2026· SINTEZA· pp. 171-177· 0 citations· 29 references
TL;DR
A scoping review of XAI applications in telemedicine is presented, examining 20 studies published between 2022 and 2026 to characterise the methods used, their evaluation approaches, and gaps between technical explainability and clinical usability.
Abstract
: Remote healthcare services have grown significantly since the COVID-19 pandemic, with AI increasingly deployed in telemedicine for diagnosis support, triage, and monitoring. While Explainable AI (XAI) methods have been proposed to address trust and transparency concerns, their adoption in clinical practice remains limited — particularly in general practice settings where time constraints, diagnostic breadth, and patient-facing communication impose unique demands on explanation design. This paper presents a scoping review of XAI applications in telemedicine, examining 20 studies published between 2022 and 2026 to characterise the methods used, their evaluation approaches, and gaps between technical explainability and clinical usability. SHAP was the dominant method across the corpus, yet only three papers operated in a telemedicine context, and none evaluated XAI with GPs or in primary care. Empirical evaluation with clinical users was rare, small-scale, and methodologically inconsistent, with a median sample size of 21 participants across five empirical studies. We identify systematic gaps in telemedicine context, GP user focus, and HCI integration, and conclude with research directions for human-centred XAI in telemedicine, derived from identified gaps.
Abstract Objective: Antibiotic resistance is a major global health threat, driven by inappropriate antimicrobial prescribing. Mobile health (mHealth)–based clinical decision-support systems (CDSS) may strengthen antibiotic stewardship, but evidence from resource-limited settings remains limited. This study reports the development and implementation of ComBact, an mHealth-based CDSS for seven infectious disease syndromes, examines physicians’ perceptions of its clinical utility, and evaluates system-level usability metrics at a private tertiary-care hospital in Pakistan. Methods: A convergent parallel mixed-methods design was used. Semi-structured focus group discussions (FGDs) were conducted with internal medicine physicians who had access to ComBact for one year. Transcripts were analyzed using Braun and Clarke’s thematic framework. Quantitative analysis included system-generated data on user registration, uptake, and detailed usage metrics. Findings from both components were integrated using a joint display. Results: 61 clinicians registered for ComBact, all accessing the dashboard at least once. The app recorded 134 sessions, with a mean of 1.23 pathway revisits per session and a mean workflow duration of 1 minute 25 seconds; 32.7% of users completed a ComBact plan. Mobile phones accounted for 57.4% of access and desktops for 42.6%. Two FGDs were conducted with fifteen physicians (median age 31 years (IQR: 27–34 yr). Five themes emerged: (1) clinical applicability, (2) user experience, (3) need of the app, (4) content limitations, and (5) recommendations. Conclusions: ComBact was perceived as a user-friendly tool with meaningful potential to support antimicrobial stewardship in LMICs, though significant content and functional enhancements are needed.
It is argued that usability engineering should be a formative, safety-critical discipline integrated throughout the product lifecycle, including aftermarket deployment, and not merely a compliance task.
Preetha Moorthy, T. Nagel, Eva Hornecker· i-com· 0 citations
This mixed-methods evaluation suggests that a deliberately constrained, language-focused AI system can improve the accessibility of medical notes while preserving clinical accuracy and safety while extending into clinical interpretation.
Nicholas Lamb· Frontiers in Digital Health· 0 citations
Introduction Telemedicine and artificial intelligence (AI) are reshaping healthcare delivery, yet their integration into routine family practice remains inconsistent. This systematic review and meta-analysis aimed to identify barriers and enablers influencing the adoption of telemedicine and AI in primary care and to quantify their effects on clinical and operational outcomes. Methods This review followed PRISMA guidelines and was registered with PROSPERO (CRD420251029675). Six databases—PubMed, Scopus, Web of Science, Cochrane Library, CINAHL, and IEEE Xplore—were searched from inception to March 15, 2025. Eligible studies were randomized controlled trials examining telemedicine or AI implementation in family practice or primary care settings. Data extraction covered study characteristics, intervention type, outcomes, and reported barriers and enablers. Risk of bias was assessed using the Cochrane Risk of Bias 2 tool. Narrative synthesis, thematic analysis, and random-effects meta-analysis were conducted where appropriate. Results Thirteen randomized controlled trials involving more than 29,000 participants were included. Telemedicine interventions showed favorable study-level effects on chronic disease management, access to care, and patient satisfaction, although the pooled clinical effect across ten trials did not reach statistical significance. AI applications significantly improved diagnostic accuracy and clinical decision-making, with a pooled log odds ratio of 0.73 (95% CI: 0.46–1.00). Key enablers included clinician engagement, reliable digital infrastructure, leadership support, training, and workflow integration. Major barriers included technological interoperability, clinician skepticism, patient digital literacy limitations, privacy concerns, and uncertain reimbursement or governance frameworks. Discussion Telemedicine and AI have promising roles in strengthening family practice, particularly for access, chronic disease management, diagnostic support, and decision-making. Sustainable implementation requires attention to technological, organizational, regulatory, and human factors, alongside targeted training, policy support, and integration into routine primary care workflows.
M. Albarqi· Frontiers in Digital Health· 0 citations
BackgroundThe rapid expansion of telemedicine has reshaped healthcare delivery, offering increased accessibility and convenience. However, its impact on the diagnostic process is still undergoing evaluation. This study explored key stakeholder perspectives to enhance understanding of telemedicine's role in the diagnostic process.MethodsWe conducted semistructured interviews with 34 subject-matter experts (SMEs) in telemedicine and practicing clinicians across various healthcare organizations and 10 patients with prior telemedicine experience. Using inductive qualitative content analysis, we identified themes related to facilitators and challenges in the diagnostic process via telemedicine encounters.ResultsSMEs and clinicians noted telemedicine's potential to improve access and enhance continuity of care, but they raised concerns about diagnostic accuracy due to the absence of hands-on physical exams and challenges in managing diagnostic uncertainty. Specifically, clinicians described relying more on additional testing, patient self-reports, and scheduling in-person follow-ups to compensate. Patients emphasized the convenience and accessibility of telemedicine, particularly for those with disabilities, and valued the ability to communicate with clinicians in a familiar environment. However, few patients had received a new diagnosis via telemedicine; and many preferred in-person visits for new or complex concerns. Additionally, barriers related to digital literacy, technology challenges, and incomplete follow-up on diagnostic testing emerged as critical factors influencing telemedicine's effectiveness in diagnostic decision-making.ConclusionsOur qualitative study of stakeholder perspectives underscores certain limitations of telemedicine in the diagnostic process and outlines the need to consider strategies to enhance the effectiveness of diagnostic decision-making in telemedicine.
T. Giardina, Umber Shahid, Rosann T. Cholankeril et al.· Journal of Telemedicine and...· 0 citations
The integration of telemedicine, artificial intelligence (AI), and interprofessional collaboration is transforming healthcare delivery with promising implications for patient outcomes and system efficiency. This qualitative literature review analyzes peer-reviewed and gray literature published between 2023 and 2025 to explore the interplay of these elements in contemporary healthcare. Telemedicine has emerged as a crucial tool in long-term care and rural health, enabling remote consultations and bridging access gaps. However, its implementation is often hindered by communication barriers and unclear role delineation among healthcare professionals. AI applications show potential for improving diagnostics and patient management, yet data privacy concerns and user resistance remain significant barriers to adoption. The coronavirus disease (COVID-19) pandemic underscored the urgency of global health cooperation, emphasizing the value of interprofessional education, dynamic leadership, and collaborative crisis response. Cross-sector models such as One Health illustrate how integration across disciplines can enhance system resilience. A case study from Kyrgyzstan, featuring the TeleMed.Kg initiative, demonstrates the potential of telemedicine to improve maternal and child health in remote areas while also highlighting infrastructural and regulatory limitations. The findings suggest that realizing the full benefits of telemedicine and AI depends on strengthening interprofessional collaboration, promoting digital literacy, and establishing inclusive policy frameworks. Addressing these challenges is essential for building equitable, adaptive health systems capable of meeting evolving healthcare needs worldwide.
Prince Xavier, B. Kulambaev· Medicine India· 0 citations
