Purpose
Healthcare planning and resource allocation require accurate estimates of the burden of motor neuron diseases (MNDs). This study evaluated the global impact of MNDs from 1990 to 2021 as part of the Global Burden of Disease (GBD) Study 2021.
Methods
GBD 2021 data were used to assess the global burden of MNDs from 1990 to 2021 in terms of prevalence, incidence, disability-adjusted life years (DALYs), and deaths. The relationship between MND burden and the Socio-demographic Index (SDI) was also examined.
Results
Globally, MNDs accounted for 272,732 prevalent cases (95% uncertainty interval [UI], 236,195–313,676), 64,178 incident cases (95% UI, 58,506–70,270), 1,040,566 DALYs (95% UI, 963,064–1,123,956), and 39,082 deaths (95% UI, 35,757–42,433) in 2021. The corresponding age-standardized rates per 100,000 people were 3.31 (95% UI, 2.86–3.80) for prevalence, 0.46 (95% UI, 0.42–0.49) for mortality, and 12.17 (95% UI, 11.24–13.15) for DALYs. From 1990 to 2021, the numbers of prevalent and incident cases increased, but their age-standardized rates decreased by 1.36% and 4.69%, respectively. By contrast, the age-standardized mortality rate increased by 19.84%. MND burden was generally higher in regions with a high SDI, although rates in high-income Asia Pacific were relatively low compared with those in regions with similar SDI values.
Conclusion
From 1990 to 2021, the absolute burden of MNDs increased, age-standardized prevalence and incidence rates declined slightly, and mortality-related burden increased. These trends underscore the need for evidence-based national and global healthcare planning. Geographic variation in MND burden may reflect regional differences in the roles of sociodemographic and genetic factors.

Purpose
Neck pain is a leading musculoskeletal cause of disability in the United States. This study aimed to assess temporal, geographic, and demographic disparities in its burden across US states from 1990 to 2021.
Methods
Global Burden of Disease 2021 data for all 50 US states and the District of Columbia were analyzed for 1990–2021. Counts and age-standardized rates per 100,000 population for prevalence, incidence, and years lived with disability (YLD) were compared by region, state, sex, age group, and sociodemographic index (SDI) level.
Results
In 2021, neck pain accounted for 9,430,000 (95% uncertainty interval [UI], 7,400,000–11,590,000) prevalent cases, 1,900,000 (95% UI, 1,490,000–2,320,000) incident cases, and 920,000 (95% UI, 620,000–1,300,000) YLD, increases of 41.17%, 37.44%, and 38.72%, respectively, from 1990. Although age-standardized incidence increased globally by 1.18% (0.07%–2.39%) over 1990–2021, the United States had small declines in age-standardized incidence (−0.11%; 95% UI, −0.18% to −0.06%), prevalence (−0.20%; 95% UI, −0.32% to −0.10%), and YLD (−1.12%; 95% UI, −2.02% to −0.22%). Neck pain rates were highest in the District of Columbia, Georgia, and Delaware and lowest in North Carolina, Alaska, and Wyoming. The burden peaked at ages 40–49 years and was higher in females. Age-standardized YLD rates for neck pain were significantly positively correlated with the SDI (Spearman’s ρ=0.601, P<0.001).
Conclusion
The geographic and demographic disparities in neck pain burden across US states indicate a need for targeted interventions.

Purpose
This study aimed to address gaps in Korean Standard Series (KSS) information, highlight allergens with increasing patch test positivity, describe potential sources encountered in daily life, and provide guidance on selecting allergen-free alternatives.
Methods
Relevant information was identified from KSS patient instruction sheets (Chemotechnique, Sweden), T.R.U.E. TEST patient instruction sheets (SmartPractice, United States), the Contact Dermatitis Institute allergen database, the American Contact Dermatitis Society allergen information sheets, and searches of the PubMed database. English-language review articles, case series, and case reports identified using keywords related to the 25 KSS allergens were selected.
Results
Information was updated for the following allergens: nickel, cobalt, potassium dichromate, balsam of Peru, paraben mix, N-isopropyl-N'-phenyl-p-phenylenediamine, formaldehyde, p-tert-butylphenol formaldehyde resin, methylchloroisothiazolinone/methylisothiazolinone, colophonium, imidazolidinyl urea, and 2-mercaptobenzothiazole. Emerging sources included electronic devices, personal protective equipment, including masks whose use increased during the COVID-19 (coronavirus disease 2019) pandemic, nail products, and children’s toy slime. In addition, occupational allergen information sheets were developed for hairdressers, healthcare workers, dentists, dental hygienists, and cooks. The Korean-language allergen sheets are provided in the Supplementary Materials.
Conclusion
Because the KSS has not been revised for more than 2 decades, emerging allergen sources may be inadequately represented in the existing patient information. Accordingly, updated patient instruction sheets were developed to improve patient understanding and facilitate the practical application of patch test results.

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.

Citations

• The One-and-a-Half Syndrome of Korean Clinical Training: 1.5 Years of Fracturing
  Jong Seok Bae, Jeeyoung Oh
  Journal of Clinical Neurology.2026; 22(2): 143.     CrossRef
• Impact of mass resident physician resignation on inpatient mortality and admissions in Korea
  Joon Young Choi, Hyonsoo Joo, Ju Sang Kim, Eung Gu Lee, Hyeong Jun Cho, Yeonhee Park, Chang Dong Yeo, Soon Kyu Lee, Donghoon Kang, Sang Hun Eum, Kwan Yong Lee, Tai Joon An
  Public Health.2026; 254: 106225.     CrossRef
• Changes in American Society of Anesthesiologists Physical Status Distribution and Prognostic Performance During the 2024 South Korean Healthcare Crisis: A Large-Scale Retrospective Cohort Study
  Chan-Sik Kim, Sang-Wook Lee
  Journal of Clinical Medicine.2026; 15(11): 4261.     CrossRef
• Dictionary-Augmented Large Language Model Postprocessing for Bilingual Code-Switched Medical Speech Recognition: Development and Evaluation Study
  Chanryeong Oh, Yul Hwangbo, Wonjoong Cheon, Jaedong Lee
  Journal of Medical Internet Research.2026; 28: e91696.     CrossRef
• Impact of Mass Resignation of Junior Doctors in Korea on Major Interventions: Interrupted Time Series Analysis
  Youngjin Kim, Sung Ju Kim, Tae Hyun Ban, Sukil Kim
  Journal of Korean Medical Science.2026;[Epub]     CrossRef
• Changes in the Distribution of General Physicians in Korea During the 2024–2025 Medical Crisis: A Descriptive Analysis Using Nationwide HIRA Data
  Jun Young Park, Sang Gyu Lee
  Journal of Korean Medical Science.2026;[Epub]     CrossRef
• Keep medical doctors in academia — without them, health-care research will suffer
  Daniyal J. Jafree, Mingze Sun, Gordon W. Stewart, Áine Burns, Muzlifah Haniffa, Rupert Beale, Charles Swanton, Reza Motallebzadeh
  Nature.2026; 658(8136): 604.     CrossRef
• Current challenges in Korean medical research and highlights from this issue of Annals of Clinical Microbiology
  Hae-Sun Chung
  Annals of Clinical Microbiology.2025; 28(2): 11.     CrossRef

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.

Citations

• Development and validation of an explainable prediction model for schistosomiasis seropositivity: a population-based screening study in Hunan Province, China
  Yu Zhou, Ling Tang, Mao Zheng, Benjiao Hu, Yanfeng Gong, Liyun Zhu, Liang Shi, Lei Lin, Xinran Yang, Pin Long, Yue Chen, Qingwu Jiang, Yibiao Zhou
  International Journal for Parasitology.2026; 56(7): 104766.     CrossRef
• Developing SHAP interpretable machine learning models for assessing biopsychosocial risk in female drug users: a small sample study
  Xiao Wang, Mingjian Gao, Jialin Gao, Fei Geng, Xiqing Yuan, Xinyu Cheng, Qiulian Xing, Yu Ming, Gancheng Zhu, Huimin Shi, Peng Wang
  Frontiers in Psychiatry.2026;[Epub]     CrossRef
• Multiclass Prediction of Stroke-Hypertension Comorbidity Using Soft Voting Ensemble with SMOTE Evaluation: A National Stroke Hospital Study in Sumatra
  Arinda Mahadesyawardani, Nur Chamidah, Renatalia Fika, Marisa Rifada, I Nyoman Budiantara, Bayu Satria Wiratama, Muhammad Anshari Ali, Norma Latif Fitriyani, Naufal Ramadhan Al Akhwal Siregar
  Journal of Multidisciplinary Applied Natural Science.2026;[Epub]     CrossRef
• Leaving behind fond memories, I am stepping away from my role as editor of the Ewha Medical Journal after finalizing this issue's theme
  Sun Huh
  Ewha Medical Journal.2025; 48(4): e51.     CrossRef
• Intelligent Diagnosis and Treatment Model Based on Clinical Data for Home Rehabilitation Management of Chronic Obstructive Pulmonary Disease
  Bin Zhu, Youqin Chen, Huihui Hu
  Journal of Visualized Experiments.2025;[Epub]     CrossRef

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.

Citations

• Artificial Intelligence Algorithms for Insulin Management and Hypoglycemia Prevention in Hospitalized Patients—A Scoping Review
  Eileen R. Faulds, Melanie Natasha Rayan, Matthew Mlachak, Kathleen M. Dungan, Ted Allen, Emily Patterson
  Diabetology.2026; 7(1): 19.     CrossRef

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.

Citations

• Feature engineering and explainable artificial intelligence for state of health estimation of Lithium-ion batteries
  Tugba Tetik
  Journal of Energy Storage.2026; 144: 119873.     CrossRef
• Evaluating the limitations of gradient boosting and SHAP in predicting magnetite separation performance in PLIMS
  Arif Mustafa, Yoshiyasu Takefuji
  Powder Technology.2026; 471: 122108.     CrossRef
• Research on a machine learning-based predictive model for postoperative neurological dysfunction in acute Stanford type A aortic dissection
  Lun Li, Ruiyi Wang, Lei Qin, Xiaoyong Jing, Junming Zhu
  Frontiers in Medicine.2026;[Epub]     CrossRef
• Enhancing prognostic model interpretability for advanced engine failure prediction using prognostic metrics and explainable AI
  R. Avsar
  The Aeronautical Journal.2026; 130(1347): 1683.     CrossRef
• Leveraging explainable artificial intelligence to improve advanced driver assistance systems through driver eye-tracking interpretation
  Methusela Sulle, Gurcan Comert, Kamrul Islam, Jun Deng, Negash Begashaw, Varghese Vaidyan
  Digital Engineering.2026; 10: 100101.     CrossRef
• A leakage-controlled and SHAP driven machine learning framework for paediatric respiratory disease classification using Indian hospital EHR data
  Anusha Prashanth Shetty, Surendra Shetty, Pavan Hegde, Shwetha Shetty, Nagaraja Shetty
  BMC Medical Informatics and Decision Making.2026;[Epub]     CrossRef
• Predictors of quality of life in OCD: Machine-derived features beyond expert consensus
  Max Thorsson, Angela Trujillo, Maritza J. Romero, Jonathan Irreño-Sotomonte, Tania Borda, Raquel M. Zepeda-Burgos, Mayra C. Martinez Mallen, Beatriz Moyano, Jacey L. Anderberg, Josselyn S. Muñoz, Hannah C. Moore, Renee M. Frederick, Dayan Berrones, Vaness
  Comprehensive Psychiatry.2026; 151: 152737.     CrossRef
• Uncovering Key Factors of Student Performance in Math: An Explainable Deep Learning Approach Using TIMSS 2019 Data
  Abdelamine Elouafi, Ilyas Tammouch, Souad Eddarouich, Raja Touahni
  Information.2025; 16(6): 480.     CrossRef
• Concurrent high-grade appendiceal mucinous neoplasm and adenocarcinoma: a unique case report and literature review
  Mohammed N AlAli, Jawad S Alnajjar, Mohamed S Essa, Arwa F Alrasheed, Ruba M Alzuhairi, Nouf A Alromaih, Sadiq M Amer, Mohammed Sbaih
  Journal of Surgical Case Reports.2025;[Epub]     CrossRef
• Infrared window properties of AB₂C₄ (A=Zn; B In, Ga; C Te, Se) materials via machine learning and density functional theory
  Changcheng Chen, Chunlian Xiong, Xinhui Zhang, Chunling Zhang, Yue Cheng, Weijun Wang, Wenkang Yu, Xunzhe Zhang, Jinkang Yu, Zhengjun Wang, Xiaoning Guan, Jiangzhou Xie, Yaxin Xu, Gang Liu, Pengfei Lu
  Journal of Alloys and Compounds.2025; 1044: 184560.     CrossRef
• Advanced Computational Modeling and Machine Learning for Risk Stratification, Treatment Optimization, and Prognostic Forecasting in Appendiceal Neoplasms
  Jawad S. Alnajjar, Faisal A. Al-Harbi, Ahmed Khalifah Alsaif, Ghaida S. Alabdulaaly, Omar K. Aljubaili, Manal Alquaimi, Arwa F. Alrasheed, Mohammed N. AlAli, Maha A. Alghamdi, Ahmed Y. Azzam
  Healthcare.2025; 13(23): 3074.     CrossRef

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

• Association between longitudinal trajectories of cognitive functioning and all-cause mortality among middle-aged and older adults in South Korea: Exploring the mediating role of oral health-related quality of life
  Seong-Uk Baek, Jin-Ha Yoon
  GeroScience.2026; 48(5): 6463.     CrossRef
• 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

Citations

• Leaving behind fond memories, I am stepping away from my role as editor of the Ewha Medical Journal after finalizing this issue's theme
  Sun Huh
  Ewha Medical Journal.2025; 48(4): e51.     CrossRef