Application of Machine Learning Techniques to the Prediction of Onset and Persistence of Binge Eating: A Prospective Study

ABSTRACTObjectiveMachine learning (ML) techniques have shown promise for enhancing prediction of clinical outcomes; however, its application to predicting binge eating has been scarcely explored. We applied ML techniques to predict binge eating onset (vs. continued absence) and persistence (vs. remission) over time.MethodData were used from a larger prospective study of 1106 participants who were assessed on a range of putative risk, maintaining, and protective factors at baseline and 8 months follow‐up. Nine ML models for classification were developed and compared against a generalised linear model (GLM) for predicting onset (n = 334) and persistence (n = 623) outcomes using 39 self‐reported baseline variables as predictors.ResultsAll models performed poorly at predicting onset (AUC = 0.49–0.61) and persistence (AUC = 0.50–0.59) outcomes, with ML models demonstrating comparable performance to the GLM.ConclusionWe suspect that poor ML performance may have been a result of the limited set of self‐reported baseline predictors used to generate prediction models. Improved predictive accuracy and optimisation of ML models in future research may require consideration of a larger, more disparate set of predictors that also incorporate various data types, such as neuroimaging, physiological, or smartphone sensor data.