Historical visit attendance as predictor of treatment interruption in South African HIV patients

Extension of a validated machine learning model

Bibliographic Data

ID19594683
AuthorsRachel T Esra (0000-0002-7668-1792, University of Geneva, corresponding author), Jacques Carstens (0000-0003-1119-8182, corresponding author), Janne Estill (0000-0001-9544-1447, University of Geneva, corresponding author), Ricky Stoch (0000-0001-6073-1815, corresponding author), Sue Le Roux (Aurum Institute, corresponding author), Tonderai Mabuto (0000-0002-5784-746X, Aurum Institute, corresponding author), Michael Eisenstein (Aurum Institute, corresponding author), Olivia Keiser (0000-0001-8191-2789, University of Geneva, corresponding author), Mhairi Maskew (0000-0003-4238-0200, University of the Witwatersrand, corresponding author), Matthew P Fox (0000-0002-5132-7818, Boston University, corresponding author), Lucien De Voux (corresponding author), Kieran Sharpey-Schafer (corresponding author)
EditorsHannah Hogan Leslie
Year2023
Volume3
Issue7
Pagese0002105
Publication date2023-07-19
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenuePLOS Global Public Health (JOURNAL)
Journal identifiersISSN: 2767-3375 • E-ISSN: 2767-3375
PublisherPublic Library of Science (PLoS) (PUBLISHER)
DOI10.1371/journal.pgph.0002105
PMID37467217
OpenAlexW4384819097
LanguageEN
Citations received3
References cited24

Retention of antiretroviral (ART) patients is a priority for achieving HIV epidemic control in South Africa. While machine-learning methods are being increasingly utilised to identify high risk populations for suboptimal HIV service utilisation, they are limited in terms of explaining relationships between predictors. To further understand these relationships, we implemented machine learning methods optimised for predictive power and traditional statistical methods. We used routinely collected electronic medical record (EMR) data to evaluate longitudinal predictors of lost-to-follow up (LTFU) and temporal interruptions in treatment (IIT) in the first two years of treatment for ART patients in the Gauteng and North West provinces of South Africa. Of the 191,162 ART patients and 1,833,248 visits analysed, 49% experienced at least one IIT and 85% of those returned for a subsequent clinical visit. Patients iteratively transition in and out of treatment indicating that ART retention in South Africa is likely underestimated. Historical visit attendance is shown to be predictive of IIT using machine learning, log binomial regression and survival analyses. Using a previously developed categorical boosting (CatBoost) algorithm, we demonstrate that historical visit attendance alone is able to predict almost half of next missed visits. With the addition of baseline demographic and clinical features, this model is able to predict up to 60% of next missed ART visits with a sensitivity of 61.9% (95% CI: 61.5–62.3%), specificity of 66.5% (95% CI: 66.4–66.7%), and positive predictive value of 19.7% (95% CI: 19.5–19.9%). While the full usage of this model is relevant for settings where infrastructure exists to extract EMR data and run computations in real-time, historical visits attendance alone can be used to identify those at risk of disengaging from HIV care in the absence of other behavioural or observable risk factors

Attendance · Categorical variable · Machine learning · Predictive power · Computer Science · Demography · HIV, Drug Use, Sexual Risk · HIV/AIDS Research and Interventions · Medicine · Artificial Intelligence