Artificial intelligence for HIV care: a global systematic review of current studies and emerging trends
Bibliographic record
Abstract
INTRODUCTION: Artificial intelligence (AI) and, in particular, machine learning (ML) have emerged as transformative tools in HIV care, driving advancements in diagnostics, treatment monitoring and patient management. The present review aimed to systematically identify, map and synthesize studies on the use of AI methods across the HIV care continuum, including applications in HIV testing and linkage to care, treatment monitoring, retention in care, and management of clinical and immunological outcomes. METHODS: A comprehensive literature search was conducted across databases, including PubMed and ProQuest Central, Scopus and Web of Science, covering studies published between 2014 and 2024. The review followed PRISMA guidelines, screening 3185 records, of which 47 studies were included in the final analysis. RESULTS: Forty-seven studies were grouped into four thematic areas: (1) HIV testing, AI models improved diagnostic accuracy, with ML achieving up to 100% sensitivity and 98.8% specificity in self-testing and outperforming human interpretation of rapid tests; (2) Retention in care and virological response, ML predicted clinic attendance, viral suppression and virological failure (72-97% accuracy; area under the curve up to 0.76), enabling early identification of high-risk patients; (3) Clinical and immunological outcomes, AI predicted disease progression, immune recovery, comorbidities and HIV complications, achieving up to 97% CD4 status accuracy and outperforming clinicians in tuberculosis diagnosis; (4) Testing and treatment support, AI chatbots improved self-testing uptake, linkage to care and adherence support. Methods included random forests, neural networks, support vector machines, deep learning and many others. DISCUSSION: AI has the potential to transform HIV care by improving early diagnosis, treatment adherence and retention in care. However, challenges such as data quality, infrastructure limitations and ethical considerations must be addressed to ensure successful implementation. CONCLUSIONS: AI has demonstrated immense potential to address gaps in HIV care, improving diagnostic accuracy, enhancing retention strategies and supporting effective treatment monitoring. These advancements contribute towards achieving the UNAIDS 95-95-95 targets. However, challenges such as data quality and integration into healthcare systems remain. Future research should prioritize scalable AI solutions tailored to high-burden, resource-limited settings to maximize their impact on global HIV care. PROSPERO NUMBER: PROSPERO 2024 CRD42024517798 Available from: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42024517798.
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 | 0.013 | 0.040 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.005 |
| Bibliometrics | 0.016 | 0.017 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 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 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".