Risk factors for inadequate bowel preparation before colonoscopy: a retrospective cohort study

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

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.

High volume, low volume, or pills, which way should we go? a review of bowel preparation for colonoscopy

PURPOSE OF REVIEW

Colorectal cancer (CRC) is the second leading cause of adult cancer-related deaths in the United States. Colonoscopy is the gold standard for CRC screening. Adequate bowel preparation prior to colonoscopy is essential for good visualization, which results in higher polyp detection rates and shorter procedural times. Achieving adequate preparation prior to colonoscopy is accomplished approximately 75% of the time. This review covers current recommendations and recent updates in bowel preparation for colonoscopy.

RECENT FINDINGS

Split-dose bowel preparation is recommended, but recent studies show that same day, low-volume preparations are noninferior. Low-volume polyethylene glycol with electrolytes + ascorbic acid can achieve high-quality bowel preparation and 1-day, low-residue diets prior to colonoscopy, particularly prepackaged low-residue diets, can lead to better outcomes. Utilizing visual aids and artificial intelligence in the form of smartphone applications and quality prediction systems can also lead to higher rates of bowel preparation adequacy.

SUMMARY

An individualized approach should be used to decide on the best preparation option for patients. Lower volume, same day preparations are available and lead to better patient tolerability and compliance, along with less stringent precolonoscopy diets. Smartphone applications and artificial intelligence will allow us to better educate and guide patients with regards to following preparation instructions.