Objective This scoping review aimed to map the global research landscape of the 11th revision of the International Classification of Diseases (ICD-11), characterize thematic distributions across major research domains, and empirically test the hypothesized structural imbalance in existing ICD-11 research to identify key knowledge gaps and provide a targeted strategic roadmap for future research. Methods Systematic searches were conducted across PubMed, Web of Science, Ovid/MEDLINE, Scopus, and ProQuest, and Chinese-language databases (CNKI, VIP, and Wanfang), covering publications from January 2020 to December 2025. Official WHO grey literature was additionally collated. Studies were screened against predefined eligibility criteria using a two-stage process, and data were synthesized using bibliometric network analysis and descriptive thematic categorization. Results A total of 543 documents were included, comprising 531 peer-reviewed articles (104 Chinese-language; 427 non-Chinese-language) and 12 official WHO grey literature documents. Four dominant research themes were identified: (1) Development and structure of ICD-11 (17.1%); (2) Clinical adaptation of ICD-11, the largest domain (51.6%), within which mental health disorders constituted the predominant subtheme (41.8% of this category); (3) Implementation of ICD-11, encompassing coder training, coding accuracy evaluation, and technical integration (22.8%); and (4) Public health application of ICD-11, including mortality reporting, patient safety, and disease burden assessment (8.5%). The overall literature exhibited a pronounced thematic imbalance, with a disproportionate focus on disease-specific clinical adaptation, while system-level implementation evaluation and real-world impact assessment remained comparatively underexplored. Conclusion The findings confirm the hypothesized thematic imbalance in ICD-11 research, with disproportionate emphasis on disease-specific clinical classification updates relative to system-level implementation science. This scoping review provides an evidence-based baseline and novel practical guidance for policymakers navigating the ICD-11 transition. Future efforts should prioritize redirecting funding toward longitudinal implementation evaluation rather than descriptive coding demonstrations, establishing clinical-academic embedded research partnerships to bridge the innovation-implementation gap, and developing context-appropriate digital tools to lower adoption barriers in resource-constrained settings.
Background Emotion recognition from electroencephalography (EEG) signals has emerged as an important research area within Affective Computing and Human-Centered Artificial Intelligence due to its potential applications in mental health assessment, adaptive human-computer interaction, and emotion-aware intelligent systems. EEG signals provide a non-invasive and reliable means of capturing neural responses associated with emotional states, while Artificial Intelligence (AI) enables efficient analysis of complex and high-dimensional physiological data. Methods This study investigates EEG-based emotion recognition using two publicly available Kaggle datasets: the Emotion Bandpower Dataset and the Gamma-Theta Enhanced EEG Dataset. Both datasets contain statistical and spectral features extracted from multiple EEG frequency bands and are labelled for binary emotion classification tasks involving Relaxed and Funny/Happy states. A comprehensive comparative analysis was conducted using five Machine Learning (ML) algorithms, namely Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and XGBoost, together with six Deep Learning (DL) architectures including MobileNetV2, ResNet50, VGG16, LSTM, EEG-Former, and Swin Transformer. To improve model transparency and trustworthiness, Explainable Artificial Intelligence (XAI) techniques, including Local Interpretable Model-Agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), and Partial Dependence Plots (PDP), were employed to identify influential EEG features. Furthermore, a quantitative explanation consistency framework based on Spearman Rank Correlation, Feature Overlap Score, and Agreement on Feature Significance was applied to evaluate the reliability of explanations generated by LIME and SHAP. Findings Experimental results demonstrated that Random Forest achieved 99% classification accuracy on both datasets, while XGBoost attained 99% accuracy on the Emotion Bandpower Dataset, outperforming the remaining models. The analysis revealed that Gamma and Delta-related features played a significant role in emotion classification. The findings demonstrate that, despite minor variations in feature rankings, the explainability methods consistently identified a common set of important EEG attributes. Interpretation Overall, the proposed framework provides a transparent, accurate, and reliable approach for EEG-based emotion recognition, supporting the development of trustworthy emotion-aware systems for healthcare, neurotechnology, and human-computer interaction applications.
Background Lack of interoperability is widely recognized as a major barrier to data-driven improvements in patient care and health care research. This systematic review aims to answer how interoperability affects the achieved quality of care, both medically and economically. Methods We conducted a systematic review to go beyond the basic assumption that greater interoperability inevitably leads to better patient care. We are specifically looking for studies that measure the relationship between interoperability and quality of care, following PICOS and PRISMA statements. We searched the databases PubMed, EBSCO CINAHL, EBSCO Business Source Premier, EBSCO Library, Information Science & Technology, as well as ACM Digital Library. Findings Results show that such studies are scarce (n = 13), and those that empirically measure the relationship are even rarer. However, the identified studies show a positive relationship between increased interoperability and improved quality of care. The predictors of interoperability cover different application areas. Interpretation The relationship between quality improvement and economic costs of increased interoperability remains unclear and requires further study.
Digital health innovation has expanded rapidly, producing various tools to improve patient outcomes, care efficiency, and clinical decision-making. However, many fail to achieve widespread use in everyday practice, not due to technological limitations but because they do not align with real-world healthcare workflows. Healthcare environments are busy and complex, where doctors and nurses work within fixed routines, limited time, and established systems shaped by patient needs. Even minor issues, such as slow logins or complicated data entry, can make digital tools frustrating. When technology adds such friction instead of support, clinician trust declines and adoption becomes difficult. Clinicians therefore play a central role in whether digital innovations succeed. They reflect whether tools are practical, reliable, and relevant to patient care, while also understanding patients’ concerns and everyday challenges. However, many digital solutions are designed primarily by technical teams who may not fully appreciate real-world clinical pressures. This disconnect contributes to underuse even when tools demonstrate strong accuracy or theoretical benefit. In this regard, clinician-engaged co-creation offers a practical bridge between innovation and implementation. When healthcare professionals are involved early in the development process, tools can be designed to fit naturally into daily workflows rather than adding extra work. Moreover, continuous feedback with clinicians would enable refinement based on real experience. Along with institutional support, training, and appropriate infrastructure, digital tools could become sustainable in practice. Hence the goal should not be to create more digital tools, but to build better ones that truly support healthcare professionals and patients.
Background: This study aims to develop accurate and interpretable machine learning models for the early prediction of Type 2 and Gestational Diabetes. The primary objective is to investigate how ensemble learning, data balancing, and explainable AI can be combined to enhance predictive performance, particularly in conditions of class imbalance and small sample sizes typical of clinical datasets. Methods: Fifteen machine learning models, including advanced ensemble methods such as Extra Trees Classifier (ETC), Light Gradient Boosting Machine (LightGBM), Random Forest (RF), and XGBoost, were evaluated. To address severe class imbalance, especially in the Gestational Diabetes dataset, three oversampling techniques were applied: Synthetic Minority Over-sampling Technique (SMOTE), SMOTETomek, and Adaptive Synthetic Sampling (ADASYN). Model performance was assessed using standard evaluation metrics across two publicly available datasets. SHapley Additive exPlanations (SHAP) were used to interpret model predictions and identify the most influential clinical features. Findings : For the Type 2 Diabetes dataset, ensemble models, most notably the Extra Trees Classifier, achieved the highest performance, demonstrating competitive results compared to approaches reported in the literature. In the Gestational Diabetes dataset, SMOTE-based augmentation combined with ensemble learning (RF-SMOTE, ETC-SMOTE, LightGBM-SMOTE) led to notable improvements in prediction accuracy within the evaluated datasets, showing consistent performance gains over baseline models and the considered machine learning and deep learning methods. SHAP analysis provided clinically meaningful explanations by highlighting the dominant predictors that influence model decisions. Interpretation : Integrating ensemble learning with targeted data balancing and model explainability yields robust, high-performing, and transparent models for diabetes prediction. The results demonstrate consistent and reliable performance within the evaluated datasets, particularly in imbalanced and limited-data scenarios, highlighting the effectiveness of the proposed framework and its potential suitability for real-world clinical decision support.
