Search Results (44)

Poor diet is the leading preventable risk factor for death worldwide, associated with over 10 million premature deaths and USD 8 trillion related costs every year. Artificial intelligence or AI is rapidly emerging as the most historically disruptive, innovatively dynamic, rapidly scaled, cost-efficient, and economically productive technology (which is increasingly providing transformative countermeasures to these negative health trends, especially in low- and middle-income countries (LMICs) and underserved communities which bear the greatest burden from them). Yet widespread confusion persists among healthcare systems and policymakers on how to best identify, integrate, and evolve the safe, trusted, effective, affordable, and equitable AI solutions that are right for their communities, especially in public health nutrition. We therefore provide here the first known global, comprehensive, and actionable narrative review of the state of the art of AI-accelerated nutrition assessment and healthy eating for healthcare systems, generated by the first automated end-to-end empirical index for responsible health AI readiness and maturity: the Responsible Health AI readiness and Maturity Index (RHAMI). The index is built and the analysis and review conducted by a multi-national team spanning the Global North and South, consisting of front-line clinicians, ethicists, engineers, executives, administrators, public health practitioners, and policymakers. RHAMI analysis identified the top-performing healthcare systems and their nutrition AI, along with leading use cases including multimodal edge AI nutrition assessments as ambient intelligence, the strategic scaling of practical embedded precision nutrition platforms, and sovereign swarm agentic AI social networks for sustainable healthy diets. This index-based review is meant to facilitate standardized, continuous, automated, and real-time multi-disciplinary and multi-dimensional strategic planning, implementation, and optimization of AI capabilities and functionalities worldwide, aligned with healthcare systems’ strategic objectives, practical constraints, and local cultural values. The ultimate strategic objectives of the RHAMI’s application for AI-accelerated public health nutrition are to improve population health, financial efficiency, and societal equity through the global cooperation of the public and private sectors stretching across the Global North and South. Full article

Ensuring the integrity of medical images is essential to securing clinical workflows, telemedicine platforms, and healthcare IoT environments. Existing watermarking and reversible data-hiding approaches often modify pixel intensities, reducing diagnostic fidelity, introducing embedding constraints, or causing instability under compression and format conversion. This work proposes a distortion-free, non-embedding authentication framework that leverages the inherent stability of the most significant bit (MSB) patterns in the Non-Region of Interest (NROI) to construct a secure and tamper-sensitive reference for the diagnostic Region of Interest (ROI). The ROI is partitioned into fixed blocks, each producing a 256-bit SHA-256 signature. Instead of embedding this signature, each hash bit is mapped to an NROI pixel whose MSB matches the corresponding bit value, and only the encrypted coordinates of these pixels are stored externally in a secure database. During verification, hashes are recomputed and compared bit-by-bit with the MSB sequence extracted from the referenced NROI coordinates, enabling precise block-level tamper localization without modifying the image. Extensive experiments conducted on MRI (OASIS), X-ray (ChestX-ray14), and CT (CT-ORG) datasets demonstrate the following: (i) perfect zero-distortion fidelity; (ii) stable and deterministic MSB-class mapping with abundant coordinate diversity; (iii) 100% detection of intentional ROI tampering with no false positives across the six clinically relevant manipulation types; and (iv) robustness to common benign Non-ROI operations. The results show that the proposed scheme offers a practical, secure, and computationally lightweight solution for medical image integrity verification in PACS systems, cloud-based archives, and healthcare IoT applications, while avoiding the limitations of embedding-based methods. Full article

Sensor faults can produce incorrect data and disrupt the operation of entire systems. In critical environments, such as healthcare, industrial automation, or autonomous platforms, these faults can lead to serious consequences if not detected early. This study explores how faults in MEMS microphones can be classified using lightweight ML models suitable for devices with limited resources. A dataset was created for this work, including both real faults (normal, clipping, stuck, and spikes) caused by issues like acoustic overload and undervoltage, and synthetic faults (drift and bias). The goal was to simulate a range of fault behaviors, from clear malfunctions to more subtle signal changes. Convolutional Neural Networks (CNNs) and hybrid models that use CNNs for feature extraction with classifiers like Decision Trees, Random Forest, MLP, Extremely Randomized Trees, and XGBoost, were evaluated based on accuracy, F1-score, inference time, and model size towards real-time use in embedded systems. Experiments showed that using 2-s windows improved accuracy and F1-scores. These findings help design ML solutions for sensor fault classification in resource-limited embedded systems and IoT applications. Full article

Breast cancer is a leading cause of mortality among women, disproportionately affecting Hispanic populations in the U.S., particularly those with limited health literacy and language access. To address these disparities, we present a bilingual, web-based educational platform tailored to low-literacy Hispanic users. The platform supports full navigation in English and Spanish, with seamless language switching and both written and spoken input options. It incorporates automatic speech recognition (ASR) capable of handling code-switching, enhancing accessibility for bilingual users. Educational content is delivered through culturally sensitive videos organized into four categories: prevention, detection, diagnosis, and treatment. Each video includes embedded and post-video assessment questions aligned with Bloom’s Taxonomy to foster active learning. Users can monitor their progress and quiz performance via a personalized dashboard. An integrated chatbot, powered by large language models (LLMs), allows users to ask foundational breast cancer questions in natural language. The platform also recommends relevant resources, including nearby treatment centers, and support groups. LLMs are further used for ASR, question generation, and semantic response evaluation. Combining language technologies and LLMs reduces disparities in cancer education and supports informed decision-making among underserved populations, playing a pivotal role in reducing information gaps and promoting informed healthcare decisions. Full article

Background/Objectives: Functional cognition, integrating cognitive abilities during real-life task performance, is essential for understanding daily functioning in children and adolescents. Traditional paper-based cognitive assessments in controlled environments often lack ecological validity. Although performance-based assessments more accurately represent functioning in natural contexts, most have not been transformed into digital formats. With technology increasingly embedded in education and healthcare, examining the extent/nature of adaptations, benefits, and challenges of digitizing these tools is important. This conceptual review aimed to (1) examine the extent/nature of traditional performance-based cognitive assessments adapted into digital platforms, (2) compare ecological validity/scoring metrics of traditional and digital tools, and (3) identify opportunities and propose recommendations for future development. Methods: We used an AI-based tool (Elicit Pro, Elicit Plus 2024) to conduct a literature search for publications from the past decade, focusing on transformations of traditional assessments into digital platforms for children and adolescents. This initial search yielded 240 items. After screening, 45 were retained for manual review. Studies were extracted based on their discussion of the assessments (traditional or digital) and assessment tools used. Ultimately, 13 papers that met the inclusion criteria were evaluated based on units of analysis. Results: The analysis yielded three units. The first unit focused on digital transformation trends: four assessments (31%) were converted to digital platforms, two (15%) were developed as native digital tools, and the majority (seven, 54%) remained traditional. In the second unit, assessments were evaluated according to ecological validity and digital availability, demonstrating that assessments with high ecological validity tended not to be digitally accessible. The third unit synthesized scoring metrics, identifying eight distinct cognitive domains. Conclusions: Digitizing functional cognitive assessments offers greater accessibility, precision, and scalability, but replicating real-world contexts remains challenging. Emerging technologies may enhance ecological validity and support development of effective, technology-enhanced assessment practices. Full article

Microcontroller units (MCUs) serve as the core components of embedded systems. In the era of smart IoT, embedded devices are increasingly deployed on mobile platforms, leading to a growing demand for low-power consumption. As a result, low-power technology for MCUs has become increasingly critical. This paper systematically reviews the development history and current technical challenges of MCU low-power technology. It then focuses on analyzing system-level low-power optimization pathways for integrating MCUs with artificial intelligence (AI) technology, including lightweight AI algorithm design, model pruning, AI acceleration hardware (NPU, GPU), and heterogeneous computing architectures. It further elaborates on how AI technology empowers MCUs to achieve comprehensive low power consumption from four dimensions: task scheduling, power management, inference engine optimization, and communication and data processing. Through practical application cases in multiple fields such as smart home, healthcare, industrial automation, and smart agriculture, it verifies the significant advantages of MCUs combined with AI in performance improvement and power consumption optimization. Finally, this paper focuses on the key challenges that still need to be addressed in the intelligent upgrade of future MCU low power consumption and proposes in-depth research directions in areas such as the balance between lightweight model accuracy and robustness, the consistency and stability of edge-side collaborative computing, and the reliability and power consumption control of the sensor-storage-computing integrated architecture, providing clear guidance and prospects for future research. Full article

Background: Transitions from hospital to long-term care (LTC) facilities are critical periods for older adults living with dementia, often involving complex medical, cognitive, and psychosocial needs. Virtual team-based care has emerged as a promising strategy to improve communication, coordination, and continuity of care during these transitions. However, there is limited evidence on how such approaches are implemented in practice, particularly with respect to inclusion, equity, and engagement of older adults and families. Objective: This study aimed to identify the enablers and barriers to delivering virtual team-based care to support older adults with dementia in transitioning from hospital to LTC. Methods: We conducted a qualitative study using semi-structured interviews, focus groups, and a policy review. Data were collected from 60 participants, including healthcare providers, older adults, and family care partners across hospital and LTC settings in British Columbia, Canada. Thematic analysis was conducted using a hybrid inductive and deductive approach. Eighteen institutional policies and guidelines on virtual care and dementia transitions were reviewed to contextualize findings. Results: Four themes were identified: (1) enhancing communication and collaboration, (2) engaging families in care planning, (3) digital access and literacy, and (4) organizational readiness and infrastructure. While virtual huddles and secure messaging platforms supported timely coordination, implementation was inconsistent due to infrastructure limitations, unclear protocols, and staffing pressures. Institutional policies emphasized privacy and security but lacked guidance for inclusive engagement of older adults and families. Many participants described limited access to reliable technology, a lack of training, and the absence of tools tailored for individuals with cognitive impairment. Conclusions: Virtual care has the potential to support more coordinated and inclusive transitions for people with dementia, but its success depends on more than technology. Structured protocols, inclusive policies, and leadership commitment are essential to ensure equitable access and meaningful engagement. The proposed VIRTUAL framework offers practical tips for strengthening virtual team-based care by embedding ethical, relational, and infrastructural readiness across settings. Full article

Background: Artificial intelligence (AI) and machine learning (ML) have been reshaping maternal, fetal, neonatal, and reproductive healthcare by enhancing risk prediction, diagnostic accuracy, and operational efficiency across the perinatal continuum. However, no comprehensive synthesis has yet been published. Objective: To conduct a scoping review of reviews of AI/ML applications spanning reproductive, prenatal, postpartum, neonatal, and early child-development care. Methods: We searched PubMed, Embase, the Cochrane Library, Web of Science, and Scopus through April 2025. Two reviewers independently screened records, extracted data, and assessed methodological quality using AMSTAR 2 for systematic reviews, ROBIS for bias assessment, SANRA for narrative reviews, and JBI guidance for scoping reviews. Results: Thirty-nine reviews met our inclusion criteria. In preconception and fertility treatment, convolutional neural network-based platforms can identify viable embryos and key sperm parameters with over 90 percent accuracy, and machine-learning models can personalize follicle-stimulating hormone regimens to boost mature oocyte yield while reducing overall medication use. Digital sexual-health chatbots have enhanced patient education, pre-exposure prophylaxis adherence, and safer sexual behaviors, although data-privacy safeguards and bias mitigation remain priorities. During pregnancy, advanced deep-learning models can segment fetal anatomy on ultrasound images with more than 90 percent overlap compared to expert annotations and can detect anomalies with sensitivity exceeding 93 percent. Predictive biometric tools can estimate gestational age within one week with accuracy and fetal weight within approximately 190 g. In the postpartum period, AI-driven decision-support systems and conversational agents can facilitate early screening for depression and can guide follow-up care. Wearable sensors enable remote monitoring of maternal blood pressure and heart rate to support timely clinical intervention. Within neonatal care, the Heart Rate Observation (HeRO) system has reduced mortality among very low-birth-weight infants by roughly 20 percent, and additional AI models can predict neonatal sepsis, retinopathy of prematurity, and necrotizing enterocolitis with area-under-the-curve values above 0.80. From an operational standpoint, automated ultrasound workflows deliver biometric measurements at about 14 milliseconds per frame, and dynamic scheduling in IVF laboratories lowers staff workload and per-cycle costs. Home-monitoring platforms for pregnant women are associated with 7–11 percent reductions in maternal mortality and preeclampsia incidence. Despite these advances, most evidence derives from retrospective, single-center studies with limited external validation. Low-resource settings, especially in Sub-Saharan Africa, remain under-represented, and few AI solutions are fully embedded in electronic health records. Conclusions: AI holds transformative promise for perinatal care but will require prospective multicenter validation, equity-centered design, robust governance, transparent fairness audits, and seamless electronic health record integration to translate these innovations into routine practice and improve maternal and neonatal outcomes. Full article

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

Robust and efficient contactless human–machine interaction is critical for integrated sensor systems in clinical settings, demanding low-power solutions adaptable to edge computing platforms. This paper presents a real-time hand gesture recognition system using a low-power Frequency-Modulated Continuous Wave (FMCW) radar sensor, featuring a novel Multiple Feature Fusion (MFF) framework optimized for deployment on edge devices. The proposed system integrates velocity profiles, angular variations, and spatial-temporal features through a dual-stage processing architecture: an adaptive energy thresholding detector segments gestures, followed by an attention-enhanced neural classifier. Innovations include dynamic clutter suppression and multi-path cancellation optimized for complex clinical environments. Experimental validation demonstrates high performance, achieving 98% detection recall and 93.87% classification accuracy under LOSO cross-validation. On embedded hardware, the system processes at 28 FPS, showing higher robustness against environmental noise and lower computational overhead compared with existing methods. This low-power, edge-based solution is highly suitable for applications like sterile medical control and patient monitoring, advancing contactless interaction in healthcare by addressing efficiency and robustness challenges in radar sensing for edge computing. Full article

The increasing integration of digital technologies in healthcare has expanded the attack surface for privacy violations in critical systems such as electronic health records (EHRs), telehealth platforms, and medical device software. However, current vulnerability detection datasets lack domain-specific privacy annotations essential for compliance with healthcare regulations like HIPAA and GDPR. This study presents C3-VULMAP, a novel and large-scale dataset explicitly designed for privacy-aware vulnerability detection in healthcare software. The dataset comprises over 30,000 vulnerable and 7.8 million non-vulnerable C/C++ functions, annotated with CWE categories and systematically mapped to LINDDUN privacy threat types. The objective is to support the development of automated, privacy-focused detection systems that can identify fine-grained software vulnerabilities in healthcare environments. To achieve this, we developed a hybrid construction methodology combining manual threat modeling, LLM-assisted synthetic generation, and multi-source aggregation. We then conducted comprehensive evaluations using traditional machine learning algorithms (Support Vector Machines, XGBoost), graph neural networks (Devign, Reveal), and transformer-based models (CodeBERT, RoBERTa, CodeT5). The results demonstrate that transformer models, such as RoBERTa, achieve high detection performance (F1 = 0.987), while Reveal leads GNN-based methods (F1 = 0.993), with different models excelling across specific privacy threat categories. These findings validate C3-VULMAP as a powerful benchmarking resource and show its potential to guide the development of privacy-preserving, secure-by-design software in embedded and electronic healthcare systems. The dataset fills a critical gap in privacy threat modeling and vulnerability detection and is positioned to support future research in cybersecurity and intelligent electronic systems for healthcare. Full article

Continuous-time Recurrent Neural Networks (CTRNNs) are well-suited for modeling temporal dynamics in low-power neuromorphic and analog computing systems, making them promising candidates for edge-based human activity recognition (HAR) in healthcare. However, training CTRNNs remains challenging due to their continuous-time nature and the need to respect physical hardware constraints. In this work, we propose G-CTRNN, a novel gradient-based training framework for analog-friendly CTRNNs designed for embedded healthcare applications. Our method extends Backpropagation Through Time (BPTT) to continuous domains using TensorFlow’s automatic differentiation, while enforcing constraints on time constants and synaptic weights to ensure hardware compatibility. We validate G-CTRNN on the WISDM human activity dataset, which simulates realistic wearable sensor data for healthcare monitoring. Compared to conventional RNNs, G-CTRNN achieves superior classification accuracy with fewer parameters and greater stability—enabling continuous, real-time HAR on low-power platforms such as MEMS computing networks. The proposed framework provides a pathway toward on-device AI for remote patient monitoring, elderly care, and personalized healthcare in resource-constrained environments. Full article

A nanostructured sensing platform was developed by integrating gold-decorated lignin nanoparticles (AuLNPs) into electrospun polylactic acid (PLA) fibre mats. The composite material combines the high surface-to-volume ratio of PLA nanofibres with the chemical functionality of lignin—a polyphenolic biopolymer rich in hydroxyl and aromatic groups—enabling selective interactions with volatile amines through hydrogen bonding and Van der Waals forces. The embedded gold nanoparticles (AuNPs) further enhance the sensor’s electrical conductivity and provide catalytic sites for improved analyte interaction. The sensor exhibited selective adsorption of amine vapours, showing particularly strong affinity for dimethylamine (DMA), with a limit of detection (LOD) of approximately 440 ppb. Relative humidity (RH) was found to significantly influence sensor performance by facilitating amine protonation, thus promoting interaction with the sensing surface. The developed sensor demonstrated excellent selectivity, sensitivity and reproducibility, highlighting its potential for real-time detection of amines in environmental monitoring, industrial safety and healthcare diagnostics. Full article

Large Language Models (LLMs), like GPT and BERT, have significantly advanced Natural Language Processing (NLP), enabling high performance on complex tasks. However, their size and computational needs make LLMs unsuitable for deployment on resource-constrained devices, where efficiency, speed, and low power consumption are critical. Tiny Language Models (TLMs), also known as BabyLMs, offer compact alternatives by using advanced compression and optimization techniques to function effectively on devices such as smartphones, Internet of Things (IoT) systems, and embedded platforms. This paper provides a comprehensive survey of TLM architectures and methodologies, including key techniques such as knowledge distillation, quantization, and pruning. Additionally, it explores potential and emerging applications of TLMs in automation and control, covering areas such as edge computing, IoT, industrial automation, and healthcare. The survey discusses challenges unique to TLMs, such as trade-offs between model size and accuracy, limited generalization, and ethical considerations in deployment. Future research directions are also proposed, focusing on hybrid compression techniques, application-specific adaptations, and context-aware TLMs optimized for hardware-specific constraints. This paper aims to serve as a foundational resource for advancing TLMs capabilities across diverse real-world applications. Full article

With the rapid digitization of healthcare, the secure transmission of medical images has become a critical concern, especially given the increasing prevalence of cyber threats and data privacy breaches. Medical images are frequently transmitted via the Internet and cloud platforms, making them susceptible to unauthorized access, tampering, and theft. While traditional cryptographic techniques play a vital role, they are often insufficient to fully ensure the integrity and confidentiality of these sensitive images. In this paper, we present AGFI-GAN, a robust and secure framework for medical image watermarking that leverages attention-guided and Feature-Integrated mechanisms within a Generative Adversarial Network (GAN). Specifically, a Feature-Integrated Module (FIM) is proposed to effectively capture and combine both shallow and deep image features to facilitate multilayer fusion with the watermark. The dense connections within the module facilitate feature reuse, boosting the system’s robustness. To mitigate distortion from watermark embedding, an Attention Module (AM) is utilized, generating an attention mask by extracting global image features. This attention mask prioritizes features in less prominent and textured regions, allowing for stronger watermark embedding, while other features are downplayed to enhance the overall effectiveness of the watermarking process. The framework is evaluated based on its versatility, embedding capacity, robustness, and imperceptibility, and the results confirm its effectiveness. The study shows a marked improvement over the baseline, thus highlighting the framework’s superiority. Full article