Advanced Health Science and Technology Journal · مجلد 2 (1) · 97-103
Abstract Background: Artificial intelligence (AI), particularly large language models (LLMs), is increasingly used in medical education and examination preparation. Recent studies suggest that frontier LLMs may have reached near-ceiling performance on standardized medical benchmarks; however, less is known about whether such performance converges across models and whether shared reasoning vulnerabilities persist, particularly in clinically complex domains such as Alzheimer’s disease. Aims and Objectives: This study aimed to evaluate the performance of three frontier LLMs—ChatGPT-4 (OpenAI), Gemini 2.5 Flash (Google), and Claude Sonnet 4 (Anthropic)—on Alzheimer’s disease-related multiple-choice questions drawn from international medical licensing examinations. A secondary objective was to assess the guideline alignment of model explanations to identify differences in reasoning quality beyond accuracy. Materials and Methods: A total of 49 Alzheimer’s disease-focused multiple-choice questions were curated from peer-reviewed preparatory resources and represented five international examinations: USMLE, SMLE, MCCQE, IFOM, and PNA. Each model answered all questions under standardized, independent conditions. Accuracy was recorded, and explanations were evaluated using a guideline alignment score (0–1) based on consistency with authoritative clinical guidelines (NICE, WHO, and AAN). Interrater reliability was assessed using Cohen’s kappa. Results: All three models achieved identical overall accuracy of 98% (48/49 correct). Each model made the same diagnostic error on a single USMLE vignette, misclassifying Alzheimer’s disease as normal pressure hydrocephalus, revealing a shared reasoning blind spot. Accuracy was uniform across clinical domains, except for diagnosis (94.1%). Guideline alignment scores differed modestly, with Claude Sonnet 4 demonstrating the highest alignment (0.95), followed by ChatGPT-4 (0.92) and Gemini 2.5 Flash (0.88). Conclusion: Frontier LLMs demonstrate performance convergence on structured Alzheimer’s disease examination questions, achieving near-identical accuracy. However, convergence also extends to shared diagnostic errors, highlighting systematic reasoning vulnerabilities. Incorporating guideline alignment reveals meaningful differences in explanatory quality despite similar accuracy. These findings underscore the importance of evaluating not only correctness but also reasoning quality and guideline fidelity when integrating LLMs into medical education and clinical decision support.
large language modelsAlzheimer's diseasemedical licensing examinationsmultiple-choice questions
Advanced Health Science and Technology Journal · مجلد 2 (1) · 73-80
Abstract Background: Medical training is academically intense and psychologically demanding, often leading to sustained stress exposure. Although the mental health effects of stress among medical students are well documented, its somatic manifestations, particularly cardiovascular-type symptoms, remain underexplored in Middle Eastern settings. Aim: This study aimed to examine the association between academic stress and self-reported cardiovascular-type symptoms among medical students in Riyadh, Saudi Arabia. Methodology: A cross-sectional descriptive study was conducted among 400 undergraduate medical students selected using stratified random sampling. Data were collected using a structured questionnaire covering sociodemographic variables, perceived stress measured by the 10-item Perceived Stress Scale, and a cardiovascular symptom checklist. Statistical analyses included descriptive statistics, Chi-square tests, and logistic and multiple linear regression analyses using IBM SPSS version 27. Statistical significance was set at P < 0.05. Results: Most participants reported moderate-to-high perceived stress. Non-Saudi students had significantly higher stress levels than Saudi students ( P = 0.020), and lower grade point average (GPA) was significantly associated with higher stress ( P = 0.017). Female students reported a significantly higher prevalence of fatigue, palpitations, and paresthesia ( P < 0.05). Students in earlier academic years experienced palpitations and vertigo more frequently ( P = 0.001). Regression analyses identified female sex, junior academic level, and lower GPA as significant predictors of increased cardiovascular-type symptom burden. Conclusion: Academic stress is associated with cardiovascular-type symptoms among medical students and may affect academic performance. Medical schools should prioritize stress management strategies psychological support, and wellness programs to mitigate stress-related health effects and promote well-being.
Advanced Health Science and Technology Journal · مجلد 2 (1) · 104-108
Abstract Objective: This study examined how patient volume and crowding in pediatric emergency departments (EDs) affect the quality of care, focusing on impacts on patients, healthcare staff, and the healthcare system. Methods: A cross-sectional design was used, and data were collected through a structured questionnaire from 134 randomly selected healthcare providers working in pediatric EDs across Riyadh. Descriptive and inferential statistics were applied for data analysis. Results: Pediatric ED crowding significantly affected patients ( M = 4.26, standard deviation [SD] = 0.58, P = 0.001), resulting in lower satisfaction, delayed assessment and treatment, longer hospital stays, and increased mortality risk. Staff outcomes were similarly impacted ( M = 4.29, SD = 0.61, P = 0.001), including higher stress, increased exposure to workplace violence, and slower patient response times. System-level effects were also significant ( M = 4.27, SD = 0.55, P = 0.001), with prolonged ED stays, reduced efficiency, and increased operational costs. Conclusion: Crowding in pediatric EDs has a measurable negative impact on patient safety, staff well-being, and healthcare system performance. These findings highlight the need for evidence-based strategies to improve patient flow, optimize staffing models, and strengthen the efficiency and quality of pediatric emergency care in Riyadh.
patient volumequality of carepatient satisfactionpatient mortality
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder and the leading cause of dementia worldwide. Public knowledge and awareness of AD play an important role in early recognition, risk reduction, and support for affected individuals. This study aimed to assess AD-related knowledge among adults in Riyadh, Saudi Arabia, using the validated Alzheimer’s Disease Knowledge Scale (ADKS), and to identify sociodemographic factors associated with knowledge levels. A community-based cross-sectional study was conducted among 1282 adults recruited from public locations across Riyadh using a stratified convenience sampling approach. Data were collected through face-to-face interviews using a structured questionnaire and the 30-item ADKS. The scale assessed knowledge across seven domains: life impact, risk factors, disease course, assessment and diagnosis, caregiving, treatment and management, and symptoms. Descriptive statistics, independent-samples t -tests, one-way analysis of variance, Tukey’s post hoc analysis, and multiple linear regression were performed using SPSS version 25 (IBM Corp., Armonk, NY, USA). The mean total ADKS score was 17.09 ± 3.00 out of 30, corresponding to 56.95% correct responses, indicating moderate knowledge of AD among participants. The highest domain-specific knowledge scores were observed in assessment and diagnosis (66.25%) and treatment and management (66.25%), while the lowest scores were observed in caregiving (46.2%). Mean ADKS scores differed significantly by age group ( P = 0.037), gender ( P < 0.001), educational level ( P = 0.007), marital status ( P = 0.007), and family history of AD ( P < 0.001). Multiple linear regression analysis showed that female gender ( B = 0.952, P < 0.001), higher educational level ( B = 0.177, P = 0.012), increasing age category ( B = 0.229, P = 0.012), and having a family history of AD ( B = 0.800, P < 0.001) were independently associated with higher ADKS scores. Adults in Riyadh demonstrated moderate knowledge regarding AD, with notable knowledge gaps particularly related to caregiving and other disease-related domains. Sociodemographic characteristics, especially gender, education, age, and family exposure to AD, were associated with knowledge levels. Targeted community-based educational interventions addressing identified knowledge gaps are warranted to improve AD awareness and promote early recognition and supportive care in Saudi Arabia.
Background: Plaque psoriasis, which is a chronic immune-mediated inflammatory skin condition, significantly reduces patients' quality of life. The cytokine interleukin-23 (IL-23) is a pivotal factor in the development of psoriasis, and icotrokinra is a new oral IL-23 receptor antagonist that has shown potential effectiveness in clinical trials. The main goal of this systematic review and meta-analysis was to assess the effectiveness and safety of icotrokinra in adults and adolescents with moderate-to-severe plaque-type psoriasis. Methods: A comprehensive literature search in PubMed, ScienceDirect, and the Cochrane Library, conducted in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) standards, identified randomized controlled trials that evaluated daily oral icotrokinra 200 mg versus placebo. The primary outcomes were Psoriasis Area and Severity Index (PASI) 90, Investigator's Global Assessment (IGA) 0/1, and adverse events (AEs) at 16 weeks. Risk ratios with 95% confidence intervals were summed up through a random-effects model. Results: A total of five randomized controlled trials involving 2,755 participants were included. Icotrokinra showed a significant increase in PASI 90, IGA 0/1, IGA 0, and Psoriasis Symptoms and Signs Diary 0 responses compared to placebo. The overall frequency of AEs was similar in both groups, but the rate of treatment discontinuation due to AEs was lower with icotrokinra. Conclusions: Icotrokinra is an effective and well-tolerated oral treatment for moderate-to-severe plaque psoriasis with considerable clinical and patient-reported benefits.
BACKGROUND: Neonatal nurses in high-risk Neonatal Intensive Care Units (NICUs) navigate complex, time-sensitive clinical decisions where accuracy and judgment are critical. Generative artificial intelligence (AI) has emerged as a supportive tool, yet its integration raises concerns about its impact on nurses' decision-making, professional autonomy, and organizational workflows. AIM: This study explored how neonatal nurses experience and integrate generative AI in clinical decision-making, examining its influence on nursing practice, organizational dynamics, and cultural adaptation in Saudi Arabian NICUs. METHODS: An interpretive phenomenological approach, guided by Complexity Science, Normalization Process Theory, and Tanner's Clinical Judgment Model, was employed. A purposive sample of 33 neonatal nurses participated in semi-structured interviews and focus groups. Thematic analysis was used to code and interpret data, supported by an inter-rater reliability of 0.88. Simple frequency counts were included to illustrate the prevalence of themes but were not used as quantitative measures. Trustworthiness was ensured through reflexive journaling, peer debriefing, and member checking. RESULTS: Five themes emerged: (1) Clinical Decision-Making, where 93.9% of nurses reported that AI-enhanced judgment but required human validation; (2) Professional Practice Transformation, with 84.8% noting evolving role boundaries and workflow changes; (3) Organizational Factors, as 97.0% emphasized the necessity of infrastructure, training, and policy integration; (4) Cultural Influences, with 87.9% highlighting AI's alignment with family-centered care; and (5) Implementation Challenges, where 90.9% identified technical barriers and adaptation strategies. CONCLUSIONS: Generative AI can support neonatal nurses in clinical decision-making, but its effectiveness depends on structured training, reliable infrastructure, and culturally sensitive implementation. These findings provide evidence-based insights for policymakers and healthcare leaders to ensure AI integration enhances nursing expertise while maintaining safe, patient-centered care.
People of all demographics are impacted by mental illness, which has become a widespread and international health problem. Effective treatment and support for mental illnesses depend on early discovery and precise diagnosis. Notably, delayed diagnosis may lead to suicidal thoughts, destructive behaviour, and death. Manual diagnosis is time-consuming and laborious. With the advent of AI, this research aims to develop a novel mental health disorder detection network with the objective of maximum accuracy and early discovery. For this reason, this study presents a novel framework for the early detection of mental illness disorders using a multi-modal approach combining speech and behavioral data. This framework preprocesses and analyzes two distinct datasets to handle missing values, normalize data, and eliminate outliers. The proposed NeuroVibeNet combines Improved Random Forest (IRF) and Light Gradient-Boosting Machine (LightGBM) for behavioral data and Hybrid Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) for voice data. Finally, a weighted voting mechanism is applied to consolidate predictions. The proposed model achieves robust performance and a competitive accuracy of 99.06% in distinguishing normal and pathological conditions. This framework validates the feasibility of multi-modal data integration for reliable and early mental illness detection.
mental disorder detectionearly diagnosisspeech analysisbehavioral data
Diabetes, a chronic condition affecting millions worldwide, necessitates early intervention to prevent severe complications. While accurately predicting diabetes onset or progression remains challenging due to complex and imbalanced datasets, recent advancements in machine learning offer potential solutions. Traditional prediction models, often limited by default parameters, have been superseded by more sophisticated approaches. Leveraging Bayesian optimization to fine-tune XGBoost, researchers can harness the power of complex data analysis to improve predictive accuracy. By identifying key factors influencing diabetes risk, personalized prevention strategies can be developed, ultimately enhancing patient outcomes. Successful implementation requires meticulous data management, stringent ethical considerations, and seamless integration into healthcare systems. This study focused on optimizing the hyperparameters of an XGBoost ensemble machine learning model using Bayesian optimization. Compared to grid search XGBoost (accuracy: 97.24%, F1-score: 95.72%, MCC: 81.02%), the XGBoost with Bayesian optimization achieved slightly improved performance (accuracy: 97.26%, F1-score: 95.72%, MCC:81.18%). Although the improvements observed in this study are modest, the optimized XGBoost model with Bayesian optimization represents a promising step towards revolutionizing diabetes prevention and treatment. This approach holds significant potential to improve outcomes for individuals at risk of developing diabetes.
The satellite Internet of Things (IoT), utilizing Cyber-Physical Systems (CPS) Communication Networks and various satellite-borne and ground-based terminal devices, enables integrated human-object connectivity and information exchange across space, sky, and ground. A terminal authentication method based on trust evaluation is proposed to ensure the secure and efficient utilization of satellite IoT resources. This method optimizes authentication strategies by evaluating the trustworthiness of terminal devices. A satellite IoT terminal trust evaluation mechanism is proposed for scenarios where a previously strongly authenticated terminal needs re-authentication within a short time or where trust is granted via a strongly authenticated node. This mechanism describes dynamically adjusted trust metrics and evaluation models based on direct and indirect trust. A satellite IoT access authentication protocol based on trust evaluation is also designed, employing corresponding authentication mechanisms according to the device’s trust level. This simplifies the re-authentication process for highly trusted devices, enabling differentiated authentication services for various terminal devices within the same authentication framework. A comprehensive security analysis of the protocol is conducted using informal methods and the Tamarin formal verification tool. Experiments validate the protocol’s effectiveness, showing that it can reduce overall authentication costs and streamline the authentication process through trust-based simplifications.
satellite Internet of Thingsterminal authenticationtrust evaluationre-authentication
BACKGROUND: Workplace violence (WPV) remains a formidable concern among nurses worldwide, with up to 60% in Saudi Arabia reportedly experiencing some form of aggression. In tertiary care hospitals, robust hierarchies and cultural norms intensify underreporting, thwarting evidence-based prevention and obscuring vital data. AIM: This qualitative study investigated the perceived barriers to WPV reporting among nurses in tertiary care settings in the Aljouf region of Saudi Arabia, specifically addressing how organizational and cultural factors converge to discourage formal incident reporting. METHODS: A qualitative descriptive design was employed, guided by Ajzen's Theory of Planned Behavior and the Social Ecological Model. Thirty-six registered nurses, purposively sampled from three tertiary hospitals, participated in six semi-structured focus groups conducted in Arabic or English, depending on participant preference. Data were thematically analyzed in NVivo, with methodological rigor ensured through triangulation and inter-coder reliability. RESULTS: Three principal themes emerged: (1) Emotional and Psychological Barriers (78%), encompassing distress, anxiety, and fears of professional blame; (2) Organizational Ineffectiveness (65%), marked by convoluted reporting processes and perceived managerial indifference; and (3) Cultural and Hierarchical Influences (57%), reflecting deference to authority and normalization of violence. These themes illustrate how attitudes, subjective norms, and perceived behavioral control shaped by socio-cultural dynamics collectively contribute to persistent underreporting. CONCLUSIONS: Mitigating WPV underreporting in Saudi tertiary care hospitals requires streamlined, user-friendly reporting channels, leadership accountability, and holistic psychosocial support. Implementing interprofessional education aimed at dismantling hierarchical imbalances can foster a zero-tolerance ethos toward violence. Longitudinal and comparative research should further examine evolving reporting behaviors to refine context-specific, culturally attuned strategies for addressing WPV. CLINICAL TRIAL NUMBER: Not applicable.
workplace violenceunderreportingnursesbarriers to reporting
The Internet of Things (IoT) consists of physical objects and devices embedded with network connectivity, software, and sensors to collect and transmit data. The development of the Internet of Things (IoT) has led to various security and privacy issues, including distributed denial-of-service (DDoS) attacks. Conventional attack detection methods face significant challenges related to privacy, scalability, and adaptability due to the dynamic nature of IoT environments. To address these limitations, this research proposes GraphFedAI, a novel framework that integrates adaptive session-based graph modeling, Pearson correlation-guided feature selection, interpolation-aware graph neural network (GNN) training, and federated learning to enable robust, scalable, and privacy-preserving DDoS detection in heterogeneous Internet of Things (IoT) networks.The framework represents the IoT network as dynamic graphs where communication patterns among devices are modeled as edges that evolve over time. Graph neural networks are utilized to extract both temporal and structural features from these graphs, thereby enhancing the accuracy of DDoS detection. Federated learning is incorporated to maintain data privacy by training models locally on each device without sharing raw data. This integration also ensures system scalability, as FL adapts training based on localized network topology.The system is evaluated using the CIC-IoT-2023 dataset, demonstrating its effectiveness in achieving high detection accuracy, low false positive rates, and strong resilience under dynamic IoT conditions.
DDoS attack detectionInternet of Things securityfederated learninggraph neural networks