Artificial Intelligence in Outpatient Primary Care: A Scoping Review on Applications, Challenges, and Future Directions

BackgroundArtificial intelligence (AI) has the potential to revolutionize clinical decision-making and significantly improve patient outcomes in outpatient primary care. AI technologies, including machine learning, deep learning, and transformers, enhance diagnostic accuracy, risk prediction, personalized treatment, workflow efficiency, clinical documentation, and continuous patient monitoring. However, despite rapid advancements, the extent of AI implementation in outpatient primary care remains unclear. This scoping review explores how AI functions, undergoes trials or integrates into non-urgent outpatient primary care settings. MethodsThis scoping review follows PRISMA Extension for Scoping Reviews (ScR) guidelines. We searched five databases, including published and gray literature, to identify studies published between January 1, 2019, and November 22, 2024, using AI and primary care-related terms. We used Covidence, a web-based systematic review tool, to screen titles, abstracts, and full texts of English-language manuscripts. We then extracted data and categorized studies by research phase and AI application in primary care. ResultsWe screened 3,203 manuscripts and found 61 met the eligibility criteria. Most studies (26) focused on model development, while only eight reported clinical trial results. AI applications included provider support (5) and radiological disease diagnosis (1). Most studies examined clinical decision-making, disease diagnosis, and risk prediction, but none addressed provider cognitive support, workflow automation, or risk-adjusted paneling. Despite AIs potential, real-world implementation remains limited. ConclusionAI in primary care remains in the developmental stage, with minimal real-world use beyond ambient scribing, clinical decision support, and workflow automation. Researchers must collaborate with professional societies and industry partners to accelerate adoption, expand clinical trials, enhance AI education for providers and patients, facilitate model deployment, and conduct periodic assessments of real-world AI adoption trends to guide future integration.