Maternal undernutrition and micronutrient deficiencies remain pervasive, contributing to adverse pregnancy outcomes and long-term health risks for mothers and offspring. Multiple micronutrient supplementation (MMS) during pregnancy has demonstrated benefits, including reduced risks of low birth weight, small-for-gestational-age births, and neonatal mortality, when compared with standard iron-folic acid supplementation. Current MMS strategies, however, often follow a standard MMS, overlooking variations in nutritional status, health profiles, and context. Advances in artificial intelligence (AI), particularly deep learning and natural language processing, provide opportunities to strengthen maternal nutrition programs by integrating diverse data sources. Rather than promising fully individualized recommendations, AI could help stratify women by risk of insufficiencies or deficiencies, highlight groups most likely to benefit from additional support, and inform the design of more responsive supplementation strategies during preconception and pregnancy. We outline a conceptual model in which multimodal health data-including electronic health records (EHRs), wearable sensor outputs, nutrition and fertility app logs, genomic markers, and sociodemographic information-are aggregated and analyzed by AI systems to inform personalized MMS plans. The framework introduces the concept of a "nutritional digital twin," a virtual profile of the patient's nutritional and metabolic state. This digital twin can simulate micronutrient needs and predict maternal-fetal outcomes under different supplementation scenarios, enabling clinicians to test scenario-based options (e.g. standard MMS ± targeted add-ons) for individuals. We describe how deep learning models can identify complex patterns (e.g. diet-genome interactions or behavioral trends) while natural language processing (NLP) algorithms extract clinically relevant insights from unstructured data (such as medical notes or patient queries). In addition, we discuss the role of digital maternal health tools, such as mobile apps and wearable trackers, in supplying real-time data to the AI models and in engaging women to improve adherence to supplementation regimens. Harnessing AI for MMS could transform maternal nutrition care in both high- and low-resource settings. In high-income contexts, rich data (comprehensive EHRs, genetic tests, continuous monitoring devices) could feed advanced predictive models to support risk-stratified care with protocolized supplementation options, under clinical oversight. In low- and middle-income countries, where maternal undernutrition and micronutrient gaps are most prevalent, AI-driven approaches can help stratify risk groups and optimize limited resources. Ubiquitous mobile phone access and digital health tools in many such settings provide avenues for data collection and intervention delivery. We highlight examples where machine learning on population data revealed "hidden hunger" patterns and key predictors of low supplement uptake (e.g. low education, minimal antenatal visits)-insights that policymakers can use to target nutrition programs. A nutritional digital twin could further allow scenario-testing (e.g. predicting the impact of adding a vitamin D supplement for a specific patient) before clinical decisions are made. To realize this vision, the key concerns are ethics, credibility, and fairness. Ethical frameworks must guide development so that sensitive reproductive health data are protected and clinician oversight remains central. The credibility of AI-generated recommendations depends on transparency about the assumptions used to translate nutritional and health data into supplement type and dose, and on prospective validation against maternal and neonatal outcomes. This requires a continuous feedback loop in which recommendations are tested in real-world settings and recalibrated using outcomes data, ensuring that the system learns from observed benefits and harms, rather than relying solely on theoretical modeling. Fairness demands that training data sets represent diverse populations and that solutions are tailored to local contexts to reduce bias and avoid widening disparities. Critically, the approach must be fed by data streams that extend beyond initial demographics and clinical baselines to include biomarkers, adherence patterns, and pregnancy outcomes, so that the models can be refined and dosing rules adjusted over time. If these safeguards are embedded, AI-enhanced personalized MMS can move beyond proof of concept towards a credible, equitable, and empirically grounded contribution to global maternal health. AI-driven personalized nutrition support represents a frontier in obstetric care. By combining clinical knowledge with data-driven intelligence, we can move beyond generalized prenatal supplements towards precision maternal nutrition. The integration of deep learning models and digital health innovations into antenatal care pathways has the potential to better nourish pregnancies, save lives, and ensure healthier futures for mothers and children worldwide.

Digital mindfulness and the laboring self: A discourse analysis of burnout in Headspace.

Frontline heroes: Leveraging community health workers as first responders for climate-related digital mental health support

Digital health technology in oncology: results from a survey by the ESMO Young Oncologists Committee and medical student alumni.

The mediating association of food safety awareness between digital literacy and health status among Chinese rural residents: A cross-sectional study.

Major Depressive Disorder (MDD) is common and burdensome. Repetitive Transcranial Magnetic Stimulation (rTMS) is recommended for individuals who do not respond to first-line treatments. Coach-supported digital mental health programs are scalable strategies for delivering therapeutic content. This randomized controlled trial tested whether digital mental health programs bolster rTMS for MDD. N=36 depressed adults completed a six-week course of rTMS. Of this group, n=18 were randomized to digital cognitive behavioral therapy (iCBT with Coaching), and n=18 were randomized to digital narrative stories of hope (iNarratives with Coaching). Multilevel models tested group differences in treatment outcomes over time. Principal outcomes focused on the Hamilton Rating Scale for Depression. Exploratory analyses compared outcomes versus a Benchmarking Sample of N=29 patients who received rTMS without coaching. There was a main effect of time (p<.001), indicating an overall reduction in depression symptoms during the trial. Contrary to hypotheses, there was no Group x Time interaction (p=.662), and groups did not differ on clinical response rates (p=.654). Secondary analyses found that the iNarratives group showed greater improvement in positive emotion and functional impairment, whereas the iCBT group showed less dropout from the coaching intervention. Exploratory analyses found a Group x Time interaction (p=.039), potentially suggesting that participants in iCBT or iNarratives showed steeper symptom reduction versus the Benchmarking Sample. The coach-supported iCBT and iNarratives approaches are comparable as adjuncts to rTMS for depression and may yield lower depression scores versus rTMS alone. iNarratives effects appeared specific to increases in positive emotions and decreases in functional impairment.

Social media use is ubiquitous, permeating nearly all populations globally, including men who have sex with men (MSM), despite there being mixed impacts to its use. To fill this gap, we sought to typologize social media usage, mental health, and sleep health among MSM in Paris, France, a city with a large LGBTQIA+ community and high social media usage. Participants were recruited using broadcast advertisements on a popular geosocial networking application in Paris in October 2016. Consenting participants completed a self-administered survey online (French or English) that assessed: sleep characteristics; mental health; and social media use behaviors. We conducted a Latent Class Analysis (LCA) to characterize the number of distinct latent classes across the three primary constructs of interest. A total of 580 participants completed the survey and 539 (92.9%) provided complete data for the LCA. The four-class model fit our data best; thus, we assigned participants to one of four distinct latent classes: 1) MSM using social media for sex with stress and poor sleep (n=97), 2) MSM using social media generally with good mental and sleep health (n=172), 3) MSM using social media for sex with good mental and sleep health (n=147), and 4) MSM using social media for sex with distress and poor sleep (n=123). Findings from this work may inform culturally-tailored interventions, public health messaging, and policy efforts to promote mental, behavioral, and digital health among MSM in France and beyond, while identifying opportunities to leverage digital platforms for sleep and mental health in digital communities. • Most men who have sex with men in France used at least one social media platform • Distinct patterns of sleep quality, mental health, and social media use emerged • Using social media for sex typologized with poor mental health and sleep • Digital networks are important when designing interventions for MSM

Innovations in targeted drug delivery: From nanotechnology to clinical applications

Implementation of early postnatal discharge within 24 h in France: Safety, satisfaction, and feasibility trial supported by a connected home monitoring application (NICE-BIRTH study).

The integration of new technologies such as artificial intelligence (AI) into healthcare has initiated profound changes in clinical practice, reshaping not only clinical workflows but the relational structure of care itself. Among the most significant developments is the transformation of the traditional doctor–patient dyad into a doctor–patient–technology triad. Philosophical studies of technology, especially postphenomenological research, argue that technologies should not be understood as neutral tools but as mediators of perception and action. Building on this perspective, we argue that ethical evaluation must move beyond description toward a normative orientation for understanding how such mediation reshapes care relations. To this end, we draw on postphenomenological theory of technological mediation in relation to contemporary clinical practices and develop a normative evaluative framework grounded in patient wellbeing, understood as an emergent, relational quality of care. Rather than deriving evaluative categories from a single tradition, the framework integrates insights from quality-of-care scholarship and care-ethical perspectives, informed by relational accounts of clinical practice. It operationalizes this orientation across five domains (care quality, patient-centeredness, decision-making, access and communication, and care practices) understood as relational sites where technological mediation can enhance or compromise care. Using clinical decision support systems (CDSS) as an analytically demanding test case, we introduce the concept of the care optimizer as a descriptive-normative category identifying technologies that structure the conditions under which care unfolds. By anchoring evaluation in patient wellbeing and situating technological mediation within a normative horizon, the framework translates postphenomenological insights into ethically actionable guidance and aims to ensure that digital health innovations reinforce, rather than undermine, the moral commitments of medicine.

To evaluate the effectiveness of the Smart Post-Discharge Elderly Health Management Platform on health-related quality of life and self-management after hospital discharge. The global aging population has increased challenges in post-discharge care for older adults, particularly due to chronic conditions and the need for continuous care. Cluster randomised controlled trial. The trial enrolled 383 elderly patients assigned to a platform-based intervention or standard telephone follow-up, with health-related quality of life, self-management, usability and economic outcomes assessed over 6 months. This study was reported in accordance with the CONSORT guidelines. Repeated measures analyses showed significantly greater improvements in HRQoL in the intervention group over 6 months (p = 0.026), with significant improvements across multiple physical and mental health domains (p = 0.002-0.021). Self-management total scores increased significantly (p < 0.001). Platform usability was rated highly by 96.35% of users, and 70.83% reported reduced healthcare costs. Providing a practical framework for integrating technology into nursing practice for aging populations, this platform shows promise for post-discharge elderly care by strengthening nurse-led digital health delivery, care continuity, self-management and health outcomes beyond hospital settings. ChiCTR2400089720.

Artificial intelligence robots for mental health applications: a scoping review.

Online learning has become a central mode of delivery in higher education worldwide, offering new opportunities for non-traditional students such as working professionals, caregivers, and mature-age learners. However, in developing countries such as Uganda, online education faces significant challenges, including limited digital infrastructure, high data costs, and inadequate institutional policies. While previous research has examined online learning, little is known about how instructors in Ugandan higher education institutions adapt their strategies to support non-traditional students. This study seeks to address this gap by exploring the instructional and institutional practices that enable student persistence in resource-constrained environments. Using a qualitative research design, semi-structured interviews were conducted with 52 online instructors from 12 institutions between January and March 2025. Data were transcribed, coded, and analysed thematically, revealing six interrelated themes: flexibility, institutional support services, community building and engagement, balancing multiple roles, perceptions of success, and institutional policies and practices. Findings highlight the importance of flexibility, including extended deadlines, asynchronous learning, and mobile-friendly materials, given students’ competing responsibilities and technological barriers. Instructors emphasised the critical role of support services, particularly digital literacy guidance and mental health counselling. They stressed the value of informal engagement strategies, such as WhatsApp study groups and personal check-ins, for fostering a sense of belonging. Notably, instructors defined success holistically, focusing on persistence, skill acquisition, and workplace application rather than solely degree completion. The study concludes that institutional policies must be reformed to address digital inequities, support informal engagement, and recognise diverse definitions of success. Recommendations include affordable internet initiatives, community-based learning hubs, and context-sensitive student support systems.

Artificial intelligence in mental health: Knowledge mapping from traditional methods to large language models

Influence of social networks and digital competency on loneliness and mental health among older adults in Thailand: A structural equation modeling analysis.

Rethinking the prediction and prevention of dropout in digital mental health.

Digital competencies of health professionals: German translation and content validation of DigiHealthCom and DigiComInf Abstract: Background: Digitalisation in the healthcare sector places new demands on the skills of healthcare professionals. In German-speaking countries, comprehensive instruments that consider both, individual competencies and organisational aspects, are lacking. The English-language instruments DigiHealthCom (5 Factors, 42 Items) and DigiComInf (3 Factors, 15 Items) measure these dimensions; however, they are not available in German. Aim: Culturally sensitive translation and content validation of both measurement instruments. Methods: The translation followed international guidelines using forward and backward translation to ensure conceptual and semantic equivalence. Two tests were conducted with twelve and seven specifically selected healthcare professionals, respectively, to determine content equivalence (relevance, comprehensibility) and content validity using the Content Validity Index (CVI) at item level (I-CVI) and scale level (S-CVI/Ave). Results: Conceptual equivalence and relevance were supported for all factors. Semantic adjustments were made to eight items in DigiHealthCom. Due to insufficient S-CVI/Ave values for relevance (DigiHealthCom: 0.86; DigiComInf: 0.69) and clarity (0.93; 0.90) 27 items were revised. The second test reached appropriate S-CVI/Ave values for relevance (0.90; 0.76) and clarity (0.97; 0.97). Conclusions: DigiHealthCom and DigiComInf are culturally adapted and content-valid instruments for assessing digital health literacy in German-speaking countries. A follow-up study on measurement equivalence is currently being conducted.

Secure authentication and traceability of medical audio data remain critical challenges in modern telemedicine systems and digital health record management.. This paper proposes a novel blind and robust audio watermarking scheme for medical applications. The method combines the Fractional Charlier Transform (FrCT) for optimized time–frequency decomposition, local entropy analysis with critical-band masking for intelligent coefficient selection, and adaptive dithered quantization index modulation (ADQIM) for imperceptible watermark embedding. The proposed scheme provides comprehensive encryption of metadata including patient information and acquisition context through AES-based cryptographic mechanisms, while maintaining imperceptibility and embedding robustness. Comprehensive experimental validation on a diverse medical audio corpus demonstrates that the method achieves a practical payload capacity of 71.8 bits per second, high audio transparency with an SNR of 38.2 dB and a PESQ score of 4.15, and strong resilience against various signal processing attacks with an average BER of 3.2%. The approach provides a computationally efficient solution suitable for integration into operational telemedicine platforms and large-scale medical archiving systems, offering reliable authentication and integrity verification of medical audio records.

The role of artificial intelligence in usability testing and its potential impact on designing inclusive medical devices and digital health tools

Headache disorders are the leading cause of neurological disability globally, yet their management remains marked by profound inequities in access to diagnosis, evidence-based treatment, specialist care, and policy prioritization. This review examines current regional disparities in headache care delivery and highlights emerging system-level approaches aimed at reducing the global treatment gap. High-income regions in Western and Northern Europe, East Asia, and North America have developed advanced care models but continue to face inequities related to socioeconomic gradients, insurance coverage, and fragmented care pathways. In contrast, Eastern Europe, South and Central Asia, Latin America, and much of Africa experience substantial limitations in workforce capacity, diagnostic infrastructure, and medication availability, with population-based surveys indicating high prevalence but minimal health-system readiness. Transitional health systems, including Türkiye and the MENA region, demonstrate increasing awareness and partial integration of structured headache pathways, though coverage remains insufficient. Across regions, telemedicine, digital health tools, community-based initiatives, and workplace programs have shown promise in expanding access, reducing stigma, and improving continuity of care, while reinforcing the central role of primary care. Collectively, these developments signal a shift toward more coordinated and equity-oriented headache service models. Sustainable progress will require strengthened global collaboration, integration of AI-supported decision tools, expansion of cross-border registries and real-world data platforms, and the systematic inclusion of headache disorders within national noncommunicable disease frameworks to ensure high-quality care across diverse populations.