Artificial intelligence (AI) is becoming an increasingly important component of healthcare, supporting diagnosis, clinical decision-making, medical imaging, triage, and patient-facing services. While these technologies offer significant opportunities to improve healthcare delivery, they also raise important questions about patient safety, fairness, privacy, transparency, cybersecurity, and accountability. This paper examines the regulatory framework governing medical AI in the European Union, focusing on the interaction between the Artificial Intelligence Act (AI Act), the Medical Device Regulation (MDR), the In Vitro Diagnostic Medical Device Regulation (IVDR), the General Data Protection Regulation (GDPR), and the European Health Data Space (EHDS). Drawing on doctrinal and conceptual regulatory analysis, it argues that many AI-enabled medical systems should be regulated through continuous lifecycle compliance rather than by relying primarily on a one-time assessment at market entry. The analysis identifies the training and validation dataset as a particularly important point of regulatory convergence, especially among the EHDS, GDPR, and AI Act data-governance requirements, and examines how responsibility is allocated across the general-purpose AI value chain under Article 25. Building on this analysis, the paper proposes a compliance-by-design framework that translates overlapping legal requirements into a set of auditable governance artefacts covering system classification, regulatory mapping, data governance, validation, human oversight, conformity assessment, post-market monitoring, and change control. The framework is illustrated through two contested use cases and complemented by recommendations tailored to the responsibilities of different stakeholder groups. The analysis incorporates Regulation (EU) 2026/1744 (Digital Omnibus on AI), while recognising that supporting guidance, harmonised standards, and implementation of the EHDS continue to evolve and should be checked when the framework is applied. The framework is conceptually derived and illustrated through constructed use cases rather than empirically validated; future work should assess its usability, consistency, and discriminating power through structured expert assessment and Delphi-based consensus methods.
BackgroundSynchronous tele-interconsultations — real-time interactions linking primary care physicians and hospital-based specialists — have been proposed as a way to support clinical decision-making and, potentially, to build clinical competencies over time through repeated exposure to specialist reasoning. However, causal evidence on whether such programs reduce reliance on specialist referrals remains limited, particularly in low- and middle-income country settings characterized by large territories and uneven specialist distribution.MethodsWe conducted a quasi-experimental evaluation of the TeleNordeste project, a large-scale telehealth initiative implemented in Northeast Brazilian states under a public-private partnership. Using staggered difference-in-differences methods, our primary aim was to estimate the treatment effect on primary care referral rates, using a panel of primary care units observed from 2018 through 2025. After applying a municipality-level restriction to reduce spillover contamination, the analytical sample comprised 6,825 primary care units: 3,918 never-treated comparison units, 1,002 low-dose units (1–4 cumulative telehealth interactions), and 1,905 high-dose units (≥5 interactions). Secondary analyses explored whether estimated effects were more consistent with immediate care-flow reorganization or workplace learning.ResultsAny exposure to the program was associated with a statistically significant reduction in referral rates (−0.356 percentage points, no-covariate specification; p < 0.001). Similar estimates were observed across low- and high-exposure groups, with no evidence that effects increased with cumulative exposure.ConclusionsParticipation in the TeleNordeste program was associated with meaningful reductions in referrals to specialized care. Although immediate case resolution during tele-interconsultations provides a plausible explanation for this association, workplace learning cannot be confirmed or excluded with the available data. In the absence of a clear dose-response gradient, these mechanisms cannot be disentangled, and the results indicate that program participation itself can strengthen primary care case resolution and reduce reliance on specialist referrals. Interpretation of mechanisms is limited by potential under-registration of referrals and by the use of primary care units, rather than individual physicians, as the unit of analysis. Future evaluations would benefit from collecting physician-level identifiers and strengthening audits of referral-registration completeness, thereby enabling a more detailed assessment of how tele-interconsultations affect clinical practice and referral decisions over time.
People with dementia in residential care often experience reduced social connectedness. Person-centered care approaches foreground meaningful social interactions to support well-being, but staff and time pressures increasingly constrain opportunities for such care. Digital technologies offer possibilities to help care professionals facilitate social connectedness, despite increasing care pressures. Yet, the meaningful integration of such technologies into the complex sociotechnical setting of residential dementia care is not straightforward. To responsibly design and position digital technologies for dementia care, this study empirically explores care professionals’ perspectives on social connectedness and the sociotechnical role of conventional digital technologies in residential dementia care. We conducted five workshops with 15 care professionals from three care organizations to pursue this objective. Our findings show that fostering social connectedness is a relational process involving continuous interpretation, negotiation, and adaptation to residents’ individual needs, personal values, and institutional constraints. Digital technologies were used by care professionals to support communication, interaction, and shared activities, yet remained largely peripheral to everyday care routines and were primarily used reactively in response to observed behavior. Drawing on an ethics of care framework, we derive ethical and sociotechnical implications for the responsible design and positioning of digital technologies in residential dementia care.
BackgroundDigital communication ecosystems have profoundly transformed the circulation of health information. During public health crises, large volumes of information—including misinformation and disinformation—can spread rapidly across online platforms, generating complex information environments commonly described as infodemics. These dynamics can influence public risk perception, undermine trust in health institutions, and affect adherence to preventive measures. At the same time, advances in artificial intelligence (AI) and digital technologies have created new opportunities for monitoring information flows and identifying emerging misinformation patterns in real time. However, the translation of AI-generated insights into coordinated public health decision-making processes remains limited.MethodsThis study developed a conceptual governance framework aimed at explaining how AI-generated insights derived from digital information ecosystems can be translated into evidence-informed public health responses. The framework was developed through a secondary conceptual analysis of the complete evidence extraction database generated from a previously published scoping review including 63 studies. The methodological approach combined thematic synthesis of empirical evidence with conceptual modeling techniques commonly used in public health systems research.ResultsThe synthesis of the literature identified several thematic domains describing how digital technologies and artificial intelligence are used to monitor and respond to health misinformation within digital communication ecosystems. Building on these domains, this study proposes a governance-oriented conceptual framework integrating digital data ecosystems, artificial intelligence analytics, interpretive public health expertise, and institutional governance mechanisms.ConclusionsArtificial intelligence technologies offer powerful tools for monitoring complex digital information environments, yet their integration into public health decision-making requires governance models capable of linking analytical insights with institutional responses. The proposed framework contributes to the emerging field of digital public health governance by providing a structured conceptual model for translating AI-generated insights into coordinated public health actions during infodemic events. Although the framework remains preliminary and requires formal validation, it provides a structured conceptual basis for future empirical implementation and governance research.
BackgroundTherapist-guided internet-delivered cognitive behavioural therapy (guided iCBT) is an effective treatment for common mental disorders and has the potential to improve access to care. However, its integration into routine practice remains limited. This study explored healthcare professionals’ perceptions of the suitability of guided iCBT in specialised mental healthcare and examined how perceived fit influences implementation across clinical and organisational contexts.MethodsSemi-structured interviews and participatory observations were conducted at three specialised mental health clinics in Norway that offered guided iCBT to adults with anxiety and depression. Thirty-one healthcare professionals were recruited through purposive and snowball sampling. Data were analysed using a combination of inductive and deductive approaches. The deductive analysis was informed by Lau et al.'s framework of contextual fit, which conceptualises fit as alignment between an intervention and professional, organisational, and external contexts.ResultsHealthcare professionals’ perceptions of fit varied across contextual levels and influenced the implementation of guided iCBT. At the intervention level, participants identified a perceived mismatch between the evidence base for guided iCBT and limitations in its technological design, which was viewed as insufficiently aligned with contemporary therapeutic practices. At the professional level, differing professional values and therapeutic norms shaped perceptions of appropriateness and acceptability. At the organisational level, limited readiness for implementation and concerns about patient complexity in specialised care settings contributed to doubts about the intervention's suitability. At the external level, tensions emerged between evidence-based expectations and prevailing clinical assumptions favouring face-to-face care, further affecting perceptions of fit and legitimacy.ConclusionsThe findings suggest that implementing guided iCBT in specialised mental healthcare depends on aligning the intervention with the clinical, organisational, and broader system contexts in which it is introduced. Efforts to improve technological usability, strengthen organisational readiness, engage clinicians, and address assumptions about legitimate forms of therapy may enhance perceived fit and support sustained implementation of guided iCBT.
BackgroundMyelodysplastic syndromes (MDS) are common hematologic malignancies among older adults. With the rapid growth of short-video platforms, patients increasingly seek MDS-related health information online; however, the quality of MDS-related health information available on short-video platforms has not been systematically evaluated.ObjectiveThis study assessed the quality and reliability of MDS-related short videos across three major Chinese platforms and examined the relationship between content quality and user engagement.MethodsBetween June 25 and June 30, 2026, a total of 210 MDS-related videos were systematically collected from TikTok (Chinese version: Douyin), Bilibili, and Xiaohongshu (70 videos per platform). Video metadata were extracted, and content quality was independently evaluated using three validated instruments: the modified DISCERN (mDISCERN), the Journal of the American Medical Association (JAMA) benchmark criteria, and the Global Quality Scale (GQS). An overall quality score (SUM) was calculated by combining the three assessment tools. Spearman correlation analysis was performed to examine the associations between user engagement metrics and content quality.ResultsBilibili videos demonstrated the highest overall educational quality (mean SUM score: 9.79 ± 2.35), whereas TikTok generated the greatest user engagement (median number of likes: 81.00). Videos produced by professional creators achieved significantly higher scores across all quality assessment instruments than those produced by non-professional creators (mean SUM score: 8.81 vs. 5.03, p < 0.001). No significant associations were observed between any user engagement metric and content quality. Video duration was the only variable positively correlated with content quality (r = 0.332, p < 0.01).ConclusionsUser engagement was disconnected from information quality in MDS-related short videos. Professional creators provided greater educational value without consistently receiving commensurate engagement. Digital health communication should prioritize expert-led content, transparent source attribution, and quality-informed dissemination.
Artificial intelligence (AI) is transforming disease surveillance by enabling early outbreak detection, predictive modeling, and real-time analysis of diverse health data sources. These advances can strengthen epidemic preparedness and improve public health decision-making. However, AI adoption has progressed faster than the development of effective governance frameworks, creating challenges related to algorithmic bias, transparency, privacy, cybersecurity, accountability, and global equity. Low- and middle-income countries face additional barriers due to limited digital infrastructure and technical capacity. This policy brief highlights the urgent need for responsible AI governance through international standards, explainable algorithms, independent validation, strong data protection, and inclusive stakeholder engagement. Ensuring ethical and equitable AI implementation is essential to maximize its potential for improving disease surveillance and global health security.
IntroductionMental health triage-level intent classification in linguistically diverse and resource-constrained clinical environments requires models that simultaneously meet strict patient data privacy regulations, cross-lingual generalization to low-resource languages, and real-time inference on edge hardware. No existing federated NLP system has jointly demonstrated this combination. This work proposes Fed-XLM-R, a unified federated learning framework designed to close that gap.MethodsFed-XLM-R integrates XLM-RoBERTa with lightweight bottleneck adapter layers, adapter-scoped differentially private stochastic gradient descent (DP-SGD), proximal regularization for straggler-robust aggregation (FedProx), and INT8 post-training quantization for edge deployment. Gradient perturbation is confined exclusively to the 0.87% trainable adapter subspace rather than the full 270-million-parameter model. The framework was evaluated in a simulated 10-client federation on a public benchmark, with intent classification trained and evaluated on English data. A cross-lingual diagnostic was additionally run on the XNLI benchmark across five languages (English, Spanish, Hindi, Swahili, Arabic) against an mBERT baseline, and canary phrase memorization analysis was conducted across all 50 federated rounds to assess data extraction risk.ResultsAt the clinically meaningful privacy budget of ε = 1.0 (δ = 10−5, Fed-XLM-R achieves 96% accuracy retention, yielding an overall accuracy of 0.923, F1-score of 0.918, and AUC-ROC of 0.956, within 0.5% of a centralized baseline while providing formal differential privacy guarantees. Canary phrase analysis confirms the DP-SGD mechanism prevents training data extraction. The XLM-R backbone retains strong discriminative capacity in low-resource languages relative to mBERT on the XNLI diagnostic. Adapter-only parameter transmission reduces cumulative communication cost by 40.7-fold at the 85% accuracy threshold, at a per-round volume compatible with standard mobile data networks. INT8 quantization reduces inference latency from 1,974 ms to 523 ms on low-end CPU hardware, a 3.8-fold speedup.DiscussionThese findings characterize the mechanism's behavior under controlled conditions in a simulated federation rather than demonstrating field deployment. The cross-lingual results support the feasibility of future multilingual extension but do not themselves constitute multilingual intent classification. The three-category label scheme (Anxiety/Depression/Normal) supports triage-level intent routing but has not been validated against standardized clinical instruments; the system is not proposed as a clinical diagnostic or screening tool. Overall, Fed-XLM-R demonstrates that privacy-preserving, communication-efficient, and edge-deployable federated NLP is achievable without substantial accuracy loss, offering a practical pathway toward privacy-compliant mental health triage systems pending real-world and multilingual validation.
IntroductionRadiologists in resource-limited settings often face high workloads, especially in chest X-ray interpretation. Manual annotation of large-scale imaging datasets remains costly and time-consuming. This study aims to explore the feasibility of using large language models (LLMs), specifically GPT-4o, to generate binary disease presence labels from free-text radiology reports, and to use these labels to train deep learning models for automated chest X-ray classification.MethodsA two-stage supervised learning pipeline was developed using the publicly available MIMIC-CXR v2.1.0 dataset. First, GPT-4o was prompted with a structured clinical protocol to classify each radiology report as either “diseased” or “no disease.” Second, the generated labels were used to supervise the training of four convolutional neural networks: ResNet-18, DenseNet-121, EfficientNet-B1, and ConvNeXt-Tiny. A patient-level 70/10/20 split was employed to prevent data leakage across sets. Each model was trained across five random seeds (42–46), and 95% confidence intervals were computed using the t-distribution. Label quality was evaluated by comparing 210 generated labels against radiologist annotations from a board-certified radiologist.ResultsGPT-4o achieved an overall accuracy of 92.9% with expert labels on the 210-report validation set. For the “diseased” class, the precision was 97.4% and recall was 90.5%; for “no disease,” precision was 87.1% and recall was 96.4%. Among the CNN models evaluated on the held-out test set, ConvNeXt-Tiny achieved the highest area under the curve (AUC=0.832, 95% CI [0.801, 0.863]) and balanced accuracy (0.739), significantly outperforming EfficientNet-B1 (AUC=0.797; paired t-test, p=0.014). ResNet-18 (AUC=0.822) and DenseNet-121 (AUC=0.808) showed intermediate performance. All models demonstrated AUC values above 0.79, confirming the viability of LLM-derived weak supervision.DiscussionThis study demonstrates that LLMs can be effectively employed to generate supervision labels for medical imaging tasks. The proposed approach offers a scalable and low-cost solution for preliminary disease screening, particularly in healthcare environments with limited expert availability. The multi-seed evaluation with confidence intervals provides a rigorous assessment of model stability. Further work is needed to improve label reliability and expand to multi-label classification.
IntroductionTeleophthalmology depends on secure exchange of retinal fundus images between primary care screening locations and referral centers. Current image-sharing systems remain vulnerable to quantum attacks on public-key cryptography and to centralized storage failures with limited auditability.MethodsThis paper presents PQ-FundusChain, a consortium blockchain framework for quantum-resistant fundus image sharing. Each image is encrypted with an AES-256-GCM session key encapsulated using ML-KEM (FIPS 203). ML-DSA (FIPS 204) authenticates blockchain transactions. Encrypted images are stored in decentralized off-chain storage, while content hashes, metadata, and access policies are recorded on-chain. Access requests are evaluated through a risk-aware policy combining trust, access-history, and location scores with a fundus sensitivity score based on retinal anatomy and diabetic retinopathy severity.ResultsExperimental evaluation on the public Messidor-2 dataset shows a share-side cryptographic and hashing cost of approximately 4.02 ms per image, an access-side cost of approximately 3.48 ms, smart-contract execution of approximately 0.25 ms for both AccessGrant and PolicyUpdate, and a per-image on-chain record of approximately 4.83 KB independent of image resolution. The additional latency introduced by postquantum mechanisms remains below 1 ms for image sharing.DiscussionThe results demonstrate that postquantum protection can be incorporated into teleophthalmology workflows with modest computational overhead, with security analysis confirming confidentiality, integrity, authentication, non-repudiation, fine-grained access control, and resistance to harvest-now, decrypt-later attacks.
IntroductionOpioid Use Disorder (OUD) is an ongoing and pervasive public health problem. Despite the availability of efficacious Medication treatments for OUD (MOUD), many patients require additional support to address OUD's wide-ranging consequences. Mobile Health Interventions (MHIs), or smartphone-based software applications (“apps”), could serve as a scalable and flexible medium to increase adjunctive care access within MOUD.MethodAs an initial step in potential MHI creation, we conducted semi-structured interviews with U.S. military veterans receiving MOUD (N = 21) via rapid qualitative methods. Our team developed a start-list of interview questions. Interview transcripts were independently coded by interviewers, who then convened to discuss and refine code definitions, develop summary templates, organize codes into hierarchical structures, and refine domain categories through consensus.ResultsTwenty-one veterans participated [M[SD]Age = 59.95[10.50]; 90.48% male sex-assigned-at-birth; 80.95% White; 85.71% Non-Hispanic/Latinx; 52.38% on buprenorphine, 47.62% on methadone at time of interview]. Veteran attitudes were typically either neutral- positively valenced and characterized by willingness (Open Prudency) or neutral-negatively valenced and characterized by concern and contingencies for use, such as assurance for continued access to in-person care (Hesitancy). A small but notable proportion of veterans expressed strongly favorable views towards MHIs, often grounded in their own technological fluency (Enthusiasm). Outright Opposition to MHIs was rare. Desired MHI functions were variable and included their use for enhancing care accessibility and convenience (e.g., Resource Centralization, Patient-Provider Communication), as well as supporting autonomy, motivation and individualization (e.g., Self-Monitoring, Positive Reinforcement, Adjunctive Intervention).ConclusionsResults from this qualitative investigation of U.S. military veterans provide foundational data to guide future development of MHIs for supporting MOUD engagement. Findings suggest that veterans receiving MOUD are generally open towards and interested in using MHIs as part of their care regimens, which were broadly described as potential means to enhance treatment accessibility, convenience, and individualization.
BackgroundRadiology reports contain critical information for monitoring patients' clinical progress and evaluating treatment outcomes. Sequential radiological images are particularly valuable, providing not only current findings but also comparative assessments against previous reports. Automatically detecting temporal changes between free-text reports remains a significant challenge in Natural Language Processing.MethodsThis study evaluated the performance of Large Language Models in detecting temporal novelty using the LUNGUAGE dataset, which contains sequential chest radiography reports. The comparative multi-model and multi-prompt evaluation was carried out on a fixed, class-stratified subset of 1,500 of these examples. Seven language models from OpenAI, Anthropic, and Google Gemini were tested across five prompt strategies: zero-shot, few-shot, structured reasoning, memory-augmented, and temporal graph prompting. Each model classified target findings as new, improved, worsened, stable, or resolved by evaluating current and previous reports together. Performance was measured using accuracy, macro-F1, weighted-F1, and class-based metrics. The “new” class was analyzed separately due to its clinical importance. Model errors were categorized into clinically interpretable types, including missed new findings, missed resolved findings, temporal errors, and change direction errors. Bootstrap confidence intervals and paired McNemar significance tests assessed performance uncertainty.ResultsGPT-4.1 emerged as the top-performing model. Its few-shot prompt strategy achieved the best results: 0.8369 accuracy, 0.7888 macro-F1, 0.8322 weighted-F1, and 0.5385 recall for the “new” class.ConclusionThese findings demonstrate that Large Language Models hold substantial promise for temporal clinical reasoning in sequential radiology reports, and that performance depends not only on model architecture but also on prompt strategy and the class being evaluated.
BackgroundImproved methods of cognitive testing are urgently needed for primary care settings faced with a growing older adult population and higher rates of dementia. We tested the feasibility and acceptability of a novel online cognitive test that can be completed at home prior to an annual exam.Methods32 older adults completed testing at home on personal devices 1–4 weeks prior to an annual exam with their primary care provider. Additional cognitive screening was completed in-clinic to provide preliminary validation evidence. Completion rates were examined to assess feasibility, and patient acceptability was assessed via survey.ResultsCompletion rate was 78.5% for at-home testing online. Participants reported that they generally preferred at-home over in-clinic testing. At-home test performance was moderately correlated with the standard Montreal Cognitive Assessment completed in clinic.ConclusionFindings provide initial support for the acceptability of self-administered online cognitive screening for older adults in primary care. Completion rates were slightly below a preset benchmark, suggesting that additional support may be needed to facilitate at-home testing in routine care. Further validation research is needed in larger samples including examination of digital measure convergence with clinical diagnoses and additional cognitive testing.
BackgroundArtificial intelligence (AI) and digital health technologies are increasingly shaping how public healthcare services are planned, delivered, and governed. In Egypt, national digital health reforms have created an urgent need to assess whether public healthcare institutions have the administrative readiness, institutional capacity, and governance arrangements required for AI-enabled digital health transformation.MethodsA sequential explanatory mixed-methods design was employed across 24 Egyptian governorates. Phase 1 consisted of a cross-sectional survey of 387 healthcare administrators and policymakers from Ministry of Health and Population hospitals, university hospitals, primary healthcare units, and Health Insurance Organization facilities. The survey measured eight operationalized constructs: institutional capacity, administrative readiness, organizational governance, leadership support, IT infrastructure, staff training and skills, regulatory framework, and digital health transformation success. Phase 2 comprised semi-structured interviews with 18 senior policymakers, hospital leaders, digital health consultants, health information system managers, and health policy researchers. Quantitative findings were analyzed using descriptive statistics, confirmatory factor analysis, and structural equation modeling, while qualitative data were analyzed thematically and integrated with the survey results through explanatory joint display logic.ResultsAmong survey respondents, 62.3% were male, 71.6% held a master's degree or higher, and 58.1% had more than 10 years of professional experience. The structural model showed acceptable fit (CMIN/DF = 2.14, CFI = .96, TLI = .95, RMSEA = .045, SRMR = .038) and explained 68% of the variance in perceived digital health transformation success. Institutional capacity, administrative readiness, and organizational governance were positively associated with transformation success. The specified indirect pathways through leadership support, IT infrastructure, staff training and skills, and regulatory framework were also significant and are interpreted as hypothesis-generating associations because of the cross-sectional design. Interview findings helped explain the quantitative patterns by identifying fragmented governance, weak infrastructure, workforce digital literacy gaps, regulatory ambiguity, and resource allocation constraints.ConclusionsEgypt's public healthcare system faces interrelated institutional, administrative, workforce, infrastructure, and regulatory barriers to AI-enabled digital health transformation. Strengthening governance coordination, infrastructure equity, workforce capability, and AI-specific regulatory safeguards is essential before large-scale AI deployment can be reliably translated into public value.
Coronary artery disease (CAD) is one of the leading causes of global mortality, necessitating accurate assessment of coronary artery stenosis and plaque-associated angiographic findings from coronary angiography images. Although deep learning-based diagnostic models have demonstrated high predictive capability, their deployment on resource-constrained embedded platforms remains challenging because of computational complexity and memory requirements. To address these limitations, this study proposes a knowledge-distillation-based hardware-aware framework that transfers discriminative knowledge from a high-capacity teacher network to a lightweight convolutional neural network (CNN). The proposed framework integrates software-level localization of plaque-associated angiographic findings with FPGA-oriented optimization. Using a 90% training and 10% testing split, the proposed model achieved an accuracy of 98.64%, precision of 99.06%, recall of 97.82%, PPV of 0.99, NPV of 0.98, MCC of 0.96, and an AUC of 0.9940. And under 10-fold cross-validation, the model achieved a mean accuracy of 97.53% ± 0.27%, precision of 97.82%, recall of 96.94%, PPV of 0.98, NPV of 0.97, MCC of 0.95, and a mean AUC of 0.9897, which confirms that our proposed model exhibits high robust performance. For hardware realization, the optimized student CNN was deployed on a Xilinx Zynq UltraScale + MPSoC FPGA using the Vitis High-Level Synthesis (HLS) toolchain. The implemented accelerator achieved a kernel-level inference latency of 10.6 µs and a Peak On-Chip Kernel Throughput of approximately 94,339 inferences/s, while maintaining balanced hardware resource utilization and low power consumption. Overall, the proposed framework demonstrates accurate classification of plaque-associated angiographic findings with efficient FPGA deployment.
BackgroundWomen with HIV have increased risk of cardiovascular disease compared to women without HIV. Adopting healthy lifestyle habits in early adulthood, including adequate sleep and physical activity, can mitigate this risk. Fitness watches provide objective measures of sleep and physical activity, and may enable proactive interventions to optimize long-term cardiovascular health. However, the acceptability and feasibility of wearable devices for continuous monitoring of these two measures among women living with HIV has not been adequately explored.MethodsA pilot acceptability and feasibility study was conducted with thirty women with HIV participating in a US-based prospective observational study. Participants were assigned to one of three fitness watches, two requiring data transfer every 3–5 days, and one without a transfer requirement. Acceptability of using the fitness watch and feasibility of collecting sleep and physical activity data were assessed.ResultsAmong the 30 women, median participant age was 36.0 years (Interquartile Range: 30.1, 40.3) with 8 (27%) having > a high school education, and 19 (63%) never having owned a fitness watch. All participants agreed or strongly agreed that the device was easy to use, regardless of device type. Over 80% found it acceptable to collect and share sleep and physical activity data. Only three (10%) participants reported data transfer to be somewhat difficult. Sleep and physical activity data collection was feasible for 90% of devices requiring interim data transfer and 100% of devices without a transfer requirement.ConclusionsAll three fitness watches demonstrated high acceptability and feasibility for continuous data collection among women living with HIV, including participants without prior experience using wearable devices, with minimal concerns regarding privacy or confidentiality. Participants expressed a preference for devices that provided real-time access to personal data, suggesting that user visibility of health metrics may enhance engagement with sleep and physical activity interventions. These findings may inform the design and implementation of wearable device–based interventions to support sleep health and physical activity among women living with HIV of reproductive age.
IntroductionObjective assessment of infant suckling biomechanics remains limited despite decades of pressure-based measurement research, and tongue-tie (ankyloglossia) is still largely evaluated using semi-quantitative anatomical scoring. We developed a hydraulic differential-pressure device — the electronic baby bottle (EBB) — designed to record real-time net intraoral mechanical load during nutritive suckling through a fluid-filled sensing cavity with a controlled air inclusion coupled to a differential pressure transducer. This study aimed to: (1) describe the EBB measurement principle, (2) develop automated machine learning–based classification of effective suckling activity, and (3) evaluate whether quantitative biomechanical parameters derived from automated analysis demonstrate responsiveness one week after frenotomy.MethodsTime-series recordings from iterative prototype testing were segmented into overlapping windows and manually annotated to train a supervised classifier using the ROCKET transform implemented in Python (sktime) with ridge classification and cross-validation. Performance was evaluated on an internal held-out test set and an independent external validation set of full-length recordings excluded from model development. Quantitative parameters were computed from automatically identified effective suckling bursts in 25 infants with restrictive tongue-tie recorded before and one week after frenotomy and compared with 10 control infants with normal tongue mobility.ResultsAutomated classification achieved >99% accuracy on the internal test set and 92% segment-level classification accuracy on external validation recordings. Mean negative intraoral pressure during effective suckling bursts increased in 19/25 (76%) treated infants one week after frenotomy (paired t-test, p = 0.010), shifting toward control values.DiscussionHydraulic differential-pressure recording combined with time-series machine learning enables objective and reproducible quantification of nutritive suckling activity and detects short-term functional change following frenotomy in most infants with restrictive tongue-tie. This framework supports future work on normative reference ranges, standardized digital metrics, and data-driven diagnostic thresholds for infant feeding dysfunction.
IntroductionAlthough remote patient management (RPM) shows promise for improving chronic heart failure (HF) management, its effectiveness depends on technology acceptance, usability, and patient engagement. However, patients are often involved only after systems are implemented, limiting opportunities to align RPM with their needs. This study explored patients' expectations, wishes, and concerns regarding future RPM using participatory design methods to inform more patient-centred RPM.MethodsPatients with HF using RPM were recruited from a Dutch hospital for individual, semi-structured interviews. We employed a co-constructing stories approach, inviting participants to imagine future scenarios of remote care. Guided by narrative prompts about potential developments in RPM, participants were encouraged to discuss how such technologies might shape their experiences. During the interviews, one researcher concurrently created sketches of the participants' answers, creating an evolving trace of the dialogue. The visual data were subsequently analysed using Annotated Visual Analysis to identify themes.ResultsSix patients were interviewed, producing 7 h of audio and 18 A3 pages of sketch notes. Four key themes emerged: Data Feedback, reflecting patients' desire to receive clear and constructive feedback that supports self-management beyond alert-based monitoring, to be able to take more responsibility for their health through RPM; Invasiveness, including camera-based monitoring or collection of non-medical data, was perceived as a barrier to adoption, although concerns were reduced when monitoring was clearly explained and considered proportional to disease severity; Adaptability and Integration highlighted the need for RPM to extend support beyond monitoring and to remain useful in daily life; Healthcare Provider contact emphasised that human interaction is irreplaceable, with empathy from healthcare professionals fostering trust in the system and patients' confidence in managing their health.ConclusionInviting patients to reflect on remote care provided valuable insights into their needs and expectations for future RPM. Participatory design methodologies facilitated rich discussions about patients' experiences, needs, and expectations regarding future RPM. Patients emphasised RPM should be actionable, minimally invasive, adaptable to daily life, and complemented by human contact. This highlights the importance of socio-technical systems that empower self-management while maintaining professional support. These findings can guide more human-centred RPM designs for HF care.
BackgroundCervical cancer remains a leading cause of cancer death among women in sub-Saharan Africa, with Tanzania bearing a disproportionate burden. The critical shortage of trained pathologists, coupled with the unprecedented disease burden in low-resource settings, underscores the urgent need for point-of-care screening and diagnosis to enable timely decision-making. We assessed the diagnostic accuracy of AI-driven cytopathological tools to improve diagnostic efficiency and accessibility.MethodsThis retrospective secondary data analysis evaluated five convolutional neural network (CNN) architectures: EfficientNetB7, MobileNet, ResNet50, ResNet152, and InceptionNetV3, for semi-automated classification of cervical cell abnormalities. A total of 11,955 Pap smear cytological images were used from the publicly available Center for Recognition and Inspection of Cells (CRIC) Searchable Image Database, spanning six cellular classes: Normal, ASC-US, LSIL, ASC-H, HSIL, and carcinoma. Performance was assessed on a hold-out test set (n = 961) using macro-averaged metrics.ResultsEfficientNetB7 achieved the highest overall performance, with a macro F1 score of 0.9324 (95% CI: 0.920–0.945), an accuracy of 0.9775 (95% CI: 0.968–0.987), and a sensitivity of 0.9324 (95% CI: 0.920–0.945). ResNet50 ranked second (F1 score: 0.9282 [95% CI: 0.916–0.941]) and ResNet152 third (F1 score: 0.9240 [95% CI: 0.911–0.937]), showing minimal performance gaps. InceptionNetV3 followed closely (F1 score: 0.9220 [95% CI: 0.909–0.935]). MobileNet achieved the lowest F1 score (0.8918 [95% CI: 0.875–0.908]), but its lightweight architecture is suitable for edge deployment. The Carcinoma (CA) class achieved near-perfect recall across all models (> = 0.978). Notable interclass confusion was observed between ASC-US and LSIL, attributable to cytomorphological overlap.ConclusionEfficientNetB7 offers promising diagnostic accuracy for automated cervical cancer screening using Pap smear images and shows potential for integration into point-of-care workflows in low-resource settings. Future work should focus on training models on locally representative datasets and exploring whole smear analysis to reduce interclass misclassification.
