Artificial intelligence for HIV care: a global systematic review of current studies and emerging trends
Künstliche Intelligenz in der HIV-Versorgung: globale systematische Übersicht aktueller Studien und neuer Trends
Journal of the International AIDS Society · 2025-10 · 28 (10)
DOI: 10.1002/jia2.70045 ↗Auf einen Blick
Die Übersichtsarbeit fasst 47 Studien zu KI/ML in der HIV-Versorgung zusammen. Genannt werden Verbesserungen bei Diagnostik, Behandlungsmonitoring, Versorgungstreue und Unterstützung durch Chatbots.
Fragestellung
Welche Anwendungen von KI-Methoden entlang des HIV-Versorgungspfads wurden untersucht und welche Ergebnisse wurden berichtet?
Methode
Systematische Übersicht nach PRISMA; Suche in PubMed, ProQuest Central, Scopus und Web of Science zu Studien von 2014 bis 2024; 3185 Treffer gescreent, 47 Studien eingeschlossen.
Ergebnisse
47 Studien zu HIV-Tests, Verbleib in Versorgung und virologischem Ansprechen, klinischen/immunologischen Outcomes sowie Test- und Behandlungsunterstützung. ML erreichte bis 100 % Sensitivität und 98,8 % Spezifität; AUC bis 0,76.
Einschränkungen
Datenqualität, Infrastrukturgrenzen und ethische Aspekte wurden als Herausforderungen genannt.
Schlussfolgerung der Autor:innen
KI hat laut Autor:innen großes Potenzial, Lücken in der HIV-Versorgung zu schließen und Diagnostik, Adhärenz sowie Retention in care zu verbessern. Genannt werden weiterhin Probleme bei Datenqualität und Systemintegration.
Kernaussagen
- 47 eingeschlossene Studien zu KI in der HIV-Versorgung
- ML in HIV-Selbsttests: bis 100 % Sensitivität und 98,8 % Spezifität
- Herausforderungen: Datenqualität, Infrastruktur und Ethik
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift Journal of the International AIDS Society, online erschienen am 24.09.2025. Verfasst von Sanele Ngcobo und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Family Medicine, University of Pretoria, Pretoria, South Africa. Hauptthemen laut MEDLINE: Artificial Intelligence, HIV Infections. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Family Medicine, University of Pretoria, Pretoria, South Africa.
- Department of Mathematics and Applied Mathematics, University of Cape Town, Cape Town, South Africa.
- INRS, Montreal, Quebec, Canada.
- NITheCS, Stellenbosch, South Africa.
- Library, University of Pretoria, Pretoria, South Africa.
- Department of Immunology, University of Pretoria, Pretoria, South Africa.
ORCID-Profile: Sanele Ngcobo, Edith Madela Mntla, Jonathan Shock, Murray Louw, Linda Mbonambi, Thato Serite, Theresa Rossouw
Zitieren
APA
Ngcobo, S., Mntla, E. M., Shock, J., Louw, M., Mbonambi, L., Serite, T., & Rossouw, T. (2025). Artificial intelligence for HIV care: a global systematic review of current studies and emerging trends. Journal of the International AIDS Society, 28(10). https://doi.org/10.1002/jia2.70045
Vancouver
Ngcobo S, Mntla EM, Shock J, Louw M, Mbonambi L, Serite T, et al. Artificial intelligence for HIV care: a global systematic review of current studies and emerging trends. Journal of the International AIDS Society. 2025;28(10). doi:10.1002/jia2.70045
BibTeX
@article{Ngcobo2025,
author = {Ngcobo, Sanele and Mntla, Edith Madela and Shock, Jonathan and Louw, Murray and Mbonambi, Linda and Serite, Thato and Rossouw, Theresa},
title = {Artificial intelligence for HIV care: a global systematic review of current studies and emerging trends},
journal = {Journal of the International AIDS Society},
year = {2025},
volume = {28},
number = {10},
doi = {10.1002/jia2.70045}
}
EUVIMED