TY - JOUR
T1 - Performance and attitudes toward real-time computer-aided polyp detection during colonoscopy in a large tertiary referral center in the United States
AU - Nehme, Fredy
AU - Coronel, Emmanuel
AU - Barringer, Denise A.
AU - Romero, Laura G.
AU - Shafi, Mehnaz A.
AU - Ross, William A.
AU - Ge, Phillip S.
N1 - Funding Information:
DISCLOSURE: The following author disclosed financial relationships: P. S. Ge: Consultant for Alira Health, Boston Scientific, Ovesco America, and Neptune Medical. All other authors disclosed no financial relationships.
Publisher Copyright:
© 2023 American Society for Gastrointestinal Endoscopy
PY - 2023/7
Y1 - 2023/7
N2 - Background and Aims: Computer-aided detection (CADe) has been shown to improve polyp detection in clinical trials. Limited data exist on the impact, utilization, and attitudes toward artificial intelligence (AI)-assisted colonoscopy in daily clinical practice. We aimed to evaluate the effectiveness of the first U.S. Food and Drug Administration–approved CADe device for polyp detection in the United States and the attitudes toward its implementation. Methods: We performed a retrospective analysis of a prospectively maintained database of patients undergoing colonoscopy at a tertiary center in the United States before and after a real-time CADe system was made available. The decision to activate the CADe system was at the discretion of the endoscopist. An anonymous survey was circulated among endoscopy physicians and staff at the beginning and conclusion of the study period regarding their attitudes toward AI-assisted colonoscopy. Results: CADe was activated in 52.1% of cases. Compared with historical control subjects, there was no statistically significant difference in adenomas detected per colonoscopy (1.08 vs 1.04, P =.65), even after excluding diagnostic and therapeutic indications and cases where CADe was not activated (1.27 vs 1.17, P =.45). In addition, there was no statistically significant difference in adenoma detection rate (ADR), median procedure, and withdrawal times. Survey results demonstrated mixed attitudes toward AI-assisted colonoscopy, of which main concerns were high number of false-positive signals (82.4%), high level of distraction (58.8%), and impression it prolonged procedure time (47.1%). Conclusions: CADe did not improve adenoma detection in daily practice among endoscopists with high baseline ADRs. Despite its availability, AI-assisted colonoscopy was only activated in half of the cases, and multiple concerns were raised by staff and endoscopists. Future studies will help elucidate the patients and endoscopists that would benefit most from AI-assisted colonoscopy.
AB - Background and Aims: Computer-aided detection (CADe) has been shown to improve polyp detection in clinical trials. Limited data exist on the impact, utilization, and attitudes toward artificial intelligence (AI)-assisted colonoscopy in daily clinical practice. We aimed to evaluate the effectiveness of the first U.S. Food and Drug Administration–approved CADe device for polyp detection in the United States and the attitudes toward its implementation. Methods: We performed a retrospective analysis of a prospectively maintained database of patients undergoing colonoscopy at a tertiary center in the United States before and after a real-time CADe system was made available. The decision to activate the CADe system was at the discretion of the endoscopist. An anonymous survey was circulated among endoscopy physicians and staff at the beginning and conclusion of the study period regarding their attitudes toward AI-assisted colonoscopy. Results: CADe was activated in 52.1% of cases. Compared with historical control subjects, there was no statistically significant difference in adenomas detected per colonoscopy (1.08 vs 1.04, P =.65), even after excluding diagnostic and therapeutic indications and cases where CADe was not activated (1.27 vs 1.17, P =.45). In addition, there was no statistically significant difference in adenoma detection rate (ADR), median procedure, and withdrawal times. Survey results demonstrated mixed attitudes toward AI-assisted colonoscopy, of which main concerns were high number of false-positive signals (82.4%), high level of distraction (58.8%), and impression it prolonged procedure time (47.1%). Conclusions: CADe did not improve adenoma detection in daily practice among endoscopists with high baseline ADRs. Despite its availability, AI-assisted colonoscopy was only activated in half of the cases, and multiple concerns were raised by staff and endoscopists. Future studies will help elucidate the patients and endoscopists that would benefit most from AI-assisted colonoscopy.
UR - http://www.scopus.com/inward/record.url?scp=85153514700&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85153514700&partnerID=8YFLogxK
U2 - 10.1016/j.gie.2023.02.016
DO - 10.1016/j.gie.2023.02.016
M3 - Article
C2 - 36801459
AN - SCOPUS:85153514700
SN - 0016-5107
VL - 98
SP - 100-109.e6
JO - Gastrointestinal endoscopy
JF - Gastrointestinal endoscopy
IS - 1
ER -