S625 Adenoma Detection Rate Using LCI vs White Light Colonoscopy Both With and Without the Use of Artificial Intelligence: A Prospective Study in a Non-Academic Center in Latin America

Abstract

Introduction: The adenoma detection rate (ADR) is a strong predictor of cancer prevention. The use of artificial intelligence could increase the detection of colorectal polyps. The Computer-Aided Polyp Detection systems (CADe) have shown high accuracy in polyp detection when retrospectively applied to endoscopy videos or images, but their live performance is still under scrutiny. There are other ways in which technology has helped in performance and efficiency, Linked Color Imaging (LCI) is a modern image-enhancing technology, its use along with artificial intelligence could be another tool in the detection of precancerous lesions. Methods: A prospective observational study was conducted on 637 subjects undergoing screening colonoscopies, follow up colonoscopies, or work-up from a fecal occult blood test, from January 2021 through June 10th, 2022, in a nonacademic center in the Dominican Republic. Colonoscopies performed during 2021 did not use the CADe technology, while patients in 2022 were exposed to the CADe technology, in addition, each patient was alternatively assigned to either LCI or white light colonoscopy. Two endoscopists performed the procedures during these two years. The primary outcome evaluated was the ADR using LCI vs. white light colonoscopy both with and without the use of artificial intelligence. Secondary outcomes were polyp detection rate (PDR) and average withdrawal time. Results: The ADR in patients not exposed to CADe (2021) was 56.6%, while patients exposed to CADe (2022) presented an ADR of 54.5%. PDR in 2021 was 72.3%, and in 2022 the result was 70.6%. The average withdrawal time in 2021 was 13 minutes and 14 minutes in 2022. When it comes to the use of LCI and white light without the use of AI (2021), the ADR with LCI was 52%, while the use of white light colonoscopy resulted in an ADR of 50.9%. The ADR in patients exposed to LCI with AI (2022) was 61.1%, while patients exposed to white light with AI presented an ADR of 61%. Conclusion: The polyp and adenoma detection rates calculated were higher than the average considered for a high-quality colonoscopy both with and without the use of artificial intelligence. When it comes to the use of other technologies like LCI, ADR was higher with LCI when compared to white light colonoscopy, while the NNT was 90. When comparing the use of both technologies, there was still no significant difference. Further studies are still needed to assess these new technologies and their effect on colonoscopy and polyp detection.