Artificial Intelligence, Colonoscopy, Real-time Feedback
Conditions
Keywords
Colonoscopy, Intubation, Real-time feedback, Red-out
Brief summary
This study will employ a prospective, multicenter, controlled design. It will be conducted across multiple centers, with participated centers randomly assigned to one of four groups: Group A, Group B, Group C, and Group D. The research will primarily focus on the AI-based analysis of colonoscopic images to calculate the following metrics: caecal intubation time, red-out percentage, and the AI-based red-out avoiding score. Based on the study's implementation protocol, a decision will be made regarding whether to provide real-time feedback. Additionally, the presence of any complications will be assessed both during and after the colonoscopy procedure.
Interventions
OTHERAI system
AI-system Performance Feedback in group B, group C, and group D.
Sponsors
The First Affiliated Hospital of Anhui Medical University
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
PREVENTION
Masking
NONE
Eligibility
Sex/Gender
ALL
Age
18 Years to 70 Years
Healthy volunteers
No
Inclusion criteria
1. Study Participants (Patients): Aged 18 to 70 years, any gender. Individuals scheduled to undergo diagnostic or screening colonoscopy at the investigational site. 2. Colonoscopists: Expert-level colonoscopists (having performed a total of \>1000 colonoscopy procedures). Right-handed.
Exclusion criteria
1. Study Participants (Patients): Individuals undergoing the following procedures: cases with a history of colorectal surgery; cases with a history of chemotherapy, raditherapy; cases with a history of abdominal, and/or pelvic surgery; cases with a history of difficult colonoscopies; cases with colorectal tumours and obstructive lesions; cases with colorectal diverticula; cases with ulcerative colitis or Crohn's disease; cases with ischemic bowel disease; cases with colorectal polyposis; cases with melanosis coli; cases undergoing sigmoidoscopy; cases with poor intestional cleanliness (segment Boston bowel preparation scale (BBPS) of \< 2 points, total BBPS of \< 6 points); cases undergoing therapy procedures such as biopsy or CSP during the intubation phase; cases with transparent cap assisted colonoscopy; cases with water-assisted colonoscopy; cases with air insufflation level of M or L; cases failed caecal intubation within 15 min; cases with colonoscope stiffness level \> 0; obese cases or underweight cases; and cases refusing participation. Individuals who decline to provide informed consent. 2. Colonoscopists: Those who have performed fewer than 300 complete colonoscopies in any calendar year within the past three years. Those who decline to participate in the study.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Caecal intubation time | Stage 3 (projected to begin in 3-6 months) | The impact of real-time feedback on caecal intubation time. |
| AI-based red-out avoiding score | Stage 3 (projected to begin in 3-6 months) | The impact of real-time feedback on AI-based red-out avoiding score. |
| Red-out percentage | Stage 3 (projected to begin in 3-6 months) | The impact of real-time feedback on red-out percentage. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Complications | Stage 3 (projected to begin in 3-6 months) | During and after the colonoscopy, assess for any signs of complications |
Outcome results
None listed