Search Results (462)

Dengue fever is a mosquito-borne viral disease that annually affects 100–400 million people worldwide. Early detection of dengue enables easy treatment planning and helps reduce mortality rates. This study proposes three Swarm-based Metaheuristic Algorithms, Golden Jackal Optimization, Fox Optimizer, and Sea Lion Optimization, for feature selection and hyperparameter tuning, and an Extreme Gradient Boost classifier to forecast dengue fever using the Predictive Clinical Dengue dataset. Several existing models have been proposed for dengue fever classification, with some achieving high predictive performance. However, most of these studies have overlooked the importance of feature reduction, which is crucial to building efficient and interpretable models. Furthermore, prior research has lacked in-depth analysis of model behavior, particularly regarding the underlying causes of misclassification. Addressing these limitations, this study achieved a 10-fold cross-validation mean accuracy of 99.89%, an F-score of 99.92%, a precision of 99.84%, and a perfect recall of 100% by using only two features: WBC Count and Platelet Count. Notably, FOX-XGBoost and SLO-XGBoost achieved the same performance while utilizing only four and three features, respectively, demonstrating the effectiveness of feature reduction without compromising accuracy. Among these, GJO-XGBoost demonstrated the most efficient feature utilization while maintaining superior performance, emphasizing its potential for practical deployment in dengue fever diagnosis. SHAP analysis identified WBC Count as the most influential feature driving model predictions. Furthermore, DiCE explanations support this finding by showing that lower WBC Counts are associated with dengue-positive cases, whereas higher WBC Counts are indicative of dengue-negative individuals. SHAP interpreted the reasons behind misclassifications, while DiCE provided a correction mechanism by suggesting the minimal changes needed to convert incorrect predictions into correct ones. Full article

Purpose: This systematic review explores the ethical, legal, and regulatory frameworks governing the deployment of artificial intelligence technologies in radiology. It aims to identify key governance challenges and highlight strategies that promote the safe, transparent, and accountable integration of artificial intelligence in clinical imaging. This review is intended for both medical practitioners and AI developers, offering clinicians a synthesis of ethical and legal considerations while providing developers with regulatory insights and guidance for future AI system design. Methods: A systematic review was conducted, examining thirty-eight peer-reviewed articles published between 2018 and 2025. Studies were identified through searches in PubMed, Scopus, and Embase using terms related to artificial intelligence, radiology, ethics, law, and regulation. The inclusion criteria focused on studies addressing governance implications, rather than technical design. A thematic content analysis was applied to identify common patterns and gaps across ethical, legal, and regulatory domains. Results: The findings reveal widespread radiology-specific concerns, including algorithmic bias in breast and chest imaging datasets, opacity in image-based AI systems such as pulmonary nodule detection models, and unresolved legal liability in cases where radiologists rely on FDA-cleared AI tools that fail to identify abnormalities. Regulatory frameworks vary significantly across regions with limited global harmonization, highlighting the need for adaptive oversight models and improved data governance. Conclusion: Responsible deployment of AI in radiology requires governance models that address bias, explainability, and medico-legal accountability while integrating ethical principles, legal safeguards, and adaptive oversight. This review provides tailored insights for medical practitioners, AI developers, policymakers, and researchers: clinicians gain guidance on ethical and legal responsibilities, developers on regulatory and design priorities, policymakers (especially in the Middle East) on regional framework gaps, and researchers on future directions. Full article

Streptococcus pharyngitis (strep throat) poses a significant health challenge in rural and remote Indigenous communities in Australia, where access to medical resources is limited. Delays in diagnosis and treatment increase the risk of serious complications, including acute rheumatic fever and rheumatic heart disease. This paper presents a proof-of-concept AI-based diagnostic model designed to support clinicians in underserved communities. The model combines a lightweight Swin Transformer–based image classifier with a BLIP-2-based explainable image annotation system. The classifier predicts strep throat from throat images, while the explainable model enhances transparency by identifying key clinical features such as tonsillar swelling, erythema, and exudate, with synthetic labels generated using GPT-4o-mini. The classifier achieves 97.1% accuracy and an ROC-AUC of 0.993, with an inference time of 13.8 ms and a model size of 28 million parameters; these results demonstrate suitability for deployment in resource-constrained settings. As a proof-of-concept, this work illustrates the potential of AI-assisted diagnostics to improve healthcare access and could benefit similar research efforts that support clinical decision-making in remote and underserved regions. Full article

Wireless sensor networks (WSNs) are a key enabling technology for modern e-Health applications. However, their deployment in clinical environments faces critical challenges due to dynamic network topologies, signal interference, and stringent energy constraints. Static resource allocation schemes often prove inadequate in these mission-critical settings, leading to communication failures that can compromise data integrity and patient safety. This paper proposes a novel hybrid framework for intelligent, dynamic resource allocation that addresses these challenges. The framework combines classical graph-coloring heuristics—Greedy and Recursive Largest First (RLF) for efficient initial channel assignment with the adaptive power of metaheuristics, specifically Simulated Annealing and Genetic Algorithms, for localized refinement. Unlike conventional approaches that require costly, network-wide reconfigurations, our method performs targeted adaptations only in interference-affected regions, thereby optimizing the trade-off between network reliability and energy efficiency. Comprehensive simulations modeled on dynamic, hospital-scale WSNs demonstrate the effectiveness of various hybrid strategies. Notably, our results demonstrate that a hybrid strategy using a Genetic Algorithm can most effectively minimize interference and ensure high data reliability, validating the framework as a scalable and resilient solution. These results validate the proposed framework as a scalable, energy-aware solution for resilient, real-time healthcare telecommunication infrastructures. Full article

Background/Objectives: An ASD diagnosis from EEG is challenging due to non-stationary, low-SNR signals and small cohorts. We propose a compact, interpretable pipeline that pairs a shift-invariant Stationary Wavelet Transform (SWT) with Fisher’s Linear Discriminant (FLDA) as a supervised projection method, delivering band-level insight and subject-wise evaluation suitable for resource-constrained clinics. Methods: EEG from the KAU dataset (eight ASD, eight controls; 256 Hz) was decomposed with SWT (db4). We retained levels 3, 4, and 6 (γ/β/θ) as features. FLDA learned a low-dimensional discriminant subspace, followed by a linear decision rule. Evaluation was conducted using a subject-wise 70/30 split (no subject overlap) with accuracy, precision, recall, F1, and confusion matrices. Results: The β band (Level 4) achieved the best performance (accuracy/precision/recall/F1 = 0.95), followed by γ (0.92) and θ (0.85). Despite partial overlap in FLDA scores, the projection maximized between-class separation relative to within-class variance, yielding robust linear decisions. Conclusions: Unlike earlier FLDA-only pipelines and wavelet–entropy–ANN approaches, our study (1) employs SWT (undecimated, shift-invariant) rather than DWT to stabilize sub-band features on short resting segments, (2) uses FLDA as a supervised projection to mitigate small-sample covariance pathologies before classification, (3) provides band-specific discriminative insight (β > γ/θ) under a subject-wise protocol, and (4) targets low-compute deployment. These choices yield a reproducible baseline with competitive accuracy and clear clinical interpretability. Future work will benchmark kernel/regularized discriminants and lightweight deep models as cohort size and compute permit. Full article

The rapid evolution of artificial intelligence (AI) and machine learning (ML) technologies has initiated a paradigm shift in contemporary spine care. This narrative review synthesizes advances across imaging-based diagnostics, surgical planning, genomic risk stratification, and post-operative outcome prediction. We critically assess high-performing AI tools, such as convolutional neural networks for vertebral fracture detection, robotic guidance platforms like Mazor X and ExcelsiusGPS, and deep learning-based morphometric analysis systems. In parallel, we examine the emergence of ambient clinical intelligence and precision pharmacogenomics as enablers of personalized spine care. Notably, genome-wide association studies (GWAS) and polygenic risk scores are enabling a shift from reactive to predictive management models in spine surgery. We also highlight multi-omics platforms and federated learning frameworks that support integrative, privacy-preserving analytics at scale. Despite these advances, challenges remain—including algorithmic opacity, regulatory fragmentation, data heterogeneity, and limited generalizability across populations and clinical settings. Through a multidimensional lens, this review outlines not only current capabilities but also future directions to ensure safe, equitable, and high-fidelity AI deployment in spine care delivery. Full article

Background: Skin cancer represents one of the most prevalent malignancies worldwide, with melanoma accounting for approximately 75% of skin cancer-related deaths despite comprising fewer than 5% of cases. Early detection dramatically improves survival rates from 14% to over 99%, highlighting the urgent need for accurate and accessible diagnostic tools. While deep learning has shown promise in dermatological diagnosis, existing approaches lack clinical explainability and deployable interfaces that bridge the gap between research innovation and practical healthcare applications. Methods: This study implemented a comprehensive multimodal deep learning framework using the HAM10000 dataset (10,015 dermatoscopic images across seven diagnostic categories). Three CNN architectures (DenseNet-121, EfficientNet-B3, ResNet-50) were systematically compared, integrating patient metadata, including age, sex, and anatomical location, with dermatoscopic image analysis. The first implementation of XRAI (eXplanation with Region-based Attribution for Images) explainability for skin lesion classification was developed, providing spatially coherent explanations aligned with clinical reasoning patterns. A deployable web-based clinical interface was created, featuring real-time inference, comprehensive safety protocols, risk stratification, and evidence-based cosmetic recommendations for benign conditions. Results: EfficientNet-B3 achieved superior performance with 89.09% test accuracy and 90.08% validation accuracy, significantly outperforming DenseNet-121 (82.83%) and ResNet-50 (78.78%). Test-time augmentation improved performance by 1.00 percentage point to 90.09%. The model demonstrated excellent performance for critical malignant conditions: melanoma (81.6% confidence), basal cell carcinoma (82.1% confidence), and actinic keratoses (88% confidence). XRAI analysis revealed clinically meaningful attention patterns focusing on irregular pigmentation for melanoma, ulcerated borders for basal cell carcinoma, and surface irregularities for precancerous lesions. Error analysis showed that misclassifications occurred primarily in visually ambiguous cases with high correlation (0.855–0.968) between model attention and ideal features. The web application successfully validated real-time diagnostic capabilities with appropriate emergency protocols for malignant conditions and comprehensive cosmetic guidance for benign lesions. Conclusions: This research successfully developed the first clinically deployable skin lesion classification system combining diagnostic accuracy with explainable AI and practical patient guidance. The integration of XRAI explainability provides essential transparency for clinical acceptance, while the web-based deployment democratizes access to advanced dermatological AI capabilities. Comprehensive validation establishes readiness for controlled clinical trials and potential integration into healthcare workflows, particularly benefiting underserved regions with limited specialist availability. This work bridges the critical gap between research-grade AI models and practical clinical utility, establishing a foundation for responsible AI integration in dermatological practice. Full article

Background: Differentiating pediatric pneumonia from acute bronchitis remains a persistent clinical challenge due to overlapping symptoms, often leading to diagnostic uncertainty and inappropriate antibiotic use. Methods: This study introduces DAPLEX, a structured ensemble learning framework designed to enhance diagnostic accuracy and reliability. A retrospective cohort of 868 pediatric patients was analyzed. DAPLEX was developed in three phases: (i) deployment of diverse base learners from multiple learning paradigms; (ii) multi-criteria evaluation and pruning based on generalization stability to retain a subset of well-generalized and stable learners; and (iii) complementarity-driven knowledge fusion. In the final phase, out-of-fold predicted probabilities from the retained base learners were combined with a consensus-based feature importance profile to construct a hybrid meta-input for a Multilayer Perceptron (MLP) meta-learner. Results: DAPLEX achieved a balanced accuracy of 95.3%, an F1-score of ~0.96, and a ROC-AUC of ~0.99 on an independent holdout test. Compared to the range of performance from the weakest to the strongest base learner, DAPLEX improved balanced accuracy by 3.5–5.2%, enhanced the F1-score by 4.4–5.6%, and increased sensitivity by a substantial 8.2–13.6%. Crucially, DAPLEX’s performance remained robust and consistent across all evaluated demographic subgroups, confirming its fairness and potential for broad clinical. Conclusions: The DAPLEX framework offers a robust and transparent pipeline for diagnostic decision support. By systematically integrating diverse predictive models and synthesizing both outcome predictions and key feature insights, DAPLEX substantially reduces diagnostic uncertainty in differentiating pediatric pneumonia and acute bronchitis and demonstrates strong potential for clinical application. Full article

Deep learning (DL) has revolutionized medical image analysis (MIA), enabling early anomaly detection, precise lesion segmentation, and automated disease classification. However, its clinical integration faces two major challenges: reliance on limited, narrowly annotated datasets that inadequately capture real-world patient diversity, and the inherent “black-box” nature of DL decision-making, which complicates physician scrutiny and accountability. Eye tracking (ET) technology offers a transformative solution by capturing radiologists’ gaze patterns to generate supervisory signals. These signals enhance DL models through two key mechanisms: providing weak supervision to improve feature recognition and diagnostic accuracy, particularly when labeled data are scarce, and enabling direct comparison between machine and human attention to bridge interpretability gaps and build clinician trust. This approach also extends effectively to multimodal learning models (MLMs) and vision–language models (VLMs), supporting the alignment of machine reasoning with clinical expertise by grounding visual observations in diagnostic context, refining attention mechanisms, and validating complex decision pathways. Conducted in accordance with the PRISMA statement and registered in PROSPERO (ID: CRD42024569630), this review synthesizes state-of-the-art strategies for ET-DL integration. We further propose a unified framework in which ET innovatively serves as a data efficiency optimizer, a model interpretability validator, and a multimodal alignment supervisor. This framework paves the way for clinician-centered AI systems that prioritize verifiable reasoning, seamless workflow integration, and intelligible performance, thereby addressing key implementation barriers and outlining a path for future clinical deployment. Full article

Background: Hypertension remains the leading global risk factor for cardiovascular morbidity and mortality, with suboptimal control rates despite guideline-directed therapies. Digital health and artificial intelligence (AI) technologies offer novel approaches for improving diagnosis, monitoring, and individualized treatment of hypertension. Objectives: To critically review the current landscape of AI-enabled digital tools for hypertension management, including emerging applications, implementation challenges, and future directions. Methods: A narrative review of recent PubMed-indexed studies (2019–2024) was conducted, focusing on clinical applications of AI and digital health technologies in hypertension. Emphasis was placed on real-world deployment, algorithmic explainability, digital biomarkers, and ethical/regulatory frameworks. Priority was given to high-quality randomized trials, systematic reviews, and expert consensus statements. Results: AI-supported platforms—including remote blood pressure monitoring, machine learning titration algorithms, and digital twins—have demonstrated early promise in improving hypertension control. Explainable AI (XAI) is critical for clinician trust and integration into decision-making. Equity-focused design and regulatory oversight are essential to prevent exacerbation of health disparities. Emerging implementation strategies, such as federated learning and co-design frameworks, may enhance scalability and generalizability across diverse care settings. Conclusions: AI-guided titration and digital twin approaches appear most promising for reducing therapeutic inertia, whereas cuffless blood pressure monitoring remains the least mature. Future work should prioritize pragmatic trials with equity and cost-effectiveness endpoints, supported by safeguards against bias, accountability gaps, and privacy risks. Full article

The extensive deployment of diverse sensors in hospitals has resulted in the collection of various medical time-series data. However, these real-world medical time-series data suffer from limited volume, poor data quality, and privacy concerns, resulting in performance degradation in downstream tasks, such as medical research and clinical decision-making. Existing studies provide generated medical data as a supplement or alternative to real-world data. However, medical time-series data are inherently complex, including temporal data such as laboratory measurements and static event data such as demographics and clinical outcomes, with each patient’s temporal data being influenced by their static event data. This intrinsic complexity makes the generation of high-quality medical time-series data particularly challenging. Traditional methods typically employ Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs), but these methods struggle to generate high-quality static event data of medical time-series data and often lack interpretability. Currently, large language models (LLMs) introduce new opportunities for medical data generation, but they face difficulties in generating temporal data and have challenges in specific domain generation tasks. In this study, we are the first to propose an LLM-based framework for modularly generating medical time-series data, QAMT, which generates quality-assured data and ensures the interpretability of the generation process. QAMT constructs a reliable health knowledge graph to provide medical expertise to the LLMs and designs dual modules to simultaneously generate static event data and temporal data, constituting high-quality medical time-series data. Moreover, QAMT introduces a quality assurance module to evaluate the generated data. Unlike existing methods, QAMT preserves the interpretability of the data generation process. Experimental results show that QAMT can generate higher-quality time-series medical data compared with existing methods. Full article

Aim: Hostile aortic neck anatomy—characterized by short neck length, severe angulation, conical shape, and mural thrombus or calcifications—represents a major limitation to the durability and applicability of standard endovascular aneurysm repair (EVAR). In response to these challenges, newer endografts with improved conformability have been developed. This study aimed to evaluate the mid-term outcomes of EVAR using the GORE EXCLUDER Conformable AAA Endoprosthesis (CEXC) (W.L. Gore & Associates Inc., Flagstaff, AZ, USA) in patients with hostile neck anatomy, with specific attention to type III endoleak occurrence, aortic sac remodeling, and maintenance of distal sealing. Methods: A retrospective observational analysis was conducted on 50 consecutive patients treated with the CEXC endograft between October 2019 and September 2023. Patients included had either elective or urgent indications for EVAR and were evaluated preoperatively using CT angiography. Hostile neck criteria were defined according to the 2019 Delphi Consensus. Procedural variables, imaging follow-up, and clinical outcomes were collected. The primary endpoints were technical and clinical success, while secondary outcomes included endoleak rates, aneurysm sac evolution, and reintervention-free survival. Results: Technical success was achieved in 100% of cases, with a clinical success rate of 98%. No type Ia, Ib, or III endoleaks were observed at a median follow-up of 23 months. Sac shrinkage (>5 mm reduction) occurred in 70% of patients, and distal sealing was preserved in 100% of cases. One perioperative death occurred in an emergency setting, and no late reinterventions or aneurysm-related mortalities were reported. The use of intravascular ultrasound (IVUS) and floppy guidewires contributed to precise deployment and sealing in angulated anatomies. Conclusions: The CEXC endograft proved to be a safe and effective option for EVAR in patients with hostile aortic anatomy, ensuring durable proximal and distal sealing, promoting favorable sac remodeling, and preventing type III endoleaks. These findings support the use of CEXC in anatomically complex settings, as long as procedures are meticulously planned and guided by appropriate intraoperative imaging and deployment techniques. Full article

Glucose-6-phosphate dehydrogenase (G6PD) deficiency is a common enzymopathy with significant clinical implications, particularly in malaria-endemic regions and in the management of neonatal hyperbilirubinemia. Timely and accurate detection of G6PD deficiency is critical to prevent life-threatening hemolytic events following oxidative drug administration. This study evaluated the MyG6PD device, a quantitative point-of-care (PoC) tool, for the assessment of hemoglobin concentration and G6PD enzyme activity. Analytical performance was benchmarked against laboratory spectrophotometry and the STANDARD G6PD Analyzer™ (SD Biosensor; Suwon-si, Republic of Korea). MyG6PD demonstrated excellent linearity (R² ≥ 0.99), accuracy (bias < ±15%), and precision (CV < 15%) across normal, intermediate, and deficient activity ranges, including heterozygous females with intermediate phenotypes. The device’s compact, battery-operated design, rapid turnaround, and minimal training requirements support its use in decentralized and resource-limited settings. Furthermore, cost-effective consumables and robust detection of intermediate activity highlight its potential for large-scale deployment. Overall, MyG6PD provides a reliable, accessible, and clinically actionable solution for urgent G6PD deficiency screening, enabling safer administration of oxidative therapies and improving patient outcomes in high-risk populations. Full article

This study investigates on-edge seizure detection that aims to resolve two major constraints that hold the deployment of deep learning models in clinical settings at present. First, centralized training requires gathering and consolidating data across institutions, which poses a serious issue of privacy. Second, a high computational overhead inherent in inference imposes a crushing burden on resource-limited edge devices. Hence, we propose NeuroFed-LightTCN, a federated learning (FL) framework, incorporating a lightweight temporal convolutional network (TCN), designed for resource-efficient and privacy-preserving seizure detection. The proposed framework integrates depthwise separable convolutions, grouped with structured pruning to enhance efficiency, scalability, and performance. Furthermore, asynchronous aggregation is employed to mitigate training overhead. Empirical tests demonstrate that the network can be reduced fully to 70% with a 44.9% decrease in parameters (65.4 M down to 34.9 M and an inferencing latency of 56 ms) and still maintain 97.11% accuracy, a metric that outperforms both the non-FL and FL TCN optimizations. Ablation shows that asynchronous aggregation reduces training times by 3.6 to 18%, and pruning sustains performance even at extreme sparsity: an F1-score of 97.17% at a 70% pruning rate. Overall, the proposed NeuroFed-LightTCN addresses the trade-off between computational efficiency and model performance, delivering a viable solution to federated edge-device learning. Through the interaction of federated-optimization-driven approaches and lightweight architectural innovation, scalable and privacy-aware machine learning can be a practical reality, without compromising accuracy, and so its potential utility can be expanded to the real world. Full article

Background. Severe left ventricular hypertrophy (SLVH) is a high-risk structural cardiac abnormality associated with increased risk of heart failure. It is typically assessed using echocardiography or cardiac magnetic resonance imaging, but these modalities are limited by cost, accessibility, and workflow burden. We introduce a deep learning framework that classifies SLVH directly from chest radiographs, without intermediate anatomical estimation models or demographic inputs. A key contribution of this work lies in interpretability. We quantify how clinically relevant attributes are encoded within internal representations, enabling transparent model evaluation and integration into AI-assisted workflows. Methods. We construct class-balanced subsets from the CheXchoNet dataset with equal numbers of SLVH-positive and negative cases while preserving the original train, validation, and test proportions. ResNet-18 is fine-tuned from ImageNet weights, and a Vision Transformer (ViT) encoder is pretrained via masked autoencoding with a trainable classification head. No anatomical or demographic inputs are used during training. We apply Mutual Information Neural Estimation (MINE) to quantify dependence between learned features and five attributes: age, sex, interventricular septal diameter (IVSDd), posterior wall diameter (LVPWDd), and internal diameter (LVIDd). Results. ViT achieves an AUROC of 0.82 [95% CI: 0.78–0.85] and an AUPRC of 0.80 [95% CI: 0.76–0.85], indicating strong performance in SLVH detection from chest radiographs. MINE reveals clinically coherent attribute encoding in learned features: age > sex > IVSDd > LVPWDd > LVIDd. Conclusions. This study shows that SLVH can be accurately classified from chest radiographs alone. The framework combines diagnostic performance with quantitative interpretability, supporting reliable deployment in triage and decision support. Full article