RESUMO
INTRODUCTION: Pharmacologic therapies for symptoms of gastroparesis have limited efficacy and it is difficult to predict which patients will respond. In this study, we implemented a machine-learning model to predict the response to prokinetics and/or neuromodulators in patients with gastroparesis-like symptoms. METHODS: Subjects with suspected gastroparesis underwent simultaneous gastric emptying scintigraphy (GES) and wireless motility capsule (WMC) and were followed for 6 months. Subjects were included if they were started on neuromodulators and/or prokinetics. Subjects were considered responders if their Gastroparesis Cardinal Symptom Index (GCSI) at 6 months decreased by ≥1 from baseline. A machine-learning model was trained using lasso regression, ridge regression or random forest. Five-fold cross-validation was used to train the models and the area under the receiver operator characteristic curve (AUC-ROC) was calculated using the test set. RESULTS: Of the 150 patients enrolled, 123 patients received either a prokinetic and/or a neuromodulator. Of the 123, 45 were considered responders and 78 were non-responders. A ridge regression model with the variables: BMI, Infectious prodrome, delayed GES, no diabetes (BIDnD), had the highest AUC-ROC of 0.72. The model performed well for subjects on prokinetics without neuromodulators (AUC-ROC of 0.83) but poorly for those on neuromodulators without prokinetics. A separate model with GET, duodenal MI, no diabetes, and functional dyspepsia performed better (AUC-ROC of 0.75). DISCUSSION: This machine learning model has an acceptable accuracy in predicting those who will respond to neuromodulators and/or prokinetics. If validated, our model provides valuable data in predicting treatment outcomes in patients with gastroparesis-like symptoms.
