Managing indirect contacts in Family Health Units (FHUs) via email is characterized by an unstructured workflow that is difficult to triage. This situation results in a critical clinical workload, involving the systematic reception of inappropriate or clinically irrelevant requests directly by physicians, such as private-sector exam transcriptions or administrative reports. The lack of filtering generates communication noise and compromises the team's operational efficiency.To implement the OSGA platform (Orientation of Requests for Management and Support), utilizing the Scrum methodology, to structure request flows, reduce the volume of inappropriate inquiries, and empower patients to access the healthcare system appropriately.The use of informal channels prevents effective task prioritization. The OSGA platform acts as a pedagogical guide that directs patients based on their specific needs: it provides instructions on verifying active prescriptions via government health app "SNS24" portal before requesting new ones, clarifies legislation regarding short-term school excuses (up to 3 days), and redirects acute illness situations to the SNS24 helpline. This workflow ensures that only pertinent requests, supported by the required documentation, reach healthcare professionals.The methodology established a process of continuous inspection and adaptation, allowing the platform to evolve dynamically based on ongoing feedback from both patients and professionals. The system functions as a pedagogical filter that teaches patients how to navigate the healthcare system, discouraging the use of email for situations that can be resolved through official channels. Qualitative feedback indicated a decrease in work-related anxiety.The application of the Scrum methodology in the FHU proved to be a catalyst for organizational innovation. OSGA not only structured the workflow but also established a commitment to continuous improvement and patient education, proving fundamental for operational sustainability and health literacy in primary care.

Primary care faces escalating administrative workload that outpaces available workforce capacity. Manual processing of pathology results, prescriptions, registrations and clinical documents creates delays, reduces accuracy and contributes to staff burnout. To address these issues, we implemented an intelligent automation programme to reduce administrative burden and improve the working day through robotic process automation (RPA) operating across high-volume workflows.To evaluate the impact of intelligent automation on: Administrative workload (clinical and non-clinical) and task turnaround Clinical and non-clinical capacity release Standardisation and accuracy of administrative processes Workforce wellbeing and absenteeismThe evaluation was conducted across multiple primary care sites serving approximately 500,000 patients. A retrospective analysis was conducted using organisational automation logs from more than 35 automated workflows. Data included total automated tasks, hours saved, appointment equivalents generated, absenteeism trends and process consistency indicators. Tasks automated included registrations, prescription processing, document classification, pathology routing and administrative triage. Descriptive statistics were applied to assess operational, workforce and patient-facing outcomes.The automation programme processed more than 900,000 tasks across workflows, releasing over 55,000 hours of staff time. This equated to 30 whole-time-equivalent clinicians’ time redirected from administrative work. Standardisation of automated workflows enabled an additional 330,000 appointments to be made available to patients by improving workflow throughput and reducing bottlenecks. Workforce impact was substantial: peak absenteeism reduced from 42% to 17%, and staff reported improved workload manageability and job satisfaction. Turnaround times improved across all automated pathways, leading to improved service continuity and patient experience.Intelligent automation delivered meaningful operational efficiencies while improving safety and consistency. Automation worked most effectively when paired with workflow redesign, real-time monitoring and staff engagement. Cultural and behavioural factors were more influential than technology in determining adoption speed. Performance varied across workflows, highlighting the need for iterative optimisation and local workflow readiness.Large-scale automation of administrative workflows can significantly strengthen primary care capacity, improve the working day and enhance patient access. These findings demonstrate that intelligent automation is a scalable and cost-effective component of modern primary care operations. This model demonstrates a scalable approach to strengthening primary care delivery and may inform international efforts to modernise primary care.

Practices faced increasing demand, rising appointment requests and growing pressure on reception and clinical teams. Multiple routes into the system—phone, walk-in requests, and limited online access—created inequity in how patients were prioritised. Those who could queue early by phone or in person were often seen first, while online requests were handled inconsistently or as a lower priority. Staff described the process as “unfair for patients and overwhelming for us.” A more structured, safe and equitable access model was needed.Over 50 practices first mapped existing access routes and found significant variation in how requests were handled. The introduction of an AI-enabled digital triage system provided a single front door through which all appointment requests—online, telephone and face-to-face—were triaged consistently. To support patients with low digital confidence, practices enlisted digital champions from Patient Participation Groups to help individuals complete requests in waiting rooms. Early strengths included clearer prioritisation and improved visibility of clinical need. A limitation was the initial adjustment period for staff, who had to change long-established habits and trust a new workflow. Safety checks were embedded at critical points and concerns about clinical safety addressed in DTAC, DPIA and DCB0129/0160-aligned safety assessment.Digital champions drawn from patient groups became powerful advocates for adoption. Offering supported digital access in reception improved inclusion. Future work will focus on iterative refinement and extending triage logic.The experience demonstrates that digital triage can improve fairness and transparency when integrated into all modes of access. Engagement from both staff and patients was essential to redesigning safe and equitable pathways.Consistent digital triage, taking <4mins per patient, has supported more than 500,000 patients through consistent decision-making and improved access equity; strengthening the ability of teams to manage demand safely with 76% patients offered appointments ≤7-days.

Healthcare systems worldwide are undergoing rapid digital transformation. Advanced technologies such as artificial intelligence (AI), big data analytics, and automation tools are increasingly integrated into clinical workflows to enhance diagnostic accuracy, streamline processes, and improve patient outcomes. While these innovations promise efficiency and quality of care, they also introduce challenges: increased cognitive workload, ethical dilemmas, and uneven implementation across institutions.To identify and characterize non-remunerated technologies implemented in clinical practice within the Catalan healthcare system, focusing on their purpose, context of use, and associated risks.A scoping review was conducted following PRISMA-ScR guidelines. Searches were performed in Scopus, Web of Science, PubMed, and grey literature. Inclusion criteria targeted studies describing advanced technologies used in clinical settings without direct economic benefit for professionals. Data extraction classified technologies by type (e.g., AI diagnostic tools, electronic health records, automation systems), objectives, institutional context, and reported challenges. Findings were synthesized in a comparative matrix and validated through participatory knowledge exchange spaces (ECICs).The review identified widespread adoption of three main technologies: AI-based diagnostic systems for imaging and decision support, electronic health records integrated with predictive analytics and automation tools for administrative and clinical workflows. Reported benefits include improved efficiency and accuracy; however, concerns emerged regarding increased cognitive load, ethical dilemmas, and uneven implementation across institutions. Evidence suggests potential exacerbation of structural inequalities if integration lacks regulatory oversight.Non-remunerated technologies are transforming clinical practice, but their rapid implementation without adequate support may compromise professional well-being. Participatory strategies and institutional evaluation are essential to mitigate risks and ensure equitable adoption.The integration of advanced clinical technologies is reshaping professional roles and care delivery in Catalonia. While these tools promise efficiency and improved patient outcomes, their rapid implementation without adequate institutional support may increase cognitive workload, blur boundaries between personal and professional life, and exacerbate psychosocial stress. Moreover, adoption is not neutral: structural inequalities related to gender, age, and employment conditions may influence access and impact, creating uneven benefits and risks. Ensuring equity in technology integration is essential not only for professional well-being but also for maintaining the quality and safety of primary care services.

Artificial intelligence is increasingly used for skin-lesion image analysis. Because dermatology wait times are long, general practitioners serve as key gatekeepers for identifying skin diseases that require prompt treatment.This study aims to examine the diagnostic accuracy of AI in diagnosing skin lesions encountered in primary care and to perform a meta-analysis of AI’s in diagnostic accuracy for melanoma detection.This systematic review and meta-analysis, conducted according to the 2020 PRISMA guidelines, included diagnostic accuracy studies using any type of AI applied to photographs or dermoscopy images to diagnose skin lesions encountered in primary care settings. The reference standard was dermatologist consensus or histopathological examination. Searches were conducted in PubMed, Web of Science and Cochrane in December 2023. Risk of bias and concerns of applicability were assessed using the QUADAS-2 tool. Data extraction was conducted by two investigators and meta-analysis was performed using a bivariate random effects model.Between 2013 and 2023, 382 studies were found and 38 met the inclusion criteria.AI's accuracy was reported as non-inferior or superior to that of dermatologists in 30 studies (less acurate than dermatologists in 4 studies) . AI's accuracy was non-inferior or superior to that of GPs in 8 studies (less acurate than GPs  in 1 study). AI for the diagnosis of melanoma had a pooled sensitivity of 0.86 (95% CI: 0.80–0.90) and a specificity of 0.94 (95% CI: 0.89–0.97). The diagnostic odds ratio was 44.36 (95% CI: 29.28; 67.1), with an AUC of 0.922 for the SROC curve. Of the 38 included studies, 25 were at high risk of bias, primarily due to patient selection. Datasets were frequently not representative of the outpatient population, as malignant conditions were often overestimated.The review followed PRISMA methods, yet constraints such as limited database access, reliance on MeSH-only searches, and scarce comparable source data reduced the robustness of the meta-analysis.AI appears to perform at a similar level to dermatologists, and the same is true when comparing AI to GPs. This is especially true for serious conditions like melanoma, suggesting that AI could be a valuable tool for GPs in improving patient care.

Vertigo is a common complaint in primary care and significantly affects patients’ quality of life. Its management is challenging due to the wide range of clinical presentations and etiologies, as well as the lack of practical, primary-care–oriented diagnostic guidelines. General practitioners (GPs), often the first point of contact and coordinators of care, face difficulties in efficiently evaluating vertigo during consultations. A dedicated, accessible decision support resource may help optimize clinical assessment in this setting.To develop a free, ergonomic, open-source online decision support tool designed to guide GPs in the evaluation and management of vertigo in primary care, and to assess its usability and perceived relevance in practice.In 2023, the initial prototype was developed during a collaborative health hackathon involving physicians, developers, and engineers. The tool integrates an intuitive interface and a simple decision algorithm based on current recommendations, with expert validation. In November 2024, a nationwide acceptability study was conducted among French GPs using an online questionnaire. Usability was evaluated with the System Usability Scale (SUS). The tool is freely accessible and maintained as an open-source project to ensure transparency and equitable access. Ongoing work aims to update clinical content and the referral directory to improve patient pathways.The decision support tool created, has now been available online for more than one year. Among 78 respondents, the SUS score reached 84.01, indicating excellent usability. Participants reported that the tool was relevant, reliable, and easy to use. More than 65% expressed willingness to integrate it into routine practice, with strong interest among practitioners in rural and semi-rural areas.This innovative open-source resource aims to improve vertigo management in primary care by offering a practical, clinically grounded tool. While based on stable clinical criteria, its digital nature requires vigilance regarding potential “e-iatrogenic” effects. Further research is needed to assess long-term impacts, including on the doctor–patient relationship.The tool demonstrates strong usability and perceived usefulness. Its open-source framework and planned regular updates support accessibility, sustainability, and potential integration into everyday primary care.

Cardiovascular diseases are a major cause of mortality and morbidity. General practitioners play a key role in preventing these conditions, particularly by assessing their patients’ cardiovascular risk and implementing preventive measures. However, applying increasingly complex guidelines is a challenge in daily practice. Existing digital tools are often outdated, are not suited to the diversity of patient profiles, and do not provide the visual support needed for effective shared decision-making.To design a clinical decision support tool ("XXX") for cardiovascular risk assessment in primary care and to evaluate its usability among physicians.A web-based tool was developed, integrating ESC guidelines and specific risk scores to cover various clinical profiles. A cross-sectional study was conducted from April to July 2025 among physicians who used the website. Usability was assessed via an anonymous online questionnaire based on the standardized System Usability Scale (SUS). The primary endpoint was the SUS score, interpreted according to standardized thresholds (poor, acceptable, good, excellent). Subgroup analyses examined variations across sociodemographic and professional characteristics.The analysis included 357 physicians, 94% of whom were general practitioners. The mean SUS score was 91.9/100 (95% CI 90.9–92.9), significantly exceeding the threshold for "excellent" usability (> 85; p < 0.001). A small absolute difference was noted between genders (p = 0.049), whereas no significant differences were found according to age, professional status, or practice location.The high perceived usability suggests that XXX is well-adapted to the requirements of routine practice. Further research will be necessary to assess whether this usability translates into improved guideline adherence and shared decision-making in daily practice.XXX is a new clinical decision support tool that has demonstrated excellent perceived usability. It is a promising resource to facilitate cardiovascular risk assessment and prevention in France.