Limited Predictability of Client Attendance in a Support Program for HIV Vertical Transmission Prevention: A Comparison of Machine Learning and Community Health Worker Predictions
ACM Journal on Computing and Sustainable Societies · 30.09.2026 · 4 (3) · 1-18
DOI: 10.1145/3820498 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Journal on Computing and Sustainable Societies, online erschienen am 15.07.2026. Verfasst von Matthew Olckers und 3 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Client attendance is vital for the success of HIV vertical transmission prevention programs, yet 23.4% of clients missed follow-up appointments after enrolling in a community health worker-led program (n=24,807, August–December 2022). Predicting which clients are most likely to miss appointments could enable targeted interventions to improve retention. While machine learning appears well-suited for this prediction task, its effectiveness compared to community health worker judgment remains unexplored. We evaluated three machine learning approaches—logistic regression, balanced random forest, and gradient-boosted trees—trained on client enrollment records (n=51,297 training; n=18,577 test) and compared their performance to predictions by community health workers (n=61), who possess direct client interactions and contextual insights. Machine learning models achieved modest predictive performance, with the balanced random forest showing the best performance (ROC AUC=0.689). Community health worker predictions showed no evidence of strong predictive performance in the matched sample, although the analysis cannot rule out modest predictive ability. Qualitative insights identified complex and dynamic barriers, including stigma, transportation difficulties, and competing personal commitments, often unpredictable at enrollment. These findings highlight limitations in predicting client attendance from enrollment-period information alone. Instead, resources might be better allocated to addressing systemic barriers identified by community health workers.
Zitieren
APA
Olckers, M., Lam, A., Makhupula, L., & Mvubu, M. (2026). Limited Predictability of Client Attendance in a Support Program for HIV Vertical Transmission Prevention: A Comparison of Machine Learning and Community Health Worker Predictions. ACM Journal on Computing and Sustainable Societies, 4(3), 1-18. https://doi.org/10.1145/3820498
Vancouver
Olckers M, Lam A, Makhupula L, Mvubu M. Limited Predictability of Client Attendance in a Support Program for HIV Vertical Transmission Prevention: A Comparison of Machine Learning and Community Health Worker Predictions. ACM Journal on Computing and Sustainable Societies. 2026;4(3):1-18. doi:10.1145/3820498
BibTeX
@article{Olckers2026,
author = {Olckers, Matthew and Lam, Alexander and Makhupula, Lazola and Mvubu, Mhlasakululeka},
title = {Limited Predictability of Client Attendance in a Support Program for HIV Vertical Transmission Prevention: A Comparison of Machine Learning and Community Health Worker Predictions},
journal = {ACM Journal on Computing and Sustainable Societies},
year = {2026},
volume = {4},
number = {3},
pages = {1--18},
doi = {10.1145/3820498}
}
EUVIMED