Machine Learning and Artificial Intelligence in Health Services and Policy Research literature for Primary Health Care: A Scoping Review protocol
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Objective
Artificial intelligence (AI) and machine learning (ML) are widely used in healthcare, primarily for clinical tasks like diagnostics and decision support. However, their role in organization- and system-level processes, such as resource allocation and workforce planning, remains underexplored. This scoping review aims to review AI and ML applications at the meso- and macro-levels of primary health care (PHC) systems reported in Health Services and Policy Research literature, assessing their strengths, limitations, and gaps to guide future research.
Methods
This scoping review will follow Arksey and O’Malley’s five-stage framework and PRISMA-ScR guidelines. A comprehensive literature search will be conducted in Medline, CINAHL, Embase, Cochrane Library, PsycINFO, and IEEE Xplore, as well as grey literature from OpenGrey, Google Scholar, and ProQuest. The search will cover January 2010 to December 2024, with a final search update in 2025 prior to manuscript submission to ensure inclusion of the most current evidence. Two independent reviewers will screen titles, abstracts, and full texts, resolving discrepancies by consensus. Eligible studies will include primary research describing, evaluating, implementing, or developing AI and ML applications at the meso-level (e.g., organizational monitoring and evaluation) and macro-level (e.g., system-wide funding and workforce/resource allocation) in PHC. Studies on micro-level applications, non-implemented research, and secondary literature will be excluded. Data will be extracted using a protocol and synthesized based on meso- and macro-level PHC dimensions, adapted from WHO’s operational and measurement frameworks. The protocol has been registered in Open Science Framework (OSF) (osf.io/wzj5x).
Conclusions
This review will synthesize AI and ML applications in organizational and structural dimensions of PHC, highlighting understudied areas and informing future research and policy. The findings will provide insights into AI and ML’s strengths and limitations in supporting critical PHC elements, such as governance, resource allocation and workforce planning.
