Schulman, Michael I.

ABSTRACTIntroductionStudies demonstrate an overlap of constipation with gastroparesis and functional dyspepsia, but the impact of treatments that target constipation on improving upper gastrointestinal (UGI) symptoms is unexplored. We quantified the effects of constipation medication therapies on UGI and constipation symptom severity in subjects presenting with symptoms of gastroparesis.MethodsFifty‐six subjects with symptoms of gastroparesis underwent concurrent wireless motility capsule and gastric emptying scintigraphy and were recommended to receive either a new medication therapy for constipation or a change in constipation therapy based on investigator interpretation of test results. Gastroparesis Cardinal Symptom Index (GCSI), upper abdominal pain, and constipation scores were compared between baseline and 6 months. Data were compared between delayed or non‐delayed gastric emptying and the presence or absence of slow colonic transit.Key ResultsSubjects with slow colonic transit had improvements in GCSI (p = 0.007) and constipation scores (p = 0.004) after treatment with a new or changed constipation medication, with the delayed emptying subgroup driving GCSI improvements (p = 0.004). Reductions in nausea/vomiting (p = 0.02) and early satiety/fullness subscores (p = 0.002) with trends to improved bloating/distention subscores (p = 0.06) were observed in this subgroup, but upper abdominal pain was unchanged. Subjects with normal colonic transit showed no improvement in GCSI scores regardless of gastric emptying status (p > 0.05).Conclusions and InferencesIdentifying and treating delayed colonic transit in gastroparetic (delayed gastric emptying) subjects improves global UGI symptoms as well as selected individual symptoms. Evaluation of whole gut motility as well as recognizing and managing extragastric delay may promote improved outcomes in these patients.Trial RegistrationClinicalTrials.gov: NCT02022826

INTRODUCTION: Pharmacologic therapies for symptoms of gastroparesis (GP) 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 GP-like symptoms. METHODS: Subjects with suspected GP underwent simultaneous gastric emptying scintigraphy (GES) and wireless motility capsule and were followed for 6 months. Subjects were included if they were started on neuromodulators and/or prokinetics. Subjects were considered responders if their GP Cardinal Symptom Index 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 nonresponders. A ridge regression model with the variables, such as body mass index, infectious prodrome, delayed gastric emptying scintigraphy, no diabetes, 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 gastric emptying time, duodenal motility index, 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 GP-like symptoms.