A Machine Learning Approach to Predict Weight Change in ART-Experienced People Living With HIV.

Introduction: The objective of the study was to develop machine learning (ML) models that predict the percentage weight change in each interval of time in antiretroviral therapy-experienced people living with HIV.
Methods: This was an observational study that comprised consecutive people living with HIV attending Modena HIV Metabolic Clinic with at least 2 visits. Data were partitioned in an 80/20 training/test set to generate 10 progressively parsimonious predictive ML models. Weight gain was defined as any weight change >5%, at the next visit. SHapley Additive exPlanations values were used to quantify the positive or negative impact of any single variable included in each model on the predicted weight changes.
Results: A total of 3,321 patients generated 18,322 observations. At the last observation, the median age was 50 years and 69% patients were male. Model 1 (the only 1 including body composition assessed with dual-energy x-ray absorptiometry) had an accuracy greater than 90%. This model could predict weight at the next visit with an error of <5%.
Conclusions: ML models with the inclusion of body composition and metabolic and endocrinological variables had an excellent performance. The parsimonious models available in standard clinical evaluation are insufficient to obtain reliable prediction, but are good enough to predict who will not experience weight gain.
Competing Interests: G.G. and C.M. received research grant and speaker honorarium from Gilead, ViiV, MERCK, and Jansen. G.G. and C.M. attended advisory boards of Gilead, ViiV, and MERCK. Other authors reported no conflict of interest.
(Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.)