• Journal of Life Science
• /
• v.33 no.6
• /
• pp.490-497
• /
• 2023

Pregnant women may need to take medications to treat preexisting diseases or diseases that develop during pregnancy. However, some drugs may be fetotoxic and lead to, for example, teratogenicity and growth retardation. Predicting the fetotoxicity of drugs is thus important for the health of the mother and fetus. The fetotoxicity of many drugs has not been established because various challenges hinder the ability of researchers to determine their fetotoxicity. The need exists for in silico-based fetotoxicity assessment models, as they can modernize the testing paradigm, improve predictability, and reduce the use of animals and the costs of fetotoxicity testing. In this study, we collected data on the fetotoxicity of drugs and constructed fetotoxicity prediction models based on various machine learning algorithms. We optimized the models for more precise predictions by tuning the hyperparameters. We then performed quantitative performance evaluations. The results indicated that the constructed machine learning-based models had high performance (AUROC >0.85, AUPR >0.9) in fetotoxicity prediction. We also analyzed the feature importance of our model's predictions, which could be leveraged to identify the specific features of drugs that are strongly associated with fetotoxicity. The proposed model can be used to prescreen drugs and drug candidates at a lower cost and in less time. It provides a predictive score for fetotoxicity risk, which may be beneficial in the design of studies on fetotoxicity in human pregnancy.

• Korean Journal of Radiology
• /
• v.24 no.11
• /
• pp.1093-1101
• /
• 2023

Objective: Cine magnetic resonance imaging (MRI) has emerged as a noninvasive method to quantitatively assess bowel motility. However, its accuracy in measuring various degrees of small bowel motility has not been extensively evaluated. We aimed to draw a quantitative small bowel motility score from cine MRI and evaluate its performance in a population with varying degrees of small bowel motility. Materials and Methods: A total of 174 participants (28.5 ± 7.6 years; 135 males) underwent a 22-second-long cine MRI sequence (2-dimensional balanced turbo-field echo; 0.5 seconds per image) approximately 5 minutes after being intravenously administered 10 mg of scopolamine-N-butyl bromide to deliberately create diverse degrees of small bowel motility. In a manually segmented area of the small bowel, motility was automatically quantified using a nonrigid registration and calculated as a quantitative motility score. The mean value (MV) of motility grades visually assessed by two radiologists was used as a reference standard. The quantitative motility score's correlation (Spearman's ρ) with the reference standard and performance (area under the receiver operating characteristics curve [AUROC], sensitivity, and specificity) for diagnosing adynamic small bowel (MV of 1) were evaluated. Results: For the MV of the quantitative motility scores at grades 1, 1.5, 2, 2.5, and 3, the mean ± standard deviation values were 0.019 ± 0.003, 0.027 ± 0.010, 0.033 ± 0.008, 0.032 ± 0.009, and 0.043 ± 0.013, respectively. There was a significant positive correlation between the quantitative motility score and the MV (ρ = 0.531, P < 0.001). The AUROC value for diagnosing a MV of 1 (i.e., adynamic small bowel) was 0.953 (95% confidence interval, 0.923-0.984). Moreover, the optimal cutoff for the quantitative motility score was 0.024, with a sensitivity of 100% (15/15) and specificity of 89.9% (143/159). Conclusion: The quantitative motility score calculated from a cine MRI enables diagnosis of an adynamic small bowel, and potentially discerns various degrees of bowel motility.

• Korean Journal of Radiology
• /
• v.23 no.11
• /
• pp.1078-1088
• /
• 2022

Objective: To develop and validate a model using radiomics features from apparent diffusion coefficient (ADC) map to diagnose local tumor recurrence in head and neck squamous cell carcinoma (HNSCC). Materials and Methods: This retrospective study included 285 patients (mean age ± standard deviation, 62 ± 12 years; 220 male, 77.2%), including 215 for training (n = 161) and internal validation (n = 54) and 70 others for external validation, with newly developed contrast-enhancing lesions at the primary cancer site on the surveillance MRI following definitive treatment of HNSCC between January 2014 and October 2019. Of the 215 and 70 patients, 127 and 34, respectively, had local tumor recurrence. Radiomics models using radiomics scores were created separately for T2-weighted imaging (T2WI), contrast-enhanced T1-weighted imaging (CE-T1WI), and ADC maps using non-zero coefficients from the least absolute shrinkage and selection operator in the training set. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic performance of each radiomics score and known clinical parameter (age, sex, and clinical stage) in the internal and external validation sets. Results: Five radiomics features from T2WI, six from CE-T1WI, and nine from ADC maps were selected and used to develop the respective radiomics models. The area under ROC curve (AUROC) of ADC radiomics score was 0.76 (95% confidence interval [CI], 0.62-0.89) and 0.77 (95% CI, 0.65-0.88) in the internal and external validation sets, respectively. These were significantly higher than the AUROC values of T2WI (0.53 [95% CI, 0.40-0.67], p = 0.006), CE-T1WI (0.53 [95% CI, 0.40-0.67], p = 0.012), and clinical parameters (0.53 [95% CI, 0.39-0.67], p = 0.021) in the external validation set. Conclusion: The radiomics model using ADC maps exhibited higher diagnostic performance than those of the radiomics models using T2WI or CE-T1WI and clinical parameters in the diagnosis of local tumor recurrence in HNSCC following definitive treatment.

• Journal of Korean Academy of Nursing
• /
• v.41 no.3
• /
• pp.423-431
• /
• 2011

Purpose: The study was designed to determine the discriminating ability of a Bayesian network (BN) for predicting risk for pressure ulcers. Methods: Analysis was done using a retrospective cohort, nursing records representing 21,114 hospital days, 3,348 patients at risk for ulcers, admitted to the intensive care unit of a tertiary teaching hospital between January 2004 and January 2007. A BN model and two logistic regression (LR) versions, model-I and .II, were compared, varying the nature, number and quality of input variables. Classification competence and case coverage of the models were tested and compared using a threefold cross validation method. Results: Average incidence of ulcers was 6.12%. Of the two LR models, model-I demonstrated better indexes of statistical model fits. The BN model had a sensitivity of 81.95%, specificity of 75.63%, positive and negative predictive values of 35.62% and 96.22% respectively. The area under the receiver operating characteristic (AUROC) was 85.01% implying moderate to good overall performance, which was similar to LR model-I. However, regarding case coverage, the BN model was 100% compared to 15.88% of LR. Conclusion: Discriminating ability of the BN model was found to be acceptable and case coverage proved to be excellent for clinical use.

• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.353-360
• /
• 2022

Laryngeal disease harms quality of life, and laryngoscopy is critical in identifying causative lesions. This study extracts and analyzes using radiomics quantitative features from the lesion in laryngoscopy images and will fit and validate a classifier for finding meaningful features. Searching the region of interest for lesions not classified by the YOLOv5 model, features are extracted with radionics. Selected the extracted features are through a combination of three feature selectors, and three estimator models. Through the selected features, trained and verified two classification models, Random Forest and Gradient Boosting, and found meaningful features. The combination of SFS, LASSO, and RF shows the highest performance with an accuracy of 0.90 and AUROC 0.96. Model using features to select by SFM, or RIDGE was low lower performance than other things. Classification of larynx lesions through radiomics looks effective. But it should use various feature selection methods and minimize data loss as losing color data.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.83-86
• /
• 2020

본 논문에서는 네트워크 이상치 탐지를 위하여 정상 데이터만을 활용한 메모리 기반 정상성 학습 모델을 제안한다. 오토인코더를 기반으로 정상 데이터의 특징을 표현하는 프로토타입을 생성할 수 있도록 신경망을 구성하고, 네트워크 데이터의 특성을 반영하여 쿼리의 수를 한 개로 고정하며, 사용되는 프로토타입의 수를 지정한 값으로 고정하여 모든 프로토타입에 정상 데이터의 특징을 반영할 수 있는 학습 방법을 제안한다. 해당 모델을 네트워크 이상치 탐지 데이터 세트인 Kyoto Honeypot, UNSW-NB15, CICIDS-2018에 적용하여 본 결과 Kyoto Honeypot에서는 0.821, UNSW-NB15에서는 0.854, CICIDS-2018에서는 0.981의 AUROC를 달성했다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.805-807
• /
• 2021

In-hospital cardiac arrest is a significant problem for medical systems. Although the traditional early warning systems have been widely applied, they still contain many drawbacks, such as the high false warning rate and low sensitivity. This paper proposed a strategy that involves a deep learning approach based on a novel interpretable deep tabular data learning architecture, named TabNet, for the Rapid Response System. This study has been processed and validated on a dataset collected from two hospitals of Chonnam National University, Korea, in over 10 years. The learning metrics used for the experiment are the area under the receiver operating characteristic curve score (AUROC) and the area under the precision-recall curve score (AUPRC). The experiment on a large real-time dataset shows that our method improves compared to other machine learning-based approaches.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.1
• /
• pp.9-19
• /
• 2024

Deep learning-based computer vision anomaly detection algorithms are widely utilized in various fields. Especially in the manufacturing industry, the difficulty in collecting abnormal data compared to normal data, and the challenge of defining all potential abnormalities in advance, have led to an increasing demand for unsupervised learning methods that rely on normal data. In this study, we conducted a comparative analysis of deep learning-based unsupervised learning algorithms that define and detect abnormalities that can occur when transparent contact lenses are immersed in liquid solution. We validated and applied the unsupervised learning algorithms used in this study to the existing anomaly detection benchmark dataset, MvTecAD. The existing anomaly detection benchmark dataset primarily consists of solid objects, whereas in our study, we compared unsupervised learning-based algorithms in experiments judging the shape and presence of lenses submerged in liquid. Among the algorithms analyzed, EfficientAD showed an AUROC and F1-score of 0.97 in image-level tests. However, the F1-score decreased to 0.18 in pixel-level tests, making it challenging to determine the locations where abnormalities occurred. Despite this, EfficientAD demonstrated excellent performance in image-level tests classifying normal and abnormal instances, suggesting that with the collection and training of large-scale data in real industrial settings, it is expected to exhibit even better performance.

• The Journal of the Korean dental association
• /
• v.56 no.1
• /
• pp.8-16
• /
• 2018

Purpose: The aim of in vitro study was to compare the diagnostic accuracy to detect non-cavitated enamel caries on smooth surface by using four kinds of the QLF devices. Materials and Methods: A total of 52 human permanent premolars and molars were used. Fluorescence images were captured by the QLF devices (Inspektor Pro, QLF-D, Qraycam, and Qraypen). Fluorescence loss of the QLF was calculated. The severity of lesions was categorized into the following 3 scores using polarized light microscopy: normal (S), enamel demineralization to outer half of enamel (D1), and inner half of the enamel up to the dentin-enamel junction (D2). The Kruskal-Wallis test was used to compare the fluorescence loss among the QLF devices. Spearman rank correlation coefficient between histological scores and fluorescence loss of the devices was calculated. The sensitivity, specificity, and area under the receiver operating curve (AUROC) were calculated to compare their diagnostic accuracies. Results: The correlation coefficients between histological scores and the fluorescence loss of the devices showed 0.77 to 0.81 (P < 0.001). All histological scores, the fluorescence loss among the devices showed no statistical difference. Among the devices, sensitivity, specificity, and AUC values of the fluorescence loss showed 0.84 to 0.94, 0.76 to 0.90, and 0.90 to 0.92, respectively. Conclusions: All QLF devices had no difference with excellent diagnostic accuracies to detect non-cavitated enamel caries on smooth surface.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.6
• /
• pp.2361-2368
• /
• 2015

Objective: To evaluate the diagnostic accuracy of contrast-enhanced ultrasonography (CEUS) in differentiating between benign and malignant enlarged lymph nodes using meta-analysis. Materials and Methods: Pubmed, Embase, SCI and Cochrane databases were searched for studies (up to September 1, 2014) reporting the diagnostic performance of CEUS in discriminating between benign and malignant lymph nodes. Inclusion criteria were: prospective study; histopathology as the reference standard; and sufficient data to construct $2{\times}2$ contingency tables. Methodological quality was assessed using Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). Patient clinical characteristics, sensitivity and specificity were extracted. The summary receiver operating characteristic curve was used to examine the accuracy of CEUS. A meta-analysis was performed to evaluate the clinical utility in identification of benign and malignant lymph nodes. Sensitivity analysis was performed after omitting outliers identified in a bivariate boxplot and publication bias was assessed with Egger testing. Results: The pooled sensitivity, specificity and AUROC were 0.92 (95%CI, 0.85-0.96), 0.91 (95%CI, 0.82-0.95) and 0.97 (95%CI, 0.95-0.98), respectively. After omitting 3 outlier studies, heterogeneity decreased. Sensitivity analysis demonstrated no disproportionate influences of individual studies. Publication bias was not significant. Conclusions: CEUS is a promising diagnostic modality in differentiating between benign and malignant lymph nodes and can potentially reduce unnecessary fine-needle aspiration biopsies of benign nodes.