Search Results (1,235)

In time series analysis, the ability to effectively handle data with varying sampling rates is crucial for accurate modeling and analysis. This paper presents the MR-BoF (Multi-Resolution Bag of Functions) framework, which leverages sampling-rate-independent techniques to decompose time series data while accommodating signals with differing resolutions. Unlike traditional methods that require uniform sampling frequencies, the BoF framework employs a flexible encoding approach, allowing for the integration of multi-resolution time series. Through a series of experiments, we demonstrate that the BoF framework ensures the precise reconstruction of the original data while enhancing resampling capabilities by utilizing decomposed components. The results show that this method offers significant advantages in scenarios involving irregular sampling rates and heterogeneous acquisition systems, making it a valuable tool for applications in fields such as finance, healthcare, industrial monitoring, IoT networks, and sensor networks. Full article

Background/Objectives: Antibiotic use is common among hospitalized pediatric patients. However, inappropriate use, including excessive use of Watch antibiotics, can contribute to antimicrobial resistance, adverse events, and increased healthcare costs. Consequently, there is a need to continually assess their usage among this vulnerable population. This was the objective behind this study. Methods: The medical records of all pediatric patients (under 12 years) admitted and treated with antibiotics at a Ghanaian Teaching Hospital between January 2022 and March 2022 were extracted from the hospital’s electronic database. The prevalence and appropriateness of antibiotic use were based on antibiotic choices compared with current guidelines. Influencing factors were also assessed. Results: Of the 410 admitted patients, 319 (77.80%) received at least one antibiotic. The majority (68.65%; n = 219/319) were between 0 and 2 years, and males (54.55%; n = 174/319). Ceftriaxone was the most commonly prescribed antibiotic (20.69%; n = 66/319), and most of the systemic antibiotics used belonged to the WHO Access and Watch groups, including a combination of Access and Watch groups (42.90%; n = 136/319). Neonatal sepsis (24.14%; n = 77/319) and pneumonia (14.42%; n = 46/319) were the most common diagnoses treated with antibiotics. Antibiotic appropriateness was 42.32% (n = 135/319). Multivariate analysis revealed ceftriaxone prescriptions (aOR = 0.12; CI = 0.02–0.95; p-value = 0.044) and surgical prophylaxis (aOR = 0.07; CI = 0.01–0.42; p-value = 0.004) were associated with reduced antibiotic appropriateness, while a pneumonia diagnosis appreciably increased this (aOR = 15.38; CI = 3.30–71.62; p-value < 0.001). Conclusions: There was high and suboptimal usage of antibiotics among hospitalized pediatric patients in this leading hospital. Antibiotic appropriateness was influenced by antibiotic type, diagnosis, and surgical prophylaxis. Targeted interventions, including education, are needed to improve antibiotic utilization in this setting in Ghana and, subsequently, in ambulatory care. Full article

The exponential increase in textual data generated across sectors such as healthcare, finance, and smart manufacturing has intensified the need for effective Big Data analytics. Large language models (LLMs) have become critical tools because of their advanced language processing capabilities. However, their static nature limits their ability to incorporate real-time and domain-specific knowledge. Retrieval-augmented generation (RAG) addresses these limitations by enriching LLM outputs through external content retrieval. Nevertheless, traditional RAG systems remain inefficient, often exhibiting high retrieval latency, redundancy, and diminished response quality when scaled to large datasets. This paper proposes an innovative structured RAG framework specifically designed for large-scale Big Data analytics. The framework transforms unstructured partial prompts into structured semantically coherent partial prompts, leveraging element-specific embedding models and dimensionality reduction techniques, such as principal component analysis. To further improve the retrieval accuracy and computational efficiency, we introduce a multi-level filtering approach integrating semantic constraints and redundancy elimination. In the experiments, the proposed method was compared with structured-format RAG. After generating prompts utilizing two methods, silhouette scores were computed to assess the quality of embedding clusters. The proposed method outperformed the baseline by improving the clustering quality by 32.3%. These results demonstrate the effectiveness of the framework in enhancing LLMs for accurate, diverse, and efficient decision-making in complex Big Data environments. Full article

The development of big data analytics in healthcare has created a demand for privacy-conscious and scalable machine learning algorithms that can allow the use of patient information across different healthcare organizations. In this study, the difficulties that come with traditional federated learning frameworks in healthcare sectors, such as scalability, computational effectiveness, and preserving patient privacy for numerous healthcare systems, are discussed. In this work, a new conceptual model known as Hierarchical Federated Learning (HFL) for large, integrated healthcare organizations that include several institutions is proposed. The first level of aggregation forms regional centers where local updates are first collected and then sent to the second level of aggregation to form the global update, thus reducing the message-passing traffic and improving the scalability of the HFL architecture. Furthermore, the HFL framework leveraged more robust privacy characteristics such as Local Differential Privacy (LDP), Gaussian Differential Privacy (GDP), Secure Multi-Party Computation (SMPC) and Homomorphic Encryption (HE). In addition, a Novel Aggregated Gradient Perturbation Mechanism is presented to alleviate noise in model updates and maintain privacy and utility. The performance of the proposed HFL framework is evaluated on real-life healthcare datasets and an artificial dataset created using Generative Adversarial Networks (GANs), showing that the proposed HFL framework is better than other methods. Our approach provided an accuracy of around 97% and 30% less privacy leakage compared to the existing models of FLBM-IoT and PPFLB. The proposed HFL approach can help to find the optimal balance between privacy and model performance, which is crucial for healthcare applications and scalable and secure solutions. Full article

Background/Objectives: Access to health services is often limited due to socio-economic and organizational determinants of health systems, which lead to increased unmet healthcare needs. This study aimed to identify access barriers for the general population in Greece, including those that may have emerged following the COVID-19 pandemic. Methods: This was a cross-sectional survey of 1002 Greek citizens. A questionnaire regarding socio-demographics, healthcare utilization, and access to health services was used. Interviews took place between October and November 2022. Results: Of 837 participants who used health services in 2022, 82.6% had a medical consultation, 80.6% took diagnostic tests, and 63.6% visited a pharmacy for pharmaceuticals. Of those having a medical consultation, 33.1% did so at an NHS health unit, while 75% of the participants taking diagnostic tests visited a contracted private laboratory. Out of the 135 participants requiring hospitalization, 62% were hospitalized in a public hospital, while 85% of the participants requiring pharmaceuticals visited a private pharmacy. Access barriers in the past year were reported by 48% of the participants requiring a medical consultation, 34% of the participants requiring diagnostic tests, and 40% of the participants requiring hospitalization. The most common barriers were long waiting times and financial constraints. The main barrier to accessing pharmaceuticals was the availability and administration of the product. Conclusions: The identified healthcare access barriers highlight the vulnerabilities of the current health system in Greece, which were further exposed during the COVID-19 pandemic crisis. Addressing socioeconomic factors that are considered key access indicators should be the focus of future health policy initiatives. Full article

Surgery remains a healthcare intervention with significant risks for patients. Novel technologies can now enhance the peri-operative workflow, with artificial intelligence (AI) and extended reality (XR) to assist with pre-operative planning. This review focuses on innovation in AI, XR and imaging for hepato-biliary surgery planning. The clinical challenges in hepato-biliary surgery arise from heterogeneity of clinical presentations, the need for multiple imaging modalities and highly variable local anatomy. AI-based models have been developed for risk prediction and multi-disciplinary tumor (MDT) board meetings. The future could involve an on-demand and highly accurate AI-powered decision tool for hepato-biliary surgery, assisting the surgeon to make the most informed decision on the treatment plan, conferring the best possible outcome for individual patients. Advances in AI can also be used to automate image interpretation and 3D modelling, enabling fast and accurate 3D reconstructions of patient anatomy. Surgical navigation systems utilizing XR are already in development, showing an early signal towards improved patient outcomes when used for hepato-biliary surgery. Live visualization of hepato-biliary anatomy in the operating theatre is likely to improve operative safety and performance. The technological advances in AI and XR provide new applications in pre-operative planning with potential for patient benefit. Their use in surgical simulation could accelerate learning curves for surgeons in training. Future research must focus on standardization of AI and XR study reporting, robust databases that are ethically and data protection-compliant, and development of inter-disciplinary tools for various healthcare applications and systems. Full article

Many hospitals still lack digital traceability in hygiene and cleaning management, leading to operational inefficiencies and inconsistent quality control. This study aims to establish cleaning and hygiene processes in healthcare services that are planned in accordance with standards, as well as to enhance the traceability and sustainability of these processes through digitalization. This study proposes a Hyperledger Fabric-based blockchain architecture to establish a reliable and transparent quality assurance system in process management. The proposed Quality Assurance Model utilizes digital technologies and IoT-based RFID devices to ensure the transparent and reliable monitoring of cleaning processes. Operational data related to cleaning processes are automatically recorded and secured using a decentralized blockchain infrastructure. The permissioned nature of Hyperledger Fabric provides a more secure solution compared to traditional data management systems in the healthcare sector while preserving data privacy. Additionally, the execute–order–validate mechanism supports effective data sharing among stakeholders, and consensus algorithms along with chaincode rules enhance the reliability of processes. A working prototype was implemented and validated using Hyperledger Caliper under resource-constrained cloud environments, confirming the system’s feasibility through over 100 TPS throughput and zero transaction failures. Through the proposed system, cleaning/hygiene processes in patient rooms are conducted securely, contributing to the improvement of quality standards in healthcare services. Full article

Background: Antinuclear antibodies (ANAs) serve as crucial biomarkers for diagnosing systemic autoimmune diseases; however, their interpretation can be complex and may not always correlate with clinical symptoms. Methods: A comprehensive narrative review was conducted to evaluate the peer-reviewed literature published between 1961 and 2025. Databases, including PubMed and Scopus, were searched using combinations of controlled vocabulary and free-text terms relating to antinuclear antibodies and their clinical significance. The objective was to gather and synthesize information regarding the diagnostic utility and interpretation of ANA testing in routine medical practice. Discussion: The indirect immunofluorescence assay (IIF) on HEp-2 cells is established as the gold standard for detecting ANAs, facilitating the classification of various fluorescent patterns. While a positive ANA test can suggest autoimmune disorders, the presence and titre must be interpreted alongside clinical findings, as low titres often lack diagnostic significance. Findings indicate that titres higher than 1:160 may provide greater specificity in differentiating true positives from false positives in healthy individuals. The study also emphasizes the relevance of fluorescence patterns, with specific patterns linked to particular diseases, although many do not have strong clinical correlations. Moreover, certain autoantibodies demonstrate high specificity for diseases like systemic lupus erythematosus (SLE) and mixed connective tissue disease (MCTD). Ultimately, while ANA testing is invaluable for diagnosing connective tissue diseases, healthcare providers must consider its limitations to avoid misdiagnosis and unnecessary treatment. Conclusions: ANA testing is a valuable tool in the diagnosis of connective tissue diseases, but its interpretation must be approached with caution. Clinical context remains crucial when evaluating ANA results to avoid misdiagnosis and overtreatment. This review is about the diagnostic aspects and clinical consequences of ANA testing, as well as highlighting both the diagnostic benefits and the potential limitations of this procedure in everyday clinical practice. The review fills a gap in the literature by integrating the diagnostic and clinical aspects of ANA testing, with a focus on real-world interpretation challenges. Full article

Background: Parents of children with type 1 diabetes play a key role in managing their child’s self-management, which can be stressful and burdensome. High involvement can lead to reactions such as emotional, cognitive, and physical exhaustion in parents. Understanding parents’ psychosocial impact due to their child’s disease is crucial for the family’s overall well-being. The purpose of this study was to describe stress and burden experienced by parents in families with children living with type 1 diabetes. Methods: This study utilized a qualitative approach, analyzing interviews with 16 parents of children aged 10 to 17 years living with T1D through qualitative content analysis. The data collection occurred between January and February 2025. Results: Managing a child’s Type 1 diabetes can be tough on family relationships, affecting how partners interact, intimacy, and sibling relationships. The constant stress and worry might leave parents feeling exhausted, unable to sleep, and struggling to think clearly, on top of the pain of losing a normal everyday life. The delicate balance between allowing a child with type 1 diabetes to be independent and maintaining control over their self-management renders these challenges even more demanding for the parents. Conclusions: Parents’ experiences highlight the need for robust support systems, including dependable school environments, trustworthy technical devices, reliable family and friends, and accessible healthcare guidance. These elements are essential not only for the child’s health and well-being but also for alleviating the emotional and practical burdens parents face. Full article

Background/Objective(s): Post-discharge clinical needs of extremely preterm (EP) infants are not well defined. The aim of this study is to evaluate healthcare utilization after discharge in infants born EP and compare it to the general pediatric population. Methods: This study involved a post hoc analysis of infants born 24-0/7 to 27-6/7 weeks’ gestation enrolled in the Preterm Erythropoietin Neuroprotection (PENUT) Trial who had at least one follow-up survey representing their course between 24 and 60 months of age. The results were compared to the general population data from the Kids’ Inpatient Database, Nationwide Emergency Department Sample, and National Health and Nutrition Examination Survey. Results: Maternal, infant, and hospitalization characteristics for PENUT infants who survived to discharge (n = 828) compared to those with follow-up (n = 569) were similar except for race and maternal age. Overall, EP infants had an overall lower rate of ED visits (31% vs. 68%) but a higher rate of hospitalizations (11% vs. 3%). EP infants were less likely to go to the ED for gastrointestinal (5% vs. 12%) and dermatologic (1% vs. 6%) concerns but more likely to go to the ED for procedures (7% vs. <1%). EP infants had a higher rate of medication use (56% vs. 14%) in all categories except psychiatric medications. Conclusions: While EP infants had higher rates of specialty healthcare utilization relative to the general pediatric population, they were less likely to visit the ED overall, particularly for common concerns in this age range. This may reflect improved access and navigation of the healthcare system by EP caregivers. Full article

Artificial intelligence (AI) has already played a significant role in the healthcare sector, particularly in image-based medical diagnosis. Deep learning models have produced satisfactory and useful results for accurate decision-making. Among the various types of medical images, magnetic resonance imaging (MRI) is frequently utilized in deep learning applications to analyze detailed structures and organs in the body, using advanced intelligent software. However, challenges related to performance and data privacy often arise when using medical data from patients and healthcare institutions. To address these issues, new approaches have emerged, such as federated learning. This technique ensures the secure exchange of sensitive patient and institutional data. It enables machine learning or deep learning algorithms to establish a client–server relationship, whereby specific parameters are securely shared between models while maintaining the integrity of the learning tasks being executed. Federated learning has been successfully applied in medical settings, including diagnostic applications involving medical images such as MRI data. This research introduces an analytical intelligence system based on an Internet of Medical Things (IoMT) framework that employs federated learning to provide a safe and effective diagnostic solution for brain tumor identification. By utilizing specific brain MRI datasets, the model enables multiple local capsule networks (CapsNet) to achieve improved classification results. The average accuracy rate of the CapsNet model exceeds 97%. The precision rate indicates that the CapsNet model performs well in accurately predicting true classes. Additionally, the recall findings suggest that this model is effective in detecting the target classes of meningiomas, pituitary tumors, and gliomas. The integration of these components into an analytical intelligence system that supports the work of healthcare personnel is the main contribution of this work. Evaluations have shown that this approach is effective for diagnosing brain tumors while ensuring data privacy and security. Moreover, it represents a valuable tool for enhancing the efficiency of the medical diagnostic process. Full article

Deep learning (DL) continues to play a pivotal role in a wide range of intelligent systems, including autonomous machines, smart surveillance, industrial automation, and portable healthcare technologies. These applications often demand low-latency inference and efficient resource utilization, especially when deployed on embedded or edge devices with limited computational capacity. As DL models become increasingly complex, selecting the right inference framework is essential to meeting performance and deployment goals. In this work, we conduct a comprehensive comparison of five widely adopted inference frameworks: PyTorch, ONNX Runtime, TensorRT, Apache TVM, and JAX. All experiments are performed on the NVIDIA Jetson AGX Orin platform, a high-performance computing solution tailored for edge artificial intelligence workloads. The evaluation considers several key performance metrics, including inference accuracy, inference time, throughput, memory usage, and power consumption. Each framework is tested using a wide range of convolutional and transformer models and analyzed in terms of deployment complexity, runtime efficiency, and hardware utilization. Our results show that certain frameworks offer superior inference speed and throughput, while others provide advantages in flexibility, portability, or ease of integration. We also observe meaningful differences in how each framework manages system memory and power under various load conditions. This study offers practical insights into the trade-offs associated with deploying DL inference on resource-constrained hardware. Full article

The goal of single-image super-resolution (SISR) tasks is to generate high-definition images from low-quality inputs, with practical uses spanning healthcare diagnostics, aerial imaging, and surveillance systems. Although cnns have considerably improved image reconstruction quality, existing methods still face limitations, including inadequate restoration of high-frequency details, high computational complexity, and insufficient adaptability to complex scenes. To address these challenges, we propose an Omni-dimensional Dynamic Convolutional Network (ODConvNet) tailored for SISR tasks. Specifically, ODConvNet comprises four key components: a Feature Extraction Block (FEB) that captures low-level spatial features; an Omni-dimensional Dynamic Convolution Block (DCB), which utilizes a multidimensional attention mechanism to dynamically reweight convolution kernels across spatial, channel, and kernel dimensions, thereby enhancing feature expressiveness and context modeling; a Deep Feature Extraction Block (DFEB) that stacks multiple convolutional layers with residual connections to progressively extract and fuse high-level features; and a Reconstruction Block (RB) that employs subpixel convolution to upscale features and refine the final HR output. This mechanism significantly enhances feature extraction and effectively captures rich contextual information. Additionally, we employ an improved residual network structure combined with a refined Charbonnier loss function to alleviate gradient vanishing and exploding to enhance the robustness of model training. Extensive experiments conducted on widely used benchmark datasets, including DIV2K, Set5, Set14, B100, and Urban100, demonstrate that, compared with existing deep learning-based SR methods, our ODConvNet method improves Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM), and the visual quality of SR images is also improved. Ablation studies further validate the effectiveness and contribution of each component in our network. The proposed ODConvNet offers an effective, flexible, and efficient solution for the SISR task and provides promising directions for future research. Full article

Background: Deep surgical site infections (SSIs) represent a serious complication following abdominal trauma surgery; however, comprehensive risk factor analysis in large trauma populations remains limited. Although surgical site infections are recognized as preventable complications, little is known about the specific risk factors and clinical outcomes associated with deep SSIs in trauma patients at the national level. Methods: A retrospective cohort study analyzed data from the National Trauma Data Bank from 2020–2022, including 1,198,262 trauma patients with complete demographic, injury severity, and surgical procedure data. Deep SSI development, length of hospital stay, intensive care unit utilization, duration of mechanical ventilation, discharge disposition, and in-hospital mortality were assessed. Multivariate logistic regression was used to identify independent risk factors and quantify associations between patient characteristics and deep SSI occurrence. Results: Deep SSIs occurred in 601 patients (0.05%). Affected patients were younger (median 41 vs. 54 years, p < 0.001), predominantly male (73.7% vs. 61.8%, p < 0.001), and exhibited higher injury severity scores (median 17.0 vs. 5.0, p < 0.001). Major abdominal surgery was the strongest independent predictor (OR 3.08, 95% CI: 2.21–4.23, p < 0.001), followed by injury severity score (OR 1.05, 95% CI: 1.04–1.06, p < 0.001) and ICU length of stay (OR 1.04 per day, 95% CI: 1.03–1.05, p < 0.001). Patients with deep SSIs demonstrated dramatically increased hospital stays (89.5% vs. 4.5% exceeding 21 days, p < 0.001), reduced home discharge rates (28.5% vs. 48.9%, p < 0.001), and higher mortality (4.2% vs. 1.2%, p < 0.001). Conclusions: Major abdominal surgery and injury severity are primary risk factors for deep SSIs in trauma patients, with profound impacts on clinical outcomes and healthcare resource utilization. These findings highlight the importance of targeted prevention strategies for high-risk trauma patients undergoing major abdominal procedures and emphasize the significant burden that deep SSIs place on healthcare systems. Full article

Introduction: This prospective descriptive study explored the disparities in perceptions and experiences regarding healthcare services between providers and users during the COVID-19 pandemic, with a specific focus on the impact of the digital divide on access to and quality of care. The study revealed significant inconsistencies in the experiences of healthcare providers and patients, particularly regarding the effectiveness of digital health interventions. Methods: This study was a prospective descriptive analysis conducted to evaluate and compare the use of electronic healthcare services between healthcare employees (HΕs) (N = 290) and consumers (Cs) (N = 263) from December 2024 to May 2025, utilizing an electronic survey after the COVID-19 pandemic. To ensure the statistical validity of the sample size, a power analysis was performed using G*Power 3.1.9.2 software. A questionnaire was developed to evaluate the readiness of healthcare employees and consumers for electronic healthcare services. It was validated to ensure reliability within this population and comprised 49 questions. Results: The response rate of the participants was 89.19%, and the Cronbach’s alpha for the questionnaire was 0.738. The study revealed notable differences in perceptions regarding health-related information and digital health technologies across genders and age groups. Specifically, 28.8% of females and 27.3% of males considered it important to be well-informed about health issues (χ² = 8.83, df = 3, p = 0.032). Conclusions: This research contributes to filling a gap in comparative analyses of provider and user perspectives, offering a comprehensive view of how digital health was adopted and experienced during a global crisis. Practically, it provides an evidence base to guide future interventions aimed at fostering more equitable, resilient, and user-friendly digital healthcare systems. Full article