Evaluate the Effects of An AI System on Colonoscopy Quality of Novice Endoscopists

Evaluate the Effects of An Artificial Intelligence System on Colonoscopy Quality of Novice Endoscopists: A Randomized Controlled Trial

In this study, the AI-assisted system EndoAngel has the functions of reminding the ileocecal junction, withdrawal time, withdrawal speed, sliding lens, polyps in the field of vision, etc. These functions can assist novice endoscopists in performing colonoscopy and improve the quality.

Study Overview

• Status: Completed
• Conditions: Artificial Intelligence; Colonoscopy; Gastrointestinal Disease; Deep Learning
• Intervention / Treatment: Device: artificial intelligence assistance system

Detailed Description

Colonoscopy is a crucial technique for detecting and diagnosing lower digestive tract lesions. The demand for endoscopy is high in China, and endoscopy is in short supply. However, a colonoscopy is a complex technical procedure that requires training and experience for maximal accuracy and safety. The ability of different endoscopists varies greatly. Novice endoscopists generally have difficulty and high risk in entering colonoscopy, requiring experts' assistance. To some extent, this wastes the novice's productivity. If investigators can arrange the working mode of experts entering and novices withdrawing endoscopy, the clinical efficiency and resource utilization rate can be significantly improved. However, investigators must consider the poor examination ability of novice endoscopists. It is reported that the detection rate of adenoma in colonoscopy performed by endoscopists with different seniority is 7.4% ~ 52.5%. If the examination ability of novice endoscopists can be improved, this concern can be eliminated.

Deep learning algorithms have been continuously developed and increasingly mature in recent years. They have been gradually applied to the medical field. Computer vision is a science that studies how to make machines to "see". Through deep learning, camera and computer can replace human eyes to carry out machine vision such as target recognition, tracking and measurement. Interdisciplinary cooperation in medical imaging and computer vision is also one of the research hotspots in recent years. At present, it is mainly applied to the automatic identification and detection of lesions and quality control and has achieved good results.

Investigator's preliminary experiments have shown that deep learning has high accuracy in endoscopic quality monitoring, which can effectively regulate doctors' operations, reduce blind spots and improve the quality of endoscopic examination. At the same time, it can also monitor the doctor's withdrawal time in real-time and improve the detection rate of adenoma. In the previous work of investigator's research group, investigators have successfully developed deep learning-based colonoscopy withdraw speed monitoring and intestinal cleanliness assessment and verified the effectiveness of the AI-assisted system EndoAngel in improving the quality of gastroscopy and colonoscopy in clinical trials.

Based on the above rich foundation of preliminary work and the massive demand for improving the colonoscopy ability of novices. By comparing the performance of novices and novices with EndoAngel assistance and experts in colonoscopy, investigators want to explore whether artificial intelligence can assist novices to reach the expert level in colonoscopy.

• Study Type: Interventional
• Enrollment (Actual): 685
• Phase: Not Applicable

Contacts and Locations

Study Locations

• China
  • Hubei
    • Wuhan, Hubei, China, 430060
      • Renmin Hospital of Wuhan University

Participation Criteria

Eligibility Criteria

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

Description

Inclusion Criteria:

1. Male or female ≥18 years old;
2. Able to read, understand and sign an informed consent;
3. The investigator believes that the subjects can understand the process of the clinical study, are willing and able to complete all study procedures and follow-up visits, and cooperate with the study procedures;
4. Patients requiring colonoscopy.

Exclusion Criteria:

1. Have drug or alcohol abuse or mental disorder in the last 5 years;
2. Pregnant or lactating women;
3. Patients with known multiple polyp syndrome;
4. patients with known inflammatory bowel disease;
5. known intestinal stenosis or space-occupying tumor;
6. known colon obstruction or perforation;
7. patients with a history of colorectal surgery;
8. Patients with a previous history of allergy to pre-used spasmolysis;
9. Unable to perform biopsy and polyp removal due to coagulation disorders or oral anticoagulants;
10. High-risk diseases or other special conditions that the investigator considers the subject unsuitable for participation in the clinical trial.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

3

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: novices with AI-assisted system; The novice doctors are assisted in colonoscopy with an artificial intelligence system that can indicate abnormal lesions and the speed of withdrawal in real-time, as well as feedback on the percentage of overspeed.	Device: artificial intelligence assistance system; The artificial intelligence assistance system can indicate abnormal lesions and real-time withdrawal speed and feedback the overspeed percentage.
No Intervention: experts without AI-assisted system; The expert doctors perform routine colonoscopy without artificial intelligence assistance system and no special tips
No Intervention: novice without AI-assisted system; The novice doctors perform routine colonoscopy without artificial intelligence assistance system and no special tips

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Missed diagnosis rate of adenoma	The number of newly detected adenoma in the second examination divided by the total number of adenoma detected in both examinations	A month

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Detection rate of adenoma	The numerator is the number of patients diagnosed with adenomas, and the denominator is the total number of patients undergoing colonoscopy.	A month
Detection rate of advanced adenoma	The numerator is the number of patients diagnosed with advanced adenomas, and the denominator is the total number of patients undergoing colonoscopy. Advanced adenoma was defined as > 10mm, villous adenoma, tubular villous adenoma, high-grade intraepithelial neoplasia, and carcinoma.	A month
Polyp Detection Rate	The numerator is the number of patients with polyps detected by colonoscopy, and the denominator is the total number of patients who underwent colonoscopy	A month
Average number of adenomas detected per patient	The numerator is the total number of adenomas detected by colonoscopy, and the denominator is the total number of patients undergoing colonoscopy.	A month
The detection rate of large, small and micro polyps	The numerator is the number of patients with large (≥10 mm), small (6-9 mm) and micro-small (≤5 mm) polyps detected by colonoscopy, and the denominator is the total number of patients receiving colonoscopy.	A month
The average number of large, small and micro polyps detected	The numerator is the total number of large (≥10 mm), small (6-9 mm) and micro-small (≤5 mm) polyps detected by colonoscopy, and denominator is the total number of patients undergoing colonoscopy.	A month
The detection rate of large, small and micro adenomas	The numerator is the number of patients with large (≥10 mm), small (6-9 mm) and micro-small (≤5 mm) adenomas detected by colonoscopy, and the denominator is the total number of patients receiving colonoscopy.	A month
The average number of large, small and micro adenomas detected	The numerator is the total number of large (≥10 mm), small (6-9 mm) and micro-small (≤5 mm) adenomas detected by colonoscopy, and the denominator is the total number of patients undergoing colonoscopy.	A month
The detection rate of adenoma in different sites	The numerator is the number of patients with adenomas detected in the rectum, sigmoid colon, descending colon, transverse colon, ascending colon, ileocecal region and other sites during colonoscopy, and the denominator is the total number of patients receiving colonoscopy.	A month
The average number of adenomas detected in different sites	The numerator is the total number of adenomas detected in the rectum, sigmoid colon, descending colon, transverse colon, ascending colon, ileocecal region and other sites during colonoscopy, and the denominator is the total number of patients undergoing colonoscopy.	A month

Collaborators and Investigators

• Sponsor: Renmin Hospital of Wuhan University
• Investigators: Principal Investigator: Yu Honggang, Doctor, Renmin Hospital of Wuhan University

Study record dates

Study Major Dates

• Study Start (Actual): March 24, 2022
• Primary Completion (Actual): October 24, 2022
• Study Completion (Actual): November 24, 2022

Study Registration Dates

• First Submitted: March 1, 2022
• First Submitted That Met QC Criteria: April 9, 2022
• First Posted (Actual): April 12, 2022

Study Record Updates

• Last Update Posted (Actual): March 24, 2023
• Last Update Submitted That Met QC Criteria: March 22, 2023
• Last Verified: March 1, 2023

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Gastrointestinal Diseases; Digestive System Diseases
• Other Study ID Numbers: EA-22-002

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No