Telemedicine is now integral to health care delivery in Saudi Arabia. This study assessed patient characteristics, visit contexts, and patient-reported experiences at a capsule telemedicine clinic. We conducted a cross-sectional survey of 40 adult users of a capsule telemedicine clinic located within Masjid Al-Haram, Mecca, during a busy Ramadan Umrah period. Participants completed a questionnaire on demographics, visit context, satisfaction with services, clarity of results, and post-visit outcomes. Experience and outcome measures were summarized using descriptive statistics. The median age was 50 years. Umrah pilgrims and other visitors comprised 75% and 25%, respectively. Visit reasons were evenly split between feeling unwell and routine checkups (40% each), with 20% for follow-up of an existing condition. Patient experience was highly positive: 95% (95% CI, 84-99) rated the location convenient, and 100% (95% CI, 91-100) rated staff helpfulness, service efficiency, and result clarity as "Good." After teleconsultation, 100% (95% confidence interval [CI], 91-100) felt more confident about their health and would recommend the service. Twenty percent (8/40; 95% CI, 11-35) were referred for hospital evaluation, and no adverse events occurred. Exploratory subgroup comparisons suggested possible differences in referral patterns, but the small sample size precluded definitive inference. Patients reported high satisfaction with the capsule telemedicine service during a Ramadan Umrah period. Most participants were not referred for immediate hospital evaluation, suggesting potential feasibility and acceptability in high-density pilgrimage settings. Further studies with clinical follow-up and objective outcome measures are needed to assess effectiveness and safety.
Mass casualty incidents (MCIs) involving pediatric burn patients are rare, high-impact events that can rapidly overwhelm rural emergency departments (EDs), particularly critical access hospitals with limited pediatric and subspecialty resources. We report a pediatric burn MCI involving three critically injured children presenting within minutes of each other to a rural ED following an enclosed structural fire. Pre-arrival EMS notification enabled early activation of institutional MCI protocols and immediate telemedicine consultation with regional pediatric and burn specialists. This facilitated rapid mobilization of multidisciplinary personnel, anticipatory airway planning, and coordination of critical care transport. Upon arrival, patients required simultaneous resuscitation under conditions of limited staffing and constrained transport availability. All three patients were stabilized and transferred to a regional pediatric burn center. Two patients survived to hospital discharge while the third was compassionately extubated at the receiving facility days later. To our knowledge, this is among the first descriptions of telemedicine-supported simultaneous pediatric burn MCI resuscitations in a critical access ED. This case highlights the importance of early MCI activation, and telemedicine-enabled operational and clinical coordination in rural disaster response systems.
Health care disparities are severe across Asia. To bridge gaps in professional knowledge and skills, Doctor-to-Doctor (DtoD) telemedicine shows promise. However, the specific technical skills required for effective DtoD conferences and consultations, particularly those involving advanced technologies, remain undefined. This study aimed to establish a consensus on these essential skills. We used the Delphi method, engaging 30 participants from Asia-Pacific Advanced Network Medical Working Group DtoD training programs. Investigators and an expert panel developed an initial list of technical skills for both synchronous and asynchronous DtoD teleconferences and consultations, which participants evaluated in Round 1. Following an in-depth workshop, a revised questionnaire incorporating new skills and feedback was assessed in Round 2, yielding the final list. The study included 30 hospital IT staff, doctors, and nurses from 11 Asian countries, 57% of whom were affiliated with university hospitals. All participants completed both rounds. After integrating 46 written comments, 10 new skills were added, resulting in a final list of 43 technical skills. These encompassed conceptual understanding, technical execution, coordination, and security policy. Notably, "Extracting images from medical devices" and "Maintaining audio quality" were identified as key skills. This study is the first to delineate the technical skills necessary for DtoD telemedicine conferences and consultations in Asia. The identified skills can guide future training, assessment, and development initiatives to strengthen the telemedicine workforce across the region.
Assisted peritoneal dialysis (PD) is an important option for frail patients with advanced age, comorbidities, and reduced autonomy who face barriers to self-managed home dialysis. This study evaluates the current use of assisted PD in Italy using data from the 2024 Italian Peritoneal Dialysis Census and compares findings with previous surveys conducted since 2008. Data were collected from 228 dialysis centers, with 221 centers providing information on assisted PD, covering 4,229 prevalent PD patients. Assisted PD was reported in 904 patients (21.4%). Family members were the main caregivers (86.2%), followed by paid caregivers (8.1%), institutional staff (2.9%), and nursing home personnel (2.8%). Over time, the proportion of assisted PD remained stable between 21% and 25%, with no significant change in caregiver distribution. Centers applying assisted PD were larger, had higher PD prevalence, and managed more PD patients compared with centers not using assisted PD. Geographic variability was observed, with the highest prevalence in island regions. Only a small proportion of patients in nursing homes were treated with PD compared to hemodialysis, highlighting organizational and staffing barriers. These findings show that assisted PD in Italy has remained stable over the past two decades and is predominantly based on family caregiving, unlike Northern European countries where professional home care predominates. The limited use of institutional and nursing home support suggests unmet needs and potential areas for improvement. Economic incentives, regional support programs, and telemedicine may help expand assisted PD access and promote home-based dialysis in frail populations.
Positive Airway Pressure (PAP) therapy download reports are the currentobjective data standard for assessing sleep apnea treatment success, providing information onusage, leak, and residual apnea-hypopnea index (AHI). However, follow-up parallel testing can offer added value in measuring sleep and respiratory health in patients receiving PAP therapy. This study compares residual PAP-derived AHI (AHIFLOW) with cardiopulmonary coupling (CPC)-derived AHI3% (AHICPC). We specifically examined patients for whom PAP therapy would be considered effective, but follow-up testing indicated potentially significant residual disease. As part of standard clinical care, patients in our telemedicine sleep program undergo longitudinal home sleep testing using CPC through the SleepImage system. We retrospectively analyzed remote physiological monitoring data from ResMed PAP devices and CPC-based sleep testing on nights with concomitant data. A total of 465 patients met the inclusion criteria, contributing 24,939 nights of matched PAP and CPC data. Mean AHIFLOW was 2.4 events/hour, while mean AHICPC was 12.1 events/hour. Among nights with AHIFLOW <5 events/hour, 85% of nights had AHICPC ≥5 events/hour, 47.7% had AHICPC ≥10 events/hour; 28.3% had ≥5 minutes with SpO2 <90%, and 10.6% had ≥5 minutes with SpO2 <88%. PAP download reports are useful for assessing usage and leak, but mayunderestimate residual respiratory burden. Besides periods of non-use, device-based flow-based metrics alone can miss clinically meaningful residual disease, including hypoxic events during REM sleep. Reliance on PAP-derived AHI as the sole efficacy metric risks overlooking persistent disease.
Pediatric emergency care (PEC) in low-resource settings faces systemic challenges, including inadequate infrastructure, workforce shortages, and supply chain inefficiencies, which contribute to preventable morbidity and mortality. Quality improvement (QI) initiatives offer a structured framework to address these challenges, enhance patient safety, and improve clinical outcomes. A narrative review was conducted using literature identified from PubMed and Google Scholar, supplemented by reports and guidance documents from the World Health Organization and nongovernmental organizations. Search terms included combinations of "pediatric emergency care," "quality improvement," "patient safety," "low-resource settings," "LMICs," "triage," "task shifting," "telemedicine," "digital health," and "community health workers." Eligible sources included primary studies, reviews, implementation reports, and policy documents addressing QI interventions, implementation barriers, facilitators, or outcomes relevant to PEC in low-resource settings. Included studies reported improvements in triage reliability, time to treatment, guideline adherence, patient-flow organization, workforce capacity, and data availability. Several triage- and ETAT-based interventions reported reductions in pediatric mortality or improved time-sensitive care processes, whereas digital health interventions improved triage completion, referral monitoring, and real-time decision support. Key enablers included local adaptation, staff training, audit and feedback, interdisciplinary collaboration, community engagement, and sustainable governance structures. Strengthening QI initiatives is essential to achieving global health goals and ensuring equitable healthcare access for children in resource-limited settings. Sustainable, evidence-based interventions are critical for building resilient PEC systems and optimizing workflows.
Timely attention by home health care (HHC) and outpatient providers within one week after hospital discharge is associated with lower readmission rates among sepsis survivors. However, few patients nationwide receive this pattern of care. Improving care transitions for sepsis survivors is inhibited by barriers in sepsis identification, information transfer, care coordination, timely access to care, and patient engagement. The I-TRANSFER study was designed to address these gaps by implementing timely delivery of post-acute care (PAC) for sepsis survivors in real-world health care settings. The study aimed to identify, describe, and map the implementation strategies used to implement the I-TRANSFER care transition protocol. Five diverse health systems (16 hospitals), partnered with an affiliated HHC agency, participated in a Type 1 hybrid implementation science study. Through thematic inductive and deductive qualitative analysis, implementation determinants-barriers and facilitators-were identified, summarized, and presented back to the sites' implementation teams. This paper reports on implementation strategies used to address barriers and implement the I-TRANSFER care transition protocol. Strategies are mapped to the Expert Recommendations for Implementing Change (ERIC) taxonomy. Implementors and researchers deployed strategies spanning 62% of the 73 ERIC categories, resulting in hundreds of detailed examples. Strategies aimed at identifying sepsis and referring survivors to HHC emphasized relaying clinical data to providers; adjusting the EHR; and educating staff to improve sepsis recognition, documentation, and referral to HHC. Strategies aimed at information transfer and making outpatient appointments emphasized EHR-based tools, telemedicine workflows, and centralized scheduling to ensure communication to PAC and timely outpatient appointments. Providing timely HHC and outpatient visits required staff and patient education, tailored HHC pathways, patient-focused interventions, and quality monitoring. Cross-cutting strategies reinforced coordination and education across the full continuum of care. Heat maps illustrate which strategies were used most often across objectives and by hospital/HHC dyad. This study identified, described, and mapped to the ERIC taxonomy more than 450 implementation strategies used by hospital-HHC dyads to implement the I-TRANSFER care transition protocol, providing practical, translatable strategies to support timely post-acute care transitions for sepsis survivors. By identifying the barriers in care transitions, and reporting the strategies to address them, these findings can inform broader efforts to deliver timely, coordinated care and improve outcomes for vulnerable populations across settings.
Modern urology is undergoing a technological revolution, a key component of which is the integration of augmented reality (Augmented Reality, AR). By combining virtual 3D models with the real operating-room environment in real time, AR is transforming surgical planning, intraoperative navigation, and training. This technology creates opportunities to improve procedural accuracy, reduce invasiveness, and enhance clinical outcomes, particularly in robotic and laparoscopic surgery. To systematize current data on the use of AR technologies in urology for surgical planning, intraoperative navigation, and training, and to assess their clinical efficiency. A systematic review of publications (2019-2023) was conducted in PubMed, Scopus, and IEEE Xplore in accordance with PRISMA. clinical studies, technical reports, and reviews on the use of AR/VR in urological surgery or training with quantitative data. A total of 26 studies were included in the final analysis. Key findings: 1. Training: AR/VR platforms (HoloLens, STAR, RobotiX-Mentor) substantially improve surgical skills by reducing procedure time and error rates (e.g., a 3.6-fold decrease in instrument collisions among novices) and increasing accuracy (nerve preservation 96.6% vs 72.8%). AR-based telepresence systems with AI-driven hand tracking (98% accuracy) and AI video analysis tools have also been developed. 2. Renal surgery: AR navigation during removal of complex tumors is associated with reduced estimated blood loss (~22 mL), shorter operative time (~23 min), lower rates of warm ischemia (by 50%) and shorter ischemia duration (~4 min), fewer collecting system injuries (10.4% vs 46.5%), and higher enucleation rates. Intraoperative concordance with the 3D plan reaches 86.7%. 3. Prostate surgery (RP): 3D models/AR improve the accuracy of tumor and neurovascular bundle identification (sensitivity/specificity ~90-95% for predicting extracapsular extension), reduce positive surgical margin rates (to 2.9-6.6%), and improve functional outcomes (continence up to 94.1%, potency up to 70.6%). AI systems enable accurate targeted biopsy (87.5% in pT3). Limitations and challenges: high equipment and operating costs (up to $1500-2000 per procedure), real-time model registration accuracy issues (misalignment up to 12%), limited and heterogeneous evidence base, and the need to improve haptic feedback in VR. integration of AI for navigation and analysis, development of "digital twins", hybrid AR/VR platforms for telemedicine and training, and cloud-based solutions. AR has demonstrated clinical relevance in urology by improving the accuracy, safety, and outcomes of surgery and transforming training. Despite existing technical and economic barriers, integration with AI and the development of personalized approaches are shaping the future of this technology as a key element of digital urology. Large-scale randomized clinical trials are needed to confirm long-term effectiveness and cost savings.
Heart failure with reduced ejection fraction (HFrEF) remains a leading cause of morbidity, hospitalization, and mortality in low- and middle-income countries (LMICs). Guideline-directed medical therapy (GDMT) including angiotensin receptor-neprilysin inhibitors (ARNIs), evidence-based beta-blockers, mineralocorticoid receptor antagonists (MRAs), and sodium-glucose co-transporter 2 (SGLT2) inhibitors has consistently demonstrated reductions in mortality and heart failure (HF) hospitalizations. Despite strong evidence, real-world implementation of GDMT in LMICs remains suboptimal. This article synthesizes published evidence and expert experience to identify barriers to GDMT implementation in India and comparable LMIC settings and to propose pragmatic, resource-aligned strategies to improve uptake. Relevant English-language literature (2015-2025) was identified through PubMed, Google Scholar, and guideline repositories (ESC, ACC/AHA/HFSA, CSI). Search terms included "heart failure," "GDMT," "LMIC," "India," "implementation barriers," and "pharmacist-led care." Key guidelines, randomized trials, observational studies, registries, and relevant reviews were included. Barriers span economic constraints, limited insurance coverage, high out-of-pocket costs, low health literacy, cultural beliefs, fragmented follow-up, limited access to specialized HF services, inconsistent drug availability, and clinician-level knowledge-practice gaps. Evidence from observational studies and implementation reports supports early low-dose combination GDMT, simplified titration pathways, pharmacist- and nurse-led follow-up models, task-shifting, and telemedicine-enabled monitoring as feasible strategies in LMIC settings. Bridging the evidence-practice gap for GDMT in LMICs requires coordinated, multi-level interventions tailored to resource constraints. Strengthening team-based care and aligning policy with essential HF therapies can substantially improve outcomes and equity.
Health systems worldwide face growing pressure from population aging, multimorbidity, and rising emergency admissions, prompting reconsideration of traditional inpatient care models. In response, digitally enabled models such as tele-intensive care unit (tele-ICU) programs, hospital-at-home services, virtual wards, and other remote specialist pathways have expanded, particularly after the COVID-19 pandemic accelerated telemedicine adoption and cross-site virtual staffing. However, nationally coordinated, multispecialty virtual hospitals remain uncommon worldwide, and robust evidence on their system-level effects is still limited. As a result, policy discussions about national virtual hospitals must often draw on evidence from related virtual-care models rather than from mature national implementations. This viewpoint synthesizes representative international evidence from tele-ICU systems, hospital-at-home programs, virtual wards, telestroke networks, and other condition-specific virtual-care pathways, and examines Saudi Arabia's Seha Virtual Hospital (SVH) as a national case study to identify policy lessons relevant to the design, governance, and evaluation of national virtual hospitals. Across settings, these models suggest that remote and digitally supported care can achieve outcomes comparable to in-person hospital care when patient selection is appropriate, escalation and transfer pathways are explicit, monitoring intensity matches clinical risk, and multidisciplinary teams are integrated into local workflows. Tele-ICU programs have reported reductions in intensive care mortality and length of stay under well-structured organizational models, while hospital-at-home and virtual-ward programs have shown comparable safety, reduced hospital usage, and improved patient experience among selected patient groups. Telestroke networks likewise demonstrate outcomes comparable to specialist in-person care in acute stroke pathways. Nevertheless, the evidence base remains heterogeneous and strongly context-dependent. Much of the literature is short-term, with limited consistent evidence on long-term outcomes, caregiver burden, cost-effectiveness, workforce implications, and digital equity. SVH illustrates the emerging implementation of a centralized national virtual hospital model. Launched in 2022 under Saudi Arabia's Vision 2030 Health Sector Transformation Program, SVH operates as a national telehealth hub embedded within the country's broader digital-health ecosystem and links hospitals across the Kingdom to specialized clinical expertise. Its service portfolio includes urgent and critical care consultations, specialized virtual clinics, multidisciplinary case discussions, and supportive diagnostic services. Early reports indicate rapid operational expansion, broad institutional participation, and national-scale feasibility. However, independent comparative evidence evaluating SVH's effects on mortality, readmissions, length of stay, cost-effectiveness, equity, and workforce sustainability remains limited. National virtual hospitals should therefore be understood as evidence-generating health-system innovations rather than fully validated care models. Sustainable scale-up requires embedding rigorous prospective evaluation within implementation, aligning financing mechanisms with substitution of inpatient care, establishing clear governance and regulatory frameworks, and addressing digital inclusion and workforce sustainability. These considerations can help guide policymakers and health-system leaders in the accountable, equitable, and evidence-informed development of national virtual hospital programs.
Pakistan faces a rapidly growing dementia crisis with an estimated 374,060 cases, projected to rise substantially as the older adult population triples to 38.3 million by 2050. Yet no provincial-level assessment of service readiness has been published. To our knowledge, this study provides the first structured literature-based provincial assessment of dementia-relevant geriatric mental health infrastructure across Pakistan's four provinces and two administrative territories. We conducted an integrative review synthesizing peer-reviewed literature, grey literature, and government reports. Drawing on the conceptual structure of WHO-AIMS (2007), we developed a novel six-criteria framework to categorize provincial readiness across three dimensions: governance, infrastructure, and specialized care. Findings were contextualized through comparison with India, Bangladesh, and Sri Lanka. Our framework stratified Pakistan into three tiers. Tier 1 provinces (Punjab, Sindh) demonstrated partial system maturity; Tier 2 provinces (Khyber Pakhtunkhwa, Balochistan) exhibited foundational but inactive governance structures; and Tier 3 territories (Gilgit-Baltistan, Azad Jammu and Kashmir) showed absent legislative frameworks and no identifiable dementia services. Validated Urdu screening instruments exist (MMSE-Urdu, 10/66 battery) but are not systematically used. Pakistan's psychiatric workforce (0.24 per 100,000) lags significantly behind regional comparators such as Sri Lanka (0.47) and India (0.30). Dementia care in Pakistan remains structurally dependent on urban tertiary centers in Punjab and Sindh; four of six jurisdictions have no identifiable dedicated dementia-specific services. Post-18th Amendment devolution created coordination gaps without capacity transfer. We propose a tiered implementation roadmap and multi-channel service delivery model leveraging primary care, community health workers, and telemedicine to bridge the specialist gap.
Allergic diseases affect more than one billion people globally, yet care access is profoundly unequal. The "forgotten billion" refers to underserved populations-especially in LMICs and marginalized groups within high-income countries-who face disproportionate morbidity and preventable deaths due to gaps in diagnosis, essential medicines, immunotherapy and biologics, trained workforce, and policy prioritization. To synthesize recent (2014-2026) evidence on global burden and inequities in allergic disease care, analyze system-level gaps, review scalable innovations, present diverse case studies, and propose prioritized recommendations, monitoring frameworks, and a research and financing agenda. We conducted a structured narrative review of peer-reviewed literature and global guidance documents, focusing on burden metrics (prevalence, DALYs, mortality), access indicators, interventions (task-sharing, telemedicine, point-of-care tools, immunotherapy access, digital health, procurement/policy levers), and implementation science frameworks. Sources prioritized include WHO materials and guideline bodies (GINA, ARIA, EAACI), plus global reports and primary studies. Asthma illustrates the equity chasm: in 2019 it caused approximately 21.6 million DALYs and approximately 461,000 deaths globally, with approximately 90% of burden borne in LMICs and most deaths occurring in LMICs. Systematic reviews show essential inhaled asthma medicines-especially inhaled corticosteroids (ICS) and ICS-containing combinations-are often unavailable or unaffordable in LMICs. Scalable strategies with documented impact include task-shifted care packages (Malawi), standardized primary care training (South Africa), community health worker home visiting (Boston), and public-sector access programs (Brazil), alongside national allergy strategies (Finland). Closing the allergy care chasm requires shifting from specialist-centric innovation to systems-first equity: universal access to essential medicines and equitable pathways to targeted therapies for severe disease, standardized primary care delivery with task-sharing, market-shaping and pricing policy reform, digitally enabled self-management designed to reduce (not widen) inequities, and integrated environmental action. Implementation must be measured with equity-sensitive frameworks and supported by durable financing aligned with UHC and NCD agendas.
Institutional maternal and perinatal outcomes are highly specific to local contextualized conditions and are suited to inform local policy. As institutional delivery increases, maternal health events are more likely to occur in facilities than at home. This was a before-after impact evaluation study through the implementation of a 3-year quality improvement project undertaken in Central Region. The goal was to reduce institutional maternal mortality ratio and perinatal mortality rate over a 3-year period from 2021 to 2023 with 2020 as a baseline year. Baseline assessment was conducted by reviewing 2020 maternal death audit reports to identify key challenges associated with maternal deaths. Interventions were drawn to address identified challenges by key stakeholders. Sensitization meetings were held with stakeholders, health managers and health staff to discuss the interventions and solicited their support. Interventions implemented were life-saving skills and safe motherhood trainings for health staff across the region, introduction of maternal death tracker to improve surveillance on maternal death, clinical supervision of health staff at the peripheral level by specialist through telemedicine using WhatsApp platforms from 2021 to 2023. Baseline indicators were collected from the District Health Information Management System-2 (DHIM2) in 2020. The outcome indicators were improved family planning coverages, increased skilled delivery rates and reduction in maternal mortality ratio and perinatal mortality rates. Process indicators were proportion of practicing midwives and clinicians trained in life saving skills, number of health centers conducting basic emergency obstetric care signal functions, percentage of audited maternal deaths entered DHIMS2. Over the course of the project, 4,800 health staff were trained, skilled birth rate improved from 61.6 to 63.9%, family planning acceptor rate from 28.5 to 45.1% and reported maternal deaths audited improved from 78.7 to 100%. The implementation of institutional audit recommendations also improved from 20 to 72%. Institutional maternal mortality ratio declined by 25.3% and neonatal deaths by 45.2%. Quality improvement methods using the project approach to strengthen maternal health services can lead to improve mother and baby health outcomes. This approach when scaled up nationally may help increase the chances of meeting the sustainable development goal three, I recommend the implementation of the interventions to policymakers such as the Ministry of Health to support in reducing institutional maternal and perinatal mortalities.
Sustainable head and neck cancer (HNC) surgery is challenged by environmental impact, workforce shortages, inequitable access to advanced techniques, and policy constraints. Addressing these areas is critical for equitable, high-quality care. This structured narrative review synthesizes evidence on environmental sustainability, workforce development, technological innovation, health policy, and socioeconomic determinants in HNC surgery, without aiming to provide a systematic or exhaustive evidence synthesis. Sources included peer-reviewed literature, global workforce surveys, and international policy reports, with a focus on disparities between high-income countries (HICs) and low- and middle-income countries (LMICs). Operating rooms produce up to 70% of hospital solid waste and consume 3-6 times more energy than other units; reusable instruments and improved waste segregation can reduce carbon footprints by over 50%. Workforce shortages are severe in LMICs, where subspecialty training is scarce; global partnerships, bidirectional education, and simulation-based learning can expand local capacity. Telemedicine, artificial intelligence, and three-dimensional printing enhance surgical planning, training, and access but may widen disparities without equitable deployment. Policy tools-including diagnosis-related groups, bundled payments, and universal coverage-affect access and innovation uptake. Pandemic preparedness underscores the value of resilient systems with flexible staffing and telehealth integration. HNC surgery requires coordinated action across environmental, workforce, technological, socioeconomic, and policy domains; however, future systematic reviews are needed to comprehensively map the evidence base and assess its methodological quality. Embedding sustainability in clinical practice, ensuring equitable innovation access, and aligning reimbursement with high-value care can strengthen system resilience, improve outcomes, and support long-term surgical service viability.
The letter reports on a teleconsultation program for patients with Parkinson's Disease after hospital-based rehabilitation. PwPD and their caregivers were contacted with regular video/phone calls assessing therapy adherence and addressing emerging difficulties. Results showed high satisfaction, continuity of care, and feasibility, confirming telemedicine as a valuable extension of clinical practice.
Digital health and virtual care are increasingly reshaping how healthcare is organized, delivered, and experienced. In Tanzania, digital transformation is evident in national commitments to digital health governance, health information exchange, hospital information systems, digital referral and emergency transportation, telemedicine, and emerging diagnostic applications supported by artificial intelligence. At the same time, patients are increasingly using social media, mobile platforms, and other digital channels to seek health information, consultations, diagnoses, and medicines, creating new forms of digitally mediated care that often operate alongside formal healthcare systems. Using a narrative synthesis design informed by a practice-based perspective, this study reviewed policy documents, national strategies, implementation reports, peer-reviewed empirical studies, global guidance documents, and conceptual literature relevant to Tanzania's digital health ecosystem. Evidence was identified through a structured search, source-selection, and thematic synthesis process. The review examined three interrelated questions: (i) how Tanzania's digital health and virtual care landscape is evolving; (ii) how e-patient behaviours, informal digital consultations, and emerging e-provider practices are interacting with formal health systems; and (iii) what these developments imply for workforce preparedness, clinical governance, patient safety, antimicrobial stewardship, confidentiality, accountability, and trust. The findings suggest that Tanzania's digital health transition is not primarily a technology-adoption challenge but a practice challenge involving how healthcare workers, patients, digital technologies, and governance systems interact in everyday care. While substantial progress has been made in establishing digital health policies and governance frameworks, important gaps remain in workforce preparedness, digital professionalism, virtual care governance, stewardship, privacy protection, and management of informal digital health practices. The review highlights the growing influence of e-patients and digitally mediated health-seeking behaviours in reshaping traditional patient-provider relationships and expectations of care. To support policy and implementation action, this paper proposes the TRUST framework: Transparent Credentials and Workforce Preparedness, Robust Clinical Governance, User-Centred Engagement, Safety and Stewardship, and Trusted e-Health Technologies and Data Practices. Grounded in a practice-based perspective and implementation evidence, TRUST is proposed as a practice-based framework for strengthening accountable digital health work practices, patient trust, workforce readiness, and regulatory preparedness in Tanzania and similar settings where formal and informal digital health pathways increasingly coexist.
ObjectiveTo evaluate the diagnostic accuracy of a multi-disease offline artificial intelligence system (Medios-AI, MAI), integrated into a smartphone-based fundus camera, for simultaneous screening of diabetic retinopathy (DR), glaucoma, and age-related macular degeneration (AMD) in a real-world setting.MethodsIn this prospective cross-sectional study, 193 adults (371 eyes) aged ≥18 years with DR, glaucoma, AMD, or normal fundus were enrolled between May and December 2024. Dilated fundus imaging was performed using the Remidio Fundus on Phone (FoP) and Zeiss Clarus 500 cameras. Ungradable images were excluded. The offline MAI algorithm generated disease-specific reports, which were compared to masked grading of Clarus images by two fellowship-trained ophthalmologists. In ambiguous cases, the AI report defaulted to "either DR or AMD."ResultsMAI achieved sensitivity of 99.3% (95% CI: 96-100), specificity of 95.7% (95% CI: 92-98), and AUROC of 0.99 for detecting any retinal disease. For glaucoma (n = 109), sensitivity was 98.2% (95% CI: 94-100), specificity 99.0% (95% CI: 97-100), AUROC 0.99. For AMD (n = 56), sensitivity was 88.9% (95% CI: 77-96), specificity 97.5% (95% CI: 95-99), AUROC 0.93. For DR (n = 78), sensitivity was 84.6% (95% CI: 75-92), specificity 99.0% (95% CI: 97-100), AUROC 0.92. Agreement on vertical cup-to-disc ratio between AI and graders ranged from -0.1 to +0.1, with intergrader ICC of 0.97 (P < 0.001 for all comparisons).ConclusionsMAI demonstrated significant diagnostic accuracy for DR, glaucoma, and AMD using an offline, smartphone-based platform, supporting scalable, point-of-care retinal screening in resource-limited settings.
Machine learning (ML) has become a transformative force in clinical research, offering predictive precision and data-driven decision-making across diverse medical domains. Despite this rapid adoption, a comprehensive informatic-based synthesis of ML applications in clinical trials remains lacking. This study systematically maps the scientific landscape, thematic evolution, and emerging directions of ML-related clinical trial research. The analysis was conducted on PubMed-indexed clinical trials (1995-2025) using Bibliometrix R package, VOSviewer, and Microsoft Excel 2021 (Microsoft Corp., USA). Temporal trends were modeled using ARIMA(5,1,0) forecasting and additive time-series decomposition. Collaboration networks, productivity patterns (Lotka's Law), journal dispersion (Bradford's Law), keyword co-occurrence, and thematic mapping (Walktrap clustering, Callon's centrality/density) were analyzed to identify conceptual structures and research frontiers. A total of 1,195 publications across 563 journals were identified, showing exponential growth after 2018 and a forecasted stabilization by 2030. The USA (24.8%) and China (19.5%) led global output, reflecting strong North American-Asian collaboration. Keyword co-occurrence revealed eight clusters centered on machine learning, artificial intelligence, and radiomics, transitioning toward deep learning, precision medicine, and mHealth. Bradford's Law identified 36 core journals, including Scientific Reports, BMJ Open, and PLOS ONE. Thematic evolution showed a shift from algorithmic and retrospective studies to clinically grounded themes such as cognitive behavioral therapy and telemedicine. Emerging topics emphasized translational and patient-centered applications. This study delineates the dynamic evolution of ML in clinical trials, highlighting its growing integration into precision medicine. Future research should prioritize inclusivity, real-world implementation, and ethical frameworks to sustain equitable and clinically impactful innovation.
We conducted research showing that chronic disease management continued to challenge healthcare systems, payers, and patients. At the same time, digital therapeutics emerged as a promising and potentially transformative approach. They supported better management of long-term conditions, improved patient outcomes, and helped streamline healthcare delivery. We carried out a comprehensive literature search to identify both original reports and reviewed publications. The search covered multiple databases, including Google Scholar and PubMed, and we also gathered relevant information from credible online sources such as the World Health Organization and India's National Crime Records Bureau. Using these findings, the narrative explained how digital therapeutics reshaped chronic disease management by highlighting key benefits, the technologies that enabled these solutions, and the expected impacts on both clinical and economic outcomes. We also discussed the obstacles the sector encountered as it developed, and we considered the future prospects of digital therapeutics in chronic care. In conclusion, digital therapeutics offered personalised care, improved patient engagement and adherence, provided real-time monitoring and feedback, enhanced accessibility and convenience, and were cost-effective in managing chronic disease; however, challenges such as cybersecurity concerns, reliability of data, the digital divide, and a lack of extensive clinical validation needed to be addressed for widespread adoption. While the evidence to date suggested clear clinical and economic promise, realizing that promise required coordinated action stronger clinical trials to build robust evidence, clear regulatory pathways to ensure safety and efficacy, investment in secure interoperable infrastructure, and targeted efforts to close the digital divide so vulnerable populations were not left behind; policymakers, clinicians, payers, and technology developers had to collaborate to translate innovation into equitable, scalable care improvements.
Sub-Saharan Africa (SSA) has 1.3 billion people, 2.1 billion by 2050; the life expectancy has increased so the burden of non-communicable diseases (NCD) has almost reached that of communicable diseases. In SSA NCD neurological diseases rank at the top: stroke is a leading cause of death, and there are more than 20 million persons with epilepsy (PWE); 75% PWE lack proper treatment. Hospitals are few and under-resourced with a persistent neurologist shortage, hence the majority of neurologic patients seek care at primary care level: improving access to care for neurologic diseases at primary care level is a strategic objective of the WHO-Intersectoral Global Action Plan. HIV, highly prevalent in SSA, increases the burden of neurologic conditions and the United Nations-WHO called to integrate HIV and NCD-neurologic diseases at HIV primary care centres. At this level much of the care to neurologic patients is delivered by non-physician clinicians (NPC) whose education in neurology is insufficient. The Italian Society of Neurology (SIN) established a partnership with the DREAM program, a sub-Saharan Africa primary care program treating chronic diseases as HIV and other diseases since 2002, whose successful intervention model can be applied to epilepsy and other neurologic conditions. So far, the partnership trained more than 430 local healthcare workers, over 2,800 people with epilepsy receive regular care at 14 DREAM centers, more than 4,000 epilepsy teleconsultations have been performed by Italian neurologists along with more than 1,200 electroencephalograms reports thanks to a tele-neurology platform. In addition, SIN started an education course to young Italian neurologists to provide them knowledge and tools on SSA primary care, a step forward to build a globalized neurology.