Search Results (936)

Background: Telemedicine complements traditional healthcare delivery and may improve access, continuity of care, and patient engagement, particularly in chronic conditions requiring regular follow-up. Video consultation is a widely adopted telemedicine modality and is increasingly integrated into hybrid care models. Methods: This real-world implementation project describes scheduled video consultations embedded in a hybrid care model for children and adolescents with type 1 diabetes using continuous glucose monitoring (CGM) and integrated insulin delivery technologies as part of routine clinical care. A total of 38 families were offered video consultations as part of routine care; 18 adopted the hybrid model. Video consultations were used for routine follow-up, shared review of device data, treatment adjustment, and diabetes education. Family experience was assessed using a voluntary 5-point Likert-scale satisfaction questionnaire. Complete longitudinal CGM data were available for 13 participants, all of whom were established users of the same automated insulin delivery (AID) platform (MiniMed™ 780G (Medtronic MiniMed, Inc. Minneapolis, MN, USA) integrated with Guardian™ 4 (Medtronic MiniMed, Inc. Minneapolis, MN, USA) continuous glucose monitoring). Results: Between 2022 and 2024, 162 video consultations were conducted. Acceptability was high, with 95% (17/18) of respondents reporting high satisfaction (score ≥ 4 on the 5-point Likert scale). 89% (16/18) of families perceived the quality of care as comparable to face-to-face visits for routine follow-up. Families highlighted convenience, reduced travel burden, and flexibility, as well as the value of shared review of CGM and AID system data. Group-level CGM-derived metrics appeared descriptively similar across sequential face-to-face visits and video consultations. Individual patient trajectories showed expected variability but no consistent pattern of deterioration during periods of remote follow-up. Conclusions: Video consultation is a feasible and well-accepted complementary modality within hybrid care models for pediatric type 1 diabetes. When integrated with CGM and automated insulin delivery systems, it supports personalized, data-driven clinical decision-making and continuity of care. Structured implementation and systematic evaluation are essential for sustainable integration into routine practice. Full article

Remote tele-rehabilitation requires objective pain assessment, but existing approaches fail in two distinct ways. Self-report scales such as the Visual Analog Scale and the Numeric Pain Rating Scale are easy to falsify, opening a special case of the Oracle problem in blockchain-based insurance. Cloud-based computer vision handles falsification but transmits raw biometric video off the patient’s device, violating privacy requirements. A decentralized Edge AI-Oracle architecture is proposed that combines MediaPipe Face Mesh landmark extraction with a recurrent classifier mapping Action-Unit feature sequences to a learned pain score aligned with the Prkachin and Solomon Pain Intensity scale. The recurrent cell is selected empirically across short-context (T = 2) and long-context (T = 120 frames at 24 fps) regimes, with a two-layer Long Short-Term Memory (LSTM) network adopted for deployment. Inference and Elliptic Curve Digital Signature Algorithm (ECDSA) signing run inside an ARM TrustZone Trusted Execution Environment (TEE). Biometric logs are stored off-chain on the InterPlanetary File System (IPFS). Smart contracts anchor results on-chain and open a 24 h optimistic verification window for an off-chain Watchtower auditor. On SynPAIN the LSTM reaches F1 = 0.683 on T = 120 video (leave-one-stratum-out), with a directional but non-significant advantage over Gated Recurrent Unit (GRU) (Wilcoxon p = 0.167). Cross-dataset validation on BioVid Heat Pain Database Part A (87 subjects, 174 paired observations, leave-one-subject-out) yields F1 = 0.519 for LSTM and 0.499 for GRU (Wilcoxon p = 0.549). A processor-only TEE surrogate benchmark estimates 1.96 ms (FP32) and 0.45 ms (INT8) inference latency at T = 120 with a 0.34 MB footprint and 707 µs ECDSA signing latency, leaving the INT8 inference latency more than an order of magnitude below the 33 ms per-frame budget. The dual-layer storage reduces gas costs by a factor of 23.4 (160,261 vs. 3,744,872 gas), corresponding to an illustrative mainnet cost of approximately 0.53 USD per submission at 1 gwei, rising to roughly 16 USD at a busier 30 gwei, and falling to approximately 0.005 USD on Arbitrum One (April 2026 reference parameters), so that continuous monitoring is economically practical on Layer-2. An adaptive-adversary analysis of the Watchtower shows that gross score tampering is detected at every usable operating threshold, whereas a rational adversary who inflates by less than the dispute threshold, or who shapes the injected score to fall just inside it, evades detection. Because the false-positive rate reaches zero only for $\mathsf{\delta }\gtrsim 0.15$, the protocol bounds rather than eliminates patient-side fraud and motivates a zero-knowledge proof-of-inference successor. The framework is architecturally and economically feasible as a cryptographically verifiable, privacy-preserving tele-rehabilitation substrate aligned with General Data Protection Regulation (GDPR) and Health Insurance Portability and Accountability Act (HIPAA) requirements through the Zero-Video Transmission principle, while remaining economically viable under post-Dencun mainnet and Layer-2 conditions. Recognition accuracy on real-world data and robustness to small-magnitude tampering remain limitations that the interchangeable recognition and audit components must improve before clinical deployment. Full article

Musculoskeletal disorders caused by poor posture are a major global health concern, contributing to spinal deformities and chronic pain. This study presents a mobile health (mHealth) enabled smart orthosis for real-time monitoring and correction of spinal posture. The wearable system integrates inertial measurement units along the spine to capture curvature data, processed through computational models to detect postural deviations. A connected mobile application enables real-time feedback, continuous monitoring, and remote assessment. Laboratory validation demonstrated reliable sensor performance. The proposed mHealth solution supports early diagnosis, long-term monitoring, and prevention of posture-related disorders, promoting personalized spine care and patient engagement in daily life. Full article

Background/Objectives: As a key health information and communication technology, mobile health information services (MHISs) play a critical role in delivering health information, enabling remote monitoring, and supporting patient well-being. However, widespread resistance among older adults hinders their access to these information services and undermines these benefits. Employing the technology–personal–environment (TPE) framework, this study constructed and verified a comprehensive model to explain older adults’ resistance to MHIS use. Methods: Quantitative data from 430 elderly individuals aged 65 and above from China who participated in the free health check-up basic public health program were analyzed using structural equation modeling. Results: Technology access barriers, technology usage barriers, declining physiological conditions, and resistance to change were positively related to technology anxiety. Declining physiological conditions, resistance to change, social legitimacy power, and perceived institutional effort were negatively related to perceived autonomy. Additionally, technology anxiety was positively related to resistance to MHIS use, while perceived autonomy was negatively related to resistance to MHIS use. Conclusions: The findings clarify the mechanisms linking technological barriers, individual characteristics, and environmental factors to older adults’ resistance to MHIS use. Therefore, relevant health information service providers should adopt systematic actions that simultaneously alleviate technology anxiety through user-centric design and supportive training while fostering perceived autonomy by respecting older adults’ choices and enabling meaningful participation. These findings offer actionable insights for healthcare information system designers and providers to reduce older adults’ exclusion from digital health information ecosystems, thereby enhancing patient well-being among aging populations. Full article

Stroke remains a leading cause of death and long-term disability worldwide, making prevention strategies a global health priority. Emerging technologies—including artificial intelligence (AI), wearable devices, digital health applications, and drone-assisted emergency systems—are increasingly being explored to improve stroke prevention and early management. In primary prevention, machine learning models can identify individuals at high risk of stroke using clinical and behavioral data with high reported predictive accuracy, although most models are derived from retrospective, single-center datasets and still require prospective external validation. Digital devices and wearable technologies enable continuous monitoring of cardiovascular risk factors and support behavioral interventions aimed at reducing vascular risk. In secondary prevention, AI-based tools are being developed to predict stroke recurrence, identify modifiable risk factors, and detect patients at risk of poor medication adherence. In the acute setting, AI-assisted neuroimaging platforms are already integrated into clinical and telestroke workflows, supporting rapid triage and treatment decisions. In parallel, drone-based emergency systems may contribute to improved outcomes by reducing prehospital delays and facilitating telemedicine-based triage in remote or resource-limited settings, although current evidence is derived largely from out-of-hospital cardiac arrest pathways rather than stroke-specific trials. Although advanced neurotechnological systems capable of real-time neurophysiological monitoring and closed-loop neuromodulation exist in other neurological disorders, their role in stroke prevention remains largely theoretical. Overall, these technologies offer promising opportunities to reshape the continuum of stroke prevention and care, but further validation, integration into clinical workflows, and evidence of real-world effectiveness are required before widespread implementation. Full article

Epidermolysis bullosa (EB) comprises a group of rare inherited genodermatoses characterized by fragility and blistering of the skin and mucous membranes, chronic wounding, and significant morbidity including increased risk of squamous cell carcinoma in severe subtypes. Key unmet priorities include reducing diagnostic latency, establishing objective wound monitoring, enabling early detection of malignant transformation within chronic ulcerations, and developing therapies that durably modify disease progression. Artificial intelligence (AI) encompassing machine learning (ML), and deep learning (DL) is increasingly integrated into EB research and clinical practice to address these unmet needs. This structured narrative review synthesises current evidence on AI applications in EB spanning genetic diagnostics, wound assessment, inflammatory endotyping, drug repurposing, and emerging therapeutic technologies, and integrates evidence from registered clinical trials. In genomics, DL-based splicing prediction models and variant prioritisation frameworks accelerate pathogenic variant detection and reduce diagnostic latency. In wound care, convolutional neural networks-based platforms enable automated lesion segmentation and remote monitoring, while multimodal AI models predict healing trajectories and support stratification of wounds by chronicity. Computational transcriptomic analyses have identified candidate repurposing agents by reversing pathogenic gene expression signatures in EB tissue. Emerging convergence of AI with biosensors-integrated wound dressings and three-dimensional bioprinting of genetically corrected skin substitutes represents a transformative future direction. Translational barriers include limited EB-specific training datasets, algorithmic bias across diverse skin phototypes, the interpretability deficit of DL systems, and evolving regulatory frameworks for AI as a medical device. Expansion of internationally interoperable EB disease registries with standardised wound imaging protocols is identified as the single most impactful intervention to accelerate AI adoption. A minimum endpoint set for AI-assisted EB wound assessment, incorporating wound area trajectory, wound type classification, tissue composition, and paired patient-reported pain and itch scores, is proposed to standardise outcome reporting across future studies. Full article

The COVID-19 pandemic exposed critical vulnerabilities in healthcare systems worldwide, placing healthcare workers (HCWs) at severe infection risk through direct patient contact. Epidemiological data confirm that HCWs were approximately seven times more likely to develop severe COVID-19 than other occupations, with over 7000 HCW deaths recorded globally by mid-2020. This paper presents the design and laboratory proof-of-concept validation of an IoT-based remote patient-monitoring system prototype—the IoT-Based Isolation Ward Monitoring System Prototype—designed to eliminate unnecessary patient-to-HCW physical contact while maintaining continuous, real-time physiological surveillance. The system integrates multi-sensor hardware comprising an AD8232 ECG module, a MAX30100 pulse oximeter, an NTC thermistor, and an MQ-135 ${\mathrm{C}\mathrm{O}}_2$ sensor. These sensors interface with an Arduino UNO for data acquisition, while localized edge computing is executed on a Raspberry Pi 3B. A convolutional neural network (CNN) trained on the MIT-BIH Arrhythmia Database classifies heartbeats into five distinct categories. By utilizing SMOTE resampling on 109,446 samples, the network achieves an on-device inference latency of under 200 ms. The sensor data are transmitted to a Firebase Realtime Database via an authenticated REST API, which synchronizes data across dual front-end interfaces: a LabVIEW desktop dashboard for clinical oversight and a cross-platform Flutter mobile application for mobile monitoring. End-to-end technical validation under controlled laboratory conditions confirmed round-trip cloud latencies between 300 and 800 ms, error-free threshold alert generation, and sub-second latency for the integrated chat utility. The proposed system uniquely combines hardware sensing, ML-based ECG classification, cloud storage, a LabVIEW physician dashboard, and bidirectional doctor–patient mobile communication into a single unified, low-cost platform. Full article

Background/Objectives: Artificial Intelligence (AI) integration in healthcare promises improved diagnostic accuracy, patient safety, and operational efficiency. However, AI acceptance among healthcare workers remains limited due to knowledge gaps, risk concerns, and governance challenges, particularly in developing countries like Saudi Arabia, where rapid healthcare modernization faces unique infrastructure, organizational, and cultural challenges. This research investigates the factors influencing AI acceptance among medical practitioners, nurses, administrators, and students in Saudi Arabian hospitals to identify key determinants and barriers to adoption. Methods: This cross-sectional study employed an extended Unified Theory of Acceptance and Use of Technology (UTAUT) framework integrated with ethical considerations from the Model for Ethical Assessment and Analysis of AI in Medicine (MEAAM). A structured bilingual questionnaire was administered to 119 healthcare professionals and students across Saudi Arabia, measuring constructs including Awareness and Knowledge, Performance Expectancy, Effort Expectancy, Facilitating Conditions, Social Influence, Trust, Perceived Risk, Ethical Governance, and Price Value. Partial Least Squares Structural Equation Modeling (PLS-SEM) was employed for quantitative analysis, supplemented by thematic analysis of open-ended qualitative responses. Results: The PLS-SEM analysis explained 59.8% of variance in behavioral intention to adopt AI (R² = 0.598). Awareness and Knowledge emerged as the strongest predictor (β = +0.505, p < 0.001), followed by Performance Expectancy (β = +0.229, p < 0.05) and Social Influence (β = +0.123). Perceived Risk functioned as the primary barrier (β = −0.185, p < 0.05). Qualitative findings identified infrastructure gaps, regulatory ambiguities, and training deficiencies as major implementation barriers, while emphasizing opportunities in diagnostic accuracy and remote monitoring. Conclusions: AI acceptance in Saudi healthcare is primarily driven by knowledge, with perceived usefulness and peer support as secondary facilitators, while safety and accountability concerns remain substantial obstacles. Successful AI integration requires coordinated efforts in education, transparent governance frameworks, and institutional support. This study contributes theoretically by validating extended UTAUT in a non-Western healthcare context and practically by providing evidence-based strategies for sustainable AI adoption that enhance healthcare quality while respecting professional roles and ethical principles. Full article

Background/Objectives: Artificial intelligence (AI) is increasingly transforming cardiology through advanced analytical tools capable of identifying complex patterns across cardiovascular imaging, electrophysiology, and clinical datasets. Machine learning (ML) and deep learning (DL) algorithms are being integrated into echocardiography, cardiac computed tomography (CT), cardiac magnetic resonance imaging (MRI), and electrocardiography (ECG), enabling earlier diagnosis and more personalized cardiovascular care. This narrative review summarizes current clinical and organizational applications of AI in cardiology and discusses emerging concepts related to explainable and trustworthy AI. Methods: A narrative review was conducted according to SANRA recommendations using the PubMed, MEDLINE, Web of Science, and Scopus databases, including peer-reviewed publications from 2015 to 2026 addressing clinical, organizational, and ethical applications of AI in cardiology, with particular emphasis on cardiovascular imaging, electrocardiography, heart failure, digital health, and explainable AI frameworks. Results: Substantial evidence demonstrates that AI-based tools can achieve expert-level performance in cardiovascular imaging interpretation, automated electrocardiographic analysis, and clinical risk prediction. Across multiple cardiovascular settings, AI has been associated with improved diagnostic accuracy, enhanced workflow efficiency, and earlier detection of cardiovascular disease. Predictive models support risk stratification in heart failure and ischemic heart disease, while chatbots and digital health platforms may facilitate patient engagement, remote monitoring, and continuity of care. Despite these advances, important challenges remain, including algorithmic bias, limited transparency, insufficient external validation, data heterogeneity, and barriers to routine clinical implementation. Emerging explainable AI approaches may improve model interpretability, clinician confidence, and the safe adoption of AI-driven decision support systems. Conclusions: Artificial intelligence is rapidly evolving from a research-oriented technology into a clinically relevant component of cardiovascular care. Current evidence indicates that AI can enhance diagnostic performance, improve risk prediction, streamline clinical workflows, and facilitate more personalized management across multiple cardiovascular domains. However, the successful translation of AI into routine practice will depend on robust external validation, transparent decision-making mechanisms, regulatory oversight, and clinician acceptance. The development of explainable and trustworthy AI frameworks represents a critical step toward the safe, ethical, and sustainable integration of AI into modern cardiology. Full article

Background/Objectives: Remote monitoring (RM) of cardiac implantable electronic devices (CIEDs) has been associated with potential clinical and economic benefits; however, its adoption among patients remains limited in some healthcare settings. This study examined patients’ intention to use RM services by applying an extended Technology Acceptance Model (TAM) that incorporates perceived effectiveness (PE), perceived barriers (PB), perceived threat (PT), and economic considerations, as well as the influence of socioeconomic factors. Methods: A cross-sectional survey was conducted among 104 patients with CIEDs in Taiwan using validated questionnaires. Structural equation modeling (SEM) was employed to examine the relationships among the proposed constructs. The association between intention to use and actual service utilization was explored. The correlations between sociodemographic factors and the constructs were analyzed using analysis of variance (ANOVA). Results: SEM showed that perceived effectiveness (PE), perceived usefulness (PU) and perceived ease of use (PEOU) were significantly associated with intention to use RM services, with economic considerations also having a significant contribution. Intention to use RM services further predicted actual adoption. However, PB and PT did not moderate these relationships. Sociodemographic factors influenced RM acceptance, with younger, more educated, employed, higher-income, and professionally employed patients reporting stronger perceptions and greater intention to use RM. Conclusions: This study reinforces the TAM framework in the context of health-related technology adoption. Overall, the adoption of RM services is complex and shaped by psychological, economic, and demographic factors, highlighting the need for user-friendly design, targeted education on clinical benefits, and flexible pricing and reimbursement strategies to improve equitable and sustained use. Full article

Background: Wearable cardioverter-defibrillators (WCDs) are equipped with the TRENDS remote-monitoring system, enabling continuous assessment of arrhythmias, physiological parameters, and patient-reported outcomes. This study evaluated the clinical utility of TRENDS-integrated WCD management and compared it with a historical control. Methods: We prospectively analyzed 36 consecutive patients who received a WCD with TRENDS between 2019 and 2024 and compared them with 30 historical controls treated before the implementation of TRENDS. Results: The WCD indications were heart failure as primary prevention (64%) and acute coronary syndrome with ventricular arrhythmias (28%). Among 18 patients who met the criteria for an implantable cardioverter-defibrillator (ICD), including 1 patient with WCD shock, 9 ultimately underwent ICD implantation. The mean daily WCD wear-time was 21.3 h and did not differ significantly from that of the historical control. The response rate to health-related questionnaires was 89%. TRENDS detected symptom exacerbation in 31% of patients, weight gain in 19% of patients, and missed medication in 19% of patients. Daily step-count was significantly lower in patients with ICD indications than in those without (5012 ± 2980 steps vs. 7977 ± 3584 steps, p = 0.01). TRENDS data also aided in initiating anticoagulation therapy and optimizing beta-blocker therapy. Conclusions: TRENDS provided clinically actionable physiologic and patient-reported information that supported individualized cardiovascular management. Full article

Background/Objectives: Digital, remote, and ecological tools may complement clinic-based assessment in multiple sclerosis (MS), but the distribution of evidence across fatigue/fatigability, mobility, and real-world functional activity remains unclear. This scoping review mapped tools, metrics, constructs, contexts of use, and reported clinical utility in adults with MS, with attention given to whether the evidence was balanced across domains. Methods: Following Joanna Briggs Institute guidance and PRISMA-ScR/PRISMA-S reporting standards, five databases were searched on 14 March 2026. After deduplication, title/abstract screening, full-text assessment, and manual extraction and verification, the findings were synthesized descriptively without formal critical appraisal. Results: Of 3100 records identified, 1433 unique records were screened and 125 sources were included. Gait was the most frequently assessed domain (105/125), followed by fatigue/fatigability (33/125), physical activity (29/125), and sleep (2/125). The most frequent technologies were wearable devices (60/125), accelerometry (54/125), remote/home-based/telemonitoring modalities (52/125), and inertial measurement units (42/125). Conclusions: The evidence is predominantly gait- and mobility-focused, while fatigue/fatigability and broader real-world functional activity are less consistently represented. Reported clinical utility was usually framed around functional assessment, longitudinal/remote monitoring, rehabilitation planning, patient stratification, and decision support, but these characteristics were extracted as reported and were not independently appraised. Full article

This paper presents a compact wearable patch antenna operating in the 2.4 GHz ISM band for biomedical Internet of Things (IoT)-based healthcare monitoring applications. The proposed antenna is intended for integration with wearable biomedical sensors in order to support real-time physiological data transmission in remote patient monitoring systems. The antenna was designed on an FR4 substrate to achieve good impedance matching and stable radiation performance. The antenna showed good performance, with a reflection coefficient of −39.56 dB and a gain of 3.01 dB. SAR analysis confirmed compliance with IEEE and ICNIRP safety standards for wearable applications. In addition, the antenna prototype was fabricated and experimentally validated using a vector network analyzer (VNA), showing good agreement between simulated and measured results. Furthermore, the proposed system was implemented by integrating an ESP32 microcontroller with a MAX30100 physiological sensor, where the sensor is responsible for acquiring real-time biomedical data, including heart rate and blood oxygen saturation (SpO₂). The ESP32 processes the acquired data and enables wireless transmission through the proposed antenna to a smartphone and laptop using the Blynk IoT platform, which allows real-time remote monitoring and visualization of physiological parameters. The obtained results confirm the suitability of the proposed antenna for wearable biomedical devices, remote healthcare monitoring, and IoT-enabled healthcare applications. Full article

Background: Large language models and other generative artificial intelligence (AI) tools are increasingly being embedded in digital healthcare services, including mobile health applications, telerehabilitation, remote monitoring, and hybrid care pathways. In this review, digital healthcare refers to technology-mediated healthcare services in which digital platforms, mobile applications, wearables, remote communication, and AI-enabled interfaces support health assessment, self-management, rehabilitation, clinical decision support, or service delivery. When AI-generated exercise guidance moves from general education to individualized recommendations about dose, progression, contraindications, or rehabilitation, it may become directly actionable and safety-relevant. Objectives: This review aimed to clarify when AI-generated exercise guidance in digital healthcare may warrant safety-relevant governance attention and to outline implementation considerations for explainability, human oversight, and service-level governance. It addresses a gap in the literature: general AI-governance and exercise-prescription discussions rarely specify how point-of-use explanations, review thresholds, and escalation safeguards can be organized for directly actionable AI exercise guidance. Methods: We conducted a governance-oriented narrative review of peer-reviewed literature and representative regulatory or guidance documents. This review was not designed as a systematic review, scoping review, or exhaustive evidence map; transparent source mapping was used to support conceptual synthesis. Searches and source mapping focused on generative AI, large language models, explainable AI, clinical decision support, digital health, mobile health, exercise prescription, rehabilitation, trust, automation bias, and human oversight. Sources were included when they informed the safety, explainability, governance, or real-world implementation of patient-facing AI-generated exercise guidance. Extracted material was grouped by evidentiary role and synthesized through framework synthesis and governance mapping to distinguish literature-supported observations, author interpretation, and proposed implementation tools. Results: The included sources were first organized into five thematic groups: digital exercise delivery and exercise-prescription evidence; explainability, trust, and automation bias literature; professional responsibility, ethics, and patient disclosure literature; regulatory and policy documents; and digital literacy, patient/clinician attitudes, and equity literature. The synthesis then proceeded from safety relevance to explanation needs, human oversight and escalation needs, and selected regulatory and policy signals before translating these strands into conceptual and implementation-oriented outputs rather than empirically validated instruments. AI-generated exercise guidance was most safety-relevant in scenarios involving individualized dose, progression, contraindication-sensitive action, or rehabilitation strategy. Across the included sources, generic transparency alone was not sufficient to support reviewable use; relevant explanation elements included evidence sources, risk warnings, reasoning paths, and reasonable alternatives. Oversight considerations varied with embodied risk, clinical ambiguity, user vulnerability, and likelihood of direct enactment. Implementation considerations linked interface design, clinical review, escalation, auditability, and post-deployment monitoring. Conclusions: AI-generated exercise guidance in digital healthcare may warrant governance attention as a patient-safety and accountability issue when it influences actionable exercise decisions. The proposed framework offers a conceptual basis for designing more reviewable and accountable mobile and remote exercise-support services. Future work can validate these outputs in patient-facing services, clinician review workflows, usability studies, implementation pilots, and safety evaluations. Full article

Intelligent sensors and Internet of Medical Things (IoMT) platforms are rapidly changing smart healthcare by enabling continuous capture of physiological, behavioral, and clinical events outside conventional hospital settings. Yet the value of connected sensing depends on more than signal acquisition alone. A practical remote-monitoring ecosystem must also convert sensor alerts, clinician-facing summaries, and historical electronic clinical records (ECRs) into ranked evidence that supports care decisions. This study reframes a large-AI clinical retrieval model as the intelligence layer of an edge–cloud IoMT architecture. The proposed framework combines Transformer-Based Sequence (TBS) encoding, BioBERT-driven representation learning, explicit retrieval, and domain-guided re-ranking to connect sensor-originated narratives, patient records, and clinician queries. The empirical evaluation is conducted on Medical Information Mart for Intensive Care III (MIMIC-III) and i2b2, two de-identified clinical text benchmarks that approximate the documentation layer of real-world remote patient monitoring. Compared with strong baselines, including DeepBio, UniT2T, Web4IR, A2A-API, CoLTiD, VLRG, ColBERT, DeepSDH, BiRex, and DL4BTM, the proposed model achieves the best overall performance, reaching F1/Pre/NDCG scores of 0.8399/0.8338/0.5235 on MIMIC-III and 0.8090/0.8100/0.5129 on i2b2. Ablation experiments confirm the importance of exploratory data adaptation, critical feature modeling, critical token learning, cross-disciplinary supervision, and data-driven regularization. Parameter sensitivity analysis shows stable behavior for beta values greater than or equal to 1, with the strongest results at beta = 5. The study concludes that large-AI retrieval can strengthen the clinical interpretation layer required for IoMT-enabled remote monitoring, while future work should validate the approach on live multimodal sensor streams and privacy-preserving deployments. Full article