B0179 - Comparing the Adenoma Detection Rate of Endocuff-Assisted Colonoscopy (EAC) Against Combined Artificial Intelligence and Endocuff-Assisted Colonoscopy (AEAC)

Monday, October 24, 2022

10:00 AM – 12:00 PM ET

Location: Crown Ballroom

Has Audio

Presenting Author(s)

Matthew O'Mara, BS

NYU Langone Health
New York, NY

Matthew O'Mara, BS, Jonathan Galati, MD, Samantha Gross, , Mark Pochapin, MD, Seth A. Gross, MD
NYU Langone Health, New York, NY

Introduction: Colorectal cancer (CRC) is the second leading cause of cancer-related mortality in the world. While effective at preventing CRC, standard colonoscopy can miss precancerous polyps placing patients at risk for interval CRC. Endoscopic mechanical attachments and artificial intelligence (AI) are technologies that have independently shown improvement in adenoma detection rate (ADR). We sought to compare the performance of Endocuff-assisted colonoscopy (EAC) to combined AI and EAC (AEAC) in relation to ADR.

Methods: This was a single-center study involving patients who underwent either AEAC or EAC between December 2021 and May 2022. Demographic (age, sex) and clinical (indication, Boston Bowel preparation scale (BBPS), withdrawal time, polyp location, histology and size) data on patients was obtained from the electronic health record. The primary outcome was ADR. Secondary outcomes were polyp detection rate (PDR), adenomas per colonoscopy (APC), polyps per colonoscopy (PPC), sessile serrated lesion rate (SSR) and sessile serrated lesions per colonoscopy (SSPC). Categorical variables were analyzed using a two-sided chi square test. Continuous variables were assessed using the student’s t-test or Mann-Whitney U-test. Odds ratios (OR) and 95% confidence intervals (CI) were calculated using logistic regression.

Results: 148 patients (50.7% men, mean age 60.9 years; 74 AEAC vs 74 EAC) were included. The AEAC group did not differ by age, sex, indication or BBPS from the EAC group (Table 1). ADR in the AEAC group was higher (71.6% vs 60.8%; OR 1.63; 95% CI 0.82-3.24; P = 0.17). SSR was 14.9% in the EAC group versus 24.3% in the AEAC group (P > 0.05) (Table 1). For adenomas >5-10mm in size, the AEAC group had a significantly higher ADR (28.4% vs 14.9%; OR 2.27; 95% CI 1.00-5.13; P = 0.05). Withdrawal time was longer in the AEAC group (8.0min vs 7.3min; P = 0.03). Subgroup analysis by indication revealed that ADR trended towards significance for patients in the AEAC group undergoing colonoscopy for CRC screening (70.3% vs 52.3%; OR 2.17; 95% CI 0.94-4.98; P = 0.068).

Discussion: Combining AI with Endocuff-assisted colonoscopy increased ADR, PDR, APC, PPC, SSR and SSPC when compared to EAC. ADR trended towards significance for patients in the AEAC group undergoing CRC screening. This study highlights the potential benefits of maximizing surface area exposure (mechanical enhancement) combined with enhanced mucosal inspection (AI). Future larger studies will be needed to further validate this combination.

Variable	EAC (n=74)	AEAC (n=74)	P
Mean age (SD), y	60.8 (9.7)	61.0 (9.9)	0.91
Sex, n (%)			0.87
Male	38 (51.4)	37 (50)
Female	36 (48.6)	37 (50)
Indication for colonoscopy, n (%)			0.08
Screening	44 (59.5)	54 (73)
Surveillance	30 (40.5)	20 (27)
Mean BBPS (SD)	8.6 (0.8)	8.5 (0.9)	0.55
Median withdrawal time (IQR), min*	7.3 (6.6-8.2)	8.0 (7.3-8.7)	0.03
Patients with >1 adenoma (ADR), n (%)	45 (60.8)	53 (71.6)	0.17
Adenomas per colonoscopy (APC), (range)	1.43 (0-12)	1.45 (0-5)	0.96
Patients with >1 polyp (PDR), n (%)	66 (89.2)	70 (94.6)	0.23
Polyps per colonoscopy (PPC), (range)	2.55 (0-13)	2.62 (0-16)	0.85
Patients with >1 sessile serrated lesion (SSR), n (%)	11 (14.9)	18 (24.3)	0.15
Sessile serrated lesions per colonoscopy (SSPC), (range)	0.23 (0-4)	0.27 (0-2)	0.67
Adenoma location, n (%)**
Right colon	31 (41.9)	33 (44.6)	0.74
Transverse colon	16 (21.6)	17 (23)	0.84
Left colon	22 (29.7)	26 (35.1)	0.48
Adenoma size, n (%)**
1-5mm	40 (54.1)	39 (52.7)	0.87
>5-10mm	11 (14.9)	21 (28.4)	0.05
>10mm	8 (10.8)	11 (14.9)	0.46
Polyp location, n (%)**
Right colon	34 (45.9)	42 (56.8)	0.19
Transverse colon	22 (29.7)	22 (29.7)	1.00
Left colon	49 (66.2)	51 (68.9)	0.73
Polyp size, n (%)**
1-5mm	62 (83.8)	55 (74.3)	0.16
>5-10mm	15 (20.3)	24 (32.4)	0.09
>10mm	8 (10.8)	12 (16.2)	0.34
Sessile serrated lesion location, n (%)**
Right colon	3 (4.1)	10 (13.5)	0.08
Transverse colon	7 (9.5)	3 (4.1)	0.33
Left colon	5 (6.8)	6 (8.1)	1.00
Sessile serrated lesions size, n (%)**
1-5mm	5 (6.8)	5 (6.8)	1.00
>5-10mm	3 (4.1)	8 (10.8)	0.21
>10mm	4 (5.4)	6 (8.1)	0.75

Table: Title: Patient Demographics and Per-Patient Lesion Analysis
Caption: EAC, Endocuff-assisted colonoscopy; AEAC, artificial intelligence and EAC; SD, standard deviation; BBPS, Boston Bowel Preparation scale; IQR, interquartile range; PDR, polyp detection rate; PPC, polyps per colonoscopy; ADR, adenoma detection rate; APC, adenomas per colonoscopy; SSR, sessile serrated lesion rate; SSPC, sessile serrated lesions per colonoscopy
*There was 1 case missing data in the EAC cohort
**Number of patients with >1 adenoma/polyp/sessile serrated lesion

Disclosures:

Matthew O'Mara indicated no relevant financial relationships.

Jonathan Galati indicated no relevant financial relationships.

Samantha Gross indicated no relevant financial relationships.

Mark Pochapin indicated no relevant financial relationships.

Seth Gross: ColoWrap, LLC – Advisory Committee/Board Member. Olympus – Consultant.

Matthew O'Mara, BS, Jonathan Galati, MD, Samantha Gross, , Mark Pochapin, MD, Seth A. Gross, MD. B0179 - Comparing the Adenoma Detection Rate of Endocuff-Assisted Colonoscopy (EAC) Against Combined Artificial Intelligence and Endocuff-Assisted Colonoscopy (AEAC), ACG 2022 Annual Scientific Meeting Abstracts. Charlotte, NC: American College of Gastroenterology.