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.

8 مُخرَج نتائج البحث عن «Deep learning»

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 مفتوح20261استشهاد· Semantic Scholar

Diabetic retinopathy severity detection using an improved Whale optimization algorithm and convolutional Kolmogorov-Arnold network

Frontiers in Medicine · مجلد 13 · 1709872-1709872

Introduction: Diabetic retinopathy (DR) is an inflammatory condition affecting the retina caused by elevated and unregulated blood glucose levels. On a global scale, it is a contributing factor to vision impairment. Several deep learning (DL) methods use retinal images to identify DR severity. However, a significant improvement is required to assist medical professionals in recognizing DR in its early phases. Methods: Thus, the author introduced a method based on the DL technique to determine the DR severity grades using retinal images. A ShuffleNet V2 model with vision transformers' (ViT) attention mechanism was used to extract the features. An improved Whale optimization method (IWO) was used to fine-tune the feature extraction model. We employed a convolutional Kolmogorov-Arnold Network to categorize the DR severity using the extracted features. The EyePACS dataset was utilized to train the proposed DR severity grading model using a five-fold cross-validation strategy. We generalized the model on the Messidor-2 dataset. Results: The findings revealed an average accuracy of 93.84% on the MESSIDOR-2 dataset, demonstrating a substantial improvement in detecting DR using the fundus images. Discussion: Furthermore, the model demands minimal processing resources to generate the outcomes, leading to the deployment of the proposed DR severity detection model in healthcare facilities with limited computational resources.

diabetic retinopathyseverity classificationfundus imageswhale optimization algorithm
مقالوصول مفتوح20261استشهاد· Semantic Scholar

A hybrid deep learning framework for early detection of developmental disabilities using speech and behavioral biomarkers

Array · مجلد 29 · 100691-100691

Early and precise recognition of developmental disabilities (DDs) is essential for the timely intervention of preschool-age children. Although various predictive models have been developed in the past, they cannot provide accurate detections and face challenges like high false prediction, limited generalization, etc. To address these issues, a novel artificial intelligence (AI)-based algorithm was proposed for accurate DD detection. The proposed system integrates digital biomarkers from speech and behavioral domains for predicting DDs. Consequently, an Enhanced Gaussian-Based Noise Filtering (EGNF) is applied to speech data, and Z-score normalization is applied to behavioral data for preprocessing, which makes the raw data reliable for subsequent analysis. Further, feature extraction is performed using Convolutional-Bidirectional Long Short-Term Memory (Conv-BiLSTM) for speech data and Graph Attention Network (GAT) for behavioral data. Subsequently, a Hybrid Feature Selection (HFS) method was developed by combining the Harmony Search Algorithm (HSA) and ReliefF ranking for selecting informative and relevant attributes for model training. Finally, a hybrid classification model named DeepSTNet has been developed by integrating MnasNet and Independently Recurrent Neural Networks (IndRNN), which allows the capture of spatial and temporal long-term dependencies within the data, resulting in high detection performances. The proposed framework was implemented in Python and validated using comprehensive data formed by combining the Dysarthria Detection dataset and the Autism Dataset for Toddlers. The execution outcomes highlighted that the developed framework achieved an accuracy of 99.46%, a precision of 97.74%, and a recall of 98.05%, illustrating that this AI-centric system can be equipped by end users, including healthcare professionals and caregivers, with tools for early screening and detection of DDs.

developmental disabilitiesearly detectionspeech biomarkersbehavioral biomarkers
مقالوصول مغلق2026

Diagnostic Accuracy of Artificial Intelligence versus Clinical Diagnosis in Detecting Acute Otitis Media: A Systematic Review and Meta-analysis

Saudi Journal of Otorhinolaryngology Head and Neck Surgery

Abstract Acute otitis media (AOM) represents a prevalent infection in children globally, leading to considerable morbidity and imposing a substantial burden on healthcare systems. Prompt and precise diagnosis is critical to reducing complications, such as tympanic membrane perforation, hearing impairment, and excessive antibiotic prescribing. Advances in artificial intelligence (AI), particularly deep learning, have created opportunities to enhance diagnostic accuracy and broaden access to care, especially in low-resource settings. This systematic review and meta-analysis aimed to evaluate the diagnostic performance of AI-based systems for detecting AOM compared with conventional clinical diagnosis and to analyze their accuracy relative to human clinicians across different model architectures and diagnostic methods. Following PRISMA-DTA standards and PROSPERO registration, systematic searches were conducted in PubMed, Web of Science, and IEEE Xplore up to July 30, 2025. Eligible studies included human participants with suspected AOM, employed AI-driven diagnostic approaches, and used a clinical reference standard. The Quality Assessment of Diagnostic Accuracy Studies-2 tool assessed bias, and pooled sensitivity and specificity were estimated using a bivariate random-effects model. Nine studies published between 2020 and 2025 met the inclusion criteria. The pooled sensitivity and specificity were 91% (95% confidence interval [CI]: 77%–97%) and 99% (95% CI: 94%–100%), respectively. AI models overall matched or outperformed general practitioners and pediatricians, approaching otolaryngologist-level accuracy. AI-based tools have the potential to improve AOM detection, mitigate inequalities in healthcare access, and promote more effective diagnosis, particularly in underserved regions.

acute otitis mediaartificial intelligencedeep learningdiagnostic accuracy
مقالوصول مفتوح2026

VG-RETFound: a hybrid retinal AI framework for early vision impairment screening through vessel-graph learning and cross-modal fusion

Frontiers in Medicine · مجلد 13 · 1905129-1905129

Introduction: Vision impairment caused by retinal diseases stands out as one of the significant sources of irreversible blindness, highlighting the importance of developing robust automated screening tools to detect eye diseases at an early stage. Despite the promising results of recent deep learning approaches to the automatic classification of retinal images, most existing solutions focus on image-based representations and do not consider the importance of vascular topology. To overcome the limitations, this study proposes VG-RETFound - a hybrid framework based on a retinal foundation model and graph-based vascular-topology modeling that can be used to classify multiple retinal categories and detect vision impairment. Methods: The authors use RETFound-a retinal foundation model-pretrained on a vast number of retinal images, as well as the Graph Attention Network (GAT), to learn vascular topology features by representing retinal vessels as graphs. The presented approach employs a cross-modal multi-head attention fusion method to integrate features from both modalities in real time. To evaluate the efficiency of VG-RETFound, experiments were conducted using the RFMiD and ODIR-5 K datasets for model training and testing across six retinal categories: Normal, Diabetic Retinopathy, Pathological Myopia, Age-related Macular Degeneration, Hypertensive Retinopathy, and Other Retinal Diseases. Results: The accuracy of 96.39%, F1-score of 95.84%, MCC of 94.87%, and Kappa of 94.71% were attained on an internal test dataset, while cross-dataset external validation on the BRSET dataset revealed accuracy of 94.81%, F1-score of 94.25%, MCC of 93.09%, and Kappa of 92.94%. Discussion: These findings demonstrate that integrating retinal foundation models with anatomically informed vessel-topology learning significantly improves classification accuracy, interpretability, and generalization, highlighting the potential of VG-RETFound as a tool for large-scale vision impairment. screening and retinal disease diagnosis.

retinal disease classificationRETFoundgraph attention networksvascular topology
مقالوصول مغلق2026

Artificial Intelligence in Anatomical Education and Clinical Anatomy: Current Applications and Future Directions

— · مجلد 5 (1) · 97-103

Artificial intelligence (AI) is increasingly influencing medical education and clinical practice by providing new approaches to learning, visualization, diagnosis, decision-making, and personalized training. Anatomical education represents an important area for AI integration because conventional teaching methods often depend on cadaveric dissection, two-dimensional illustrations, atlases, and static imaging resources. Recent advances in machine learning, deep learning, computer vision, natural language processing, generative AI, and three-dimensional reconstruction have created opportunities to enhance the teaching and understanding of human anatomy. AI-supported anatomical education can facilitate automated identification of anatomical structures, generation of personalized learning materials, interactive three-dimensional models, intelligent tutoring, image-based assessment, and adaptive learning environments. In clinical anatomy, AI can assist with anatomical segmentation, interpretation of medical images, surgical planning, identification of anatomical variations, and simulation-based training. Nevertheless, the implementation of AI also presents challenges related to accuracy, bias, data privacy, explainability, cost, technological infrastructure, academic integrity, and the potential overreliance of students on automated systems. This review discusses the current applications of AI in anatomical education and clinical anatomy, examines its potential advantages and limitations, and considers future directions for responsible integration into anatomy curricula and healthcare practice. The future of AI-assisted anatomy is likely to involve multimodal learning environments combining three-dimensional visualization, augmented and virtual reality, intelligent tutoring systems, medical imaging, and generative AI. Rather than replacing anatomists and educators, AI is expected to function as an augmentative technology that supports deeper anatomical understanding, individualized learning, and clinically oriented education.

artificial intelligenceanatomy educationclinical anatomygenerative AI
مقالوصول مفتوح2026

RAD-OAEnsemble: Residual attention DenseNet with radiograph-EHR fusion and dual-stream deep feature embedding for knee osteoarthritis risk prediction

Egyptian Informatics Journal · مجلد 34 · 100929-100929

Knee osteoarthritis (OA) is a popular and progressive degenerate joint disease and require a predictor of risk at the primary stage to predict drug treatment and propose an early intervention. The current methods of deep learning are not sufficient enough to deal with integrating the heterogeneous modality component, modeling of irregular temporal follow ups, and capture of the fine grained variations of pathological types. In order to address such limitations, this paper suggests a new multimodal approach named, RAD-OAEnsemble which introduces three main innovations. First, a novel Cross Bi-modal Heterogeneous Graph Fusion Network (CBHGF-Net) is introduced for the multi-scale semantic fusion of Radiographs and Electronic Health Records (EHRs). Second, a Modified DenseNet with Multi-scale Attention Criss-Cross Blocks (MACC-Blocks) is presented to extract the anatomical features of knee OA patterns by utilizing dilated convolution, criss-cross attention, residual attention gating. Third, a Dual-Stream Tranfo-Convo (DTC) Deep Temporal Embedding module is proposed that consists of a Time-Warped Convolutional Blocks and a Temporal Decay Encoded Informer for the knee OA risk prediction. The suggested approach delivered better outcomes with accuracy of 99.275%, precision of 98.175%, specificity of 99.165%, sensitivity of 98.95%, and F1-score of 98.175% in having considerably a low rate of false positives (1.875%) and false negatives (2.175%). The findings support the relevance of the suggested framework in providing resilient, time-sensitive, and explainable OA progression predictions by multimodal combination and high-fidelity feature learning.

knee osteoarthritismultimodal fusionDenseNetattention mechanism
مقالمفتوح (مستودع)2026

Optimized Deep Learning Techniques for Enhanced Epilepsy Prediction from Electroencephalogram Signals

Advanced Health Science and Technology Journal · مجلد 2 (1) · 63-72

Abstract Background: Well over 65 million people throughout the world suffered from epilepsy, a common neurological illness. The success rate of standard medical interventions, including medication and surgery, is <30%. On the other hand, seizure prevention methods involving prompt therapeutic interventions are possible with early seizure prediction. Effective and highly accurate epilepsy prediction is still a challenge, despite experts’ best efforts. Aims and Objectives: We present the Particle Swarm Optimized–Convolutional Neural Network and Long Short Term Memory (PSO CNN LSTM) model for electroencephalogram (EEG) signal categorization to support epilepsy diagnosis. Materials and Methods: For EEG classification, we acquire EEG samples from the Bonn dataset that has been used in many reliable studies, which contains five categories of EEG signals, including both normal and epileptic samples. The dataset is preprocessed by removing artifacts and noise. The Short Time Fourier Transform method is subsequently employed for converting the EEG signals into spectrogram images. The postulated PSO CNN LSTM model and other deep learning models, such as CNN and CNN LSTM, employed these spectrogram images as inputs. MATLAB software was implemented for training and verifying models. Results and Conclusions: The studies’ findings revealed that the suggested PSO CNN LSTM model performs better than the other models, with an accuracy of 96% as opposed to 84% and 94%, respectively.

epileptic seizure predictionseizure predictionEEGEEG classification