Search Results (149)

Background and Objectives: Public health needs collaborative, privacy-preserving analytics, but centralized AI is constrained by data sharing and governance. Federated learning (FL) enables training without moving sensitive data. This review assessed how FL is used for disease prevention in population and public health, and mapped benefits, challenges, and policy implications. Methods: Following PRISMA 2020, we searched PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar for peer reviewed English-language studies from January 2020–30 June 2025, applying FL to surveillance, outbreak detection, risk prediction, or policy support. Two reviewers screened and extracted data with third-reviewer arbitration. Quality was appraised with a tool adapted from MMAT and AI reporting frameworks. No meta-analysis was performed. Results: Of 5230 records identified (4720 after deduplication), 200 full texts were assessed and 19 were included. Most used horizontal FL across multiple institutions for communicable diseases, COVID-19, tuberculosis and some chronic conditions. Reported gains included privacy preservation across sites, better generalizability from diverse data, near real-time intelligence, localized risk stratification, and support for resource planning. Common barriers were non-IID data, interoperability gaps, compute and network limits in low-resource settings, unclear legal pathways, and concerns about fairness and transparency. Few studies linked directly to formal public-health policy or low-resource deployments. Conclusions: FL is promising for equitable, secure, and scalable disease-prevention analytics that respect data sovereignty. Priorities include robust methods for heterogeneity, interoperable standards, secure aggregation, routine fairness auditing, clearer legal and regulatory guidance, and capacity building in underrepresented regions. Full article

The emergence of large language models (LLMs) has redefined the potential of artificial intelligence in clinical domains. In this context, retrieval-augmented generation (RAG) systems provide a promising approach to enhance traceability, timeliness, and accuracy in tasks such as biomedical question answering (QA). This article presents a narrative and thematic review of the evolution of these technologies in maternal health, structured across five axes: technical foundations of RAG, advancements in biomedical LLMs, conversational agents in healthcare, clinical validation frameworks, and specific applications in obstetric telehealth. Through a systematic search in scientific databases covering the period from 2022 to 2025, 148 relevant studies were identified. Notable developments include architectures such as BiomedRAG and MedGraphRAG, which integrate semantic retrieval with controlled generation, achieving up to 18% improvement in accuracy compared to pure generative models. The review also highlights domain-specific models like PMC-LLaMA and Med-PaLM 2, while addressing persistent challenges in bias mitigation, hallucination reduction, and clinical validation. In the maternal care context, the review outlines applications in prenatal monitoring, the automatic generation of clinically validated QA pairs, and low-resource deployment using techniques such as QLoRA. The article concludes with a proposed research agenda emphasizing federated evaluation, participatory co-design with patients and healthcare professionals, and the ethical design of adaptable systems for diverse clinical settings. Full article

Background: Interoperability is fundamental for advancing digital health and digital therapeutics, particularly with the integration of technologies such as artificial intelligence (AI), blockchain, and federated learning. Low- and middle-income countries (LMICs), where digital infrastructure remains fragmented, face specific challenges in implementing standardized and scalable systems. Methods: This scoping review was conducted using the Arksey and O’Malley framework, refined by Levac et al., and the Joanna Briggs Institute guidelines. Five databases (PubMed, Scopus, IEEE Xplore, ACM Digital Library, and Google Scholar) were searched for peer-reviewed English language studies published between 2015 and 2025. We identified 255 potentially eligible articles and selected a 10% random sample (n = 26) using Stata 18 by StataCorp LLC, College Station, TX, USA, for in-depth data charting and thematic synthesis. Results: The selected studies spanned over 15 countries and addressed priority technologies, including mobile health (mHealth), the use of Health Level Seven (HL7)’s Fast Healthcare Interoperability Resources (FHIR) for data exchange, and blockchain. Interoperability enablers include standards (e.g., HL7 FHIR), data governance frameworks, and policy interventions. Low- and Middle-Income Countries (LMICs) face common issues related to digital capacity shortages, legacy systems, and governance fragmentation. Five thematic areas were identified: (1) policy and governance; (2) standards-based integration; (3) infrastructure and platforms; (4) emerging technologies; and (5) LMIC implementation issues. Conclusions: Emerging digital health technologies increasingly rely on interoperability standards to scale their operation. Although global standards such as FHIR and the Trusted Exchange Framework and Common Agreement (TEFCA) are gaining momentum, LMICs require dedicated governance, infrastructure, and capacity investments to make equitable use feasible. Future initiatives can benefit from using science- and equity-informed frameworks. Full article

Wireless Sensor Networks (WSNs) consist of numerous battery-powered sensor nodes that operate with limited energy, computation, and communication capabilities. Designing routing strategies that are both energy-efficient and attack-resilient is essential for extending network lifetime and ensuring secure data delivery. This paper proposes Adaptive Federated Reinforcement Learning-Hunger Games Search (AFRL-HGS), a Hybrid Routing framework that integrates multiple advanced techniques. At the node level, tabular Q-learning enables each sensor node to act as a reinforcement learning agent, making next-hop decisions based on discretized state features such as residual energy, distance to sink, congestion, path quality, and security. At the network level, Federated Reinforcement Learning (FRL) allows the sink node to aggregate local Q-tables using adaptive, energy- and performance-weighted contributions, with Polyak-based blending to preserve stability. The binary Hunger Games Search (HGS) metaheuristic initializes Cluster Head (CH) selection and routing, providing a well-structured topology that accelerates convergence. Security is enforced as a constraint through a lightweight trust and anomaly detection module, which fuses reliability estimates with residual-based anomaly detection using Exponentially Weighted Moving Average (EWMA) on Round-Trip Time (RTT) and loss metrics. The framework further incorporates energy-accounted control plane operations with dual-format HELLO and hierarchical ADVERTISE/Service-ADVERTISE (SrvADVERTISE) messages to maintain the routing tables. Evaluation is performed in a hybrid testbed using the Graphical Network Simulator-3 (GNS3) for large-scale simulation and Kali Linux for live adversarial traffic injection, ensuring both reproducibility and realism. The proposed AFRL-HGS framework offers a scalable, secure, and energy-efficient routing solution for next-generation WSN deployments. Full article

Edge computing offers low-latency and distributed processing for IoT applications but poses new security challenges, due to limited resources and decentralized data. Intrusion detection systems (IDSs) are essential for real-time threat monitoring, yet traditional IDS frameworks often struggle in edge environments, failing to meet efficiency requirements. This paper presents an efficient intrusion detection framework that integrates spatiotemporal hashing, federated learning, and fast K-nearest neighbor (KNN) retrieval. A hashing neural network encodes network traffic into compact binary codes, enabling low-overhead similarity comparison via Hamming distance. To support scalable retrieval, multi-index hashing is applied for sublinear KNN searching. Additionally, we propose an attention-guided federated aggregation strategy that dynamically adjusts client contributions, reducing communication costs. Our experiments on benchmark datasets demonstrate that our method achieves competitive detection accuracy with significantly lower computational, memory, and communication overhead, making it well-suited for edge-based deployment. Full article

Background/Objectives: Children with Down syndrome (DS) present unique and multifaceted nutritional challenges arising from genetic, metabolic, and developmental factors. Despite growing interest in the health of individuals with DS, dedicated nutritional guidelines tailored to their specific needs remain lacking. This narrative review aims to summarize current scientific evidence on nutritional status, challenges, and therapeutic strategies in children with DS, with an emphasis on clinical implications and practical recommendations for healthcare professionals. Methods: A literature search was conducted across four databases (PubMed, Scopus, Web of Science, and Google Scholar) for English-language publications from 1993 to June 2025. Thirty-five peer-reviewed articles were included, comprising original studies, narrative reviews, and expert guidelines (e.g., the American Academy of Pediatrics [AAP], the European Society for Paediatric Gastroenterology, Hepatology and Nutrition [ESPGHAN], and the European Federation of Associations of Dietitians [EFAD]). The selection process followed the PRISMA protocol. Studies were categorized according to key themes: energy requirements, comorbidities, feeding difficulties, nutrient needs, and therapeutic interventions. Results: Children with DS typically exhibit lower basal metabolic rates and altered body composition (i.e., higher fat mass and reduced lean mass), which increase their risk of both obesity and nutrient deficiencies. Common comorbidities—such as hypothyroidism, celiac disease, and gastrointestinal or immune disorders—further complicate dietary management. Feeding difficulties, including sucking/swallowing impairments, food selectivity, neophobia, and delayed independence in eating, are prevalent and significantly affect diet quality. Key nutrients of concern include protein, omega-3 fatty acids, fiber, vitamins B12 and D, iron, and antioxidants. Although no official nutrition guidelines currently exist for this population, existing recommendations from pediatric and dietetic organizations provide partial guidance that can be adapted to clinical practice. Conclusions: There is an urgent need to develop evidence-based, population-specific dietary guidelines for children with Down syndrome. Clinical nutrition care should be individualized, multidisciplinary, and proactive, integrating regular assessments of growth, feeding abilities, and biochemical markers. Dietitians must play a central role in both early intervention and long-term management. Further research, particularly interventional studies, is essential to optimize dietary strategies and improve health outcomes in this vulnerable population. Full article

This comprehensive review maps the fast-evolving landscape in which artificial intelligence (AI) and deep-learning (DL) techniques converge with the Internet of Things (IoT) to manage energy, comfort, and sustainability across smart environments. A PRISMA-guided search of four databases retrieved 1358 records; after applying inclusion criteria, 143 peer-reviewed studies published between January 2019 and April 2025 were analyzed. This review shows that AI-driven controllers—especially deep-reinforcement-learning agents—deliver median energy savings of 18–35% for HVAC and other major loads, consistently outperforming rule-based and model-predictive baselines. The evidence further reveals a rapid diversification of methods: graph-neural-network models now capture spatial interdependencies in dense sensor grids, federated-learning pilots address data-privacy constraints, and early integrations of large language models hint at natural-language analytics and control interfaces for heterogeneous IoT devices. Yet large-scale deployment remains hindered by fragmented and proprietary datasets, unresolved privacy and cybersecurity risks associated with continuous IoT telemetry, the growing carbon and compute footprints of ever-larger models, and poor interoperability among legacy equipment and modern edge nodes. The authors of researches therefore converges on several priorities: open, high-fidelity benchmarks that marry multivariate IoT sensor data with standardized metadata and occupant feedback; energy-aware, edge-optimized architectures that lower latency and power draw; privacy-centric learning frameworks that satisfy tightening regulations; hybrid physics-informed and explainable models that shorten commissioning time; and digital-twin platforms enriched by language-model reasoning to translate raw telemetry into actionable insights for facility managers and end users. Addressing these gaps will be pivotal to transforming isolated pilots into ubiquitous, trustworthy, and human-centered IoT ecosystems capable of delivering measurable gains in efficiency, resilience, and occupant wellbeing at scale. Full article

Background/Objectives: Antimicrobial consumption (AMC) surveillance and antimicrobial stewardship (AMS) constitute effective strategies to combat the increasing antimicrobial resistance rates worldwide. Post-Soviet countries (Armenia, Azerbaijan, Belarus, Estonia, Georgia, Kazakhstan, Kyrgyzstan, Latvia, Lithuania, Moldova, the Russian Federation, Tajikistan, Turkmenistan, Ukraine, and Uzbekistan) implemented various elements of AMC surveillance and AMS to different extents. The limited quantity and quality of data from post-Soviet countries make it difficult to assess health system performance; therefore, this region is a blind spot in global AMR monitoring. This systematic review assesses and characterises AMC surveillance and AMS implementation in post-Soviet countries. Methods: Evidence was compiled via a search in PubMed, Google Scholar, Embase, CyberLeninka, and Scopus. The eligibility criteria included AMC surveillance- and AMS-related papers in human health within defined regions and timelines. Some literature from the official websites of international and national health organisations was included in the search. Results: As a result of the searches, screening, and critical appraisal, three peer-reviewed publications and 31 documents were selected for analysis. Eleven out of fifteen countries with updated national action plans for combating antimicrobial resistance have defined AMC surveillance and AMS as strategic objectives. All 15 examined countries submitted antimicrobial consumption data to international networks and reported the existence of approved laws and regulations on antibiotic sales. However, disparities exist in the complexity of monitoring systems and AMS implementation between high-income and low-income countries in the region. Conclusions: This review provides key insights into the existing AMC surveillance and AMS implementation in former Soviet countries. Although the approach of this review lacks quantitative comparability, it provides a comprehensive qualitative framework for national-level AMC surveillance and AMS system assessment. Full article

Federated learning (FL), which enables collaborative learning across distributed nodes, confronts a significant heterogeneity challenge, primarily including resource heterogeneity induced by different hardware platforms, and statistical heterogeneity originating from non-IID private data distributions among clients. Neural architecture search (NAS), particularly one-shot NAS, holds great promise for automatically designing optimal personalized models tailored to such heterogeneous scenarios. However, the coexistence of both resource and statistical heterogeneity destabilizes the training of the one-shot supernet, impairs the evaluation of candidate architectures, and ultimately hinders the discovery of optimal personalized models. To address this problem, we propose a heterogeneity-aware personalized federated NAS (HAPFNAS) method. First, we leverage lightweight knowledge models to distill knowledge from clients to server-side supernet, thereby effectively mitigating the effects of heterogeneity and enhancing the training stability. Then, we build random-forest-based personalized performance predictors to enable the efficient evaluation of candidate architectures across clients. Furthermore, we develop a model-heterogeneous FL algorithm called heteroFedAvg to facilitate collaborative model training for the discovered personalized models. Comprehensive experiments on CIFAR-10/100 and Tiny-ImageNet classification datasets demonstrate the effectiveness of our HAPFNAS, compared to state-of-the-art federated NAS methods. Full article

The digital transformation of the Architecture, Engineering and Construction sector is accelerating the adoption of digital platforms as critical enablers of data integration, stakeholder collaboration and process optimization. This paper presents a systematic review of 125 peer-reviewed journal articles (2015–2025), selected through a PRISMA-guided search using the Scopus database, with inclusion criteria focused on English-language academic literature on platform-enabled digitalization in the built environment. Studies were grouped into six thematic domains, i.e., artificial intelligence in construction, digital twin integration, lifecycle cost management, BIM-GIS for underground utilities, energy systems and public administration, based on a combination of literature precedent and domain relevance. Unlike existing reviews focused on single technologies or sectors, this work offers a cross-sectoral synthesis, highlighting shared challenges and opportunities across disciplines and lifecycle stages. It identifies the functional roles, enabling technologies and systemic barriers affecting digital platform adoption, such as fragmented data sources, limited interoperability between systems and siloed organizational processes. These barriers hinder the development of integrated and adaptive digital ecosystems capable of supporting real-time decision-making, participatory planning and sustainable infrastructure management. The study advocates for modular, human-centered platforms underpinned by standardized ontologies, explainable AI and participatory governance models. It also highlights the importance of emerging technologies, including large language models and federated learning, as well as context-specific platform strategies, especially for applications in the Global South. Full article

Objectives: With the growing importance of mobile technology and artificial intelligence (AI) in healthcare, the development of automated cardiac diagnostic systems has gained strategic significance. This review aims to summarize the current state of knowledge on the use of AI in the analysis of electrocardiographic (ECG) signals obtained from wearable devices, particularly smartwatches, and to outline perspectives for future clinical applications. Methods: A narrative literature review was conducted using PubMed, Web of Science, and Scopus databases. The search focused on combinations of keywords related to AI, ECG, and wearable technologies. After screening and applying inclusion criteria, 152 publications were selected for final analysis. Conclusions: Modern AI algorithms—especially deep neural networks—show promise in detecting arrhythmias, heart failure, prolonged QT syndrome, and other cardiovascular conditions. Smartwatches without ECG sensors, using photoplethysmography (PPG) and machine learning, show potential as supportive tools for preliminary atrial fibrillation (AF) screening at the population level, although further validation in diverse real-world settings is needed. This article explores innovation trends such as genetic data integration, digital twins, federated learning, and local signal processing. Regulatory, technical, and ethical challenges are also discussed, along with the issue of limited clinical evidence. Artificial intelligence enables a significant enhancement of personalized, mobile, and preventive cardiology. Its integration into smartwatch ECG analysis opens a path toward early detection of cardiac disorders and the implementation of population-scale screening approaches. Full article

Root-knot nematodes, Meloidogyne spp., are widespread phytoparasites that cause a significant reduction in the yield of tomato Solanum lycopersicum. In the Russian Federation, where the use of chemical nematicides is limited due to environmental and toxicological risks, the cultivation of resistant varieties and hybrids remains the most effective and environmentally safe method to control Meloidogyne. In the course of this study, the resistance screening of 20 tomato varieties/hybrids and 21 mutant lines from the collection of the FSBSI FRCBPP to M. hapla was carried out using a comprehensive approach that included morphological and biochemical analysis methods. Resistance was assessed by calculating the gall formation index, the degree of root system damage, and biochemical parameters of fruits—vitamin C content and titratable acidity. In addition, molecular screening was carried out using the SCAR marker Mi23 to identify the Mi-1.2 gene, known as a key factor in resistance to a number of Meloidogyne spp. Although Mi-1.2 is not typically associated with resistance to M. hapla, all genotypes carrying this gene showed phenotypic resistance. This unexpected correlation suggests the possible involvement of Mi-associated or parallel mechanisms and highlights the need for further investigation into noncanonical resistance pathways. It was found that when susceptible genotypes were infected with M. hapla, there was a tendency for the vitamin C content to decrease, while resistant lines retained values close to the control. The presence of the Mi-1.2 gene was confirmed in 9.5% of samples. However, the phenotypic resistance of some lines, such as Volgogradets, which do not contain a marker for the Mi-1.2 gene, indicates a polygenic nature of resistance, alternative genetic mechanisms, or the possible influence of epigenetic mechanisms. The obtained data highlight the potential of using the identified resistant genotypes in breeding programs and the need for further studies of the molecular mechanisms of resistance, including the search for new markers specific to M. hapla, to develop effective strategies for tomato protection in sustainable agriculture. Full article

This research focuses on the ideological sphere of criminals with the highest status in the Russian Federation. This ideological sphere was studied in literary sources of various kinds on the basis of repeatability (the existence of linguistic facts) and averaging (external and internal confrontation of sources). It is suggested that, in speech, there exist some selective overinterpretations of world religions that neglect basic elements of the traditional law-abiding picture of the world and that are directly based on literary fiction instead of the scientific literature. On the other hand, there can be some search for faith connected with the belief in spiritual knowledge from the dead, divine beings, and God. Full article

In recent years, artificial intelligence (AI) has achieved significant progress and remarkable advancements across various disciplines, including biology, computer science, and industry. However, the increasing complexity of AI network structures and the vast number of associated parameters impose substantial computational and storage demands, severely limiting the practical deployment of these models on resource-constrained edge devices. Although edge intelligence methods have been proposed to alleviate the computational and storage burdens, they still face multiple persistent challenges, such as large-scale model deployment, poor interpretability, privacy and security vulnerabilities, and energy efficiency constraints. This article systematically reviews the current advancements in edge intelligence technologies, highlights key enabling techniques including model sparsity, quantization, knowledge distillation, neural architecture search, and federated learning, and explores their applications in industrial, automotive, healthcare, and consumer domains. Furthermore, this paper presents a comparative analysis of these techniques, summarizes major trade-offs, and proposes decision frameworks to guide deployment strategies under different scenarios. Finally, it discusses future research directions to address the remaining technical bottlenecks and promote the practical and sustainable development of edge intelligence. Standing at the threshold of an exciting new era, we believe edge intelligence will play an increasingly critical role in transforming industries and enabling ubiquitous intelligent services. Full article

Objectives: Limited variety in children’s diets impairs lifelong nutrition and health. Head Start is a federal program serving expectant families and children in the United States living at or below the poverty line to the age of five. Head Start children face barriers to nutrient intake. Many nutrition education curricula are implemented in Head Start settings; however, few have addressed whether taste or non-taste food exposures are more effective and appropriate for improving dietary intake in this population. This review evaluates if taste or non-taste exposures are more effective at increasing willingness to try, consume, and like food in children participating in Head Start. Methods: PubMed was searched for studies published in the last 10 years with children aged 2 to 12 years. Included studies had an intervention with exposure to food or its likeness, focusing on those studying Head Start or similar samples. Articles were excluded if they referenced exposure to marketing, disease, or foodborne illness. Results: Searches yielded 903 results. 51 articles were screened, and 15 were included in the narrative. Studies revealed that combinations of taste and non-taste exposures improved children’s willingness to try, consume, and like food. Conclusions: Taste and non-taste exposures, when used independently, inconsistently affect children’s willingness to try, consume, and like food; exposures are most effective when combined, although research on the topic faces limitations of study design and environmental controls. With federal standards for nutrition, Head Start programs should implement food exposure activities. Additional studies with improved designs and controls for exposure to the environment should be completed in this population to increase the validity and reliability of food exposure research. Full article