Abdul Rahaman Wahab Sait

Multiple Sclerosis (MS) is an immune-mediated central nervous system condition with heterogeneous clinical manifestations, progressive neurodegeneration, and considerable variability in disease trajectory. Recent advances in artificial intelligence (AI), particularly machine learning (ML) methods, have improved MS diagnosis and risk prediction. However, comprehensive review studies emphasizing the potential of existing AI-powered MS diagnosis remain limited. Thus, this study investigates the utilization of multimodal data by AI models to enhance diagnostic accuracy, evaluate disease progression, and optimize personalized care strategies. By adhering to PRISMA guidelines, this review included 26 studies encompassing MRI-based analysis, retinal OCT imaging, blood transcriptomics, SNP genotyping, and multimodal clinical datasets. An additional classification of these studies by modality was performed, and they were assessed with respect to dataset size, performance metrics, biomarkers, methodological robustness, and model interpretability. The findings indicate a consistent trend toward outstanding diagnostic performance, with some AI models achieving accuracies exceeding 95% using medical imaging and genomic data. However, limited external validation and interpretability procedures create a gap in clinical applicability and trustworthiness. This review highlights AI's growing potential to revolutionize MS diagnosis.

The increasing complexity of online misinformation requires detection systems that supplement article-level classification with transparent, evidence-grounded, and verifiable decision support. Existing methods commonly prioritize predictive accuracy, with limited assurance that generated explanations remain faithful to the source article. This study introduces SAE-HMFD, a sparse autoencoder-guided dual-stream framework that integrates fake-news classification with hallucination-aware rationale verification while preserving their functional distinction. The proposed approach incorporates Longformer-based long-context encoding, learnable fusion of upper encoder layers, a gated sparse autoencoder for selective latent representation, article-internal evidence grounding, controlled rationale construction, and cross-stream faithfulness optimization. Leakage-controlled development and internal validation employ WELFake and HaluEval, whereas CoAID and RAGTruth Recent News support independent cross-domain evaluation. Across datasets, SAE-HMFD outperforms recent fake-news and hallucination-detection baselines on complementary measures, including accuracy, precision, recall, F1-score, and Matthews correlation coefficient (MCC). A dedicated CoAID-Integrated cohort of 360 expert-annotated articles provides a unified external benchmark for jointly evaluating fake-news classification and hallucination-aware rationale verification. On this dataset, SAE-HMFD achieves a fake-news F1-score of 0.855, MCC of 0.734, hallucination-verification F1-score of 0.872, supported-rationale rate of 0.852, and faithfulness alignment of 0.909. These findings establish SAE-HMFD as a robust and generalizable framework for reliability-oriented misinformation analysis.

Cloud data storage and retrieval systems use attribute-based cryptographic primitives to obtain fine-grained access control, data-owner anonymity, and search-result verifiability without a trusted online authority. The schemes that achieve these properties together, most notably the Attribute-Based verifiable Data Storage and data Retrieval Scheme (ABDSRS), are built on bilinear pairings, whose underlying discrete-logarithm assumptions are broken by Shor’s algorithm. We present PQ-ABDSRS, a lattice-based construction that provides the same functional interface using only Learning with Errors (LWE) and Short Integer Solution (SIS) assumptions. The construction is modular: fine-grained access control is obtained from a lattice ciphertext-policy attribute-based encryption scheme for monotone disjunctive policies, keyword-policy search from a lattice key-policy attribute-based encryption scheme, and data-owner authentication from a lattice attribute-based signature, each used through a stated interface with stated security requirements. The pairing-bilinearity masking identity that ABDSRS uses for non-interactive verifiability has no lattice analogue, and we show that an additively homomorphic SIS commitment does not by itself authenticate an outsourced computation. We replace it with a SIS-based binding digest over the ciphertext components, bound into the data owner’s signature, together with a random-oracle preimage check on the search predicate. We state the decryption-error condition the composition requires and fix the modulus from it, and we prove IND-CPA confidentiality, EUF-CMA unforgeability, verifiability of the transformation step, signer privacy, and search-tag privacy in the classical random oracle model, collected in a single composition theorem that records every assumption and reduction loss. Two guarantees are deliberately narrow: verification of the search predicate holds per record only until that record’s first successful search, and the scheme provides no semantic keyword privacy, only the leakage profile we state explicitly. Parameters are derived subject to the worst-case LWE reduction condition as well as to concrete attack estimates from the lattice estimator. The resulting public parameters exceed ABDSRS’s by seven orders of magnitude and ciphertexts by three, and these figures are model-based lower bounds rather than complete serializations. We report the cost as the principal result: it is the measure of how far unstructured lattices are from reproducing this functionality. A structured-lattice variant is discussed as future work and is not claimed as an instantiated scheme.

Automated analysis of fundus images is a promising technique for efficient, scalable retinal screening. In real-time screening, binary classification provides a straightforward first-line solution by differentiating normal and abnormal images, enabling prioritization of potentially abnormal cases for subsequent medical and disease-specific analysis. This study proposes RetinoMamba-AnatomyQuery, a lightweight model that integrates Vision Mamba-based global contextual representations, EfficientNet-B3-derived local features, anatomy–lesion query refinement, and anatomy-aware feature fusion. The Ocular Disease Intelligent Recognition (ODIR)-2019 dataset and Brazilian Multilabel Ophthalmological Dataset (BRSET) are harmonized to construct the internal cohort, yielding 10,842 eligible unique patients following expert-assisted quality control and data curation. The proposed model achieves accuracy of 97.93%, recall of 97.77%, specificity of 98.07%, precision of 97.87%, and an F1-score of 97.82%, outperforming state-of-the-art models. Independent evaluation on the external dataset (Retinal Fundus Multi-disease Image Dataset (RFMiD)) reports an accuracy of 96.21% and an F1-score of 95.99%, demonstrating sustained performance across an independent data distribution. Computational evaluation demonstrates a controlled footprint of 23.9 million parameters and 8.3 giga floating-point operations, supporting computationally efficient screening. Overall, the findings demonstrate the effectiveness of anatomy-conditioned global–local feature integration for reliable normal/abnormal fundus discrimination.

Chronic obstructive pulmonary disease (COPD) leads to progressive airflow obstruction, impairing respiratory function. In this study, a deep-learning framework is developed to analyze lung sounds (LS) and support COPD screening using an explainable approach. In the proposed methodology, the LS signals are transformed into spectrograms, highlighting crucial acoustic features. Convolutional neural networks (CNNs) and vision transformers (ViTs) models are introduced to extract diverse features, enhancing feature representation. Subsequently, an attention-guided feature importance (AGFI) is employed to refine the features. An ensemble architecture leveraging TabNet and Support Vector Machine (SVM) with radial basis function (RBF) as base learners and Neural Oblivious Decision Ensembles (NODE) as a meta-learner is proposed to classify features into COPD and normal classes. Experimental outcomes validated on internal and external datasets demonstrate the model’s exceptional classification performance. The proposed model achieves outstanding generalization performance on the external dataset with an accuracy of 96.31% and an F1-score of 96.55%, outperforming the traditional ensemble methods. Through the innovative artificial intelligence-powered COPD screening approach, the shortcomings of conventional screening approaches are addressed. The feature-extraction architecture and ensemble classification enable the proposed model to provide a scalable, explainable, and clinically reliable solution across diverse healthcare settings.

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.

Introduction: Speech disorders (SD) present significant diagnostic challenges due to the complex and indistinct acoustic characteristics embedded within speech signals. Problem statement: The standalone convolutional neural networks (CNNs) and vision transformers (ViT) struggle to capture SD temporal and spectral dynamics. Objectives: To address these limitations, this study proposes an end-to-end binary pathological SD detection framework that processes raw audio waveforms to differentiate disordered speech from healthy speech while improving feature representation, interpretability, and generalization. Methods: A hybrid feature extraction integrating one-dimensional CNNs and ViT’s self-attention mechanism is developed to extract crucial SD features. An adaptive fusion and a Class-attention transformer (CaiT)-based feature refinement is introduced to transform the extracted features into a classification-optimized global representation. Through the integration of gradient-weighted class activation mapping (Grad-CAM) and attention-based visualization with the model architecture, the temporal-localization of disorder-relevant acoustic patterns is enabled. Two benchmark datasets are utilized for model’s performance evaluation, benchmarking against state-of-the-art CNNs and ViT architectures. The model is trained and internally validated on the SVD dataset using subject-level splitting, while the PD and VOICED datasets are used exclusively for external validation to assess cross-dataset generalization across neurological and heterogeneous pathological voice conditions. Results: The proposed model achieves 97.50% accuracy on both SVD and PD datasets and 95.80% accuracy on VOICED, while maintaining a lightweight design with 5.2 million parameters. Statistical analysis further confirms the results’ reliability and significance. Conclusion: The integration of adaptive fusion and transformer-based refinement significantly enhances SD detection performance while ensuring interpretability. The suggested framework offers a sound and proof-of-concept for diagnosing SD, allowing clinicians and speech-language pathologists to make reliable predictions and pay attention to diagnostically significant time intervals.

Breast cancer screening is a fundamentally probabilistic diagnostic task that requires precise identification of complex imaging characteristics from diverse patient cohorts. Despite improvements in deep learning techniques, current automatic tools are typically trained on well-curated datasets and do not generalize to heterogeneous data, thereby limiting their application. This study aims to address these shortcomings by introducing a more effective and generalizable framework for breast cancer classification that focuses on the stability of features, the learning of complementary representations, and improved decision modeling. The proposed methodology incorporates stability-driven feature extraction (SDFE) with a multi-branch architecture that consists of EfficientNetV2 (Convolutional neural networks (CNNs)), EfficientFormer (Vision transformers (ViTs)), and multi-layer perceptron (MLP)-Mixer models to extract various feature representations. To improve non-linear decision boundaries, it uses a Kolmogorov–Arnold Network (KAN)-based classification head and selects the most credible prediction via an adaptive voting mechanism. This model is trained using patient-level splitting on the VinDr-Mammo dataset, evaluated using five-fold cross-validation, and subsequently externally validated on the CBIS-DDSM dataset. Experimental findings demonstrate the consistent performance of the proposed model, with accuracies of 94.5% in cross-validation, 93.3% on the VinDr-Mammo test set, and 94.6% on CBIS-DDSM, surpassing other recent state-of-the-art solutions. It demonstrates enhanced robustness and cross-dataset generalization, offering a scalable, consistent framework for breast cancer classification that supports the development of computer-aided diagnostic systems.