S0281 Improvement in Adenoma Detection Using a Novel Artificial Intelligence-Aided Polyp Detection Device

Abstract

INTRODUCTION: Detecting colorectal neoplasia is the goal of high-quality screening and surveillance colonoscopy, as reflected by high adenoma detection rate (ADR) and adenomas per colonoscopy (APC). In addition, recent studies have highlighted the importance of sessile serrated lesions (SSLs) as precursors to colon cancer. The aim of our study was to prospectively evaluate the pilot performance of a novel AI-aided polyp detection device (APDD) in improving ADR, APC, and detection of SSLs during routine colonoscopies in a real-world setting. Finally, we assessed the increase in resection of hyperplastic polyps relative to adenomas and SSLs as defined by true histology rate (THR). METHODS: We compared ADR, APC, and detection of SSLs in a cohort of outpatients undergoing routine high resolution colonoscopy with and without the use of a real time APDD (Iterative Scopes, Cambridge MA). Patients undergoing colonoscopy with our APDD were prospectively enrolled in a single arm, open label study. The results were compared with a historical cohort performed by the same endoscopists at the same practice. All resected polyps were examined histologically. This study was approved by an institutional review board. RESULTS: 83 patients (28 screening, 55 surveillance) undergoing colonoscopy at an outpatient endoscopy center were prospectively enrolled and outcomes compared with 283 historical control patients (117 screening, 166 surveillance). Overall, ADR with and without APDD was 54.2% and 40.6% respectively (P = 0.028*) and 53.6% and 30.8% respectively in screening exams (P = 0.024*). Overall, APC rate with and without APDD was 1.46 and 1.01 respectively (P = 0.104) and 1.18 and 0.50 respectively in screening exams (P = 0.002*). In addition, overall sessile serrated lesion per colonoscopy (SSLPC) with and without APDD was 0.24 and 0.14 respectively (P = 0.178) and 0.43 and 0.09 respectively in screening exams (P = 0.034*). THR with and without APDD was 73.8% and 78.4% respectively (P = 0.463) and 75.0% and 71.0% respectively in screening exams (P = 0.731). CONCLUSION: A novel APDD increased the ADR and APC in a cohort of patients undergoing screening and surveillance colonoscopy without concomitant increase in hyperplastic polyp resection. Additionally, there was improvement in detection of SSLs in screening patients. AI-aided colonoscopy has the potential for improving the outcomes of patients undergoing colonoscopy.Table 1.: Comparison of quality metrics in the historical control group and the intervention group stratified by all exams, screening, and surveillance colonoscopiesFigure 1.: Distribution of polyps by size and histology in historical control versus intervention group.Figure 2.: Polyp detection by the APDD indicated by the blue bounding box around the perimeter of the lesion. A: detection of a 10 mm tubular adenoma in the sigmoid colon. B: detection of a 3 mm sessile serrated lesion in the rectum. C and D: detection of a 5 mm sessile serrated lesion in the ascending colon, taken upon first detection and upon closer look, respectively.