Artificial Intelligence and Bowel Cleansing Quality (CALPER2)

Design and Validation of an Artificial Intelligence System to Detect the Quality of Colon Cleansing Before Colonoscopy

The main purpose of the study is to design and validate a convolutional neural network (CNN) with the ability to discriminate between pictures of effluents with different qualities of bowel cleansing and in a second time to prospectively assess in a cohort of patients the agreement between the result of the last rectal effluent quality assessed by the CNN and the cleansing quality assessed during the colonoscopy assessed by a validated scale (Boston Bowel Preparation Scale, BBPS). Patients will be prepared with polyethylene glycol (PEG), PEG plus ascorbic acid (PEG-Asc) or sodium picosulfate-oxide magnesium solution (PS).

Study Overview

• Status: Recruiting
• Conditions: Cleansing Quality of the Colon
• Intervention / Treatment: Drug: Bowel preparation for colonoscopy; Procedure: Colonoscopy

Detailed Description

The patient perception of the last bowel movement before the colonoscopy has been shown a powerful predictor of bowel cleansing rated during colonoscopy. A large study involving 1011 patients distributed in a derivation cohort (633 patients) and a validation cohort (378 patients) using a set of 4 pictures resembling bowel cleansing qualities showed a moderate agreement with the BBPS. In addition, a good agreement was found when the staff perception and patient perception of the last bowel movement were compared. These findings offer an excellent opportunity to test rescue cleansing interventions the same day of the examination, before colonoscopy.

Over the last two years, artificial intelligence applications have wrought a substantial breakthrough in several disciplines, including endoscopy. Machine learning and its more advanced form deep learning, refers to the development of algorithms (convolutional neural networks) with the ability to learn and perform certain tasks. In the endoscopy setting, computer vision applications have been stated as research priority field. Based on all this experience, the aim of this study was to design and to validate a convolutional neural network capable of automatically predicting the quality of the patient cleansing at home after the intake of the bowel cleansing solution and before attending the colonoscopy. The other aim was to prospectively assess in a cohort of patients the agreement between the result of the last rectal effluent quality assessed by the convolutional neural network and the cleansing quality assessed during the colonoscopy assessed by a validated scale (Boston Bowel Preparation Scale, BBPS) This study is nested in an observational prospective study conducted at the Open Access Endoscopy Unit of the Hospital Universitario de Canarias between February 2021 and May 2021 (NCT04702646). A total of 633 consecutive outpatients with a scheduled colonoscopy participated in this study (a total of 266 patients (42%) sent at least one picture). After this study, patients in whom an outpatient colonoscopy was requested, were asked to provide pictures of their effluents during bowel preparation intake. A subgroup of these images will be classified by the personal of our unit in adequate and inadequate and will be used to train the convolutional neural network. Another set of images will be used to validate the convolutional neural network. Additionally, the investigators will validate in-vivo the convolutional neural network comparing its classification of the effluent quality with a validated colon cleansing scale during the colonoscopy.

• Study Type: Observational
• Enrollment (Anticipated): 667

Contacts and Locations

• Study Contact: Name: Antonio Z Gimeno García, MD, PhD; Phone Number: +34922678554; Email: antozeben@gmail.com

Study Locations

• Spain
  • S/C De Tenerife
    • La Laguna, S/C De Tenerife, Spain, 38320
      • Recruiting
      • Department of Gastroenterology
      • Contact: Antonio Z Gimeno Garcia, MD, hD; Phone Number: 34922678039; Email: antozeben@gmail.com
      • Sub-Investigator: David Nicolas Perez, MD, PhD
      • Principal Investigator: Antonio Z Gimeno García, MD
      • Sub-Investigator: Manuel Hernandez Guerra, MD, PhD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

The researchers will offer to participate in the study to patients scheduled for a colonoscopy who meet all the inclusion criteria and none of the exclusion criteria. The researchers will explain the purpose of the study and will ask to sign the informed consent. They will give verbal and written information.

Description

Inclusion Criteria:

• Age >18, to sign the informed consent,
• Patients with indication of outpatient colonoscopy
• Patients ingesting the bowel preparation

Exclusion Criteria:

• Incomplete colonoscopy (except for poor bowel preparation)
• Contraindication for colonoscopy
• Allergies.
• Refusal to participate in the study or impairment to sign the informed consent.
• Colectomy (more than 1 segment)
• Dementia with difficulty in the intake of the preparation

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Prospective

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Consecutive patients for outpatient colonoscopy; The researchers will offer to participate in the study to patients scheduled for a colonoscopy who meet all the inclusion criteria and none of the exclusion criteria	Drug: Bowel preparation for colonoscopy; one day liquid diet will be administered to every patient included in the study and: split-dose bowel preparation with 4 Liters of Polyethylene glycol solution, 2 Liters of PEG-Ascorbic acid or 2 Liters Picosulfate.; Procedure: Colonoscopy; Colonoscopy will be performed to every patient included in the study

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Effluent characteristics	Effluent characteristics. Set of 4 pictures categorized in adequate preparation (clear liquid, clear liquid with lumps) and inadequate preparation (dark liquid, or dark liquid with solid particles). The concolutional Neural Network will be trained with effluent images and validated.	1 year
Quality of bowel cleansing assessed by the Boston Bowel Preparation Scale	Quality of bowel cleansing assessed by the Boston Bowel Preparation Scale. This scale goes from 0 (no preparation) to 3 points (excellent preparation) in the three segments of the colon (proximal, transverse and distal). The maximum score is 9 points	1 years

Collaborators and Investigators

• Sponsor: Hospital Universitario de Canarias

Publications and helpful links

General Publications

• Berzin TM, Parasa S, Wallace MB, Gross SA, Repici A, Sharma P. Position statement on priorities for artificial intelligence in GI endoscopy: a report by the ASGE Task Force. Gastrointest Endosc. 2020 Oct;92(4):951-959. doi: 10.1016/j.gie.2020.06.035. Epub 2020 Jun 19.
• Mori Y, Misawa M, Kudo SE. Challenges in artificial intelligence for polyp detection. Dig Endosc. 2022 May;34(4):870-871. doi: 10.1111/den.14279. Epub 2022 Mar 22. No abstract available.
• Fatima H, Johnson CS, Rex DK. Patients' description of rectal effluent and quality of bowel preparation at colonoscopy. Gastrointest Endosc. 2010 Jun;71(7):1244-1252.e2. doi: 10.1016/j.gie.2009.11.053. Epub 2010 Apr 1.
• Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Santamaria J, Fadhel MA, Al-Amidie M, Farhan L. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data. 2021;8(1):53. doi: 10.1186/s40537-021-00444-8. Epub 2021 Mar 31.
• Harewood GC, Wright CA, Baron TH. Assessment of patients' perceptions of bowel preparation quality at colonoscopy. Am J Gastroenterol. 2004 May;99(5):839-43. doi: 10.1111/j.1572-0241.2004.04176.x.

Study record dates

Study Major Dates

• Study Start (Actual): October 1, 2022
• Primary Completion (Anticipated): April 20, 2023
• Study Completion (Anticipated): May 30, 2023

Study Registration Dates

• First Submitted: September 19, 2022
• First Submitted That Met QC Criteria: September 19, 2022
• First Posted (Actual): September 26, 2022

Study Record Updates

• Last Update Posted (Actual): January 18, 2023
• Last Update Submitted That Met QC Criteria: January 13, 2023
• Last Verified: January 1, 2023

More Information

Terms related to this study

• Keywords: Colonoscopy; Bowel cleansing; Convolutional Neural Network
• Other Study ID Numbers: CNN bowel cleansing

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No