Leveraging OGTT derived metabolic features to detect Binge-eating disorder in individuals with high weight: a “seek out” machine learning approach
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Binge eating disorder (BED) carries a 6 times higher risk for obesity and accounts for roughly 30% of type 2 diabetes cases. Timely identification of early glycemic disturbances and comprehensive treatment can impact on the likelihood of associated metabolic complications and the overall outcome. Machine learning (ML) techniques were trained with static and dynamic glucose-derived measures to detect BED among 281 individuals with high weight. The pipeline (training, validation, testing) was conducted twice, on two different datasets (2 hours, and 5 hours-long glucose load). After features selection, multiple ML algorithms were trained to classify the sample. The best classifier was then applied to an independent cohort (N = 21). A sensitivity-based analysis was run to investigate the relevance of each feature in the classification. 14 features were selected as relevant, with the support vector machine showing the best performance in classifying BED in both models. The model on the 5 hours-long OGTT exhibited the best metrics (sensitivity = 0.75, specificity = 0.67, F score = 0.71) diagnosing BED in 7 out of 10 cases. Sex, HOMA-IR, HbA1c and plasma glucose in different times, and hypoglycemia events were the most sensitive features for BED diagnosis. This study is the first to use metabolic hallmarks to train ML algorithms for detecting BED in individuals at high risk for metabolic complications. ML techniques applied to objective and reliable glycemic features might prompt the identification of BED among individuals at high risk for metabolic complications, enabling timely and tailored multidisciplinary treatment.