The Machine Learning Model for Predicting Inadequate Bowel Preparation Before Colonoscopy: A Multicenter Prospective Study.

Abstract

Introduction: Colonoscopy is a critical diagnostic tool for colorectal diseases; however, its effectiveness depends on adequate bowel preparation (BP). This study aimed to develop a machine learning predictive model based on Chinese adults for inadequate BP.

Methods: A multicenter prospective study was conducted on adult outpatients undergoing colonoscopy from January 2021 to May 2023. Data on patient characteristics, comorbidities, medication use, and BP quality were collected. Logistic regression and 4 machine learning models (support vector machines, decision trees, extreme gradient boosting, and bidirectional projection network) were used to identify risk factors and predict inadequate BP.

Results: Of 3,217 patients, 21.14% had inadequate BP. The decision trees model demonstrated the best predictive capacity with an area under the receiver operating characteristic curve of 0.80 in the validation cohort. The risk factors at the nodes included body mass index, education grade, use of simethicone, diabetes, age, history of inadequate BP, and longer interval.

Discussion: The decision trees model we created and the identified risk factors can be used to identify patients at higher risk of inadequate BP before colonoscopy, for whom more polyethylene glycol or auxiliary medication should be used.