A Clinical Study To Measure The Effect Of Use Of Artificial Intelligence (AI) Enabled Computer Aided Detection (CADe) Assistance Software In Detecting Colon Polyps During Standard Colonoscopy Procedures (ColonCADe)

A Clinical Study To Measure The Effect Of Use Of Artificial Intelligence (AI) Enabled Computer Aided Detection (CADe) Assistance Software In Detecting Colon Polyps During Standard Colonoscopy Procedures

A Prospective, Multi-Center, Randomized Controlled Clinical Study To Measure The Effect Of Use Of Artificial Intelligence (AI) Enabled Computer Aided Detection (CADe) Assistance Software In Detecting Colon Polyps During Standard Colonoscopy Procedures

EndoVigilant software device augments existing colonoscopy procedure video in real-time by highlighting colon polyps and mucosal abnormalities. It is intended to assist gastroenterologists in detection of adenomas and serrated polyps. The device is an adjunctive tool and is not intended to replace physicians' decision making related to detection, diagnosis or treatment. This study with an adaptive design measures the clinical benefit (increase in detection of adenomatous and serrated polyps) and increased risk (increased extraction of non-adenomas) during standard colonoscopy procedures when EndoVigilant software device is used.

This study will analyze the clinical benefit and risk of using the EndoVigilant polyp detection assistance software based device during screening and surveillance colonoscopy procedures. The study subjects will be randomized to a procedure with or without the use of EndoVigilant software. While using this device, colonoscopy will continue to be performed in the standard manner as is done without the use of this device. The video signal from the colonoscope will be fed into a computer running the EndoVigilant software in addition to the standard video output to the procedure monitor. The gastroenterologist performing the procedure will therefore be able to observe a standard colonoscopy video on the primary monitor and the augmented video on the second monitor. The gastroenterologist may rely on the second monitor (with augmented video generated from EndoVigilant software) for polyp detection, but the standard procedure monitor with the original feed will always be operational and available for maneuvers such as fast insertion, polypectomy etc. The study will have an adaptive design with an interim analysis after 700 subjects to re-estimate the final sample size of the study. The study will include a diverse set of endoscopists across age, sex, years of experience and practice settings. In order to comply with FDA guidance this pivotal study will only include endoscopists with ADR of 25-40% in their routine clinical practice. At the discretion of Endovigilant, endoscopists with an ADR of <25% or >40% may be included for a separate exploratory analysis to examine the impact of the system on endoscopists with ADR outside of the FDA-mandated range. But in accordance with FDA guidance, the procedures done by these endoscopists will not be included in the primary endpoint analysis.

Random allocation stratified by gastroenterologist 50% randomized to colonoscopy procedure with device and 50% randomized to colonoscopy procedure without device

Colonoscopy Procedure is performed with EndoVigilant Software assisting the gastroenterologist during colonoscopy procedure.

Colonoscopy Procedure is performed without EndoVigilant Software assisting the gastroenterologist during colonoscopy procedure.

While using this device, colonoscopy will continue to be performed in the standard manner as is done without the use of this device. The video signal from the colonoscope will be fed into a computer running the EndoVigilant software in addition to the standard video output to the procedure monitor. The gastroenterologist performing the procedure will therefore be able to observe a standard colonoscopy video on the primary monitor and the augmented video on the second monitor. The gastroenterologist may rely on the second monitor (with augmented video generated from EndoVigilant software) for polyp detection, but the standard procedure monitor with the original feed will always be operational and available for maneuvers such as fast insertion, polypectomy etc.

Average Number of Adenomas Per Colonoscopy for all study subjects undergoing colonoscopy procedures, separately calculated for each of the study arms.

Percent of extractions that are adenomas per Colonoscopy for all study subjects undergoing colonoscopy procedures, separately calculated for each of the study arms.

Average Number of Serrated Polyps per Colonoscopy for all study subjects undergoing colonoscopy procedures, separately calculated for each of the study arms.

Average Number of Non-adenomatous, non-serrated polyps per colonoscopy for all study subjects undergoing colonoscopy procedures, separately calculated for each of the study arms.

Adenoma Detection Rate in Screening Colonoscopies for study subjects undergoing screening colonoscopy procedures, separately calculated for each of the study arms.

Serrated Polyp Detection Rate in Screening Colonoscopies for study subjects undergoing screening colonoscopy procedures, separately calculated for each of the study arms.

Adenoma Detection Rate in All Colonoscopies for all study subjects undergoing colonoscopy procedures, separately calculated for each of the study arms.

Serrated Polyp Detection Rate in All Colonoscopies for all study subjects undergoing colonoscopy procedures, separately calculated for each of the study arms.

Adenomatous Polyp Location Distribution Per Colonoscopy (Distal and Proximal Colon) for all study subjects undergoing colonoscopy procedures, separately calculated for each of the study arms.

Adenomatous Polyp Size Distribution Per Colonoscopy <6mm, 6-10mm, or >=10mm) for all study subjects undergoing colonoscopy procedures, separately calculated for each of the study arms.

Adenomatous Polyp Distribution by Paris Classification (Ip/Is, IIa/b/c) Per Colonoscopy for all study subjects undergoing colonoscopy procedures, separately calculated for each of the study arms.

Average time duration from the time when cecum is reached and the end of the colonoscopy procedure for all study subjects undergoing colonoscopy procedures, separately calculated for each of the study arms.

Average duration of the entire colonoscopy procedure for all study subjects undergoing colonoscopy procedures, separately calculated for each of the study arms.

Inclusion Criteria: Patient is 45 years old or older. Patient is presenting for colon cancer screening or low-risk surveillance colonoscopy. Low risk surveillance is defined as the patient qualifying for a colonoscopy surveillance interval of 5 years based on US Multi-Society Task Force 2020 Guidelines (i.e., up to 4 tubular adenomas <1cm, up to 4 sessile serrated polyps <1cm on most recent colonoscopy). Informed consent document for participating in the study signed by patient or patient's guardian. Exclusion Criteria: Patient has known history of inflammatory bowel disease (ulcerative colitis, Crohn's disease). Patient has known or suspected polyposis or hereditary colon cancer syndrome (such as familial adenomatous polyposis, hereditary nonpolyposis colorectal cancer). Patient referred for diagnostic colonoscopy to work up symptoms (such as abdominal pain or bleeding), laboratory abnormalities (such as anemia) or imaging findings (such as masses found on imaging). Patient has history of colon resection (not including appendectomy).

Zauber AG, Winawer SJ, O'Brien MJ, Lansdorp-Vogelaar I, van Ballegooijen M, Hankey BF, Shi W, Bond JH, Schapiro M, Panish JF, Stewart ET, Waye JD. Colonoscopic polypectomy and long-term prevention of colorectal-cancer deaths. N Engl J Med. 2012 Feb 23;366(8):687-96. doi: 10.1056/NEJMoa1100370.

Klare P, Sander C, Prinzen M, Haller B, Nowack S, Abdelhafez M, Poszler A, Brown H, Wilhelm D, Schmid RM, von Delius S, Wittenberg T. Automated polyp detection in the colorectum: a prospective study (with videos). Gastrointest Endosc. 2019 Mar;89(3):576-582.e1. doi: 10.1016/j.gie.2018.09.042. Epub 2018 Oct 17.

Singh S, Singh PP, Murad MH, Singh H, Samadder NJ. Prevalence, risk factors, and outcomes of interval colorectal cancers: a systematic review and meta-analysis. Am J Gastroenterol. 2014 Sep;109(9):1375-89. doi: 10.1038/ajg.2014.171. Epub 2014 Jun 24.

Zhao S, Wang S, Pan P, Xia T, Chang X, Yang X, Guo L, Meng Q, Yang F, Qian W, Xu Z, Wang Y, Wang Z, Gu L, Wang R, Jia F, Yao J, Li Z, Bai Y. Magnitude, Risk Factors, and Factors Associated With Adenoma Miss Rate of Tandem Colonoscopy: A Systematic Review and Meta-analysis. Gastroenterology. 2019 May;156(6):1661-1674.e11. doi: 10.1053/j.gastro.2019.01.260. Epub 2019 Feb 6.

Fernandez-Esparrach G, Bernal J, Lopez-Ceron M, Cordova H, Sanchez-Montes C, Rodriguez de Miguel C, Sanchez FJ. Exploring the clinical potential of an automatic colonic polyp detection method based on the creation of energy maps. Endoscopy. 2016 Sep;48(9):837-42. doi: 10.1055/s-0042-108434. Epub 2016 Jun 10.

Misawa M, Kudo SE, Mori Y, Cho T, Kataoka S, Yamauchi A, Ogawa Y, Maeda Y, Takeda K, Ichimasa K, Nakamura H, Yagawa Y, Toyoshima N, Ogata N, Kudo T, Hisayuki T, Hayashi T, Wakamura K, Baba T, Ishida F, Itoh H, Roth H, Oda M, Mori K. Artificial Intelligence-Assisted Polyp Detection for Colonoscopy: Initial Experience. Gastroenterology. 2018 Jun;154(8):2027-2029.e3. doi: 10.1053/j.gastro.2018.04.003. Epub 2018 Apr 11. No abstract available.

Urban G, Tripathi P, Alkayali T, Mittal M, Jalali F, Karnes W, Baldi P. Deep Learning Localizes and Identifies Polyps in Real Time With 96% Accuracy in Screening Colonoscopy. Gastroenterology. 2018 Oct;155(4):1069-1078.e8. doi: 10.1053/j.gastro.2018.06.037. Epub 2018 Jun 18.

Wang P, Xiao X, Glissen Brown JR, Berzin TM, Tu M, Xiong F, Hu X, Liu P, Song Y, Zhang D, Yang X, Li L, He J, Yi X, Liu J, Liu X. Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy. Nat Biomed Eng. 2018 Oct;2(10):741-748. doi: 10.1038/s41551-018-0301-3. Epub 2018 Oct 10.

Wang P, Berzin TM, Glissen Brown JR, Bharadwaj S, Becq A, Xiao X, Liu P, Li L, Song Y, Zhang D, Li Y, Xu G, Tu M, Liu X. Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study. Gut. 2019 Oct;68(10):1813-1819. doi: 10.1136/gutjnl-2018-317500. Epub 2019 Feb 27.