Neoplasms

All Conditions

Symptoms and General Pathology

Adenoma

Polyps

Neoplasms, Glandular and Epithelial

Neoplasms by Histologic Type

Patients will receive colonoscopy without assistance of EndoAngel's any function.

Patients will receive colonoscopy with the assistance of EndoAngel's polyp detection function.

Patients will receive colonoscopy with the assistance of EndoAngel's quality monitoring function.

Patients will receive colonoscopy with the assistance of EndoAngel's polyp detection plus quality monitoring function.

Patient in this group will receive colonoscopy with assistance of EndoAngel's polyp detection function,which can remind endoscopists of the location of the polyp.

Colonoscopy with the assistance of EndoAngel's polyp detection function.

Patient in this group will receive colonoscopy with assistance of EndoAngel's quality monitoring function,which can monitor the withdrawal speed of the endoscope.

Colonoscopy with the assistance of EndoAngel's quality monitoring function.

Patient in this group will receive colonoscopy with assistance of EndoAngel's both functions.

Colonoscopy without the assistance of EndoAngel's any function.

Honggang Yu, MD

An artificial intelligence-based system, named EndoAngel,has been constructed previously,which has polyp detection and quality monitoring functions. This study aims to evaluate the two different functions of EndoAngle in improving adenoma detection rate.

The detection and removal of precancerous polyps via colonoscopy can reduce the the risk of colon cancer. However, the detection rate of adenomatous polyps can vary significantly among endoscopists. EndoAngel is an artificial intelligence-based system,consisting of polyp detection and quality monitoring functions. The polyp detection function can remind endoscopists of the location of the polyp. The quality monitoring function can monitor the velocity of insertion of the endoscope, record the time of insertion and withdrawal of the endoscope, and remind endoscopists of the blind areas caused by intestinal segment slipping.This study aims to evaluate the two different functions of EndoAngle by 2 × 2 factorial design in improving adenoma detection rate and the quality of colonscopy .

A Single Center Study on Comparing the Different Function of EndoAngel in Improving the Quality of Colonscopy

A Prospective, Randomized, Single-blind, 2 × 2 Factorial Design Single Center Study Evaluating the Polyp Detection and Quality Monitoring Function of EndoAngel in Improving the Quality of Colonoscopy

The numerator is the number of cases of adenomas detected by colonoscopy, and the denominator is the total number of cases of patients undergoing colonoscopy.

The numerator is the number of cases of polyps detected by colonoscopy, and the denominator is the total number of cases of patients undergoing colonoscopy.

The numerator is the total number of polyps detected by colonoscopy, and the denominator is the total number of patients undergoing colonoscopy.

The numerator is the total number of adenomas detected by colonoscopy, and the denominator is the total number of patients undergoing colonoscopy.

The numerator was the number of patients with large (≥10 mm), small (\>5 to \<10 mm), and diminutive(≤5 mm) polyps detected by colonoscopy, and the denominator was the total number of patients receiving colonoscopy.

The numerator was the number of large (≥10 mm), small (\>5 to \<10 mm), and diminutive(≤5 mm) polyps detected by colonoscopy, and the denominator was the total number of patients receiving colonoscopy.

The numerator was the number of patients with large (≥10 mm), small (\>5 to \<10 mm), and diminutive(≤5 mm) adenomas detected by colonoscopy, and the denominator was the total number of patients receiving colonoscopy.

The numerator was the number of large (≥10 mm), small (\>5 to \<10 mm), and diminutive(≤5 mm) adenomas detected by colonoscopy, and the denominator was the total number of patients receiving colonoscopy.

The numerator is the number of cases of adenoma detected in the rectum, sigmoid colon, descending colon, transverse colon, ascending colon and ileocecal region during colonoscopy, and the denominator is the total number of patients undergoing colonoscopy.

The numerator is the total number of adenomas detected in the rectum, sigmoid colon, descending colon, transverse colon, ascending colon and ileocecal region during colonoscopy, and the denominator is the total number of patients undergoing colonoscopy.

The duration of colonoscopic insertion from rectum to ileocecal valve or appendiceal opening

The duration of colonoscopic withdrawal from ileocecal valve or appendiceal opening to colonoscopy finished.

The numerator is the number of cases of colonoscopy reaching ileocecal valve or appendiceal opening, and the denominator is the total number of colonoscopy cases.

Renmin Hospital of Wuhan University

Colonic Polyps

Adenomatous Polyps

Pathological Conditions, Anatomical

Herbal and Botanical

All Drugs and Chemicals

Cola

A transparent cap will be affixed to tip of the high-definition wide angle colonoscope.

4mm transparent cap (Olympus) mounted to the tip of a colonoscope.

Colonoscopy Cap

Heiko Pohl

Effectiveness of screening colonoscopy in cancer prevention relies on the detection and removal of adenomatous polyps. However, a substantial rate of adenomas is missed during a colonoscopy. It has been estimated that two thirds of missed adenomas are located on the proximal aspect of colonic folds. Attaching a transparent cap to the tip of a colonoscope may allow examination of the proximal aspect of colonic folds, and some early studies have suggested an increased polyp and adenoma detection using this technology. However, the studies have in part substantial methodological limitations (e.g. missing polyp histology, single endoscopist study, polyps not removed at the time of detection). Therefore, at this point it is unclear whether cap assisted colonoscopy may improve adenoma detection. The objective of this study is to evaluate whether cap assisted colonoscopy improves adenoma detection.

The investigators propose a two-center multiple endoscopists randomized controlled trial. Patients will be randomized to cap assisted colonoscopy or standard high definition white light colonoscopy. The cap is a 4mm commercially available transparent cap that is attached to the tip of the colonoscopy. Primary outcome measure is the adenoma detection rate (mean number of adenoma per patient). The investigators will assess and adjust for possible variables that can affect adenoma detection, including withdrawal time and quality of colon preparation. As a secondary outcome of interest the investigators will evaluate a possible learning curve effect among all endoscopists (a minimum of six) new to this method. In addition the investigators will evaluate whether cap assisted endoscopy improves real time prediction of polyp histology.

All patients who present for a colonoscopy and meet inclusion and exclusion criteria will be asked to participate (see inclusion and exclusion criteria). All patients will undergo a regular bowel preparation with polyethylene glycol lavage (based on current standard of care) until clear rectal fluid is evacuated. Patients will be randomized to one of two groups:

1. Standard colonoscopy, or
2. Cap assisted colonoscopy. All colonoscopies will be performed using state of the art high-definition wide angle colonoscopy. The transparent cap, which is attached to the tip of the colonoscope, has a 4mm margin extending beyond the tip of the colonoscope. All patients will undergo a careful endoscopic examination. A timer will provide feedback on the time of insertion and the withdrawal time. Detected polyps will be assessed with standard white light and narrow band imaging to predict polyp histology (adenoma versus no adenoma), then resected and sent for histological evaluation according to standard of care. At least 8 experienced endoscopists at the participating centers will participate. Each endoscopist will perform at least 50 cap assisted colonoscopies as part of the study. Each endoscopist will be asked to complete a survey after 10 and after 50 cap assisted colonoscopies.

Patients will be randomized in blocks of four allocated to each examiner. The order of randomization will be computer generated. Information on randomization will be contained in sealed envelopes assigned to each examiner and individually opened immediately before the procedure after a patient's All participating endoscopist will fill out a questionnaire regarding the use of cap assistance colonoscopy after the initial 10 cap assisted colonoscopies and after at least 50 cap assisted cap colonoscopies. Endoscopists will also undergo a training session with respect to real time polyp diagnosis before study commencement and after each 20 colonoscopies enrollment.

Does Cap Assisted Colonoscopy Improve Detection of Adenomatous Polyps? (CAP Trial)

Mean number of adenomas per patient in each group.

• Adenoma detection rate (ADR), % of patients with at least 1 adenoma

Proportion of patients with advanced adenomas

Proportion of patients with a bowel preparation that was rated as good or excellent (four point scale that distinguishes the bowel prep as poor, fair, good or excellent).

• Time taken for the withdrawal of the colonoscope from the cecum to anus among patients, who did not have any polyps.

• Proportion of patients, for whom intubation of the terminal ileum with the colonoscope was rated as "easy". Intubation could be rated by the endoscopist as "easy", "slightly difficult", "difficult", or "unable to intubate".

Difference in recommended surveillance interval between real time polyp diagnosis and pathological diagnosis among patients with at least one diminutive polyp

Dartmouth-Hitchcock Medical Center

White River Junction Veterans Affairs Medical Center

Standard Colonoscopy

Cap Assisted Colonoscopy

Standard colonoscopy without an attachment cap

A transparent cap will be affixed to tip of the high-definition wide angle colonoscope.

Colonoscopy Cap: 4mm transparent cap (Olympus) mounted to the tip of a colonoscope.

Total

Age, Continuous

Sex: Female, Male

Race and Ethnicity were not collected from any participant.

Race and Ethnicity Not Collected

United States

Region of Enrollment

Indication

Dr. Heiko Pohl

Mean Number of Adenomas

Adenoma Detection Rate

Advanced Adenoma Detection Rate

Quality of Bowel Preparation

Withdrawal Time

Ease of Terminal Ileum Intubation

Real Time Prediction of Polyp Histology

Overall Study

Withdrawal in every colonic segment with SFV (standard forward view) followed by another withdrawal with the retroviewing endoscope. Allocation of patients to each arm (RVE or SFVE) is done by randomization using sealed envelopes.

Withdrawal in every colonic segment with SFV followed by another withdrawal with SFV. Allocation of patients to each arm (RVE or SFVE) is done by randomization using sealed envelopes.

The colon is inspected with a new retroviewing endoscope

Retroviewing endoscopy

Timo Rath, MD

Timo Rath, Professor of Endoscopy

During standard colonoscopy a substantial number of colorectal polyps may be missed. Previous studies have found a 12-28% of miss rate for all polyps, a 31% for hyperplastic polyps and 6-27% for adenomas. In this study it is tested whether a retro viewing endoscope can detect more colorectal polyps in comparisson to standard forward viewing endoscopy. Further, ppolyps detected, mean adenomas per Patient and withdrawal time are recorded.

Inspection of the Colon Using a Retrograde Viewing Device for Detection of Colorectal Polyps

calculation of the adenoma detection rate in each arm

Mean number of adenomas per patient in each arm

University of Erlangen-Nürnberg Medical School

Prof. Dr. Timo Rath

The Medtronic-GI genius (CADe) system can be used to detect polyps of all sizes. Use of CADe is left to the discretion of the treating physician performing the colonoscopy. If used CADe will provide real-time feedback throughout each colonoscopy procedure and will alert the endoscopists of the presence of a polyp in the endoscopy field by displaying a bounding box on the same screen.

In the control group (standard colonoscopy), the participating endoscopists will detect and classify colorectal lesions without using any AI modules.

Medtronic-GI genius: AI will provide real-time feedback throughout each colonoscopy procedure and alert endoscopists to the presence of a polyp in the endoscopy field by displaying a bounding box on the same screen.

Medtronic-GI genius (CADe system for detecting colorectal polyps)

Julie Fleury

Daniel von Renteln, MD

Simon Bouchard, MD

Erik Deslandres, MD

Mickael Bouin, MD

Daniel von Renteln

This is a pragmatic, double-blind, randomized, controlled trial, to evaluate the effect of implementing a CADs system within the routine clinical practice of Canadian healthcare institutions.

The main hypothesis of this study is that the ADR in the operating room equipped with the GI genius CADe system will be significantly higher than the ADR in the ordinary operating room.

This trial will be conducted in four centers across Canada. All patients who meet the in/exclusion criteria can be enrolled. The patient's personal medical history will be reviewed to verify patient inclusion and exclusion criteria (age, history of CRC or adenoma, comorbid conditions, anticoagulation, etc.).

Eligible patients will be randomized (1:1) stratified per center in two arms:

1. Intervention arm: patients will be assigned to undergo colonoscopy in a room equipped with the GI genius CAD system.
2. Control arm: patients will undergo colonoscopy in a room not equipped with the GI genius CADe system.

The endoscopists performing the colonoscopies will not be involved in the development and implementation of CADe. Additionally, they won't be informed of the ongoing trial and will have the option of not using the CADe when available in the room. This design aims to mitigate operator biases that may be partly responsible for the observed difference between the CADe performance in randomized controlled trials and the CADe performance in implementation studies.

Data will be collected on case report forms (CRF), after the procedure, from the clinical files and the endoscopy reports. The data will then be deidentified and transferred to an electronic RedCap database in each institution. A research assistant will collect all information and annotations recorded on the patient's medical file during the procedure.

In the treatment group (operating room equipped with the CADe), the Medtronic-GI genius system can be used for real-time support by the endoscopists to detect polyps of all sizes. Use of CADe is left to the discretion of the treating physician performing the colonoscopy. If used CADe will provide real-time feedback throughout each colonoscopy procedure and will alert the endoscopists of the presence of a polyp in the endoscopy field by displaying a bounding box on the same screen.

In the control group (colonoscopy performed in room without CADe system), the participating endoscopists will detect as per standard of care.

All colonoscopies (in the intervention and control groups) including polypectomy procedures will be performed at the discretion of the treating physician and per standard of care.

All polyps will be resected and sent to the pathology labs of the participating institutions to be evaluated for histology by board-certified pathologists. The histopathology outcomes will be collected and stored in the CRF forms to be used as a reference later.

pragmatic double-blinded, randomized, multi-endoscopist, multicenter

Allocation will be concealed; the the patients and the participating endoscopists will not be informed of the treatment group.

Artificial Intelligence (AI) Assisted Real-time Adenoma Detection During Colonoscopies

To assess whether the GI genius platform can significantly increase the ADR during live colonoscopies, compared to standard colonoscopy among high-risk patients.The ADR is defined as the proportion of patients undergoing GI genius-assisted/standard colonoscopy in whom superior or equal to 1 histopathologically proven adenoma or carcinoma is identified. We will use the histopathology outcomes of the resected polyps as the ground truth to calculate the ADR.

The probability of an increase in the ADR among the trainees and expert endoscopists when using GI genius AI-assisted colonoscopy compared to standard colonoscopies.

Proximal ADR is defined as the prevalence of patients with at least 1 adenoma detected proximal to the splenic flexure

Sessile serrated lesions (SSL) detection rate as the proportion of patients colonoscopy in whom superior or equal to 1 sessile serrated lesion (SSL) is identified

Mean number of adenomas per colonoscopy (APC) defined as the total number of adenomas divided by the number of colonoscopies performed

Adenomas per positive index colonoscopy (APPC) defined as the total number of adenomas divided by the total of colonoscopies where at least 1 adenoma is detected

Sessile serrated lesion per Colonoscopy (SSLPC), defined as the total number of histologically confirmed sessile serrated lesions resected divided by the total number of colonoscopies

Advanced lesion detection rate (ALDR), defined as the proportion of colonoscopies for which the number of histopathologically proven adenoma \>10mm was at least 1.

To evaluate the agreement between the surveillance intervals based on the optical diagnosis of polyps with the GI genius and the pathology-based recommendation according to the current guidelines.

Proportion neoplastic and non-neoplastic polyps (i.e., SSLs, hyperplastic polyps, and high-grade dysplasia and carcinomas (overall and according to size, location, and morphology)

CADe utilization rate (when available in the room). Since we can't directly assess the CADe utilization rate without revealing the ongoing trial to the endoscopists, we will rely on two voluntary self-reported measures and a partial objective measure.

McGill University

University of British Columbia

Université de Sherbrooke

University of Alberta

Centre hospitalier de l'Université de Montréal (CHUM)

Digestive System Diseases

Colonic Neoplasms

Intestinal Polyps

Colorectal Neoplasms

Intestinal Neoplasms

Gastrointestinal Neoplasms

Digestive System Neoplasms

Gastrointestinal Diseases

Colonic Diseases

Intestinal Diseases

Patients in this arm will be given an educational card in addition to the standard pre-endoscopy instructions.

Patients in this arm will be given the standard pre-endoscopy instructions.

A 4x6 inch educational card containing a photo of an unprepared colon and a clean colon with the caption: "Drinking all the bowel cleaning medicine as described in the enclosed instructions lets the doctor see your colon better during your colonoscopy."

Educational card

Brian C Jacobson, MD, MPH

The purpose of this study is to determine whether adding a simple educational card to standard pre-procedure instructions improves the quality of bowel preparation for colonoscopy.

Despite written instructions, many patients do not understand the importance of bowel preparation as they prepare for colonoscopy. This often leads to poor compliance with preparation protocol and therefore inadequate bowel preparation. Our goal is to include a simple educational card which will hopefully improve the quality of bowel preparation by providing a visual component with the preparation instructions. This card will stress the importance of drinking the entire bowel preparation and provide representative images of a dirty and clean colon. We will specifically target patients directly booked for screening colonoscopy (those without a pre-procedure office visit). In a randomized fashion, patients in the control group will receive the standard bowel preparation instructions and patients in the intervention group will receive the educational card along with the standard bowel preparation instructions. The primary outcome will be the endoscopist's assessment of the quality of preparation using a standardized bowel preparation scale. Secondary outcomes will include the number and types of polyps found, colonoscope insertion and withdrawal time, and patient satisfaction with the procedure.

Improving Bowel Preparation for Colonoscopy With a Simple Educational Card

An ordinal scale. 0=fully unprepared colon and 9=perfectly clean colon. Higher values represent a better outcome. For reference please see: Lai EJ, Calderwood AH, Doros G, Fix OK, Jacobson BC. The Boston bowel preparation scale: a valid and reliable instrument for colonoscopy-oriented research. Gastrointestinal Endoscopy 2009;69:620-625. PMCID: PMC2763922

time in minutes to advance colonoscope from anus to tip of cecum during insertion phase of colonoscopy.

Time in minutes to withdraw colonoscope from tip of cecum to anus during withdrawal phase of colonoscopy

The number of times a colonoscopist recommended that the bowel was too unclean to qualify as an acceptable colonoscopy and therefore recommended repeating the procedure after better cleansing. This is both the number of participants with an inadequate preparation and the number of inadequate procedures. These are synonymous.

Boston Medical Center

Associate Professor of Medicine

Educational Card

Control

Age Continuous

Brian Jacobson, MD, Principal Investigator

Boston Bowel Preparation Scale Score

Time to Advance Colonoscope From Anus to Tip of Cecum.

Time to Withdraw Colonoscope From Tip of Cecum to Anus.

Number of Repeat Procedures Recommended Due to Inadequate Bowel Preparation.

Diseases and Abnormalities at or Before Birth

Nutritional and Metabolic Diseases

Syndrome

Carcinoma

Colorectal Neoplasms, Hereditary Nonpolyposis

Neoplastic Syndromes, Hereditary

Genetic Diseases, Inborn

DNA Repair-Deficiency Disorders

Metabolic Diseases

After the caecum is reached patients will be first examined with high definition i-scan endoscopy. Each colonic segment will be investigated in a back to back fashion, during the second pass white light will be used.

After the caecum is reached patients will be first examined with high definition white light endoscopy. Each colonic segment will be investigated in a back to back fashion, during the second pass i-scan will be used.

Prior the colonoscopy patients will be randomized to white light first or i-scan first. After the caecum is reached patients will be first examined according to the randomization. Each colonic segment will be investigated in a back to back fashion, during the second pass the other modality will be used.

The use of I-scan in the detection of polyps in HNPCC

Raf Bisschops, MD PhD

Hereditary non-polyposis colon carcinoma (HNPCC or Lynch-Syndrome) is a rare cause of colorectal cancer caused by a gene defect in the so -called mismatch repair genes. Patients can present at young age with colorectal cancer and polyps can develop faster to malignant lesions in comparison to classical sporadic adenomas. New advanced imaging modalities with high definition images and virtual chromoendoscopy have a theoretical advantage to improve detection and to increase polyp detection. In patients with HNPCC polyp detection has been shown to be increased by classical chromo-endoscopy and by high definition endoscopy with narrow band imaging (NBI) (a virtual chromo-endoscopy modality activated by a button on the endoscope), in comparison to white light endoscopy. However, in these back-to-back studies there was no randomization for the order of imaging modality. It is therefore not clear whether really the image enhancement adds to increased polyp detection or if this is achieved by a second inspection of the mucosa. In this trial the investigators want to assess the real additional value of virtual chromo-endoscopy for polyp detection in patients with the Lynch syndrome. The investigators will use the high definition pentax system and will compare white light endoscopy to i-scan, the incorporated virtual chromo-endoscopy mode in this system.

Hereditary non-polyposis colon carcinoma (HNPCC) or the Lynch syndrome is a rare cause of colorectal cancer caused by a defect in mismatch repair genes. Because of this, colorectal cancer does not develop according to the classical adenoma-carcinoma sequence, resulting in faster progression to malignant lesions. As a results patients typically present at a younger age with colorectal cancer or associated cancers such as endometrium or ovarian cancer. The risk for cancer in patients with the Lynch syndrome has been estimated to be 60-90% for colon cancer presenting at a mean age of 44 years . Colonoscopy is considered the gold standard for polyp detection. However the polyp miss rate has been reported to be 2% for larger adenomas (\< 10mm) , 13% for lesions between 5 and 10 mm and up to 26% for small lesions (1-5 mm). Between 2 to 6 percent of carcinomas can be missed , resulting interval cancers. Typically, in HNPCC small colorectal lesions can already harbor cancer or high grade dysplasia, making early detection of small lesions even more clinically relevant than in an average risk population.

New endoscopic imaging systems that are currently available have a high definition video signal and have an incorporated feature of virtual chromoendoscopy. High definition endoscopy is becoming the new gold standard in endoscopy, since it is available in all new types of commercially available endoscopes. The use of high definition endoscopy may lead to improved recognition of subtle and flat lesions. Furthermore, the use of filters techniques accentuates superficial changes in the mucosal architecture and helps to characterize polyps. I-scan is a postprocessing filter incorporated in the high definition processor (EPKi) of the new Pentax endoscopes. The techniques highlights changes in surface and vessel architecture through 3 different modifications (so called surface enhancement, tone enhancement and contrast enhancement). In a randomized trial in patients with a positive feces occult blood test it has been shown that the system detects significantly more polyps than standard resolution white light.

Current literature suggests that classical chromoendoscopy with indigocarmine (Huneberg, lecomte) or narrow-band imaging (NBI) increases the detection of polyps in HNPCC patients. Although all of these studies had a cross-over design, randomization for the imaging modality was either not possible (in case of chromoendoscopy) or not applied (in case of NBI). So it is not clear whether more polyps are detected by advanced imaging techniques, or simply by a second inspection of the colon.

The aim of this study was to assess the additional value of i-scan in polyp detection in HNPCC patients in comparison to high definition white light endoscopy (HD-WLE) in a randomized controlled cross-over trial. The investigators also wanted to investigate the effect of a second inspection round on polyp detection.

I-Scan For Colon Polyp Detection In HNPCC

High Definition Endoscopy Versus Virtual Chromoendoscopy In The Detection Of Colonic Polyps In HNPCC

Universitaire Ziekenhuizen KU Leuven

Rectal Diseases

Central Nervous System Stimulants

Other Dietary Supplements

Caffeine

Patients will undergo usual colonoscopy as per usual practice, followed back to back by ENDO-AID assisted colonoscopy

Patients will undergo ENDO-AID assisted colonoscopy with all polyps treated as per usual practice, followed back to back by ENDO-AID assisted colonoscopy

ENDO-AID is a dedicated endoscopy Computer-Aided Diagnosis (CADe) system where suspicious lesions are automatically detected and highlighted on the main monitor in real-time, alerting the endoscopist during the procedure.

ENDO-AID CADe assisted Colonoscopy

Kaori Futaba

This study hypothesizes that more adenomas will be detected using the ENDO-AID assisted Colonoscopy compared to conventional colonoscopy.

A single-centre, randomized, same-day, back-to-back tandem colonoscopy trial comparing Adenoma Missed Rate and Adenoma Detection Rate in ENDO-AID assisted colonoscopy and conventional colonoscopy.

Colorectal cancer is the third common cancer in the world and the commonest cancer in Hong Kong. Most sporadic colorectal cancers arise from benign polyps via adenoma-carcinoma sequence or the serrated polyp-carcinoma sequence. There are reports of unexpectedly high risk of interval carcinomas, as high as up to 9%, raising concerns about the effectiveness of colonoscopy in preventing colorectal cancers. Different techniques have been described to improve the area of mucosa visualised but lesions may still be missed due to failure of identification by the endoscopist.

Computer Aided diagnosis (CAD) assisted colonoscopy is becoming increasingly popular to address human error. Deep learning technology has surpassed human learning and advancement in technology now allows real-time Artificial Intelligence to assist colonoscopists in polyp detection.

ENDO-AID Assisted Tandem Colonoscopy RCT

Assessment of Efficacy of ENDO-AID Assisted Colonoscopy in Adenoma Detection: a Single Centre Randomised Controlled Trial

To compare the adenoma missed rate (AMR) between ENDO-AID assisted Colonoscopy and conventional colonoscopy. AMR is defined as the number of adenomas detected in the second pass colonoscopy divided by the total number of adenomas detected in both passes for the same patients.

To compare the Polyp missed rate (PMR) between ENDO-AID assisted Colonoscopy and conventional colonoscopy. PMR is defined as the number of polyps detected in the second pass colonoscopy divided by the total number of polyps detected in both passes for the same patients.

To compare the Adenoma detection rate (ADR) between ENDO-AID assisted Colonoscopy and conventional colonoscopy for the first pass colonoscopy. ADR is defined as the proportion of patients with at least 1 adenoma detected in the first pass colonoscopy.

To compare the patient missed rate (PMR) between ENDO-AID assisted colonoscopy and conventional white light colonoscopy. PMR is defined as the number of patients in whom adenomas were detected for the first time during second pass colonoscopy divided by the number of patients with at least 1 adenoma detected.

To compare the number of polyps removed between ENDO-AID assisted Colonoscopy and conventional white light colonoscopy

Baseline Parameters will be compared, including withdrawal time and Boston Bowel Preparation Scale in the first colonoscopy procedures

To compare the Serious Adverse Events between ENDO-AID assisted Colonoscopy and conventional white light colonoscopy

Number of abnormalities highlighted on ENDO-AID and actual number of abnormalities found macroscopically and histologically

Chinese University of Hong Kong

Assistant Professor

Adenocarcinoma

Experimental arm : patients receive a colonoscopy using GI Genius™ intelligent endoscopy system (Medtronic Inc., Minneapolis, Minnesota, USA)

Control arm :The artificial intelligence is not activated during the colonoscopy exam,the patient receive a standard high definition colonoscopy

Colonoscopy

The aim of the study is to assess whether the use of artificial intelligence improves polyp detection in a segment of the colon (the right colon).

To achieve this objective, patients will be divided into two groups: one will undergo a standard colonoscopy, the other a colonoscopy with the artificial intelligence software connected to the machine.

This software does not modify the colonoscopy technique in any way, and does not require the administration of any product to the patient.

The study will compare the detection rate of right colon polyps between the group of patients who underwent standard colonoscopy and those who underwent colonoscopy with artificial intelligence. If this number does not differ between the two groups, the investigators can conclude that there is no point in using artificial intelligence.

Colorectal cancer (CRC) is the third most common cancer and remains one of the leading causes of mortality among neoplastic diseases in the world. Screening colonoscopy with detection and resection of colorectal polyps have reduced CRC incidence and mortality.

Nevertheless, colonoscopy is an imperfect screening test and its effectiveness is influenced by a range of variables including the skill and expertise of the endoscopist. Indeed, a significant proportion of colorectal neoplasia is missed during colonoscopic examinations. In the majority of studies, the rate of interval CRC among all CRCs ranged from 2% to 9% and interval cancers occurred more likely in the right colon. Interval cancers can result from missed lesion, incomplete removal or newly developed cancer. Most missed polyps are smaller than 10 mm in diameter and are sessile or flat in appearance. Therefore, sessile serrated adenomas (SSAs), which predominantly occur in the right colon, are easily missed because they are small and sessile.

Colonoscopy is less effective in screening right sided CRCs, mainly because of the increased miss rate for polyps with sessile or flat appearance. In recent years, artificial intelligence (AI) is increasingly applied in gastrointestinal endoscopy, especially in the detection of colorectal polyps. In 2019, the first prospective randomized controlled trial including 1058 patients and comparing the polyp detection rate in colonoscopy with or without AI showed a significantly higher detection rate in the group with AI (29.1% vs 20.3%). Other previous prospective studies have showed that AI had great potential for improving colonic polyp detection.

To our knowledge, this is the first study to date to evaluate the performance of the AI in the detection of right colon polyps.

In this study, the investigators aim first of all to compare the rate of right colon polyp detection with AI-aided colonoscopy (AIC) to the rate obtained by the Standard (high-definition) colonoscopy (SC) in patient undergoing diagnostic colonoscopy. Then, the investigators would to evaluate the following endpoints:

1. Comparison of time required for AIC versus SC (withdrawal time)
2. Comparison of histological classification of all polyps detected in each group
3. Comparison of the number of right colon polyps detected in each group
4. A subgroup analysis comparing the rate of colon polyp detection between the two groups will be realized according to the procedure starting time (accounting for operator fatigability).

Study title	NCT ID	Conditions	Interventions	Eligibility	Organization
A Single Center Study on Comparing the Different Function of EndoAngel in Improving the Quality of Colonscopy	NCT04453956	Adenoma	Colonoscopy wit... Colonoscopy wit... Colonoscopy wit...	18 Years -	Renmin Hospital of Wuhan University
Does Cap Assisted Colonoscopy Improve Detection of Adenomatous Polyps? (CAP Trial)	NCT01935180	Adenomatous Pol...	Colonoscopy Cap	50 Years - 85 Years	White River Junction Veterans Affairs Medical Center
Does Cap Assisted Colonoscopy Improve Detection of Adenomatous Polyps? (CAP Trial)	NCT01935180	Adenomatous Pol...	Colonoscopy Cap	50 Years - 85 Years	White River Junction Veterans Affairs Medical Center
Inspection of the Colon Using a Retrograde Viewing Device for Detection of Colorectal Polyps	NCT04107376	Adenoma Polyps	Retroviewing en...	18 Years - 85 Years	University of Erlangen-Nürnberg Medical School
Artificial Intelligence (AI) Assisted Real-time Adenoma Detection During Colonoscopies	NCT05244278	Artificial Inte...	Medtronic-GI ge...	45 Years - 89 Years	Centre hospitalier de l'Université de Montréal (CHUM)
Improving Bowel Preparation for Colonoscopy With a Simple Educational Card	NCT00643682	Colonic Polyps Colonic Neoplas...	Educational car...	18 Years -	Boston Medical Center
I-Scan For Colon Polyp Detection In HNPCC	NCT01823471	Hereditary Non-... HNPCC Lynch Syndrome	The use of I-sc...	18 Years -	Universitaire Ziekenhuizen KU Leuven
ENDO-AID Assisted Tandem Colonoscopy RCT	NCT05013125	Colorectal Neop...	ENDO-AID CADe a...	18 Years -	Chinese University of Hong Kong
ENDO-AID Assisted Tandem Colonoscopy RCT	NCT05013125	Colorectal Neop...	ENDO-AID CADe a...	18 Years -	Chinese University of Hong Kong
Performance of Artificial Intelligence in Colonoscopy for Right Colon Polyp Detection	NCT06216405	Colon Cancer Colon Polyp Colon Lesion Colon Adenocarc...	Colonoscopy	18 Years -	Groupe Hospitalier Diaconesses Croix Saint-Simon

Spots Global Cancer Trial Database for polyp detection