P1745 - Evaluation of Computer Aided Detection During Colonoscopy Among Veterans: A Randomized Clinical Trial

Monday, October 23, 2023

10:30 AM – 4:15 PM PT

Location: Exhibit Hall

Has Audio

Presenting Author(s)

Mike Wei, MD

Stanford University School of Medicine
Palo Alto, CA

Award: Presidential Poster Award

Mike Wei, MD¹, Yu Chen, MD², Susan Quan, MD³, Jennifer Pan, MD, MS⁴, Robert J.. Wong, MD, MS, FACG⁵, Shai Friedland, MD⁶
¹Stanford University School of Medicine, Palo Alto, CA; ²VA Palo Alto Health Care System, Palo Alto, CA; ³Veterans Affairs Palo Alto Healthcare System, Palo Alto, CA; ⁴VA Palo Alto Health Care System/Stanford University, Palo Alto, CA; ⁵Stanford/VA Palo Alto, Palo Alto, CA; ⁶VA Palo Alto Health Care System/Standford University, Palo Alto, CA

Introduction: There has been significant interest in use of computer aided detection (CADe) devices in colonoscopy to improve polyp detection and reduce miss rate. In this randomized controlled trial study (NCT04555135), we evaluated the use of CADe amongst veterans.

Methods: Between September 2020 and December 2021, we performed a randomized controlled trial to evaluate the impact of CADe (EndoVigilant) at Veterans Affairs Palo Alto Health Care System (Figure 1). Patients presenting for screening or low-risk surveillance were randomized to colonoscopy performed with or without CADe. Primary outcomes of interest included adenoma detection rate (ADR), adenomas per colonoscopy (APC), and adenomas per extraction (APE). In addition, we measured serrated polyps per colonoscopy, non-adenomatous, non-serrated polyps per colonoscopy, serrated polyp detection rate, and procedural time.

Results: A total of 244 patients were enrolled (124 with CADe), with similar patient characteristics (age, sex, BMI, indication) between the two groups. Use of CADe was found to have decreased number of polyps (2.51 vs 3.47, p=0.017) as well as adenomas (1.79 vs 2.53, p=0.030) per colonoscopy compared to without CADe. There was no significant difference in number of serrated polyps as well as non-adenomatous non-serrated polyps per colonoscopy between the two groups. Overall, CADe was found to have lower ADR (68.5 vs 80.0%, p=0.041) as well as serrated polyp detection rate (3.2 vs 7.5%, p< 0.0001) compared to without use of CADe. There was no significant difference in withdrawal and procedure time between the two groups as well as detection of adenomas per extraction (71.4 vs 73.1%, p=0.613). No adverse events were identified.

Discussion: While several randomized controlled trials have demonstrated improved ADR and APC with use of CADe, in this RCT performed amongst veterans in California, use of CADe was found to have decreased APC, ADR as well as serrated polyp detection rate. Further studies are needed to understand the true impact of CADe in performance quality among endoscopists.

Figure: Use of CADe to identify polyp, outlined with a blue box

	With CADe	Without CADe	p-value
Adenoma Detection Rate in All Colonoscopies, n/N(%)	85/124 (68.5)	96/120 (80.0)	0.041
Adenoma Detection Rate in Screening Colonoscopies, n/N(%)	4/13 (30.8)	6/14 (42.9)	0.516
Adenoma Detection Rate in Surveillance Colonoscopies, n/N(%)	81/111 (73.0)	90/106 (84.9)	0.032
Serrated Polyp Detection Rate in All Colonoscopies, n/N(%)	4/124 (3.2)	9/120 (7.5)	< 0.0001
Serrated Polyp Detection Rate in Screening Colonoscopies, n/N(%)	0/13 (0.0)	1/14 (7.1)	0.326
Serrated Polyp Detection Rate in Surveillance Colonoscopies, n/N(%)	4/111 (3.6)	8/106 (7.5)	0.204
Adenomas Per Extraction in All Colonoscopies, n/N(%)	222/311 (71.4)	304/416 (73.1)	0.613
Adenomas Per Extraction in Screening Colonoscopies, n/N(%)	6/8 (75.0)	18/25 (72.0)	0.868
Adenomas Per Extraction in Surveillance Colonoscopies, n/N(%)	216/303 (71.3)	286/391 (73.1)	0.587

Disclosures:

Mike Wei: AgilTX – Consultant. Capsovision – Consultant. Neptune Medical – Consultant.

Yu Chen indicated no relevant financial relationships.

Susan Quan: Capsovision – Consultant.

Jennifer Pan indicated no relevant financial relationships.

Robert Wong: Exact Sciences – Grant/Research Support. Gilead Sciences – Consultant, Grant/Research Support. Thera Technologies – Grant/Research Support.

Shai Friedland: Capsovision – Consultant. Intuitive Surgical – Consultant.

Mike Wei, MD¹, Yu Chen, MD², Susan Quan, MD³, Jennifer Pan, MD, MS⁴, Robert J.. Wong, MD, MS, FACG⁵, Shai Friedland, MD⁶. P1745 - Evaluation of Computer Aided Detection During Colonoscopy Among Veterans: A Randomized Clinical Trial, ACG 2023 Annual Scientific Meeting Abstracts. Vancouver, BC, Canada: American College of Gastroenterology.