Search Results (1,726)

The growing global population and the rapid increase in older adults are driving healthcare costs upward. In response, the healthcare system is shifting toward models that enable continuous monitoring of individuals without requiring hospital admission. Advances in sensing technologies, embedded systems, wireless communication, nanotechnology, and device miniaturization have made these smart systems possible. Wearable sensors can monitor physiological indicators and other symptoms, helping to detect unusual or unexpected events. This allows for the provision of timely assistance when it is needed most. This paper outlines the challenges associated with these systems and reviews recent developments in wearable, sensor-based human activity monitoring. The focus is on health monitoring applications, including relevant biomarkers, wearable and implantable sensors, and established sensor technologies currently used in healthcare, as well as future prospects. It also discusses the challenges involved in researching, developing, and applying these sensors. The goal is to promote the widespread use of these sensors in human health monitoring. Full article

As artificial intelligence (AI) continues to expand across clinical environments, healthcare is transitioning from static decision-support tools to dynamic, autonomous agents capable of reasoning, coordination, and continuous interaction. In the context of geriatric medicine, a field characterized by multimorbidity, cognitive decline, and the need for long-term personalized care, this evolution opens new frontiers for delivering adaptive, assistive, and trustworthy digital support. However, the autonomy and interconnectivity of these systems introduce heightened cybersecurity and ethical challenges. This paper presents a Secure Agentic AI Architecture (SAAA) tailored to the unique demands of geriatric healthcare. The architecture is designed around seven layers, grouped into five functional domains (cognitive, coordination, security, oversight, governance) to ensure modularity, interoperability, explainability, and robust protection of sensitive health data. A review of current AI agent implementations highlights limitations in security, transparency, and regulatory alignment, especially in multi-agent clinical settings. The proposed framework is illustrated through a practical use case involving home-based care for elderly patients with chronic conditions, where AI agents manage medication adherence, monitor vital signs, and support clinician communication. The architecture’s flexibility is further demonstrated through its application in perioperative care coordination, underscoring its potential across diverse clinical domains. By embedding trust, accountability, and security into the design of agentic systems, this approach aims to advance the safe and ethical integration of AI into aging-focused healthcare environments. Full article

Background: Osteoporosis (OP) is characterized by reduced bone mineral density and increased fracture risk. Many spinal surgery patients have undiagnosed OP due to the lack of preoperative screening, leading to postoperative complications. Magnetic resonance imaging (MRI), a routine, non-invasive tool for spinal assessment, offers potential for opportunistic OP detection. This study aimed to develop deep learning models to identify OP using lumbar MRI. Methods: We retrospectively enrolled 218 patients (≥50 years) who underwent both lumbar MRI and dual-energy X-ray absorptiometry (DXA). After segmentation of vertebral bodies from T1- and T2-weighted MRI images, 738 images per sequence were extracted. Separate convolutional neural network (CNN) models were trained for each sequence. Model performance was evaluated using receiver operating characteristic curves and area under the curve (AUC). Results: Among tested classifiers, EfficientNet b4 showed the best performance. For the T1-weighted model, it achieved an AUC of 82%, with a sensitivity of 85% and specificity of 79%. For the T2-weighted model, the AUC was 83%, with a sensitivity of 86% and specificity of 80%. These results were superior to those of InceptionResNet v2 and ResNet-50 for both sequences. Conclusions: The AI models provided reliable OP classification without additional imaging or radiation. AI-based analysis of standard lumbar MRI sequences can accurately identify OP. These models may assist in early detection of undiagnosed OP in surgical candidates, enabling timely treatment and perioperative strategies to improve outcomes and reduce healthcare burden. Full article

Dengue and chikungunya are endemic arboviral diseases in many low- and middle-income countries, often co-circulating and presenting with overlapping symptoms that hinder early diagnosis. Timely differentiation is critical, especially in resource-limited settings where laboratory testing is unavailable. We developed and evaluated machine-learning (ML)- and deep-learning (DL) models to classify dengue, chikungunya, and discarded cases using a large-scale, real-world dataset of over 6.7 million entries from Brazil (2013–2020). After applying the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance, we trained six ML models and one artificial neural network (ANN) using only demographic, clinical, and comorbidity features. The Random Forest model achieved strong multi-class classification performance (Recall: 0.9288, the Area Under the Curve (AUC): 0.9865). The ANN model excelled in identifying chikungunya cases (Recall: 0.9986, AUC: 0.9283), suggesting its suitability for rapid screening. External validation confirmed the generalizability of our models, particularly for distinguishing discarded cases. Our models demonstrate high-accuracy in differentiating dengue and chikungunya using routinely collected clinical and epidemiological data. This work supports the development of Artificial Intelligence-powered decision-support tools to assist frontline healthcare workers in under-resourced settings and aligns with the One Health approach to improving surveillance and diagnosis of neglected tropical diseases. Full article

Various sensors are increasingly being adopted to support intelligent healthcare systems, which address the growing problem of staff shortages in assisted-living communities. In this context, detecting and assessing pain remain critical yet challenging tasks in both clinical and non-clinical settings. Traditional approaches such as self-reporting, physiological signal monitoring, and facial expression analysis often face limitations related to accessibility, equipment costs, and the need for professional support. To overcome these challenges in this work, we investigate a sensor-assisted system for pain detection and propose a lightweight framework that enables real-time classification of pain levels using acoustic sensors. Our system exploits the spectral features of voice signals that strongly correlate with pain to train Convolutional Neural Network (CNN) models. Our system has been validated through simulations in Jupiter Notebook and a Raspberry Pi-based hardware prototype. The experimental results demonstrate that the proposed three-level pain classification approach obtains an average accuracy of 72.74%, outperforming existing methods with the same pain-level granularity by 18.94–26.74% and achieving performance comparable to that of binary pain detection methods. Our hardware prototype, built from commercial off-the-shelf components for under 100 USD, achieves real-time processing speeds ranging from approximately 6 to 22 s. In addition to CNN models, our experiments demonstrate that other machine learning algorithms, such as Artificial Neural Networks, XGBoost, Random Forests, and Decision Trees, also prove to be applicable within our pain level classification framework. Full article

Background: Neonatal mortality remains a significant public health challenge in Ethiopia. Despite efforts to implement key evidence-based interventions, their coverage and utilization remain low. The Saving Little Lives (SLL) program aims to scale-up a Minimum Care Package (MCP) of synergistic, life-saving interventions for all liveborn neonates, with a focus on preterm and low birth weight (LBW) infants, across 290 hospitals in Ethiopia (206 primary, 69 general, and 15 referral hospitals), representing 82% of all hospitals in the country at the time of the study, and evaluate the impact on neonatal mortality. Methods: A non-randomized stepped-wedge trial will be conducted to evaluate the impact of implementing the SLL MCP interventions. Quantitative evaluation data will be collected from 36 primary hospitals, selected from 206 primary hospitals across four regions, receiving the interventions. An independent evaluation research assistant will be deployed in each of the hospitals to collect data using Open Data Kit (ODK) through interviewing mothers before discharge, on the 29th day of life if discharged, and reviewing medical records. A mixed-method, cross-sectional formative assessment will be conducted prior to implementation, employing quantitative facility assessment and qualitative interviews with mothers, healthcare providers, and facility managers. This will be followed by continuous program learning assessment once implementation begins. Descriptive data will be presented using numbers, percentages, tables, and graphs. Regression modeling and generalized estimating equations (GEEs) will be used to estimate the impact of the SLL MCP interventions. Qualitative data will be gathered through in-depth interviews, digitally recorded, transcribed, and thematically analyzed using ATLAS.ti Version 7.5 software to assess facility readiness, barriers, and enablers of implementing the SLL MCP interventions. Expected Outcome: We hypothesize that achieving 80% coverage of the SLL MCP interventions among eligible neonates will result in a 35% reduction in neonatal mortality at implementation facilities. Full article

The exponential growth of multimodal orthopedic data, ranging from longitudinal Electronic Health Records to high-resolution musculoskeletal imaging, has rendered manual analysis insufficient. This has established Large Language Models (LLMs) as algorithmically necessary for managing healthcare complexity. However, their deployment in high-stakes surgical environments presents a fundamental algorithmic paradox: while generic foundation models possess vast reasoning capabilities, they often lack the precise, protocol-driven domain knowledge required for safe orthopedic decision support. This review provides a structured synthesis of the emerging algorithmic frameworks required to build modern clinical AI assistants. We deconstruct current methodologies into their core components: large-language-model adaptation, multimodal data fusion, and standardized data interoperability pipelines. Rather than proposing a single proprietary architecture, we analyze how recent literature connects specific algorithmic choices such as the trade-offs between full fine-tuning and Low-Rank Adaptation to their computational costs and factual reliability. Furthermore, we examine the theoretical architectures required for ‘agentic’ capabilities, where AI systems integrate outputs from deep convolutional neural networks and biosensors. The review concludes by outlining the unresolved challenges in algorithmic bias, security, and interoperability that must be addressed to transition these technologies from research prototypes to scalable clinical solutions. Full article

Generative artificial intelligence (GenAI), particularly large language models (LLMs) such as ChatGPT and DeepSeek, is transforming healthcare by enhancing clinical decision-making, education, and patient interaction. This exploratory study compares the responses of ChatGPT (GPT-4.1) and DeepSeek-V2 against 90 final-year physiotherapy students in Greece on the quality of the responses to 60 clinical questions across four rehabilitation domains: low back pain, multiple sclerosis, frozen shoulder, and knee osteoarthritis (15 questions per domain). The questions spanned basic knowledge, diagnosis, alternative treatments, and rehabilitation practices. The responses were evaluated for their relevance, accuracy, clarity, completeness, and consistency with clinical practice guidelines (CPGs), emphasizing conceptual understanding. This study provides novel contributions by (i) benchmarking LLMs in physiotherapy-specific domains (low back pain, multiple sclerosis, frozen shoulder, and knee osteoarthritis) underrepresented in prior AI-health evaluations; (ii) directly comparing the LLM written response quality to student performance under exam constraints; and (iii) highlighting the improvement potential for education, complementing ChatGPT’s established role in physician decision support. The results indicate that the LLMs produced higher-quality written responses than students in most domains, particularly in the global response quality and the conceptual depth of written responses, highlighting their potential as educational aids for knowledge-based tasks, although not equivalent to clinical expertise. This suggests AI’s role in physiotherapy as a supportive tool rather than a replacement for hands-on clinical skills and asks whether GenAI could transform physiotherapy practice by augmenting, rather than threatening, human-centered care, for its potential as a knowledge support tool in education, pending validation in clinical contexts. This study explores these findings, compares them with the related work, and discusses whether GenAI will transform or threaten physiotherapy practice. Ethical considerations, limitations, and future directions, including AI voice assistants and AI characters, are addressed. Full article

Background: Artificial intelligence (AI) is transforming medical practice, enhancing diagnostic accuracy, personalisation, and clinical efficiency. However, this transition raises complex ethical challenges related to transparency, accountability, fairness, and human oversight. This study examines how the literature conceptualises and distributes ethical responsibility in AI-assisted healthcare. Methods: This semi-systematic, theory-informed thematic review was conducted in accordance with the PRISMA 2020 guidelines. Publications from 2020 to 2025 were retrieved from PubMed, ScienceDirect, IEEE Xplore databases, and MDPI journals. A semi-quantitative keyword-based scoring model was applied to titles and abstracts to determine their relevance. High-relevance studies (n = 187) were analysed using an eight-category ethical framework: transparency and explainability, regulatory challenges, accountability, justice and equity, patient autonomy, beneficence–non-maleficence, data privacy, and the impact on the medical profession. Results: The analysis revealed a fragmented ethical landscape in which technological innovation frequently outperforms regulatory harmonisation and shared accountability structures. Transparency and explainability were the dominant concerns (34.8%). Significant gaps in organisational responsibility, equitable data practices, patient autonomy, and professional redefinition were reported. A multilevel ethical responsibility model was developed, integrating micro (clinical), meso (institutional), and macro (regulatory) dimensions, articulated through both ex ante and ex post perspectives. Conclusions: AI requires governance frameworks that integrate ethical principles, regulatory alignment, and epistemic justice in medicine. This review proposes a multidimensional model that bridges normative ethics and operational governance. Future research should explore empirical, longitudinal, and interdisciplinary approaches to assess the real impact of AI on clinical practice, equity, and trust. Full article

Background: Developmental coordination Disorder (DCD) is a prevalent and persistent neurodevelopmental condition characterized by motor learning difficulties that significantly affect daily functioning and participation. Despite growing interest in artificial intelligence (AI) applications within healthcare, the extent and nature of AI use in the evaluation and intervention of DCD remain unclear. Objective: This scoping review aimed to systematically map the existing literature on the use of AI and AI-assisted approaches in the evaluation, screening, monitoring, and intervention of DCD, and to identify current trends, methodological characteristics, and gaps in the evidence base. Methods: A scoping review was conducted in accordance with the PRISMA extension for Scoping Reviews (PRISMA-ScR) guidelines and was registered on the Open Science Framework. Systematic searches were performed in Scopus, PubMed, Web of Science, and IEEE Xplore, supplemented by snowballing. Peer-reviewed studies applying AI methods to DCD-relevant populations were included. Data was extracted and charted to summarize study designs, populations, AI methods, data modalities, clinical purposes, outcomes, and reported limitations. Results: Seven studies published between 2021 and 2025 met the inclusion criteria following a literature search covering the period from January 2010 to 2025. One study listed as 2026 was included based on its early access online publication in 2025. Most studies focused on AI applications for assessment, screening, and classification, using supervised machine learning or deep learning models applied to movement-based data, wearable sensors, video recordings, neurophysiological signals, or electronic health records. Only one randomized controlled trial evaluated an AI-assisted intervention. The evidence base was dominated by early-phase development and validation studies, with limited external validation, heterogeneous diagnostic definitions, and scarce intervention-focused research. Conclusions: Current AI research in DCD is primarily centered on evaluation and early identification, with comparatively limited evidence supporting AI-assisted intervention or rehabilitation. While existing findings suggest that AI has the potential to enhance objectivity and sensitivity in DCD assessment, significant gaps remain in clinical translation, intervention development, and implementation. Future research should prioritize theory-informed, clinician-centered AI applications, including adaptive intervention systems and decision-support tools, to better support occupational therapy and physiotherapy practice in DCD care. Full article

Background/Objectives: Children in paediatric palliative care often face school attendance barriers due to complex health needs. This study describes post-training perceptions of a training program by a pediatric hospice team to prepare school care assistants to safely include children with complex conditions, focusing on procedural skills, knowledge of the child, and family partnership. Methods: Care assistants who completed a structured course at the Paediatric Palliative Care Centre, University Hospital of Padua (2023–2024), were surveyed immediately after training. The program combined classroom instruction with hands-on simulation using high-fidelity mannequins and standard devices, including suction, pulse oximetry, ventilation, enteral feeding, and tracheostomy care. It also covered modules on urgent and emergency management, as well as family communication. An anonymous online questionnaire gathered socio-demographic data, prior training, clinical tasks performed, self-efficacy levels, and open-ended feedback. Quantitative results were analyzed descriptively, while qualitative comments were subjected to thematic analysis. Results: Of 130 invited assistants, 105 participated (81%). Participants reported strong perceived confidence: 85% selected the upper end of the 5-point scale (“very” or “extremely”) for routine-management ability, and 60% selected these same response options for emergency-management ability. In the most severe events recalled, 60.5% of incidents were resolved autonomously, 7.6% involved contacting emergency services, and 3.8% involved community or hospice nurses. Seventy-five percent judged the course comprehensive; thematic analysis of 102 comments identified satisfaction, requests for regular refreshers, stronger practical components, and requests for targeted topics. Conclusions: Immediately after the session, participants tended to select the upper end of the self-assurance item for both routine and emergency tasks. Combining core emergency procedures with personalized, child-specific modules and family-partnership training may support safety, trust, and inclusion. Regular refreshers and skills checks are advised. Full article

Background: Role clarity is a persistent challenge among Patient Care Technicians (PCTs), contributing to inconsistent task performance and safety risks. In Saudi Arabia, little is known about PCTs’ understanding of their responsibilities. This study evaluated the impact of a targeted educational program designed to improve PCTs’ role clarity, safety practices, and communication. Methods: A quasi-experimental pre-post study was conducted in September 2025 with 35 PCTs from the Hail Health Cluster. The one-day intervention included lectures, discussions, role-play, and case scenarios. Outcomes were measured using a validated instrument across four domains: role clarity; core clinical tasks and safety; communication and ethics; and objective knowledge. Pre-post changes were analyzed using paired t-tests (Cohen’s d), and subgroup differences in change scores were examined using one-way ANOVA (η²) in SPSS v29. Results: Baseline scores were lowest in objective knowledge (41.4%) and role clarity (62.8%). Post-training, total composite scores improved significantly (+10.88%, p < 0.001, d = 1.63), with the most significant gain in objective knowledge (+19.8%, p < 0.001, d = 0.99). Role clarity showed only a modest, non-significant increase (+3.98%, p = 0.088, d = 0.30). No demographic differences were found. Conclusions: Targeted training was effective in reducing knowledge gaps; however, improving role clarity may require organizational reinforcement beyond brief training. Full article

Background: Anxiety is highly prevalent among individuals living with disability, chronic illness, or hospitalisation, yet it often remains insufficiently addressed in healthcare settings. Animal-assisted therapy (AAT) has been proposed as a complementary intervention to reduce anxiety; however, existing evidence is fragmented across populations and methodologies. Methods: A systematic review was conducted following PRISMA 2020 guidelines. The review protocol was registered in PROSPERO (CRD42024494109); no amendments were made to the protocol after registration. Four databases (Scopus, APA PsycInfo, Web of Science, and PubMed) were searched for empirical studies (2013–2023) evaluating AAT delivered by trained professionals using domesticated species and reporting anxiety outcomes in individuals with disability, illness, or hospitalisation. Results: Thirty-one studies met eligibility criteria and were included in the review. Across heterogeneous designs, most interventions—primarily using dogs or horses—reported significant post-intervention reductions in anxiety. Randomised clinical trials consistently showed superior results compared with control conditions. AAT demonstrated beneficial effects across populations including PTSD, paediatric hospitalisation, chronic illness, disability, acute care, and trauma exposure. Long-term outcomes were mixed, and methodological variability limited comparability across studies. Conclusions: AAT appears to be a promising complementary intervention for anxiety management within clinical, psychosocial, and healthcare settings. Evidence supports short-term anxiolytic effects across diverse populations, although standardisation and long-term evaluations remain insufficient. Future research should establish optimal intervention parameters, mechanisms of action, and strategies for integrating AAT into multidisciplinary mental healthcare. 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

Background/Objectives: Blood thinners (anticoagulants) remain the first line pharmacotherapy for the management of cardiovascular and thromboembolic disorders. The increased utilization of polypharmacy, likely driven by the greater burden of comorbidities, elevates the risk of potential drug–drug interactions (pDDIs) and creates a significant challenge in anticoagulant management. The aim of the study was to assess the prescribing trend and impact of polypharmacy and pDDIs in patients receiving anticoagulant drug therapy in a public hospital providing secondary care. Methods: A cross-sectional observational study was undertaken between January–June 2023. Data from electronic medical records of prescriptions for anticoagulants were collected, analyzed for prescribing patterns, and checked for pDDIs using Micromedex database 2.0^®. Utilizing binary logistic regression, the relationship between polypharmacy and sociodemographic factors was assessed. Multivariate logistic regression analysis served to uncover determinants linked to pDDIs. Results: Of the total 130 patients, females were predominant (58.46%), with a higher prevalence among those aged 61–90 years. Atrial fibrillation emerged as the main clinical reason and apixaban (51.53%) ranked as the top prescribed anticoagulant in our cohort. Among the 766 pDDIs identified, the majority [401 (52.34%)] were categorized as moderate in severity. Polypharmacy was strongly linked to age (p = 0.001), the Charlson comorbidity index (CCI) (p = 0.040), and comorbidities (p = 0.005) in the binary logistic regression analysis. In the multivariable analysis, the number of medications remain a strong predictor of pDDIs (adjusted OR: 30.514, p = 0.001). Conclusions: Polypharmacy and pDDIs were exhibited in a significant segment of cohort receiving anticoagulant therapy, with strong correlations to age, CCI, comorbidities, and the number of medications. A multidimensional approach involving collaboration among healthcare providers assisted by clinical decision support systems can help optimize the management of polypharmacy, minimize the risks of pDDIs, and ultimately enhance health outcomes. Full article