasma concentration of acetaldehyde in the context of an alcohol-induced hangover model. In particular, from 0.5 h after SMSP intake, the blood acetaldehyde concentration (mg/L), area under the time curve (AUC; indicating the degree of bioabsorption of blood acetaldehyde), and the highest blood acetaldehyde concentration (Cmax) were reduced. Altogether, these results suggest that the test product (CKDHC) exhibits an accelerated hangover-relieving effect.

• Korean Journal of Radiology
• /
• v.23 no.12
• /
• pp.1241-1250
• /
• 2022

Objective: To conduct a simulation study to determine whether artificial intelligence (AI)-aided mammography reading can reduce unnecessary recalls while maintaining cancer detection ability in women recalled after mammography screening. Materials and Methods: A retrospective reader study was performed by screening mammographies of 793 women (mean age ± standard deviation, 50 ± 9 years) recalled to obtain supplemental mammographic views regarding screening mammography-detected abnormalities between January 2016 and December 2019 at two screening centers. Initial screening mammography examinations were interpreted by three dedicated breast radiologists sequentially, case by case, with and without AI aid, in a single session. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and recall rate for breast cancer diagnosis were obtained and compared between the two reading modes. Results: Fifty-four mammograms with cancer (35 invasive cancers and 19 ductal carcinomas in situ) and 739 mammograms with benign or negative findings were included. The reader-averaged AUC improved after AI aid, from 0.79 (95% confidence interval [CI], 0.74-0.85) to 0.89 (95% CI, 0.85-0.94) (p < 0.001). The reader-averaged specificities before and after AI aid were 41.9% (95% CI, 39.3%-44.5%) and 53.9% (95% CI, 50.9%-56.9%), respectively (p < 0.001). The reader-averaged sensitivity was not statistically different between AI-unaided and AI-aided readings: 89.5% (95% CI, 83.1%-95.9%) vs. 92.6% (95% CI, 86.2%-99.0%) (p = 0.053), although the sensitivities of the least experienced radiologists before and after AI aid were 79.6% (43 of 54 [95% CI, 66.5%-89.4%]) and 90.7% (49 of 54 [95% CI, 79.7%-96.9%]), respectively (p = 0.031). With AI aid, the reader-averaged recall rate decreased by from 60.4% (95% CI, 57.8%-62.9%) to 49.5% (95% CI, 46.5%-52.4%) (p < 0.001). Conclusion: AI-aided reading reduced the number of recalls and improved the diagnostic performance in our simulation using women initially recalled for supplemental mammographic views after mammography screening.

• Journal of Veterinary Clinics
• /
• v.39 no.5
• /
• pp.199-206
• /
• 2022

Postpartum diseases should be predicted to prevent productivity loss before calving especially in organic dairy farms. This study was aimed to investigate the incidence of postpartum metabolic diseases in an organic dairy farm in Korea, to confirm the association between diseases and prepartum blood biochemical parameters, and to evaluate the accuracy of these parameters with a receiver operating characteristic (ROC) analysis for identifying vulnerable cows. Data were collected from 58 Holstein cows (16 primiparous and 42 multiparous) having calved for 2 years on an organic farm. During a transition period from 4 weeks prepartum to 4 weeks postpartum, blood biochemistry was performed through blood collection every 2 weeks with a physical examination. Thirty-one (53.4%) cows (9 primiparous and 22 multiparous) were diagnosed with at least one postpartum disease. Each incidence was 27.6% for subclinical ketosis, 22.4% for subclinical hypocalcemia, 12.1% for retained placenta, 10.3% for displaced abomasum and 5.2% for clinical ketosis. Between at least one disease and no disease, there were significant differences in the prepartum levels of parameters like body condition score (BCS), non-esterified fatty acid (NEFA), total bilirubin (T-bil), direct bilirubin (D-bil) and NEFA to total cholesterol (T-chol) ratio (p < 0.05). The ROC analysis of each of these prepartum parameters had the area under the curve (AUC) <0.7. However, the ROC analysis with logistic regression including all these parameters revealed a higher AUC (0.769), sensitivity (71.0%), and specificity (77.8%). The ROC analysis with logistic regression including the prepartum BCS, NEFA, T-bil, D-bil, and NEFA to T-chol ratio can be used to identify cows that are vulnerable to postpartum diseases with moderate accuracy.