Can Artificial Intelligence Reduce Consumption of Standard High Volume Bowel Preparation Regimen Among Older Population, Without Compromising the Quality of Colonoscopy? An International Multi-centre Randomized Controlled Trial.

NCT06904209 | Not Yet Recruiting

• 1 other identifier: 2024.590
• Study Type: interventional
• Target: 1,824
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this study is to assess the clinical and cost-effectiveness of the AI bowel preparation evaluation system in reducing the consumption volume of the standard high-volume PEG regimen before colonoscopy among the older population. Researchers will compare bowel preparation adequacy and other colonoscopy quality matrices, and patient satisfaction between patients using the AI system and those using Standard Practice.

Conditions

Bowel Preparation Quality

Keywords

PEG; bowel preparation; colonoscopy

Outcome Measures

Primary Outcomes (1)

• Volume of PEG consumed

  The primary outcome of this study is the volume of PEG consumed before colonoscopy between the AI and SP groups.

  Baseline (before colonoscopy procedure)

Secondary Outcomes (8)

• BBPS score

  during colonoscopy

• Bowel preparation adequacy rate

  during colonoscopy

• Caecal intubation rate

  during colonoscopy

• Adenoma detection rate

  during colonoscopy

• Mean adenoma per colonoscopy

  during colonoscopy

Study Arms (2)

Standard practice group (SP group)

NO INTERVENTION

All patients undergoing outpatient colonoscopy will follow the standard bowel preparation regimen, which includes low residue diet three days prior colonoscopy, and high-volume (3 L) PEG (Klean-Prep, Helsinn Birex Pharmaceuticals, Ireland) in split-dose using a tailored measuring cup (Figure 2). Patients will be asked to consume 1 L in the evening before colonoscopy and 2 L in the morning of colonoscopy. To achieve the best bowel-cleansing effect, patients will be instructed to consume 2 L of PEG 3-6 hours before their colonoscopy9,27. Patients will be instructed to consume the purgative at a rate of 250 ml every 15 minutes14 and document the amount consumed.

AI bowel preparation (AI group)

EXPERIMENTAL

Patients who were randomized to the AI bowel preparation evaluation group will follow the same standard practice with the addition of an online AI bowel preparation evaluation system via a QR code. They will be instructed to take photos of their rectal effluent each time they use the toilet during the consumption of the split dose of 2 L PEG on the day of colonoscopy.

Device: AI

Interventions

AI DEVICE

Each photo will be uploaded and analyzed by AI to predict the adequacy of their bowel preparation with immediate results of "pass" or "not pass," indicating if their bowel preparation is adequate or inadequate. If the result is "pass," patients will stop consuming the remaining PEG solution. If the result is "not pass," patients will be advised to gently rub their lower abdomen in a clockwise direction or walk around and continue consuming the remaining PEG until the AI evaluation gives a "pass" result or until the full dose of 3 L PEG have been consumed. If the patient's rectal effluent deems IBP after consumption of the full dose of 3 L of PEG, an additional 1 L or more of PEG will be administered as a remedial dose at the discretion of the physician-in-charge.

AI bowel preparation (AI group)

Eligibility Criteria

• Age: 65 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Older Adult (65+)

You may qualify if:

• individual aged 65 years or above
• undergoing colonoscopy for any indication
• requiring a standard high-volume PEG regimen for bowel preparation
• having a smartphone themselves or their caregivers (including ward nurses) having one will be recruited.

You may not qualify if:

• allergy to PEG,
• suspected or diagnosed gastrointestinal obstruction or perforation,
• suspected or diagnosed ileus
• suspected or diagnosed gastric retention
• suspected or diagnosed toxic colitis, toxic megacolon,
• prior gastrointestinal surgery, and
• unable to provide informed consent.

Sponsors & Collaborators

• Chinese University of Hong Kong: lead

Study Sites (1)

Centre of Digestive Health

Hong Kong, Hong Kong

Location

Central Study Contacts

Felix Sia

CONTACT

852-26370428; felixsia@cuhk.edu.hk

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: PARTICIPANT
• Purpose: SUPPORTIVE CARE
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Assistant professor

Study Record Dates

• First Submitted: March 25, 2025
• First Posted: April 1, 2025
• Study Start (Estimated): June 1, 2026
• Primary Completion (Estimated): January 31, 2028
• Study Completion (Estimated): June 30, 2028
• Last Updated: April 1, 2025

Record last verified: 2025-03

Data Sharing

• IPD Sharing: Will not share

Locations

HK (1)