Machine Learning and Artificial Intelligence in Health Services and Policy Research literature for Primary Health Care: A Scoping Review protocol
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.095 | 0.103 |
| Meta-epidemiology (narrow) | 0.004 | 0.004 |
| Meta-epidemiology (broad) | 0.011 | 0.012 |
| Bibliometrics | 0.033 | 0.025 |
| Science and technology studies | 0.005 | 0.005 |
| Scholarly communication | 0.009 | 0.011 |
| Open science | 0.006 | 0.009 |
| Research integrity | 0.009 | 0.006 |
| Insufficient payload (model declined to judge) | 0.075 | 0.015 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".