Purpose
This study compares 3 deep learning models (UNet, TransUNet, and MIST) for left atrium (LA) segmentation of cardiac computed tomography (CT) images from patients with congenital heart disease (CHD). It investigates how architectural variations in the MIST model, such as spatial squeeze-and-excitation attention, impact Dice score and HD95.
Methods
We analyzed 108 publicly available, de-identified CT volumes from the ImageCHD dataset. Volumes underwent resampling, intensity normalization, and data augmentation. UNet, TransUNet, and MIST models were trained using 80% of 97 cases, with the remaining 20% employed for validation. Eleven cases were reserved for testing. Performance was evaluated using the Dice score (measuring overlap accuracy) and HD95 (reflecting boundary accuracy). Statistical comparisons were performed via one-way repeated measures analysis of variance.
Results
MIST achieved the highest mean Dice score (0.74; 95% confidence interval, 0.67–0.81), significantly outperforming TransUNet (0.53; P<0.001) and UNet (0.49; P<0.001). Regarding HD95, TransUNet (9.09 mm) and MIST (5.77 mm) similarly outperformed UNet (27.49 mm; P<0.0001). In ablation experiments, the inclusion of spatial attention did not further enhance the MIST model’s performance, suggesting redundancy with existing attention mechanisms. However, the integration of multi-scale features and refined skip connections consistently improved segmentation accuracy and boundary delineation.
Conclusion
MIST demonstrated superior LA segmentation, highlighting the benefits of its integrated multi-scale features and optimized architecture. Nevertheless, its computational overhead complicates practical clinical deployment. Our findings underscore the value of advanced hybrid models in cardiac imaging, providing improved reliability for CHD evaluation. Future studies should balance segmentation accuracy with feasible clinical implementation.

Purpose
This study developed and evaluated a feature-based ensemble model integrating the synthetic minority oversampling technique (SMOTE) and random undersampling (RUS) methods with a random forest approach to address class imbalance in machine learning for early diabetes detection, aiming to improve predictive performance.
Methods
Using the Scikit-learn diabetes dataset (442 samples, 10 features), we binarized the target variable (diabetes progression) at the 75th percentile and split it 80:20 using stratified sampling. The training set was balanced to a 1:2 minority-to-majority ratio via SMOTE (0.6) and RUS (0.66). A feature-based ensemble model was constructed by training random forest classifiers on 10 two-feature subsets, selected based on feature importance, and combining their outputs using soft voting. Performance was compared against 13 baseline models, using accuracy and area under the curve (AUC) as metrics on the imbalanced test set.
Results
The feature-based ensemble model and balanced random forest both achieved the highest accuracy (0.8764), followed by the fully connected neural network (0.8700). The ensemble model had an excellent AUC (0.9227), while k-nearest neighbors had the lowest accuracy (0.8427). Visualizations confirmed its superior discriminative ability, especially for the minority (high-risk) class, which is a critical factor in medical contexts.
Conclusion
Integrating SMOTE, RUS, and feature-based ensemble learning improved classification performance in imbalanced diabetes datasets by delivering robust accuracy and high recall for the minority class. This approach outperforms traditional resampling techniques and deep learning models, offering a scalable and interpretable solution for early diabetes prediction and potentially other medical applications.

Purpose
Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy.
Methods
ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers.
Results
CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches.
Conclusion
Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose
This study aimed to leverage Shapley additive explanation (SHAP)-based feature engineering to predict appendix cancer. Traditional models often lack transparency, hindering clinical adoption. We propose a framework that integrates SHAP for feature selection, construction, and weighting to enhance accuracy and clinical relevance.
Methods
Data from the Kaggle Appendix Cancer Prediction dataset (260,000 samples, 21 features) were used in this prediction study conducted from January through March 2025, in accordance with TRIPOD-AI guidelines. Preprocessing involved label encoding, SMOTE (synthetic minority over-sampling technique) to address class imbalance, and an 80:20 train-test split. Baseline models (random forest, XGBoost, LightGBM) were compared; LightGBM was selected for its superior performance (accuracy=0.8794). SHAP analysis identified key features and guided 3 engineering steps: selection of the top 15 features, construction of interaction-based features (e.g., chronic severity), and feature weighting based on SHAP values. Performance was evaluated using accuracy, precision, recall, and F1-score.
Results
Four LightGBM model configurations were evaluated: baseline (accuracy=0.8794, F1-score=0.8691), feature selection (accuracy=0.8968, F1-score=0.8860), feature construction (accuracy=0.8980, F1-score=0.8872), and feature weighting (accuracy=0.8986, F1-score=0.8877). SHAP-based engineering yielded performance improvements, with feature weighting achieving the highest precision (0.9940). Key features (e.g., red blood cell count and chronic severity) contributed to predictions while maintaining interpretability.
Conclusion
The SHAP-based framework substantially improved the accuracy and transparency of appendix cancer predictions using LightGBM (F1-score=0.8877). This approach bridges the gap between predictive power and clinical interpretability, offering a scalable model for rare disease prediction. Future validation with real-world data is recommended to ensure generalizability.

Purpose
This study aimed to identify the types of human rights violations and the associated psychological trauma experienced by North Korean defectors. It also examined the impact of trauma on the defectors’ interpersonal relationships, employment, and overall quality of life, while evaluating existing psychological support policies to suggest potential improvements.
Methods
A multidisciplinary research team conducted an observational survey and in-depth interviews with approximately 300 North Korean defectors residing in South Korea from June to September 2017. Standardized measurement tools, including the Post-Traumatic Stress Disorder (PTSD) Checklist (PCL-5), Patient Health Questionnaire-9 (PHQ-9), Generalized Anxiety Disorder Scale-7 (GAD-7), and Short Form-8 Health Survey (SF-8), were employed. Statistical analyses consisted of frequency analysis, cross-tabulation, factor analysis, and logistic regression.
Results
The findings revealed a high prevalence of human rights violations, such as public executions (82%), forced self-criticism (82.3%), and severe starvation or illness (62.7%). Additionally, there were elevated rates of PTSD (56%), severe depression (28.3%), anxiety (25%), and insomnia (23.3%). Defectors who resided in China before entering South Korea reported significantly worse mental health outcomes and a lower quality of life. Moreover, trauma was strongly and negatively correlated with social adjustment, interpersonal relationships, employment stability, and overall well-being.
Conclusion
An urgent revision of existing policies is needed to incorporate specialized, trauma-informed care infrastructures within medical institutions. Furthermore, broad societal education to reduce stigma and enhance integration efforts is essential to effectively support the psychological well-being and social integration of North Korean defectors.

Citations

• Recent advances in pulmonary tuberculosis, the application of deep learning to medical topics, and highlights from this issue of Ewha Medical Journal
  Hae-Sun Chung
  Ewha Medical Journal.2025; 48(2): e16.     CrossRef

Purpose
This study aimed to analyze dementia-related death statistics in Korea between 2013 and 2023.
Methods
The analysis utilized microdata from Statistics Korea’s cause-of-death statistics. Among all recorded deaths, those related to dementia were extracted and analyzed using the underlying cause-of-death codes from the International Classification of Diseases, 10th revision.
Results
The number of dementia-related deaths increased from 8,688 in 2013 to 14,402 in 2023. The crude death rate rose from 17.2 per 100,000 in 2013 to 28.2 per 100,000 in 2023, although the age-standardized death rate declined from 9.7 to 8.7 over the same period. The dementia death rate is 2.1 times higher in women than in men, and mortality among individuals aged 85 and older exceeds 976 per 100,000. By specific cause, Alzheimer’s disease accounted for 77.1% of all dementia deaths, and by place, the majority occurred in hospitals (76.2%), followed by residential institutions including nursing homes (15.3%) in 2023.
Conclusion
The rising mortality associated with dementia, especially Alzheimer’s disease, highlights a growing public health concern in Korea. These findings support the need for enhanced prevention efforts, improved quality of care, and targeted policies addressing the complexities of dementia management. It is anticipated that this empirical analysis will contribute to reducing the social burden.

Citations

• Recent advances in pulmonary tuberculosis, the application of deep learning to medical topics, and highlights from this issue of Ewha Medical Journal
  Hae-Sun Chung
  Ewha Medical Journal.2025; 48(2): e16.     CrossRef