Supervised Machine Learning for Predicting Carbohydrate Malabsorptions Using Hydrogen Breath Tests

Abstract Introduction: Carbohydrate malabsorptions symptoms include intestinal fluid retention, causing diarrhea and abdominal distention. The aim of this work is to create a machine learning model that predicts carbohydrate malabsorption using H 2 measurements from lactose fructose tolerance tests. Methods: We compare the predictive ability popular classifiers with are specifically designed for time series data. Our approach was implemented sklearn sktime Python libraries. Results: highest dataset achieved Random Forest Classifier (balanced accuracy = 0.91). In contrast, 0.81) obtained an IndividualTDE classifier. Conclusion: results indicate high distinguishing between malabsorptions. However, detection SIBO challenging but adapted classifier models could reach higher performances compared standard methods. establish basis expert system diagnosing SIBO, respectively.