Search Results (2,745)

Evaluating the difficulty of endotracheal intubation during pre-anesthesia assessment has consistently posed a challenge for clinicians. Accurate prediction of intubation difficulty is crucial for subsequent treatment planning. However, existing diagnostic methods often suffer from low accuracy. To tackle this issue, this study presented an automated airway classification method utilizing Convolutional Neural Networks (CNNs). We proposed Adaptive Attention DenseNet for Laryngeal Ultrasound Classification (AdaDenseNet-LUC), a network architecture that enhances classification performance by integrating an adaptive attention mechanism into DenseNet (Dense Convolutional Network), enabling the extraction of deep features that aid in difficult airway classification. This model associates laryngeal ultrasound images with actual intubation difficulty, providing healthcare professionals with scientific evidence to help improve the accuracy of clinical decision-making. Experiments were performed on a dataset of 1391 ultrasound images, utilizing 5-fold cross-validation to assess the model’s performance. The experimental results show that the proposed method achieves a classification accuracy of 87.41%, sensitivity of 86.05%, specificity of 88.59%, $F_1$ score of 0.8638, and AUC of 0.94. Grad-CAM visualization techniques indicate that the model’s attention is attention to the tracheal region. The results demonstrate that the proposed method outperforms current approaches, delivering objective and accurate airway classification outcomes, which serve as a valuable reference for evaluating the difficulty of endotracheal intubation and providing guidance for clinicians. Full article

This paper addresses the critical need for efficient energy management in healthcare facilities, where fluctuating energy demands pose challenges to both operational reliability and sustainability objectives. Traditional energy management approaches often fall short in healthcare settings, resulting in inefficiencies and increased operational costs. To address this gap, the paper explores AI-driven methods for demand forecasting and load balancing and proposes an integrated framework combining Long Short-Term Memory (LSTM) networks, a genetic algorithm (GA), and SHAP (Shapley Additive Explanations), specifically tailored for healthcare energy management. While LSTM has been widely applied in time-series forecasting, its use for healthcare energy demand prediction remains relatively underexplored. In this study, LSTM is shown to significantly outperform conventional forecasting models, including ARIMA and Prophet, in capturing complex and non-linear demand patterns. Experimental results demonstrate that the LSTM model achieved a Mean Absolute Error (MAE) of 21.69, a Root Mean Square Error (RMSE) of 29.96, and an R² of approximately 0.98, compared to Prophet (MAE: 59.78, RMSE: 81.22, R² ≈ 0.86) and ARIMA (MAE: 87.73, RMSE: 125.22, R² ≈ 0.66), confirming its superior predictive performance. The genetic algorithm is employed both to support forecasting optimisation and to enhance load balancing strategies, enabling adaptive energy allocation under dynamic operating conditions. Furthermore, SHAP analysis is used to provide interpretable, within-model insights into feature contributions, improving transparency and trust in AI-driven energy decision-making. Overall, the proposed LSTM–GA–SHAP framework improves forecasting accuracy, supports efficient energy utilisation, and contributes to sustainability in healthcare environments. Future work will explore real-time deployment and further integration with reinforcement learning to enable continuous optimisation. Full article

Machine Learning (ML) and Deep Learning (DL) have shown significant promise in healthcare, particularly in medical image segmentation, which is crucial for accurate disease diagnosis and treatment planning. Despite their potential, challenges such as data privacy concerns, limited annotated data, and inadequate training data persist. Decentralized learning approaches such as federated learning (FL), split learning (SL), and split federated learning (SplitFed/SFL) address these issues effectively. This paper introduces “MedSegNet10,” a publicly accessible repository designed for medical image segmentation using split-federated learning. MedSegNet10 provides a collection of pre-trained neural network architectures optimized for various medical image types, including microscopic images of human blastocysts, dermatoscopic images of skin lesions, and endoscopic images of lesions, polyps, and ulcers. MedSegNet10 implements SplitFed versions of ten established segmentation architectures, enabling collaborative training without centralizing raw data and labels, reducing the computational load required at client sites. This repository supports researchers, practitioners, trainees, and data scientists, aiming to advance medical image segmentation while maintaining patient data privacy. Full article

Objective: To evaluate the clinical success outcomes and risk factors associated with dental implants placed with simultaneous bone augmentation in a large-scale, real-world cohort. Methods: A retrospective analysis was conducted on 158,824 implants, including 45,715 Dental Bone Grafts, placed between 2014 and 2022 within a national healthcare network. Multivariate Generalized Estimating Equations were utilized to assess the impact of demographic, anatomical, and procedural variables on implant failure. Results: The augmented cohort demonstrated a high clinical success rate of 97.83% (2.17% failure), statistically comparable to the general implant population. Failures were predominantly early (<1 year), accounting for 70% of losses. Significant independent risk factors included immediate implant placement (3.08% failure vs. 2.07% for delayed), male gender, and maxillary location. Notably, low socioeconomic status (SES) emerged as a significant predictor, with a failure rate of 3.07% compared to 2.06% in high-SES groups. Conclusions: Simultaneous bone augmentation is a predictable modality that does not inherently increase implant failure risk, supporting the stabilization hypothesis. However, failure is modulated by specific variables. The identification of lower SES, male gender, and immediate placement as significant risk indicators highlights the necessity for personalized risk assessment and targeted protocols to optimize outcomes in augmented sites. Full article

Healthcare has been fundamentally changed by the expansion of IoT, which enables advanced diagnostics and continuous monitoring of patients outside clinical settings. Frequently interconnected medical devices often encounter resource limitations and lack comprehensive security safeguards. Therefore, such devices are prone to intrusions, with DDoS attacks in particular threatening the integrity of vital infrastructure. To safe guard sensitive patient information and ensure the integrity and confidentiality of medical devices, this article explores the critical importance of robust security measures in healthcare IoT systems. In order to detect DDoS attacks in healthcare networks supported by WBSN-enabled IoT devices, we propose a hybrid detection model. The model utilizes the advantages of Long Short-Term Memory (LSTM) networks for modeling temporal dependencies in network traffic and Convolutional Neural Networks (CNNs) for extracting spatial features. The effectiveness of the model is demonstrated by simulation results on the CICDDoS2019 datasets, which indicate a detection accuracy of 99% and a loss of 0.05%, respectively. The evaluation results highlight the capability of the hybrid model to reliably detect potential anomalies, showing superior performance over leading contemporary methods in healthcare environments. Full article

Background: Glaucoma is an age-related optic neuropathy frequently accompanied by systemic comorbidities. Vitamin D deficiency (VDD) has been associated with cardiovascular and renal diseases in the general population, yet its relationship with long-term systemic outcomes in glaucoma remains unclear. This study evaluated the association between baseline vitamin D status and subsequent mortality and cardiorenal events in patients with primary glaucoma. Methods: We conducted a retrospective cohort study using deidentified electronic health records from the TriNetX U.S. Collaborative Network, a federated network of participating healthcare organizations. Adults (≥18 years) with incident primary glaucoma (2005–2020) and a serum 25-hydroxyvitamin D (25(OH)D) test within 12 months prior to diagnosis were categorized as VDD (<30 ng/mL) or vitamin D adequacy (VDA; ≥30 ng/mL). After 1:1 propensity score matching across 47 demographic, clinical, medication, and laboratory variables, 11,855 patients per group were followed for up to 5 years. Outcomes included all-cause mortality, major adverse cardiovascular events (MACE), acute kidney injury (AKI), and renal function decline (eGFR < 60 mL/min/1.73 m²). Analyses incorporated Kaplan–Meier curves, Cox models, landmark tests, sensitivity analyses, and competing risk methods. Results: Among the 35,100 eligible patients, the matched cohorts demonstrated higher 5-year risks associated with VDD for all-cause mortality (HR 1.104; 95% CI 1.001–1.217), MACE (HR 1.151; 95% CI 1.078–1.229), and AKI (HR 1.154; 95% CI 1.056–1.261), whereas the risks of renal function decline did not differ (HR 0.972; 95% CI 0.907–1.042). Risk divergence emerged within the first year of follow-up and persisted through the 5-year observation period. Conclusions: In patients with primary glaucoma, vitamin D deficiency was associated with higher long-term risks of mortality and cardiorenal complications, but not renal function decline. Taken together, the results are consistent with vitamin D status serving as a marker of broader systemic vulnerability in glaucoma and highlight the need for prospective studies to further clarify its prognostic significance. Full article

Even though environmental health and climate change are rapidly intensifying the severity of determinants of disease and inequity, training for health professionals in these areas remains fragmented across Europe. To address this gap, the European Medical Association (EMA), in collaboration with the European Network on Climate and Health Education (ENCHE), the International Network on Public Health and Environment Tracking (INPHET) and University College London, convened a one-day hybrid roundtable in London on 17 September 2025, focused on “Preparing Health Professionals for Environmental Health and Climate Change: A Challenge for Europe”. The programme combined keynote presentations on global and European policy, health economics and curriculum design with three disease-focused roundtables (respiratory, cardiovascular and neurological conditions), each examining the following topics: (A) climate and environment as preventable causes of disease; (B) healthcare as a source of environmental harm; and (C) capacity building through education and training. Contributors highlighted how environmental epidemiology, community-based prevention programmes and sustainable clinical practice can be integrated into teaching, illustrating models from respiratory, cardiovascular, surgical and neurological care. EU-level speakers outlined the policy framework (European Green Deal, Zero Pollution Action Plan and forthcoming global health programme) and tools through which professional and scientific societies can both inform and benefit from European action on environment and health. Discussions converged on persistent obstacles, including patchy national commitments to decarbonising healthcare, isolated innovations that are not scaled and curricula that do not yet embed sustainability in examinable clinical competencies. The conference concluded with proposals to develop an operational education package on environmental and climate health; map and harmonise core competencies across undergraduate, postgraduate and Continuing -professional-development pathways; and establish a permanent EMA-led working group to co-produce a broader position paper with professional and scientific societies. This conference report summarises the main messages and is intended as a bridge between practice-based experience and a formal EMA position on environmental-health training in Europe. Full article

Background: Black and racialized immigrants with disabilities in Canada face overlapping systems of exclusion rooted in racism, ableism, and migration status. Yet, their experiences within health and rehabilitation services during the COVID-19 pandemic remain largely undocumented. This study explores how structural inequities shaped access to healthcare, rehabilitation, information, and community supports in the Greater Toronto and Hamilton Area (GTHA). Methods: Using narrative inquiry, ten in-depth interviews were conducted with participants who identified as Black or racialized, disabled, and having immigrated to Canada within the last 10 years. Narratives were analyzed through reflexive thematic analysis to identify how systems, relationships, and policies interacted to shape daily life, health and rehabilitation navigation during the pandemic. Results: Participants described systemic barriers in health and rehabilitation systems, experiences of “othering” and conditional belonging, and the critical role of informal and faith-based networks in navigating inaccessible services. Pandemic policies often intensified existing inequities. Conclusions: Findings underscore the need for intersectional health and rehabilitation planning that centers the voices of Black and racialized disabled immigrants. Addressing systemic racism and ableism is essential for equitable preparedness in future public health emergencies. Full article

This work presents the development and evaluation of Artificial Intelligence (AI) models for the automatic classification of brain tumors in Magnetic Resonance Imaging (MRI) scans. Several deep learning architectures were implemented and compared, including VGG-19, ResNet50, EfficientNetB3, Xception, MobileNetV2, DenseNet201, InceptionV3, Vision Transformer (ViT), and an Ensemble model. The models were developed in Python (version 3.12.4) using the Keras and TensorFlow frameworks and trained on a public Brain Tumor MRI dataset containing 7023 images. Data augmentation and hyperparameter optimization techniques were applied to improve model generalization. The results showed high classification performance, with accuracies ranging from 89.47% to 98.17%. The Vision Transformer achieved the best performance, reaching 98.17% accuracy, outperforming traditional Convolutional Neural Network (CNN) architectures. Explainable AI (XAI) methods Grad-CAM, LIME, and Occlusion Sensitivity were employed to assess model interpretability, showing that the models predominantly focused on tumor regions. The proposed approach demonstrated the effectiveness of AI-based systems in supporting early diagnosis of brain tumors, reducing analysis time and assisting healthcare professionals. Full article

In the context of the rapid growth of the Internet of Things and mobile health services, sensors and smart wearable devices are continuously collecting and uploading dynamic health data. Together with the long-term accumulated electronic medical records and multi-source heterogeneous clinical data from healthcare institutions, these data form the cornerstone of intelligent healthcare. In the context of medical data sharing, previous studies have mainly focused on privacy protection and secure data transmission, while relatively few have addressed the issue of incentive mechanisms. However, relying solely on technical means is insufficient to solve the problem of individuals’ willingness to share their data. To address this challenge, this paper proposes a three-party Stackelberg-game-based incentive mechanism for medical data sharing. The mechanism captures the hierarchical interactions among the intermediator, electronic device users, and data consumers. In this framework, the intermediator acts as the leader, setting the transaction fee; electronic device users serve as the first-level followers, determining the data price; and data consumers function as the second-level followers, deciding on the purchase volume. A social network externality is incorporated into the model to reflect the diffusion effect of data demand, and the optimal strategies and system equilibrium are derived through backward induction. Theoretical analysis and numerical experiments demonstrate that the proposed mechanism effectively enhances users’ willingness to share data and improves the overall system utility, achieving a balanced benefit among the cloud platform, electronic device users, and data consumers. This study not only enriches the game-theoretic modeling approaches to medical data sharing but also provides practical insights for designing incentive mechanisms in IoT-based healthcare systems. Full article

The COVID-19 pandemic has highlighted the importance of rapid clinical decision-making to facilitate the efficient usage of healthcare resources. Over the past decade, machine learning (ML) has caused a tectonic shift in healthcare, empowering data-driven prediction and decision-making. Recent research demonstrates how ML was used to respond to the COVID-19 pandemic. This paper puts forth new computer-aided COVID-19 disease screening techniques using six classes of ML algorithms (including penalized logistic regression, random forest, artificial neural networks, and support vector machines) and evaluates their performance when applied to a real-world clinical dataset containing patients’ demographic information and vital indices (such as sex, ethnicity, age, pulse, pulse oximetry, respirations, temperature, BP systolic, BP diastolic, and BMI), as well as ICD-10 codes of existing comorbidities, as attributes to predict the risk of having COVID-19 for given patient(s). Variable importance metrics computed using a random forest model were used to reduce the number of important predictors to thirteen. Using prediction accuracy, sensitivity, specificity, and AUC as performance metrics, the performance of various ML methods was assessed, and the best model was selected. Our proposed model can be used in clinical settings as a rapid and accessible COVID-19 screening technique. Full article

In dense Wireless Body Area Network (WBAN) environments, inter-network interference significantly degrades the reliability of medical data transmission. This paper proposes a novel MAC layer interference mitigation strategy that integrates interference-priority-weighted K-means++ clustering with graph-coloring-based time slot allocation. Unlike traditional coexistence schemes, our two-phase approach first partitions the network using a weighted metric combining physical distance and Interference Signal Strength (ISS), ensuring a balanced distribution of high-priority WBANs. Subsequently, we employ an enhanced Priority-Weighted Welch–Powell algorithm to assign collision-free time slots within each cluster. Simulation results demonstrate that the proposed strategy outperforms IEEE 802.15.4, CSMA/CA, and random coloring benchmarks. It reduces inter-network interference by 26.7%, improves priority node distribution balance by 65.7%, and maintains a transmission success rate above 80% under high-load conditions. The proposed method offers a scalable and low-complexity solution for reliable vital sign monitoring in crowded healthcare scenarios. Full article

Human Activity Recognition (HAR) using wearable sensors enables impactful applications in healthcare, fitness, and smart environments, but it also faces challenges related to data privacy, non-independent and identically distributed (non-IID) data, and limited computational resources on edge devices. This study proposes an efficient and personalized federated learning (PFL) framework for HAR that integrates federated training with model compression and per-client fine-tuning to address these challenges and support deployment on resource-constrained devices (RCDs). A convolutional neural network (CNN) is trained across multiple clients using FedAvg, followed by magnitude-based pruning and float16 quantization to reduce model size. While personalization and compression have previously been studied independently, their combined application for HAR remains underexplored in federated settings. Experimental results show that the global FedAvg model experiences performance degradation under non-IID conditions, which is further amplified after pruning, whereas per-client personalization substantially improves performance by adapting the model to individual user patterns. To ensure realistic evaluation, experiments are conducted using both random and temporal data splits, with the latter mitigating temporal leakage in time-series data. Personalization consistently improves performance under both settings, while quantization reduces the model footprint by approximately 50%, enabling deployment on wearable and IoT devices. Statistical analysis using paired significance tests confirms the robustness of the observed performance gains. Overall, this work demonstrates that combining lightweight model compression with personalization providing an effective and practical solution for federated HAR, balancing accuracy, efficiency, and deployment feasibility in real-world scenarios. Full article

IoT-based blockchain technology has improved the healthcare system to ensure the privacy and security of healthcare data. A Blockchain Bridge (BB) is a tool that enables multiple blockchain networks to communicate with each other. The existing approach combining the classical and quantum blockchain models failed to secure the data transmission during cross-chain communication. Thus, this study proposes a new BB verification for secure healthcare data transfer. Additionally, a brain tumor analysis framework is developed based on segmentation and neural networks. After the patient’s registration on the blockchain network, Brain Magnetic Resonance Imaging (MRI) data is encrypted using Hash-Keyed Quantum Cryptography and verified using a Peer-to-Peer Exchange model. The Brain MRI is preprocessed for brain tumor detection using the Fuzzy HaMan C-Means (FHMCM) segmentation technique. The features are extracted from the segmented image and classified using the LeCun Kaiming-based Convolutional ModSwish Neural Network (LCK-CMSNN) classifier. Subsequently, the brain tumor diagnosis report is securely transferred to the patient via a smart contract. The proposed model verified BB with a Verification Time (VT) of 12,541 ms, secured the input with a Security level (SL) of 98.23%, and classified the brain tumor with 99.15% accuracy, thus showing better performance than the existing models. Full article

Background: Zoonotic spillover events with pandemic potential are increasingly associated with environmental change, ecosystem disruption, and intensified human–animal interactions. Although the specific origin and timing of future pandemics remain uncertain, there is a clear need to complement traditional preparedness strategies with approaches that support earlier anticipation and prevention. Objectives: This study aims to propose a conceptual approach to reframe pandemic preparedness toward proactive surveillance and spillover prevention. Methods: We introduce a tachyon-inspired conceptual approach, using a thought experiment based on hypothetical faster-than-light particles to illustrate anticipatory observation of pandemic emergence. The framework is informed by interdisciplinary literature on emerging infectious diseases, One Health surveillance, predictive epidemiology, and public-health preparedness. Results: The proposed approach highlights the importance of proactive, integrated surveillance systems that combine human, animal, and environmental data. Key elements include the use of advanced analytical tools such as neural networks, early characterization of population risk profiles, strengthened public-health infrastructure, coordinated governance, adaptable financial resources, and a resilient healthcare workforce. The integration of animal welfare considerations, translational research, and planetary health principles is emphasized as central to reducing spillover risk. Conclusions: Tachyon-inspired thinking offers a conceptual tool to support a shift from reactive pandemic response toward proactive anticipation and prevention. Embedding integrated surveillance and One Health principles into public-health systems may enhance early detection capacity and contribute to mitigating the impact of future pandemics. Full article