Barriers and Facilitators to the Implementation of Artificial Intelligence Enabled Diabetes Interventions in Lower-Middle-Income Countries: A Systematic Review Protocol
Bibliographic record
Abstract
Abstract Background Diabetes represents an emerging global health crisis, with lower-middle-income countries experiencing a fast growth in prevalence. Diabetes care in these regions often faces significant challenges, including inadequate healthcare infrastructure, limited financial resources, a shortage of trained healthcare personnel, and a dual burden of communicable and non-communicable diseases. Artificial intelligence (AI) offers tailored and scalable solutions for addressing these systemic barriers by enabling early diagnosis and risk prediction, integrating diabetes care delivery across all levels of healthcare. However, the successful implementation of AI interventions requires an understanding of the unique infrastructural, technological, socio-political, and cultural factors influencing diabetes care in these regions. Objective This protocol outlines a systematic review to synthesize evidence on the barriers and facilitators to implementing AI-enabled diabetes interventions in lower-middle-income countries, and to examine the specific AI applications being deployed in these settings. Methods A comprehensive literature search will be performed across five databases: Medline, Web of Science, CINAHL, IEEE Xplore, and ACM Digital Library, encompassing peer-reviewed publications from 2015 to 2025. The review will include studies which assess AI-enabled interventions implemented in healthcare settings for diabetes prevention, diagnosis, and management in lower-middle-income countries. Studies that assess the efficacy of artificial intelligence tools without direct evaluation of these tools in clinical decision-making or patient care processes will be excluded. Two independent reviewers will assess studies for inclusion using a predefined search strategy. The reporting of results will adhere to the PRISMA 2020 checklist (1). The risk of bias in individual studies will be evaluated using Hawker’s tool for disparate study designs. Conclusion The findings of this systematic review will identify key considerations for implementing AI technologies in diabetes care and provide evidence to support policymakers, healthcare providers, and technology developers in designing context-appropriate interventions that improve care delivery and health outcomes in lower-middle-income countries.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.003 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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 teacher head, 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".