Evaluating Machine Learning models for predicting HIV treatment interruption: a systematic review of accuracy, validity, and applicability

Interruption in HIV treatment (IIT) remains a significant barrier to achieving global HIV/AIDS control goals. Machine learning (ML) models offer potential for predicting IIT by leveraging large clinical data. Understanding how these models were developed, validated, and applied remains essential for advancing research. We searched the PubMed, BMC, Cochrane Library, Scopus, ScienceDirect, Lancet, and Google Scholar, for studies published in English from 1990 to September 2024. Search terms covered HIV, machine learning, treatment interruption, and loss to follow-up. Articles were screened and reviewed independently, and data were extracted using the CHARMS checklist. Risk of bias was assessed with PROBAST. The PRISMA guidelines were followed throughout. Out of 116,672 records, nine studies met the inclusion criteria and reported 12 ML models. Random Forest, XGBoost, and AdaBoost were predominant models (91.7%). Internal validation was performed in all models, but only two models included external validation. Performance varied, with a mean AUC-ROC of 0.668 (SD = 0.066), indicating moderate discrimination. About 75% of models showed a high risk of bias due to inadequate handling of missing data, lack of calibration, and absence of decision curve analysis (DCA). ML models show promise for predicting IIT, particularly in resource-limited settings. Future research should prioritize external validation, robust missing data handling, decision curve analysis, and include sociocultural predictors to improve model robustness.