جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

76 مُخرَج نتائج البحث عن «SHAP»

مقالوصول مفتوح20266استشهاد· Semantic Scholar

Personalized multi-agent reinforcement learning framework for adaptive chronic disease therapy management

Scientific Reports · مجلد 16 (1)

Long-term, flexible therapy strategies are needed for chronic diseases like cardiovascular ailments, diabetes, and chronic kidney disease and they have to deal with patient heterogeneity, changing physiological states and privacy constraints. This research suggests a framework for privacy-preserving and personalized artificial intelligence that combines Federated Learning (FL), a Res-HyperTransformerNet deep prediction model, Personalized Multi-Agent Reinforcement Learning (PMARL) and Explainable Artificial Intelligence (XAI) for adaptive chronic disease management. The framework is structured with two main aims: (i) to create an accurate and privacy-aware predictive model for chronic disease risk using diverse data sources, and (ii) to permit adaptive, individual therapy optimization through multi-agent reinforcement learning. Federated learning is utilized to conduct the training of Res-HyperTransformerNet over distributed Internet of Medical Things (IoMT) nodes without the requirement of transferring raw patient data. The embeddings that are created from patient data are then passed on to a PMARL module, where several agents optimize therapy dimensions like medications, diet, physical activity, and mental health interventions independently. To make the clinical support more understandable, the SHAP-based explainability method is used for both predictive and decision-making parts. The framework is tested using two public datasets—the CDC Chronic Disease dataset and the UCI Chronic Kidney Disease Risk Factor dataset. The performance is measured by employing classification metrics (accuracy, precision, recall, F1-score, MCC) as well as reinforcement learning metrics (reward score, convergence steps, episode return) and federated system metrics (communication overhead, convergence rounds, and training time). The experiments indicate that the proposed framework demonstrated improved performance in terms of predictive accuracy and policy convergence speed compared to the baseline deep learning and reinforcement learning models, and at the same time it is more cost-effective when it comes to communication in a federated setting. This means that the proposed method suggests the potential of being a reproducible and open AI framework for adaptive chronic disease therapy management. The combination of ResNet and Transformer blocks, i.e., Federated Res-HyperTransformerNet, achieved strong performance in both datasets, namely CDC Chronic Disease (Dataset 1) and UCI CKD Risk Factor (Dataset 2). The obtained accuracy for Dataset 1 was 98.61% and for Dataset 2, it was 97.75%, under the conducted experimental settings.

chronic disease managementfederated learningprivacy-preserving healthcarechronic disease risk prediction
مقالوصول مغلق20262استشهاد· Semantic Scholar

Anatomical Fidelity in Text‐to‐Image Generative AI : A Comparative Qualitative and Quantitative Evaluation

Clinical Anatomy

Traditional anatomical resources like cadaveric dissection and professional atlases are the gold standard, but face constraints in cost and accessibility. The rapid integration of generative artificial intelligence (AI) in medical education offers new possibilities for custom anatomical illustration. Text-to-image AI generators provide an inexpensive and swift alternative for medical illustration. However, the anatomical fidelity and educational reliability of these models remain insufficiently validated. This study aimed to evaluate the accuracy of four prominent AI image generators in producing anatomically correct illustrations of the human heart, kidney, and brain. Four AI platforms-Copilot, Microsoft Designer, Gemini, and Freepik-were prompted to generate high-resolution, textbook-style illustrations of the heart (sternocostal view), kidney (coronal cross-section), and brain (lateral view). A total of 12 selected images were evaluated by a radiologist and two anatomists utilizing a structured 5-point Likert scale across five domains: textural realism, topological validity, morphometric accuracy, perspective and depth perception, and educational utility. Significant variability in performance was observed across platforms. Gemini consistently demonstrated superior performance, achieving perfect intraclass correlation coefficients (ICCs) and the highest ratings on complex topological tasks, including the representation of coronary vasculature and cortical sulci/gyri. Copilot showed high spatial accuracy in renal hilum organization. While all platforms showed high reliability and accuracy across broad morphological shapes (aortic arch, cerebral poles), accuracy declined sharply as anatomical complexity increased. AI-generated anatomical illustrations currently vary from medically indistinguishable to biologically impossible. While Gemini and Copilot show promise for supplemental educational use, the high frequency of hallucinated anatomical details in other platforms poses a risk for medical misinformation. The study underscores the necessity for expert supervision and for developing AI models trained on curated, peer-reviewed medical datasets.

text-to-image generative AIanatomical fidelitymedical illustrationAI hallucination
مقالوصول مفتوح20261استشهاد· Semantic Scholar

Knowledge, attitudes, and practices toward obesity and their determinants: a cross-sectional study

Frontiers in Public Health · مجلد 14 · 1768449-1768449

Background: Obesity remains a major global health challenge and a significant contributor to chronic diseases. This study aimed to assess knowledge, attitudes, and practices (KAP) related to obesity and to identify sociodemographic and clinical factors influencing these domains among individuals with obesity. Methods: A cross-sectional survey was conducted using a convenience, non-probability sampling method among individuals with obesity recruited from hospitals, health clinics, and community settings. Obesity-related knowledge, attitudes, and practices were assessed, and multinomial regression analyses were performed to identify factors associated with KAP outcomes. Results: A total of 419 participants were included, with a nearly equal gender distribution and a predominantly young adult population, most of whom had university-level education. Overall, 45.3% demonstrated satisfactory knowledge, 42.2% exhibited positive attitudes, and 43.0% reported effective practices regarding obesity management. Increasing age (OR = 1.361, 95% CI: 1.134-1.635) and higher education (OR = 2.417, 95% CI: 1.575-3.710) were significantly associated with satisfactory knowledge. Male participants were more likely to exhibit negative attitudes than females (OR = 1.909, 95% CI: 1.141-3.195), while individuals diagnosed with obesity were less likely to report non-satisfactory attitudes (OR = 0.495, 95% CI: 0.290-0.845). Effective practices were associated with age (OR = 1.296, 95% CI: 1.076-1.562) and obesity diagnosis (OR = 0.475, 95% CI: 0.278-0.811). Perceptions of nutritional value significantly influenced both knowledge (OR = 0.741, 95% CI: 0.571-0.961) and practices (OR = 0.384, 95% CI: 0.288-0.512). Conclusion: The findings highlight the role of key sociodemographic and clinical factors-particularly age, education, and obesity diagnosis-in shaping obesity-related knowledge, attitudes, and practices. Targeted educational and behavioral interventions, especially among younger individuals and males, along with improved awareness of nutritional value, may enhance obesity management outcomes.

obesityknowledge, attitudes and practicesobesity treatmentsociodemographic factors
مقالوصول مفتوح20261استشهاد· Semantic Scholar

A hybrid optimized framework with energy shape prior segmentation for brain tumor detection in MRI images

Digital Health · مجلد 12 · 20552076261418837-20552076261418837

Objectives: Brain tumors have been a major factor in the development of mental disorders like anxiety and depression. The primary target of this research is to develop a smart, economically feasible system that can detect and classify brain tumors by analyzing MRI images, reducing manual labor, and shortening diagnostic time. Methods: Although diagnosis with medical imaging is efficient for various health issues, accurately classifying brain tumors remains challenging for medical experts. This research introduces a new energy channel-based hybrid optimized network (ECHO-Net) as an automatic identification tool for brain tumors, aiming to facilitate medical diagnosis remotely. Energy shape prior segmentation (ESPS) is part of the framework, providing accurate segmentation and cropping of tumor regions from MRIs. Channel and spatial attention-based neural network (CSA-Net) differentiates between normal and tumor-affected images. Additionally, the hybrid chimp-based whale optimization (HCWO) algorithm enhances prediction precision and optimally sets sigmoid activation function parameters for better convergence and generalization. Results: Performance evaluation of ECHO-Net using publicly available MRI brain datasets, including Figshare, BRATS 2018-2020, and a clinical MRI dataset, shows a peak signal-to-noise ratio of 41.87 dB, a Structural Similarity Index Measure of 0.992, a sensitivity of 99.4%, an accuracy of 99.2%, and an average computational time of 2.68 s, outperforming current state-of-the-art methods. Conclusion: The proposed ECHO-Net is an automated, accurate, fast, and robust system for brain tumor detection. With low computational costs, it effectively segments abnormal regions and recognizes tumor types, demonstrating strong potential as a tool in intelligent healthcare systems and real-world clinical applications.

brain tumor detectionbrain tumor segmentationMRI imageschannel and spatial attention
مقالوصول مفتوح2026

Observational peer influence and institutional culture as predictors of preventive health compliance among Sudanese medical students

BMC Medical Education

Adherence to preventive health behaviors among medical students is essential for both personal safety and professional practice. However, compliance is not solely determined by knowledge and may be influenced by social and institutional factors. This study aimed to examine the association between peer influence, perceived institutional culture and adherence to preventive health behaviors among Sudanese medical students. A multi-institutional cross-sectional study was conducted among 400 undergraduate medical students from five universities in Khartoum State, Sudan, between June and November 2025. Data were collected using a structured, self-administered online questionnaire based on established behavioral frameworks. Preventive behaviors, peer influence and institutional culture were measured using Likert-scale items and summarized into composite scores. Spearman correlation and multivariate linear regression analyses were performed to assess associations, adjusting for demographic and institutional variables. Overall adherence to preventive health behaviors was generally favorable with highest compliance observed in hand hygiene (66.4%) and lower consistency in mask use (46.0%). Significant positive correlations were found between preventive behaviors, peer influence, and perceived institutional culture ( p < 0.01). Observational peer influence, particularly role modeling, was strongly associated with adherence ( r = 0.32–0.49), while institutional culture variables showed moderate associations ( r = 0.43–0.52). In multivariate analysis, first-year students demonstrated lower adherence (β = -0.92, p = 0.010) whereas living with family was associated with higher compliance (β = 0.28, p = 0.019). Other demographic variables were not significant predictors. Preventive health behaviors among medical students are shaped primarily by social and institutional contexts rather than individual characteristics. Interventions that leverage peer influence, strengthen professional norms and promote supportive institutional cultures may be more effective than knowledge based approaches alone particularly in resource constrained settings.

preventive health behaviormedical studentspeer influenceinstitutional culture
مقالوصول مغلق2026

From Libraries to Language Models: Exploring PhD Students’ Digital Research Tool Adoption

Serials Review · 1-13

This study investigates the digital transformation of academic research practices among doctorate (PhD) scholars, focusing on the integration and use of Online Public Access Catalogs (OPACs), electronic resources (e-resources), and large language models (LLMs). Using a descriptive survey of 355 doctoral students, the research explores the frequency, purpose, and perceived effectiveness of these tools in academic workflows. The findings reveal that while e-resources are the most utilized platform for literature searches and academic writing, OPACs remain underused due to perceived usability challenges. LLMs are gradually being adopted, especially for grammar refinement and content drafting, though concerns regarding reliability and academic integrity remain. Factor analysis highlights intuitive interfaces and information reliability as critical dimensions shaping user experience. The results call for improved digital literacy initiatives, user-centric OPAC redesigns, and ethical AI integration strategies to support contemporary scholarly practices.

digital research toolstechnology adoptiondoctoral studentslanguage models
نسخة أوليةمفتوح (مستودع)2026

Secure Big Data Analytics for Blockchain Transaction Fee Prediction and Scheduling in Distributed Systems

Research Square

Abstract This paper introduces an Intelligent and Secure Big Data Analyt-ics framework based on Explainable Hyper-Heuristic Optimization for dynamic blockchain transaction fee prediction and scheduling in distributed systems. The proposed framework is motivated by the volatility and complexity of large-scale blockchain fee markets, such as Ethereum’s EIP-1559 mechanism, which generate high-dimensional, time-varying transactional data characteristic of modern distributed and IoT-enabled ecosystems. The framework integrates a machine learning–based fee prediction module with an adaptive hyper-heuristic optimization engine that solves a mixed-integer scheduling problem over large-scale blockchain transaction datasets. In addition, a SHAP-based explainability layer is incorporated to support transparent, interpretable, and auditable decision-making, enabling trustworthy analytics in secure distributed environments. Experimental evaluation using six months of Ethereum mainnet data demonstrates that the proposed approach reduces median transaction costs by up to 14.8% and improves average confirmation delays by 8.3% compared with heuristic and fixed-fee baselines. Secure Big Data Analytics for Blockchain Scheduling Further analysis highlights the benefits of combining predictive analyt-ics, adaptive heuristic selection, and exact refinement under dynamic network conditions, while explainability results identify key transac-tional and network features influencing fee behavior and scheduling decisions. Overall, the proposed framework advances intelligent and secure big data analytics for distributed systems by improving efficiency , transparency, and trust in decentralized transaction management , with applications in wallets, decentralized applications, and latency-sensitive financial services. Future work will extend the framework to multi-chain environments, integrate Layer-2 scaling solutions, and explore real-time deployment in production blockchain systems.

transaction schedulingexplainable AISHAPEIP-1559
مراجعةوصول مفتوح2026

Beyond Lesion Control: A Narrative Review of Targeted Therapy and Surgical Decision-Making in Children With Vascular Anomalies Across Function, Growth, and Perioperative Care

Cureus · مجلد 18 (6) · e110532-e110532

Pediatric vascular anomalies are heterogeneous disorders that may cause pain, bleeding, infection, deformity, airway compromise, impaired mobility, psychosocial distress, and long-term functional morbidity. Surgery has traditionally played a central role in selected lesions through excision, debulking, staged reconstruction, and functional restoration. However, in children, operative decision-making is complicated by infiltrative anatomy, bleeding risk, lymphatic leakage, recurrence, scarring, growth potential, and the possibility of repeated procedures across childhood. The emergence of targeted therapies, particularly sirolimus for complex slow-flow malformations and alpelisib for PIK3CA-related overgrowth spectrum and selected vascular malformations, has shifted the management paradigm. These agents should not be viewed only as medical alternatives to surgery; rather, they may reshape surgical timing, extent, risk, and goals. This narrative review examines how targeted therapy may influence reconstructive surgical decision-making in children with vascular anomalies. We propose a child-centered model in which surgery may be performed, facilitated, delayed, avoided, or modified after targeted therapy. We also introduce the PERFORM framework to guide multidisciplinary assessment of patient age, lesion extent, treatment response, functional threat, operative risk, reconstruction required, and long-term follow-up. Future studies should move beyond radiologic response and report pediatric outcomes that matter: function, growth, quality of life, recurrence, revision surgery, and family burden.

pediatric vascular anomaliestargeted therapyrapamycinalpelisib
مقالوصول مفتوح2026

Federated Learning in Smart Home Intrusion Detection: Securing the Learning Process with Blockchain

Network and Communication Technologies · مجلد 10 (1) · 1-1

The rapid expansion of Internet of Things (IoT) devices has fundamentally reshaped traditional homes into highly interconnected smart environments, driving unprecedented convenience while simultaneously exposing critical cybersecurity vulnerabilities. Conventional centralized Intrusion Detection Systems (IDS) are increasingly inadequate for smart homes, owing to inherent privacy issues, latency, and susceptibility to single points of failure. Federated Learning (FL) offers a promising, privacy-preserving paradigm by enabling collaborative model training without the exchange of raw user data; however, FL remains vulnerable to model poisoning and integrity attacks. This comprehensive review systematically examines the integration of blockchain technology as a means to secure FL-based IDS in smart home contexts. We critically evaluate diverse blockchain frameworks, consensus protocols, and enhancement strategies that underpin the development of trustworthy, transparent, and resilient security architectures. Specifically, the review addresses two core research questions: (1) In what ways are blockchain frameworks and consensus mechanisms leveraged to secure FL-based IDS? and (2) What enhancement techniques and hybrid models are implemented to optimize the performance and efficiency of these integrated systems? Our synthesis reveals that permissioned blockchains—particularly those employing Proof of Authority (PoA) and Practical Byzantine Fault Tolerance (PBFT) consensus mechanisms—when combined with edge computing and lightweight architectural designs, deliver robust security while meeting the resource constraints characteristic of IoT devices. This technological synergy not only strengthens the resilience of the FL process but also advances the development of next-generation, secure smart home ecosystems.

federated learningintrusion detection systemshome automationblockchain
مقالوصول مفتوح2026

SCAG-Net: Automated Brain Tumor Prediction from MRI Using Cuttlefish-Optimized Attention-Based Graph Networks

Diagnostics · مجلد 16 (4) · 565-565

Background/Objectives: The earlier, more accurate, and more consistent prediction of the brain tumor recognition process requires automated systems to minimize diagnostic delays and human error. The automated system provides a platform for handling large medical images, speeding up clinical decision-making. However, the existing system is facing difficulties due to the high variability in tumor location, size, and shape, which leads to segmentation complexity. In addition, glioma-related tumors infiltrate the brain tissues, making it challenging to identify the exact tumor region. Method: The above-identified research difficulties are overcome by applying the Swin-UNet with cuttlefish-optimized attention-based Graph Neural Networks (SCAG-Net), thereby improving overall brain tumor recognition accuracy. This integrated approach is utilized to address infiltrative gliomas, tumor variability, and feature redundancy issues by improving diagnostic efficiency. Initially, the collected MRI images are processed using the Swin-UNet approach to identify the region, minimizing prediction error robustly. The region’s features are explored utilizing the cuttlefish algorithm, which minimizes redundant features and speeds up classification by improving accuracy. The selected features are further processed using the attention graph network, which handles structural and heterogeneous information across multiple layers, improving classification accuracy compared to existing methods. Results: The efficiency of the system, implemented with the help of public datasets such as BRATS 2018, BRATS 2019, BRATS 2020, and Figshare is ensured by the proposed SCAG-Net approach, which achieves maximum recognition accuracy. The proposed system achieved a Dice coefficient of 0.989, an Intersection over Union of 0.969, and a classification accuracy of 0.992. This performance surpassed the most recent benchmark models by margins of 1.0% to 1.8% and with statistically significant differences (p < 0.05). These findings present a statistically validated, computationally efficient, clinically deployable framework. Conclusions: The effective analysis of MRI complex structures is used in medical applications and clinical analysis. The proposed SCAG-Net framework significantly improves brain tumor recognition by addressing tumor heterogeneity and infiltrative gliomas using MRI images. The proposed approach provides a robust, efficient, and clinically deployable solution for brain tumor recognition from MRI images, supporting accurate and rapid diagnosis while maintaining expert-level performance.

brain tumor segmentationgliomamagnetic resonance imagingSwin-Unet
مقالوصول مفتوح2026

Cutaneous vascular response and its role in the efficacy of laser-based aesthetic procedures

International Journal of Community Medicine and Public Health

Laser-based aesthetic procedures rely heavily on the interaction between laser energy and the skin’s vascular system. The effectiveness of these treatments often depends on the ability to precisely target and modulate blood vessels without damaging surrounding tissue. Key to this process is selective photothermolysis, where laser wavelengths are absorbed by hemoglobin, leading to controlled thermal injury and vessel coagulation. The biological response that follows includes inflammatory signaling, thrombosis, and subsequent vascular remodeling, all of which contribute to clinical improvements in conditions like telangiectasia, port-wine stains, and facial erythema. The extent of vascular response is shaped by numerous variables such as vessel size, blood flow rate, depth, and the optical properties of the skin. Laser parameters including wavelength, pulse duration, and fluence must be carefully matched to these vessel characteristics to ensure effective treatment. In patients with darker skin tones, melanin competes with hemoglobin for light absorption, raising the risk of pigmentation issues. Protective measures like epidermal cooling and longer wavelengths help reduce adverse effects while maintaining efficacy. Treatment outcomes are also influenced by anatomical location, pre-existing vascular conditions, and patient-specific healing responses. Technological advancements, including dynamic cooling, pulse stacking, and multispectral lasers, have improved precision and safety. Monitoring vascular behavior during treatment allows for real-time adjustments, making procedures more adaptable to individual needs. Together, a deeper understanding of vascular mechanisms and improved device control continues to expand the potential of laser-based aesthetics, offering more consistent and personalized results across a wide range of skin types and vascular presentations.

selective photothermolysishemoglobin absorptionlaser parametersmelanin
مقالوصول مفتوح202540استشهاد· Semantic Scholar

Barriers to reporting workplace violence: a qualitative study of nurses’ perceptions in tertiary care settings

BMC Nursing · مجلد 24 (1) · 395-395

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
مراجعةوصول مفتوح202515استشهاد· Semantic Scholar

Bacteriophages and Their Enzymes: Allies Against Microbial Biofilms

Pharmaceuticals · مجلد 18 (12) · 1771-1771

Bacterial biofilms pose a substantial challenge in healthcare and industrial and environmental settings because of their resilience and antibiotic resistance. Biofilm formation is a complex process involving microbial communities encased in an extracellular matrix that contributes to increased resistance and persistent infections. This review explores the emerging roles of bacteriophages and their derived enzymes as promising alternatives or adjunct therapies to combat bacterial biofilms. Bacteriophages, viruses that infect bacteria, exhibit marked specificity and diverse mechanisms for targeting and lysing bacterial cells within biofilms. Enzymes, including endolysins and depolymerases, have demonstrated efficacy in disrupting biofilm matrices. Moreover, the potential synergy between bacteriophages and antibiotics enhances their antimicrobial activity, providing a multifaceted approach for combating biofilm-associated infections. This review critically evaluates the current research, highlighting the successes and limitations of bacteriophage-based strategies in biofilm control, and underscores the potential of these alternatives in shaping future therapeutic interventions against biofilm-related bacterial infections.

bacteriophagesphage enzymesbacterial biofilmsbiofilm matrix
مقالوصول مفتوح202510استشهاد· Semantic Scholar

Image classification-driven speech disorder detection using deep learning technique

SLAS TECHNOLOGY · مجلد 32 · 100261-100261

Speech disorders affect an individual's ability to generate sounds or utilize the voice appropriately. Neurological, developmental, physical, and trauma may cause speech disorders. Speech impairments influence communication, social interaction, education, and quality of life. Successful intervention entails early and precise diagnosis to allow for prompt treatment of these conditions. However, clinical examinations by speech-language pathologists are time-consuming, subjective, and demand an automated speech disorder detection (SDD) model. Mel-spectrogram images present a visual representation of multiple speech disorders. By classifying Mel-Spectrogram, various speech disorders can be identified. In this study, the authors proposed an image classification-based automated SDD model to classify Mel-Spectrograms to identify multiple speech disorders. Initially, Wavelet Transform (WT) hybridization technique was employed to generate Mel-Spectrogram using the voice samples. A feature extraction approach was developed using an enhanced LEVIT transformer. Finally, the extracted features were classified using an ensemble learning (EL) approach, containing CatBoost and XGBoost as base learners, and Extremely Randomized Tree as a meta learner. To reduce the computational resources, the authors used quantization-aware training (QAT). They employed Shapley Additive Explanations (SHAP) values to offer model interpretability. The proposed model was generalized using Voice ICar fEDerico II (VOICED) and LANNA datasets. The exceptional accuracy of 99.1 with limited parameters of 8.2 million demonstrated the significance of the proposed approach. The proposed model enhances speech disorder classification and offers novel prospects for building accessible, accurate, and efficient diagnostic tools. Researchers may integrate multimodal data to increase the model's use across languages and dialects, refining the proposed model for real-time clinical and telehealth deployment.

Mel spectrogramwavelet transformfeature extractionensemble learning