Role of Artificial Intelligence in Colonoscopy Detection of Advanced Neoplasias : A Randomized Trial.

BACKGROUND: The role of computer-aided detection in identifying advanced colorectal neoplasia is unknown. OBJECTIVE: To evaluate the contribution of computer-aided detection to colonoscopic detection of advanced colorectal neoplasias as well as adenomas, serrated polyps, and nonpolypoid and right-sided lesions. DESIGN: Multicenter, parallel, randomized controlled trial. (ClinicalTrials.gov: NCT04673136). SETTING: Spanish colorectal cancer screening program. PARTICIPANTS: 3213 persons with a positive fecal immunochemical test. INTERVENTION: Enrollees were randomly assigned to colonoscopy with or without computer-aided detection. MEASUREMENTS: Advanced colorectal neoplasia was defined as advanced adenoma and/or advanced serrated polyp. RESULTS: The 2 comparison groups showed no significant difference in advanced colorectal neoplasia detection rate (34.8% with intervention vs. 34.6% for controls; adjusted risk ratio [aRR], 1.01 [95% CI, 0.92 to 1.10]) or the mean number of advanced colorectal neoplasias detected per colonoscopy (0.54 [SD, 0.95] with intervention vs. 0.52 [SD, 0.95] for controls; adjusted rate ratio, 1.04 [99.9% CI, 0.88 to 1.22]). Adenoma detection rate also did not differ (64.2% with intervention vs. 62.0% for controls; aRR, 1.06 [99.9% CI, 0.91 to 1.23]). Computer-aided detection increased the mean number of nonpolypoid lesions (0.56 [SD, 1.25] vs. 0.47 [SD, 1.18] for controls; adjusted rate ratio, 1.19 [99.9% CI, 1.01 to 1.41]), proximal adenomas (0.94 [SD, 1.62] vs. 0.81 [SD, 1.52] for controls; adjusted rate ratio, 1.17 [99.9% CI, 1.03 to 1.33]), and lesions of 5 mm or smaller (polyps in general and adenomas and serrated lesions in particular) detected per colonoscopy. LIMITATIONS: The high adenoma detection rate in the control group may limit the generalizability of the findings to endoscopists with low detection rates. CONCLUSION: Computer-aided detection did not improve colonoscopic identification of advanced colorectal neoplasias. PRIMARY FUNDING SOURCE: Medtronic.

Factors associated with lesion detection in colonoscopy among different indications.

BACKGROUND AND OBJECTIVE: Different factors may influence colonoscopy performance measures. We aimed to analyze procedure- and endoscopist-related factors associated with detection of colorectal lesions and whether these factors have a similar influence in the context of different colonoscopy indications: positive fecal immunochemical test (+FIT) and post-polypectomy surveillance colonoscopies. METHODS: This multicenter cross-sectional study included adults aged 40-80 years. Endoscopists (N = 96) who had performed ≥50 examinations were assessed for physician-related factors. Adenoma detection rate (ADR), adenomas per colonoscopy rate (APCR), advanced ADR, serrated polyp detection (SDR), and serrated polyps per colonoscopy rate (SPPCR) were calculated. RESULTS: We included 12,932 procedures, with 4810 carried out after a positive FIT and 1967 for surveillance. Of the 96 endoscopists evaluated, 43.8% were women, and the mean age was 41.9 years. The ADR, advanced ADR, and SDR were 39.7%, 17.7%, and 12.8%, respectively. Adenoma detection rate was higher in colonoscopies after a +FIT (50.3%) with a more than doubled advanced ADR compared to non-FIT procedures (27.6% vs. 13.0%) and similar results in serrated lesions (14.7% vs. 13.5%). Among all the detection indicators analyzed, withdrawal time was the only factor independently related to improvement (p < 0.001). Regarding FIT-positive and surveillance procedures, for both indications, withdrawal time was also the only factor associated with a higher detection of adenomas and serrated polyps (p < 0.001). Endoscopist-related factors (i.e., weekly hours dedicated to endoscopy, annual colonoscopy volume and lifetime number of colonoscopies performed) had also impact on lesion detection (APCR, advanced ADR and SPPCR). CONCLUSIONS: Withdrawal time was the factor most commonly associated with improved detection of colonic lesions globally and in endoscopies for + FIT and post-polypectomy surveillance. Physician-related factors may help to address strategies to support training and service provision. Our results can be used for establishing future benchmarking and quality improvement in different colonoscopy indications.

Variation in Colonoscopy Performance Measures According to Procedure Indication.

BACKGROUND & AIMS: Most fulfillment and benchmarking information for colonoscopy quality indicators has been obtained from studies of primary screening colonoscopies. We analyzed differences in the fulfillment of colonoscopy quality indicators based on the indication for endoscopy. METHODS: We performed an observational, multicenter, cross-sectional study of 14,867 patients who underwent endoscopy procedures for gastrointestinal symptoms (40.3%), a positive result from a fecal immunochemical test (36.0%), postpolypectomy surveillance (15.3%), or primary screening (8.4%), from February 2016 through December 2017 at 14 centers in Spain. We evaluated rates of adequate colon cleansing, cecal intubation, adenoma detection, and colorectal cancer detection, among others. We used findings from primary screening colonoscopies as the reference standard. RESULTS: Fewer than 90% of patients had adequate bowel preparation; 83.1% of patients with gastrointestinal symptoms had adequate bowel preparation (odds ratio [OR] compared with patients with primary screening colonoscopies, 0.62; 95% CI, 0.49-0.78) and 85.3% of patients receiving postpolypectomy surveillance had adequate bowel preparation (OR, 0.71; 95% CI, 0.55-0.91). The cecal intubation rate was also lower in patients with gastrointestinal symptoms (93.1%) (OR, 0.34; 95% CI, 0.22-0.52). The adenoma detection rate was higher in patients with a positive result from a fecal immunochemical test (46.4%) (OR, 2.01; 95% CI, 1.71-2.35) and in patients undergoing postpolypectomy surveillance (48.2%) (OR, 1.41; 95% CI, 1.20-1.67). The highest proportion of patients with colorectal cancer was in the gastrointestinal symptom group (5.1%) (OR, 5.24; 95% CI, 2.30-11.93) and the lowest was in patients undergoing surveillance (0.8%) (OR, 0.83; 95% CI, 0.32-2.14). CONCLUSIONS: Fulfillment of colonoscopy performance measures varies substantially by indication. Policies addressing performance measures beyond colonoscopy screening procedures should be developed. Benchmarking recommendations could be adjusted according to colonoscopy indication.