Machine learning prediction of weight gain after antiretroviral therapy initiation in people with HIV: Insights from a large french real-world cohort

TL;DR

This study explores whether machine learning can predict weight gain in HIV patients starting antiretroviral therapy, but finds it lacks precision for clinical use.

Contribution

The study evaluates machine learning's ability to predict weight changes in HIV patients using a large real-world cohort, revealing its limitations.

Findings

Machine learning models achieved RMSEs of 4.6 kg, 5.3 kg, and 6.4 kg at 6, 12, and 24 months post-ART initiation.

Baseline weight was the strongest predictor, with other factors contributing minimally to weight prediction.

Excluding individuals with extreme weight changes slightly improved model accuracy but did not make predictions clinically useful.

Abstract

Excessive weight gain after initiation of antiretroviral therapy (ART) has become a recognized concern among people living with HIV. Individual weight trajectories remain highly heterogeneous and challenging to predict using conventional methods. We leveraged the French Dat’AIDS national cohort to assess whether machine learning (ML) could enhance the prediction of individual body weight at 6, 12, and 24 months after ART initiation. Using 112 baseline variables encompassing demographic, clinical, laboratory, and treatment-related data, we trained XGBoost models and evaluated performance using root mean square error (RMSE), R², and mean prediction error. A simple benchmark model based on baseline weight was used for comparison. Among 24,014 eligible ART-naïve adults, the ML models achieved RMSEs of approximately 4.6 kg, 5.3 kg, and 6.4 kg at 6, 12, and 24 months respectively, with declining predictive power over time. Baseline weight (Weight_M0) consistently emerged as the strongest predictor, while other factors contributed minimally. Although ML marginally outperformed the benchmark (Weight_M0), accuracy remained insufficient for clinical decision-making. Sensitivity analyses excluding individuals with implausibly large monthly weight changes modestly improved RMSE (3.9–6.0 kg), underscoring the impact of data quality. Our results demonstrate that, despite large sample size and rich clinical variables, ML lacks the precision necessary for individual weight forecasting in this context. These findings highlight the limitations of applying artificial intelligence to heterogeneous real-world cohorts and underscore the need to incorporate behavioral and lifestyle factors to improve predictive modeling.

Figures