Search Results (3,183)

This study presents an approach based on machine learning (ML) techniques to analyze the relationship between emergency room (ER) admissions for cardiorespiratory diseases (CRDs) and environmental factors. The aim of this study is the development and verification of an interpretable machine learning framework applied to environmental and health data to assess the relationship between environmental factors and daily emergency room admissions for cardiorespiratory diseases. The model’s predictive accuracy was evaluated by comparing simulated values with observed historical data, thereby identifying the most influential environmental variables and critical exposure thresholds. This approach supports public health surveillance and healthcare resource management optimization. The health and environmental data, collected through meteorological sensors and air quality monitoring stations, cover eleven years (2013–2023), including meteorological conditions and atmospheric pollutants. Four ML models were compared, with XGBoost showing the best predictive performance (R² = 0.901; MAE = 0.047). A 10-fold cross-validation was applied to improve reliability. Global model interpretability was assessed using SHAP, which highlighted that high levels of carbon monoxide and relative humidity, low atmospheric pressure, and mild temperatures are associated with an increase in CRD cases. The local analysis was further refined using LIME, whose application—followed by experimental verification—allowed for the identification of the critical thresholds beyond which a significant increase in the risk of hospital admission (above the 95th percentile) was observed: CO > 0.84 mg/m³, P_atm ≤ 1006.81 hPa, Tavg ≤ 17.19 °C, and RH > 70.33%. The findings emphasize the potential of interpretable ML models as tools for both epidemiological analysis and prevention support, offering a valuable framework for integrating environmental surveillance with healthcare planning. Full article

Depression represents one of the most prevalent mental health disorders globally, significantly impacting quality of life and posing substantial healthcare challenges. Traditional diagnostic methods rely on subjective assessments and clinical interviews, often leading to misdiagnosis, delayed treatment, and suboptimal outcomes. Recent advances in biosensing technologies offer promising avenues for objective depression assessment through detection of relevant biomarkers and physiological parameters. This review examines multi-modal biosensing approaches for depression by analyzing electrochemical biosensors for neurotransmitter monitoring alongside wearable sensors tracking autonomic, neural, and behavioral parameters. We explore sensor fusion methodologies, temporal dynamics analysis, and context-aware frameworks that enhance monitoring accuracy through complementary data streams. The review discusses clinical validation across diagnostic, screening, and treatment applications, identifying performance metrics, implementation challenges, and ethical considerations. We outline technical barriers, user acceptance factors, and data privacy concerns while presenting a development roadmap for personalized, continuous monitoring solutions. This integrative approach holds significant potential to revolutionize depression care by enabling earlier detection, precise diagnosis, tailored treatment, and sensitive monitoring guided by objective biosignatures. Successful implementation requires interdisciplinary collaboration among engineers, clinicians, data scientists, and end-users to balance technical sophistication with practical usability across diverse healthcare contexts. Full article

Intravascular biosensors have become a crucial and novel class of devices in healthcare, enabling the constant real-time monitoring of essential physiological parameters directly within the circulatory system. Recent developments in micro- and nanotechnology have relevantly improved the sensitivity, miniaturization, and biocompatibility of these devices, thereby enabling their application in precision medicine. This review summarizes the latest advances in intravascular biosensor technologies, with a special focus on glucose and oxygen level monitoring, blood pressure and heart rate assessment, and early disease diagnostics, as well as modern approaches to drug therapy monitoring and delivery systems. Key challenges such as long-term biostability, signal accuracy, and regulatory approval processes are critical considerations. Innovative strategies, including biodegradable implants, nanomaterial-functionalized surfaces, and integration with artificial intelligence, are regarded as promising avenues to overcome current limitations. This review provides a comprehensive roadmap for upcoming research and the clinical translation of advanced intravascular biosensors with a strong emphasis on their transformative impact on personalized healthcare. Full article

Inflammatory Bowel Diseases (IBDs) are complex, multifactorial disorders with no known cure, necessitating lifelong care and often leading to surgical interventions. This ongoing healthcare requirement, coupled with the increased use of biological drugs and rising disease prevalence, significantly increases the financial burden on the healthcare systems. Thus, a number of novel technological approaches have emerged in order to face some of the pivotal questions still associated with IBD. In navigating the intricate landscape of IBD, biosensors act as indispensable allies, bridging the gap between traditional diagnostic methods and the evolving demands of precision medicine. Continuous progress in biosensor technology holds the key to transformative breakthroughs in IBD management, offering more effective and patient-centric healthcare solutions considering the One Health Approach. Here, we will delve into the landscape of biomarkers utilized in the diagnosis, monitoring, and management of IBD. From well-established serological and fecal markers to emerging genetic and epigenetic markers, we will explore the role of these biomarkers in aiding clinical decision-making and predicting treatment response. Additionally, we will discuss the potential of novel biomarkers currently under investigation to further refine disease stratification and personalized therapeutic approaches in IBD. By elucidating the utility of biosensors across the spectrum of IBD care, we aim to highlight their importance as valuable tools in optimizing patient outcomes and reducing healthcare costs. Full article

Flexible sensors have emerged as essential components in next-generation technologies such as wearable electronics, smart healthcare, soft robotics, and human–machine interfaces, owing to their outstanding mechanical flexibility and multifunctional sensing capabilities. Despite significant advancements, challenges such as the trade-off between sensitivity and detection range, and poor signal stability under cyclic deformation remain unresolved. To overcome the aforementioned limitations, this work introduces a high-performance soft sensor featuring a dual-layered electrode system, comprising silver nanoparticles (AgNPs) and a composite of multi-walled carbon nanotubes (MWCNTs) with carbon black (CB), coupled with a laser-engraved crack-gradient microstructure. This structural strategy facilitates progressive crack formation under applied strain, thereby achieving enhanced sensitivity (1.56 kPa⁻¹), broad operational bandwidth (50–600 Hz), fine frequency resolution (0.5 Hz), and a rapid signal response. The synergistic structure also improves signal repeatability, durability, and noise immunity. The sensor demonstrates strong applicability in health monitoring, motion tracking, and intelligent interfaces, offering a promising pathway for reliable, multifunctional sensing in wearable health monitoring, motion tracking, and soft robotic systems. Full article

The increase in the elderly population globally reflects a change in the population’s mindset regarding preventive health measures and necessitates a rethinking of healthcare strategies. The integration of machine learning (ML)-type algorithms in geriatrics represents a direction for optimizing prevention, diagnosis, prediction, monitoring, and treatment. This paper presents a systematic review of the scientific literature published between 1 January 2020 and 31 May 2025. The paper is based on the applicability of ML techniques in the field of geriatrics. The study is conducted using the Web of Science database for a detailed discussion. The most studied algorithms in research articles are Random Forest, Extreme Gradient Boosting, and support vector machines. They are preferred due to their performance in processing incomplete clinical data. The performance metrics reported in the analyzed papers include the accuracy, sensitivity, F1-score, and Area under the Receiver Operating Characteristic Curve. Nine search categories are investigated through four databases: WOS, PubMed, Scopus, and IEEE. A comparative analysis shows that the field of geriatrics, through an ML approach in the context of elderly nutrition, is insufficiently explored, as evidenced by the 61 articles analyzed from the four databases. The analysis highlights gaps regarding the explainability of the models used, the transparency of cross-sectional datasets, and the validity of the data in real clinical contexts. The paper highlights the potential of ML models in transforming geriatrics within the context of personalized predictive care and outlines a series of future research directions, recommending the development of standardized databases, the integration of algorithmic explanations, the promotion of interdisciplinary collaborations, and the implementation of ethical norms of artificial intelligence in geriatric medical practice. Full article

Sensor selection in IoT-based smart healthcare systems is a complex fuzzy decision-making problem due to the presence of numerous uncertain and interdependent evaluation criteria. Traditional fuzzy multi-criteria decision-making (MCDM) approaches often assume independence among criteria and rely on aggregation operators that impose sharp transitions between preference levels. These assumptions can lead to decision outcomes with insufficient differentiation, limited discriminatory capacity, and potential issues in consistency and sensitivity. To overcome these limitations, this study proposes a novel fuzzy decision-making framework by integrating Quasi-D-Overlap functions into the fuzzy MARCOS (Measurement of Alternatives and Ranking According to Compromise Solution) method. Quasi-D-Overlap functions represent a generalized extension of classical overlap operators, capable of capturing partial overlaps and interdependencies among criteria while preserving essential mathematical properties such as associativity and boundedness. This integration enables a more intuitive, flexible, and semantically rich modeling of real-world fuzzy decision problems. In the context of real-time health monitoring, a case study is conducted using a hybrid edge–cloud architecture, involving sensor tasks such as heartrate monitoring and glucose level estimation. The results demonstrate that the proposed method provides greater stability, enhanced discrimination, and improved responsiveness to weight variations compared to traditional fuzzy MCDM techniques. Furthermore, it effectively supports decision-makers in identifying optimal sensor alternatives by balancing critical factors such as accuracy, energy consumption, latency, and error tolerance. Overall, the study fills a significant methodological gap in fuzzy MCDM literature and introduces a robust fuzzy aggregation strategy that facilitates interpretable, consistent, and reliable decision making in dynamic and uncertain healthcare environments. Full article

The Internet of Medical Things (IoMT) is revolutionizing healthcare by enabling continuous patient monitoring, early diagnosis, and personalized treatments. However, the het-erogeneity of IoMT devices and the lack of standardized protocols introduce serious security vulnerabilities. To address these challenges, we propose a hybrid BiLSTM-DNN intrusion detection system, named HBiLD-IDS, that combines Bidirectional Long Short-Term Memory (BiLSTM) networks with Deep Neural Networks (DNNs), leveraging both temporal dependencies in network traffic and hierarchical feature extraction. The model is trained and evaluated on the CICIoMT2024 dataset, which accurately reflects the diversity of devices and attack vectors encountered in connected healthcare environments. The dataset undergoes rigorous preprocessing, including data cleaning, feature selection through correlation analysis and recursive elimination, and feature normalization. Compared to existing IDS models, our approach significantly enhances detection accuracy and generalization capacity in the face of complex and evolving attack patterns. Experimental results show that the proposed IDS model achieves a classification accuracy of 98.81% across 19 attack types confirming its robustness and scalability. This approach represents a promising solution for strengthening the security posture of IoMT networks against emerging cyber threats. Full article

Heart failure (HF) is a major global health challenge, characterized by high morbidity, mortality, and frequent hospital readmissions. Despite the advent of guideline-directed medical therapies (GDMTs), the burden of HF continues to grow, necessitating a shift toward comprehensive, multidisciplinary care models. Heart Failure Disease Management Programs (HF-DMPs) have emerged as structured frameworks that integrate evidence-based medical therapy, patient education, telemonitoring, and support for social determinants of health to optimize outcomes and reduce healthcare costs. This review outlines the key components of HF-DMPs, including patient identification and risk stratification, pharmacologic optimization, team-based care, transitional follow-up, remote monitoring, performance metrics, and social support systems. Incorporating tools such as artificial intelligence, pharmacist-led titration, and community health worker support, HF-DMPs represent a scalable approach to improving care delivery. The success of these programs depends on tailored interventions, interdisciplinary collaboration, and health equity-driven strategies. Full article

Background/Objectives: Strengthening antimicrobial stewardship (AMS) programs is an invaluable intervention in the ongoing efforts to contain the threat of antimicrobial resistance (AMR), particularly in low-resource settings. This study evaluates the impact of the Telementoring, Education, and Advocacy Collaboration initiative for Health through Antimicrobial Stewardship (TEACH AMS), which uses the virtual Extension for Community Healthcare Outcomes (ECHO) learning model to enhance AMS capacity in Kenya, Ghana, and Malawi. Methods: A mixed-methods approach was used, which included attendance data collection, facility-level assessments, post-session and follow-up surveys, as well as focus group discussions. Results: Between September 2023 and February 2025, 77 virtual learning sessions were conducted, engaging 2445 unique participants from hospital-based AMS committees and health professionals across the three countries. Participants reported significant knowledge gain, and data showed facility improvements in two core AMS areas, including the implementation of multidisciplinary ward-based interventions/communications and enhanced monitoring of antibiotic resistance patterns. Along those lines, participants reported that the program assisted them in improving prescribing and culture-based treatments, and also evidence-informed antibiotic selection. The evidence of implementing ward-based interventions was further stressed in focus group discussions, as well as other strengthened practices like point-prevalence surveys, and development or revision of stewardship policies. Substantial improvements in microbiology services were also shared by participants, particularly in Malawi. Other practices mentioned were strengthened multidisciplinary communication, infection prevention efforts, and education of patients and the community. Conclusions: Our findings suggest that a virtual case-based learning educational intervention, providing structured and tailored AMS capacity building, can drive behavior change and strengthen healthcare systems in low resource settings. Future efforts should aim to scale up the engagements and sustain improvements to further strengthen AMS capacity. Full article

Background/Objectives: Enterococci, particularly Enterococcus faecalis and Enterococcus faecium, are Gram-positive cocci that can cause severe infections in hospitalized patients. The rise of vancomycin-resistant enterococci (VRE) and vancomycin-variable enterococci (VVE) poses significant challenges in healthcare settings due to their resistance to multiple antibiotics. Methods: We conducted a point prevalence survey (PPS) to assess the prevalence of VRE and VVE colonization in hospitalized patients. Rectal swabs were collected from 160 patients and analyzed using molecular assays (MAs) and culture. Whole-genome sequencing (WGS) and core-genome multilocus sequence typing (cgMLST) were performed to identify the genetic diversity. Results: Of the 160 rectal swabs collected, 54 (33.7%) tested positive for the vanA and/or vanB genes. Culture-based methods identified 47 positive samples (29.3%); of these, 44 isolates were identified as E. faecium and 3 as E. faecalis. Based on the resistance profiles, 35 isolates (74.5%) were classified as VRE, while 12 (25.5%) were classified as VVE. WGS and cgMLST analyses identified seven clusters of E. faecium, with sequence type (ST) 80 being the most prevalent. Various resistance genes and virulence factors were identified, and this study also highlighted intra- and inter-ward transmission of VRE strains. Conclusions: Our findings underscore the potential for virulence and resistance of both the VRE and VVE strains, and they highlight the importance of effective infection control measures to prevent their spread. VVE in particular should be carefully monitored as they often escape detection. Integrating molecular data with clinical information will hopefully enhance our ability to predict and prevent future VRE infections. Full article

Contactless vital sign monitoring has emerged as a transformative healthcare technology, enabling the assessment of vital signs without physical contact with the human body. This review comprehensively reviews the rapidly evolving landscape of this field, with particular emphasis on multi-modal sensing approaches and multi-task learning paradigms. We systematically categorize and analyze existing technologies based on sensing modalities (vision-based, radar-based, thermal imaging, and ambient sensing), integration strategies, and application domains. The paper examines how artificial intelligence has revolutionized this domain, transitioning from early single-modality, single-parameter approaches to sophisticated systems that combine complementary sensing technologies and simultaneously extract multiple vital sign parameters. We discuss the theoretical foundations and practical implementations of multi-modal fusion, analyzing signal-level, feature-level, decision-level, and deep learning approaches to sensor integration. Similarly, we explore multi-task learning frameworks that leverage the inherent relationships between vital sign parameters to enhance measurement accuracy and efficiency. The review also critically addresses persisting technical challenges, clinical limitations, and ethical considerations, including environmental robustness, cross-subject variability, sensor fusion complexities, and privacy concerns. Finally, we outline promising future directions, from emerging sensing technologies and advanced fusion architectures to novel application domains and privacy-preserving methodologies. This review provides a holistic perspective on contactless vital sign monitoring, serving as a reference for researchers and practitioners in this rapidly advancing field. Full article

Neurodevelopmental disorders (NDDs) significantly impact children’s health and development. They pose a substantial burden to families and the healthcare system. Challenges in early identification, accurate and timely diagnosis, and effective treatment persist due to overlapping symptoms, lack of appropriate diagnostic biomarkers, significant stigma and discrimination, and systemic barriers. Generative Artificial Intelligence (GenAI) offers promising solutions to these challenges by enhancing screening, diagnosis, personalized treatment, and research. Although GenAI is already in use in some aspects of NDD management, effective and strategic leveraging of evolving AI tools and resources will enhance early identification and screening, reduce diagnostic processing by up to 90%, and improve clinical decision support. Proper use of GenAI will ensure individualized therapy regimens with demonstrated 36% improvement in at least one objective attention measure compared to baseline and 81–84% accuracy relative to clinician-generated plans, customize learning materials, and deliver better treatment monitoring. GenAI will also accelerate NDD-specific research and innovation with significant time savings, as well as provide tailored family support systems. Finally, it will significantly reduce the mortality and morbidity associated with NDDs. This article explores the potential of GenAI in transforming NDD management and calls for policy initiatives to integrate GenAI into NDD management systems. Full article

Introduction and Objectives: Risk-sharing agreements (RSAs) have emerged as a key strategy for financing high-cost medical technologies while ensuring financial sustainability. These payment mechanisms mitigate clinical and financial uncertainties, optimizing pricing and reimbursement decisions. Despite their widespread adoption globally, Latin America has reported limited implementation, particularly for high-cost medical devices. This study aims to share insights from designing RSAs in the form of Outcome Protection Programs (OPPs) for medical devices in Latin America from the perspective of a medical devices company. Methods: The report follows a structured approach, defining key OPP dimensions: payment base, access criteria, pricing schemes, risk assessment, and performance incentives. Risks were categorized as financial, clinical, and operational. The framework applied principles from prior models, emphasizing negotiation, program design, implementation, and evaluation. A multidisciplinary task force analyzed patient needs, provider motivations, and payer constraints to ensure alignment with health system priorities. Results: Over two semesters, a panel of seven experts from the manufacturer designed n = 105 innovative payment programs implemented in Argentina (n = 7), Brazil (n = 7), Colombia (n = 75), Mexico (n = 9), Panama (n = 4), and Puerto Rico (n = 3). The programs targeted eight high-burden conditions, including Coronary Artery Disease, atrial fibrillation, Heart Failure, and post-implantation arrhythmias, among others. Private providers accounted for 80% of experiences. Challenges include clinical inertia and operational complexities, necessitating structured training and monitoring mechanisms. Conclusions: Outcome Protection Programs offer a viable and practical risk-sharing approach to financing high-cost medical devices in Latin America. Their implementation requires careful stakeholder alignment, clear eligibility criteria and endpoints, and robust monitoring frameworks. These findings contribute to the ongoing dialogue on sustainable healthcare financing, emphasizing the need for tailored approaches in resource-constrained settings. Full article

Growing interest in the future applications of nanotechnology in medicine has led to groundbreaking developments in nanosensors. Nanosensors are excellent platforms that provide reliable solutions for continuous monitoring and real-time detection of clinical targets. Nanosensors have attracted great attention due to their remarkable sensitivity, portability, selectivity, and automated data acquisition. The exceptional nanoscale properties of nanomaterials used in the nanosensors boost their sensing potential even at minimal concentrations of analytes present in a clinical sample. Along with applications in diverse sectors, the beneficial aspects of nanosensors have been exploited in healthcare systems to utilize their applications in diagnosing, treating, and preventing diseases. Hence, in this review, we have presented an overview of the disease-prognostic applications of nanosensors in chronic diseases through a detailed literature analysis. We focused on the advances in various nanosensors in the field of major diseases such as cancer, cardiovascular diseases, diabetes mellitus, and neurodegenerative diseases along with other prevalent diseases. This review demonstrates various categories of nanosensors with different nanoparticle compositions and detection methods suitable for specific diagnostic applications in clinical settings. The chemical properties of different nanoparticles provide unique characteristics to each nanosensors for their specific applications. This will aid the detection of potential biomarkers or pathological conditions that correlate with the early detection of various diseases. The potential challenges and possible recommendations of the applications of nanosensors for disease diagnosis are also discussed. The consolidated information present in the review will help to better understand the disease-prognostic potentials of nanosensors, which can be utilized to explore new avenues in improved therapeutic interventions and treatment modalities. Full article