Search Results (1,360)

Modern healthcare systems increasingly depend on wearable Internet of Medical Things (IoMT) devices for the continuous monitoring of patients’ physiological parameters. It remains challenging to differentiate between genuine physiological anomalies, sensor faults, and malicious cyber interference. In this work, we propose a hybrid fusion framework designed to attribute the most plausible source of an anomaly, thereby supporting more reliable clinical decisions. The proposed framework is developed and evaluated using two complementary datasets: CICIoMT2024 for modelling security threats and a large-scale intensive care cohort from MIMIC-IV for analysing key vital signs and bedside interventions. The core of the system combines a supervised XGBoost classifier for attack detection with an unsupervised LSTM autoencoder for identifying physiological and technical deviations. To improve clinical realism and avoid artefacts introduced by quantised or placeholder measurements, the physiological module incorporates quality-aware preprocessing and missingness indicators. The fusion decision policy is calibrated under prudent, safety-oriented constraints to limit false escalation. Rather than relying on fixed fusion weights, we train a lightweight fusion classifier that combines complementary evidence from the security and clinical modules, and we select class-specific probability thresholds on a dedicated calibration split. The security module achieves high cross-validated performance, while the clinical model captures abnormal physiological patterns at scale, including deviations consistent with both acute deterioration and data-quality faults. Explainability is provided through SHAP analysis for the security module and reconstruction-error attribution for physiological anomalies. The integrated fusion framework achieves a final accuracy of 99.76% under prudent calibration and a Matthews Correlation Coefficient (MCC) of 0.995, with an average end-to-end inference latency of 84.69 ms (p95 upper bound of 107.30 ms), supporting near real-time execution in edge-oriented settings. While performance is strong, clinical severity labels are operationalised through rule-based proxies, and cross-domain fusion relies on harmonised alignment assumptions. These aspects should be further evaluated using realistic fault traces and prospective IoMT data. Despite these limitations, the proposed framework offers a practical and explainable approach for IoMT-based patient monitoring. Full article

Parenteral nutrition (PN) is essential for patients who are unable to tolerate oral or enteral feeding, providing them with necessary nutrients intravenously, including dextrose, amino acids, electrolytes, vitamins, trace elements, and lipid emulsions. Clinical pharmacists (CPs) play a critical role in PN management by ensuring proper formulation, monitoring therapy, preventing complications, and optimizing patient outcomes. In Saudi Arabia, limited literature exists on CPs’ involvement in total parenteral nutrition (TPN) administration, health information management (HIM) systems, and pharmacist staffing ratios. This paper examines the evolving role of CPs in PN management, addressing key challenges such as the optimal patient-to-CP ratio, the impact of HIM systems on PN prescribing, and the advantages and limitations of centralized versus decentralized PN prescription models. It highlights the need for standardized staffing levels, structured pharmacist training, and improved HIM integration to enhance workflow efficiency and prescribing accuracy. Additionally, the study examines how the adoption of advanced HIM systems can streamline documentation, reduce prescribing errors, and enhance interdisciplinary collaboration. This paper provides a framework for optimizing PN delivery, enhancing healthcare quality, and strengthening CPs’ contributions to nutrition support by addressing these factors. Implementing these recommendations will improve patient outcomes and establish a more efficient PN management system in Saudi Arabia, reinforcing the vital role of CPs in multidisciplinary care. Full article

Background: The Rohingya refugee crisis is one of the largest humanitarian emergencies of the 21st century, with nearly one million Rohingya residing in overcrowded camps in southern Bangladesh. Women and children face the greatest vulnerabilities, including inadequate access to education and healthcare, which exacerbates their risks and limits opportunities for personal and community development. While international organizations continue to provide aid, resources remain insufficient, particularly in maternal and child healthcare, highlighting the urgent need for sustainable interventions. Objectives: The Hope Foundation for Women and Children in Bangladesh launched a pilot project for the Health Assistant Training (HAT) program to address critical gaps in healthcare and education for the Rohingya community. This nine-month training program equips young Rohingya women with essential knowledge and skills to support maternal health services in both clinical and community settings. Design: We conducted a qualitative evaluation of the HAT Program to explore its acceptance and anticipated benefits for both participants and the community. Methods: The research team used semi-structured interviews, focus groups, and field observations to explore the HAT Program’s impact on young Rohingya women and their community. They analyzed data through thematic analysis, developing a coding framework and identifying key themes to uncover patterns and insights. Results: The results were categorized into four themes: (1) community acceptance of the HAT Program, (2) the HAT Program’s impact on the health assistant trainees, (3) the impact of the HAT Program on the community, and (4) the potential ways to expand the HAT Program. Conclusions: This research underscores the program’s impact on improving healthcare access, enhancing women’s empowerment, and promoting community resilience. By situating this initiative within the broader context of refugee health, education, and capacity-building, this research highlights the HAT program’s potential as a replicable model in Bangladesh and in other humanitarian settings. Full article

Epileptic seizures arise from abnormally synchronized neural activity and remain a major global health challenge, affecting more than 50 million people worldwide. Despite advances in pharmacological interventions, a significant proportion of patients continue to experience uncontrolled seizures, underscoring the need for alternative neuromodulation strategies. Rhythmic neural entrainment has recently emerged as a promising mechanism for disrupting pathological synchrony, but most existing systems rely on complex analog electronics or high-power stimulation hardware. This study investigates a proof-of-concept digital custom-designed chip that generates a stable 6 Hz oscillation capable of imposing a stable rhythmic pattern onto digitized seizure-like EEG dynamics. Using a publicly available EEG seizure dataset, we extracted and averaged analog seizure waveforms, digitized them to emulate neural front-ends, and directly interfaced the digitized signals with digital output recordings acquired from the chip using a Saleae Logic analyser. The chip’s pulse train was resampled and low-pass-reconstructed to produce an analog 6 Hz waveform, allowing direct comparison between seizure morphology, its digitized representation, and the entrained output. Frequency-domain and time-domain analyses demonstrate that the chip imposes a narrow-band 6 Hz rhythm that overrides the broadband spectral profile of seizure activity. These results provide a proof-of-concept for low-power digital custom-designed entrainment as a potential pathway toward simplified, wearable neuromodulation device for future healthcare diagnostics. Full article

Background: Palliative care addresses not only physical symptoms but also the social, psychological, and spiritual needs of patients. Nurses play a key role in identifying and responding to these needs, yet their perceptions and preparedness may vary. Objectives: This study aimed to explore nurses’ perspectives on the psychological, social, and spiritual needs of palliative patients, assess how well these needs are being met, and examine the influence of nurses’ self-assessed education levels on their evaluations. Methods: A cross-sectional survey was conducted among 237 registered nurses with palliative care experience in Split-Dalmatia County, Croatia. Two validated questionnaires were used to assess the perceived importance of 53 patient needs and the extent to which these needs were satisfied. Results: Findings revealed significant discrepancies between the perceived importance and satisfaction of nearly all psychological, social, and spiritual needs (p < 0.001), particularly regarding fear of death, suffering, and future uncertainty. Only 38.4% of nurses considered themselves adequately trained in palliative care, though most had some educational exposure to it. No statistical differences were found in need assessment based on nurses’ self-rated education. Most nurses reported emotional exhaustion (72.6%) and supported interdisciplinary care (95.8%), while 90.3% noted that responsibility for care often falls on families. Conclusions: Nurses recognize critical unmet needs in palliative patients and feel insufficiently prepared to address them. These findings underscore the need to improve palliative care education, provide emotional support for nurses, and implement systemic healthcare reforms to ensure comprehensive, dignified care. Full article

Background and Objectives: Chronic low back pain (CLBP) is a prevalent condition that impairs quality of life, functionality, and work productivity. While most acute episodes of back pain resolve, 4–25% become chronic due to factors such as high pain intensity, psychological distress, and maladaptive behaviors. Nonspecific CLBP is best understood through the biopsychosocial model, encompassing biological, psychological, and social influences, including kinesiophobia. Management relies on physical activity, pain education, and psychological interventions, with therapist knowledge and attitudes affecting outcomes. This study aimed to assess the prevalence of CLBP among healthcare workers, examine their knowledge of pain neurophysiology, evaluate kinesiophobia, and explore how personal experience with CLBP influences their beliefs, attitudes, and interactions with patients. Materials and Methods: A cross-sectional observational study was conducted from January to May 2025 among healthcare professionals. A total of 50 participants completed an online questionnaire, of which 42 were valid and included in the analysis. The questionnaire collected demographic and professional data, determined the presence of CLBP, and included three standardized instruments: the Revised Neurophysiology of Pain Questionnaire (rNPQ) to assess knowledge of pain mechanisms, the Health Care Providers’ Pain and Impairment Relationship Scale (HC-PAIRS) to evaluate beliefs about pain and disability, and the Tampa Scale of Kinesiophobia (TSK-11) to measure fear of movement. Data were analyzed using SPSS and Microsoft Excel. Results: Among the 42 participants, 11 demonstrated low, 28 moderate, and 3 high knowledge of pain neurophysiology (rNPQ), with a mean score of 5.66. On the HC-PAIRS, the majority (30 participants) scored above 60, indicating beliefs that pain leads to disability, while 12 scored below 60, reflecting a biopsychosocial perspective; gender did not significantly affect HC-PAIRS scores (p = 0.213). As for kinesiophobia (TSK-11), 24 participants had low, 17 moderate, and 1 clinically significant fear of movement. Correlation analysis revealed that younger participants had higher rNPQ scores (r = −0.358, p = 0.020) and lower TSK-11 scores (r = −0.389, p = 0.011). TSK-11 scores increased with age (r = 0.432, p = 0.004), while HC-PAIRS scores showed no significant correlations. Conclusions: Healthcare professionals, particularly physiotherapists, show gaps in knowledge of pain neurophysiology and a tendency toward biomedical beliefs regarding chronic low back pain. This cross-sectional study indicates that a greater understanding of pain mechanisms is associated with lower kinesiophobia, emphasizing the importance of education. Integrating the biopsychosocial model into undergraduate and continuing professional training, through interdisciplinary and practical modules, may improve knowledge, reduce maladaptive fear-avoidance behaviors, and enhance patient care. Future studies should include larger, more diverse samples and assess the long-term impact of educational interventions on clinical practice. Full article

Recognizing cervical cancer as a major public health concern, Romania was among the first EU countries to introduce human papilloma virus (HPV) vaccination in 2008. Despite multiple strategies implemented over the past 17 years, HPV vaccine coverage remains one of the lowest in the EU, while cervical cancer mortality rates are among the highest. To explore the underlying factors, we conducted a cross-sectional study involving 209 family physicians at the national level. The study assessed their attitudes, practice, knowledge, and training needs related to HPV vaccination. The majority of physicians (90%) reported that they provide HPV vaccination services, and 88.5% considered themselves to have good and very good knowledge about HPV, which they routinely share during consultations with patients. However, respondents noted that both physician and public attitudes toward HPV vaccination are only moderately positive, which limits vaccine uptake and the success of prevention efforts. Parental hesitation was the main barrier, mentioned by 81.8% of respondents. The majority (71.3%) of doctors indicated that they were able to adequately respond to patients’ questions, but 81.4% of respondents expressed the view that additional training is needed for healthcare professionals on HPV infection and vaccination. These findings highlight the need for coordinated efforts to increase demand and trust in HPV vaccination. Recommended strategies include targeted professional training, public information campaigns, and the development of strong cross-sector partnerships to support vaccination efforts. 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

Background: Language barriers remain a major obstacle to equitable healthcare access for immigrants and refugees across Europe. Greece, as both a transit and host country, faces persistent challenges in providing linguistically and culturally appropriate care. Methods: This study presents a narrative literature review synthesizing international, European, and Greek evidence on the effects of limited language proficiency, professional interpretation, and intercultural mediation on healthcare access, patient safety, satisfaction, and clinical outcomes. Peer-reviewed studies and selected grey literature were identified through searches of PubMed, Scopus, Web of Science, and CINAHL. Results: The evidence consistently demonstrates that the absence of professional interpretation is associated with substantially higher rates of clinically significant communication errors, longer hospital stays, increased readmissions, and higher healthcare costs. In contrast, the use of trained medical interpreters and intercultural mediators improves comprehension, shared decision-making, patient satisfaction, and clinical outcomes. Comparative European data from Italy, Spain, Germany, and Sweden show that institutionalized interpretation systems outperform Greece’s fragmented, NGO-dependent approach. Greek studies further reveal that limited proficiency in Greek is associated with reduced service utilization, longer waiting times, and lower patient satisfaction. Conclusions: This narrative review highlights the urgent need for Greece to adopt a coordinated, professionally staffed interpretation and intercultural mediation framework. Strengthening linguistic support within the healthcare system is essential for improving patient safety, equity, efficiency, and the integration of migrant and refugee populations. Full article

Considering the high prevalence of adolescent depression and anxiety, the profound functional consequences of untreated early psychosis and suicide being the number one cause of death in Australia among 15–19-year-olds, ensuring that teachers are literate about these disorders should be a high priority. Teachers’ disorder-specific literacy is a pragmatic response to healthcare system constraints. This scoping review aimed to map the evidence of teacher mental health literacy training programs, specifically for depression, anxiety, early psychosis and suicide risk. PRISMA-ScR guidelines were followed. Included studies were published in English between 2000 and 2024, focused on teachers working with students in Year 7–12 and measured teachers’ knowledge of depression, anxiety, psychosis or suicide risk. Studies were appraised for quality. Eighteen studies met the inclusion criteria. Nine evaluated knowledge of student depression, five evaluated knowledge of anxiety and five evaluated knowledge of psychosis, while nine studies focused on suicide risk. Providing disorder-specific training and evaluation, rather than general mental health literacy training, is recommended for future research. When healthcare systems lack the capacity to provide care for ill adolescents, schools often function as frontline sites for recognition and triage. Disorder-specific literacy is recommended for teachers so they can manage their real-world, health-system compensation role. Full article

Background: Amyotrophic lateral sclerosis (ALS) progressively impairs motor function, compromising speech and limiting communication. Augmentative and alternative communication (AAC) is essential to maintain autonomy, social participation, and quality of life for people with ALS (PALS). This review maps technological developments in AAC, from low-tech tools to advanced brain–computer interface (BCI) systems. Methods: We conducted a scoping review following the PRISMA extension for scoping reviews. PubMed, Web of Science, SciELO, MEDLINE, and CINAHL were screened for studies published up to 31 August 2025. Peer-reviewed RCT, cohort, cross-sectional, and conference papers were included. Single-case studies of invasive BCI technology for ALS were also considered. Methodological quality was evaluated using JBI Critical Appraisal Tools. Results: Thirty-seven studies met inclusion criteria. High-tech AAC—particularly eye-tracking systems and non-invasive BCIs—were most frequently studied. Eye tracking showed high usability but was limited by fatigue, calibration demands, and ocular impairments. EMG- and EOG-based systems demonstrated promising accuracy and resilience to environmental factors, though evidence remains limited. Invasive BCIs showed the highest performance in late-stage ALS and locked-in syndrome, but with small samples and uncertain long-term feasibility. No studies focused exclusively on low-tech AAC interventions. Conclusions: AAC technologies, especially BCIs, EMG and eye-tracking systems, show promise in supporting autonomy in PALS. Implementation gaps persist, including limited attention to caregiver burden, healthcare provider training, and the real-world use of low-tech and hybrid AAC. Further research is needed to ensure that communication solutions are timely, accessible, and effective, and that they are tailored to functional status, daily needs, social participation, and interaction with the environment. Full article

Detecting anomalies in time series data is crucial across several domains, including healthcare, finance, and automotive. Large Language Models (LLMs) have recently shown promising results by leveraging robust model pretraining. However, fine-tuning LLMs with several billion parameters requires a large number of training samples and significant training costs. Conversely, LLMs under a zero-shot learning setting require lower overall computational costs, but can fall short in handling complex anomalies. In this paper, we explore the use of lightweight language models for Time Series Anomaly Detection, either zero-shot or via fine-tuning them. Specifically, we leverage lightweight models that were originally designed for time series forecasting, benchmarking them for anomaly detection against both open-source and proprietary LLMs across different datasets. Our experiments demonstrate that lightweight models (<1 Billion parameters) provide a cost-effective solution, as they achieve performance that is competitive and sometimes even superior to that of larger models (>70 Billions). Full article

This study addresses the challenge of evaluating artificial intelligence (AI) systems across heterogeneous regulatory frameworks. Although the NIST AI RMF, EU AI Act, and ISO/IEC 23894/42001 define important governance requirements, they do not provide a unified quantitative method. To bridge this gap, we propose the Cross-Assessment & Verification for Evaluation (CAVe) Framework, which maps shared regulatory requirements to four measurable indicators—accuracy, robustness, privacy, and fairness— and aggregates them into a Cross-Compliance Index (CCI) using normalization, thresholding, evidence penalties, and cross-framework weighting. Two validation scenarios demonstrate the applicability of the approach. The first scenario evaluates a Naïve Bayes-based spam classifier trained on the public UCI SMS Spam Collection dataset, representing a low-risk text-classification setting. The model achieved accuracy 0.9850, robustness 0.9945, fairness 0.9908, and privacy 0.9922, resulting in a CCI of 0.9741 (Pass). The second scenario examines a high-risk healthcare AI system using a CheXNet-style convolutional model evaluated on the MIMIC-CXR dataset. Diagnostic accuracy, distribution-shift robustness, group fairness (finding-specific group comparison), and privacy risk (membership-inference susceptibility) yielded 0.7680, 0.7974, 0.9070, and 0.7500 respectively. Under healthcare-oriented weighting and safety thresholds, the CCI was 0.5046 (Fail). These results show how identical evaluation principles produce different compliance outcomes depending on domain risk and regulatory priorities. Overall, CAVe provides a transparent, reproducible mechanism for aligning technical performance with regulatory expectations across diverse domains. Additional metric definitions and parameter settings are provided in the manuscript to support reproducibility, and future extensions will incorporate higher-level indicators such as transparency and human oversight. Full article

Assisted Reproductive Technology Units (ARTUs) constitute a rapidly growing sector in healthcare, where service quality and patient safety are closely intertwined with ethical principles, technological precision, and managerial efficiency. This study aims to explore quality management practices and certification standards—such as ISO 9001, ISO 15189, and ISO 13485—within ARTUs, with the goal of developing a model that enhances patient-centered outcomes. The analysis focuses on the roles of leadership, staff training, and internal auditing mechanisms as key factors for the successful implementation of quality management systems (QMSs). Through a structured literature review and thematic synthesis, this study identifies challenges that ARTUs face in aligning with international standards and highlights strategies that strengthen patient trust, transparency, and continuous improvement. The proposed model connects measurable quality indicators with patient perceptions and experiences, providing a comprehensive framework for sustainable quality development. This article contributes to the academic discourse on healthcare quality governance and offers practical insights for policymakers and administrators seeking to improve patient experience and organizational resilience in reproductive medicine. 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