Validation of artificial intelligence–based bowel preparation assessment in screening colonoscopy (with video)

Apr 18, 2024Gastrointestinal endoscopy

Using artificial intelligence to check bowel cleanliness during colonoscopy screening

AI simplified

GLP-1 Therapies on OpenScience ↗PubMed ↗DOI ↗

Abstract

In a study of 393 patients, 27 adenomas greater than 5 mm were missed due to inadequate bowel preparation.

Patients with inadequate bowel preparation identified by AI had a miss rate for >5 mm adenomas of 35.71%.
Qualified-AI patients demonstrated a significantly lower adenoma miss rate of 13.19% (P = .0056).
The adenoma miss rate was 50.89% in unqualified-AI patients compared to 20.79% in qualified-AI patients (P < .001).
The polyp miss rate for >5 mm polyps was higher in unqualified-AI patients at 35.82%, compared to 19.48% in qualified-AI patients (P = .0152).
These findings support the potential role of AI in enhancing bowel preparation assessments and guiding re-cleansing before colonoscopy.

AI simplified

BACKGROUND AND AIMS: Accurate bowel preparation assessment is essential for determining colonoscopy screening intervals. Patients with suboptimal bowel preparation are at a high risk of missing >5 mm adenomas and should undergo an early repeat colonoscopy. In this study, we used artificial intelligence (AI) to evaluate bowel preparation and validated the ability of the system to accurately identify patients who are at high risk of having >5 mm adenomas missed due to inadequate bowel preparation.

METHODS: This prospective, single-center, observational study was conducted at the Eighth Affiliated Hospital, Sun Yat-sen University, from October 8, 2021, to November 9, 2022. Eligible patients who underwent screening colonoscopy were consecutively enrolled. The AI assessed bowel preparation using the e-Boston Bowel Preparation Scale (e-BBPS) while endoscopists made evaluations using BBPS. If both BBPS and e-BBPS deemed preparation adequate, the patient immediately underwent a second colonoscopy; otherwise, the patient underwent bowel re-cleansing before the second colonoscopy.

RESULTS: Among the 393 patients, 72 adenomas >5 mm in size were detected; 27 adenomas >5 mm in size were missed. In unqualified-AI patients, the >5 mm adenoma miss rate (AMR) was significantly higher than in qualified-AI patients (35.71% vs 13.19% [P = .0056]; odds ratio [OR], .2734 [95% CI, .1139-.6565]), as were the AMR (50.89% vs 20.79% [P < .001]; OR, .2532 [95% CI, .1583-.4052]) and >5 mm polyp miss rate (35.82% vs 19.48% [P = .0152]; OR, .4335 [95% CI, .2288-.8213]).

CONCLUSIONS: This study confirmed that patients classified as inadequate by AI exhibited an unacceptable >5 mm AMR, providing key evidence for implementing AI in guiding bowel re-cleansing and potentially standardizing future colonoscopy screening. (Clinical trial registration number: NCT05145712.).

Full Text

Full text is available at the source.

View full text (XML) ↗View full text ↗

Validation of artificial intelligence–based bowel preparation assessment in screening colonoscopy (with video)

Abstract

Full Text

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the glp-1 therapies brief

Abstract

Full Text

Related papers

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the glp-1 therapies brief