Artificial Intelligence Aid Systems in Colorectal Adenoma Detection (INTELAID)

Usefulness of the Endo-AID Artificial Intelligence System in the Detection of Colorectal Adenomas. a Randomized Controlled Trial

The main purpose of the study to evaluate the usefulness of the Endo-AID artificial intelligence system in the detection of colorectal adenomas in consecutive patients for outpatient colonoscopy. The secondary aims were: To evaluate the benefit of Endo-AID in adenoma detection rate by comparing endoscopists with high and low adenoma detection rate. To evaluate serrated detection rate, advanced adenoma detection rate, adenoma detection rate according to the size (<= 5mm, 6-9mm,> = 10mm) and number of adenomas by colonoscopy. Stratification by location and morphology.

Priority guidelines have been established regarding IA applied to gastrointestinal endoscopy. Regarding the priority uses for their development, there are applications that improve vision, placing computer-assisted lesion detection (CADe) as one of the most necessary priorities, given the importance of colorectal cancer screening (CRC) and post-polypectomy surveillance. The evaluation of these systems in different clinical practices and patient groups has been recommend. In this regard, studies in the western population are limited and have been carried out by expert endoscopists. It has not been evaluated in endoscopists with different adenoma detection rates. In addition, there are no studies with the recent CADe Endo-AID system (Olympus Corp. Tokyo). The main purpose of the study to evaluate the usefulness of the Endo-AID artificial intelligence system in the detection of colorectal adenomas in consecutive patients for outpatient colonoscopy. In addition, the benefit of the CADe system will be assessed according to the endoscopist ADR. A randomized controlled trial will be carried out in consecutive outpatients meeting the inclusion criteria and none of the exclusion criteria. Patients with be randomized to one of the four groups: CADe system and high ADR endoscopist; CADe system and low ADR endoscopist; Control and high ADR endoscopist; Control and low ADR endoscopist. For the sample size calculation a 14.4 of difference in favor of the CADe system was considered. Taking onto account an alpha error of 0.05 in a unilateral contrast, a power of 80% and a loss of 10%, 165 patients per group would be required.

Tis system can detect in the screen suspicion areas of adenomatous polyps. This is an additional help for the endoscopist for the detection of lesions

This is the control group. As in the routine colonoscopy the endoscopist is in charge of the detection of the lesions.

Inclusion Criteria: Age ≥ 18 years. Patients referred for outpatient colonoscopy Exclusion Criteria: Colonic resection Taking anticoagulants or antiagregants that contraindicate the performance of therapy Patients with a recent colonoscopy (<6 months) of good quality (e.g. cited for endoscopic therapy) Inflammatory bowel disease Patients with incomplete colonoscopy Patients with inadequate preparation using the Boston Colonic Preparation Scale (BBPS). A cleaning quality of less than 2 points in any of the 3 colonic sections will be considered inadequate. Patients with polyposis syndromes Refusal to participate in the study.

Hassan C, Spadaccini M, Iannone A, Maselli R, Jovani M, Chandrasekar VT, Antonelli G, Yu H, Areia M, Dinis-Ribeiro M, Bhandari P, Sharma P, Rex DK, Rosch T, Wallace M, Repici A. Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis. Gastrointest Endosc. 2021 Jan;93(1):77-85.e6. doi: 10.1016/j.gie.2020.06.059. Epub 2020 Jun 26.

Berzin TM, Parasa S, Wallace MB, Gross SA, Repici A, Sharma P. Position statement on priorities for artificial intelligence in GI endoscopy: a report by the ASGE Task Force. Gastrointest Endosc. 2020 Oct;92(4):951-959. doi: 10.1016/j.gie.2020.06.035. Epub 2020 Jun 19.

Wang P, Liu X, Berzin TM, Glissen Brown JR, Liu P, Zhou C, Lei L, Li L, Guo Z, Lei S, Xiong F, Wang H, Song Y, Pan Y, Zhou G. Effect of a deep-learning computer-aided detection system on adenoma detection during colonoscopy (CADe-DB trial): a double-blind randomised study. Lancet Gastroenterol Hepatol. 2020 Apr;5(4):343-351. doi: 10.1016/S2468-1253(19)30411-X. Epub 2020 Jan 22. Erratum In: Lancet Gastroenterol Hepatol. 2020 Apr;5(4):e3.

Wang P, Liu P, Glissen Brown JR, Berzin TM, Zhou G, Lei S, Liu X, Li L, Xiao X. Lower Adenoma Miss Rate of Computer-Aided Detection-Assisted Colonoscopy vs Routine White-Light Colonoscopy in a Prospective Tandem Study. Gastroenterology. 2020 Oct;159(4):1252-1261.e5. doi: 10.1053/j.gastro.2020.06.023. Epub 2020 Jun 17.