Background/Objectives: The purpose of this research is to compare and contrast the application of machine learning and deep learning methodologies such as a dual-branch convolutional neural network (CNN) model for detecting obstructive sleep apnea (OSA) from electrocardiogram (ECG) data. Methods: This approach solves the limitations of conventional polysomnography (PSG) and presents a non-invasive method for detecting OSA in its early stages with the help of AI. Results: The research shows that both CNN and dual-branch CNN models can identify OSA from ECG signals. The CNN model achieves validation and test accuracy of about 93% and 94%, respectively, whereas the dual-branch CNN model achieves 93% validation and 94% test accuracy. Furthermore, the dual-branch CNN obtains a ROC AUC score of 0.99, meaning that it is better at distinguishing between apnea and non-apnea cases. Conclusions: The results show that CNN models, especially the dual-branch CNN, are effective in apnea classification and better than traditional methods. In addition, our proposed model has the potential to be used as a reliable, non-invasive method for accurate OSA detection that is even better than the current state-of-the-art advanced methods.

Introduction: The educational landscape has been expanded to disadvantaged and distant areas through online courses. These online courses have gained extensive interest yet there are limited studies available in the literature. The emergence of massive open online courses (MOOCs) has allowed sustainability educators to glimpse the light. Online education is gaining popularity and, with the introduction of MOOCs, would be beneficial for knowledge building and sharing, and the development of learned society. Objective: This study investigated the mediating (indirect) effects of media richness and user-based use motives on the extended UTAUT model, use behavior (UB), and actual use (AU) of MOOCs on health informatics and administration sustainability education among educators and students in Saudi higher learning institutions (HLIs). A theoretical model based on the Unified Theory of Acceptance and Use of Technology (UTAUT) and Channel Expansion Theory (CET) was used to investigate the factors that affect the adoption of MOOCs in health informatics and administration education. Methodology: A survey design approach was applied. Cross-sectional data were collected from health informatics educators and students from HLIs in Saudi Arabia. A non-probability convenience sampling technique was used for sampling. Data were collected online using Google Forms. A total of 145 completed questionnaires were used in the analysis. PLS-SEM(Version 4.1.1.2) was used for statistical analysis. To investigate the reliability and validity, a measurement model was developed and confirmatory factor analysis (CFA) was conducted. To test the hypotheses, a structural model was run using bootstrapping, coefficients, standard errors (SE) t-values, p values, and lower and upper-level confidence intervals. Results/Findings: The findings were that system quality and user satisfaction is an important factor in the UTAUT model and the inclusion of media richness and user-based use motives significantly mediated between the expanded UTAUT model and the UB and AU of MOOCs. Moreover, media richness and user-based use motives were found to be dominant factors in the overall study model to predict use behavior and actual use of health informaticians in Saudi Arabia. Conclusions: The combination of these two theories i.e., the UTAUT and CET, can effectively enhance the adoption, use behavior, and actual use of MOOCs in the emerging field of health informatics in Saudi Arabia.

The automatic classification of sleep stages and Cyclic Alternating Pattern (CAP) subtypes from electroencephalogram (EEG) recordings remains a significant challenge in computational sleep research because of the short duration of CAP events and the inherent class imbalance in clinical datasets. Background/Objectives: The research introduces a domain-specific deep learning system that employs an LSTM network optimized through a PSO-Hyperband hybrid hyperparameter tuning method. Methods: The research enhances EEG-based sleep analysis through the implementation of hybrid optimization methods within an LSTM architecture that addresses CAP sequence classification requirements without requiring architectural changes. Results: The developed model demonstrates strong performance on the CAP Sleep Database by achieving 97% accuracy for REM and 96% accuracy for stage S0 and ROC AUC scores exceeding 0.92 across challenging CAP subtypes (A1–A3). The model transparency is improved through the application of SHAP-based interpretability techniques, which highlight the role of spectral and morphological EEG features in classification outcomes. Conclusions: The proposed framework demonstrates resistance to class imbalance and better discrimination between visually similar CAP subtypes. The results demonstrate how hybrid optimization methods improve the performance, generalizability, and interpretability of deep learning models for EEG-based sleep microstructure analysis.

Background/Objectives: Alzheimer’s disease (AD), the most prevalent form of dementia, is characterized by an overall decline in cognitive functioning and represents a major public health crisis. It remains critical to be able to accurately and quickly diagnose patients with AD; however, recent deep learning approaches using MRI data do not provide sample generalization, have high computational requirements, and offer little interpretability. Methods: In this study, we present a new framework called eXplorative ViT-CNN (X-ViTCNN) that combines a customized Vision Transformer model with two previously trained CNNs (DenseNet201 and MobileNetV2). With our proposed preprocessing approach using contrast-enhanced preprocessing to highlight neuroanatomical features as well as Bayesian Optimization to tune hyperparameters, we fuse local structural features originating from the CNNs with global representations from the transformer and feed the final result to fully connected dense layers for multi-stage classification. We also use Grad-CAM visualizations to provide insight into how our model arrived at its classification. Results: Experiments conducted on ADNI and OASIS datasets demonstrate the superiority of X-ViTCNN, achieving accuracies of 97.98% and 94.52%, respectively. The model outperformed individual baselines and other pre-trained architectures, showing balanced sensitivity and specificity across all AD stages. Conclusions: The proposed X-ViTCNN framework is a powerful, interpretable method for predicting the development of multi-stage Alzheimer’s disease using MRI scans. The combination of complementary feature learning, automatic hyperparameter optimization and interpretability through visualization make it an excellent potential tool for clinicians to support their decision making in the early diagnosis and ongoing monitoring of persons with Alzheimer’s disease.

Cybersecurity has become one of the top priorities in Saudi Arabia, playing a key role in achieving Vision 2030 and advancing the kingdom’s position in digital transformation. This study investigates how cybersecurity knowledge, attitudes, and awareness influence user behaviours in health applications within Saudi Arabia. An online cross-sectional survey was distributed between March and April 2025 among Saudi Arabian residents. The collected data (n = 629) were analyzed using Smart PLS Structural Equation Modelling (SEM) to assess the relationships among the study constructs. The majority of the participants (61.4%) were between the age of 18 and 24, and 87.6% reported using health applications such as Sehhaty or Labayh to manage their health information. Results demonstrated that all three constructs significantly predicted cybersecurity behaviours: knowledge showed the strongest influence (β = 0.372), followed by attitude (β = 0.343) and awareness (β = 0.199), with all paths being statistically significant (p < 0.05). The model explained substantial variance in cybersecurity behaviours. Knowledge, attitude, and awareness significantly predict cybersecurity practices in healthcare application contexts. Findings highlight the critical need for targeted educational interventions focusing on cybersecurity knowledge enhancement and awareness programmes to promote safer digital health behaviours and strengthen patient data protection in Saudi Arabia’s healthcare system.

Online courses and distance learning are playing a significant role nowadays. These open, massive online courses (MOOCs) have garnered significant attention from academics, scholars, and policymakers; however, the literature offers limited empirical evidence, especially from a Saudi Arabian perspective. MOOCs help educators gain not only knowledge but also promote sustainability. The objective of this study was to investigate the impact of self-determination theory on the behavioral intention and actual use of MOOCs through the mediation of behavioral intention and media richness. For this purpose, convenience sampling was used, and data were collected from 145 respondents, including faculty members and students, across public and private sector universities. Smart PLS-SEM and CB-SEM were used to investigate the reliability, convergent validity, and discriminant validity by developing and testing measurement models using a confirmatory factor analysis. The hypotheses were tested using bootstrapping by developing structural models. The findings indicate that all the scales are reliable and valid, meeting the required threshold levels. Furthermore, all hypothesized relationships are positive and significant, except for the effect of perceived relatedness on the behavioral intention and actual use of MOOCs. Behavioral intention does not mediate the relationship involving perceived relatedness; however, it does mediate the relationships among perceived autonomy, competence, and actual use. Media richness also mediates the relationship between behavioral intention and actual use of MOOCs. The results suggest that MOOC providers should offer courses through renowned universities and adopt self-paced learning formats rather than fixed schedules. Additionally, learners should receive credits upon course completion, and these credits should be recognized by employers to enhance motivation for the continued use of MOOCs.