Artificial Intelligence for Real-Time Prediction of the Histology of Colorectal Polyps by General Endoscopists.

BACKGROUND: Real-time prediction of histologic features of small colorectal polyps may prevent resection and/or pathologic evaluation and therefore decrease colonoscopy costs. Previous studies showed that computer-aided diagnosis (CADx) was highly accurate, though it did not outperform expert endoscopists. OBJECTIVE: To assess the diagnostic performance of histologic predictions by general endoscopists before and after assistance from CADx in a real-life setting. DESIGN: Prospective, multicenter, single-group study. (ClinicalTrials.gov: NCT04437615). SETTING: 6 centers across the United States. PARTICIPANTS: 1252 consecutive patients undergoing colonoscopy and 49 general endoscopists with variable experience in real-time prediction of polyp histologic features. INTERVENTION: Real-time use of CADx during routine colonoscopy. MEASUREMENTS: The primary end points were the sensitivity and specificity of CADx-unassisted and CADx-assisted histologic predictions for adenomas measuring 5 mm or less. For clinical purposes, additional estimates according to location and confidence level were provided. RESULTS: The CADx device made a diagnosis for 2695 polyps measuring 5 mm or less (96%) in 1252 patients. There was no difference in sensitivity between the unassisted and assisted groups (90.7% vs. 90.8%; P = 0.52). Specificity was higher in the CADx-assisted group (59.5% vs. 64.7%; P < 0.001). Among all 2695 polyps measuring 5 mm or less, 88.2% and 86.1% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be resected and discarded without pathologic evaluation. Among 743 rectosigmoid polyps measuring 5 mm or less, 49.5% and 47.9% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be left in situ without resection. LIMITATION: Decision making based on CADx might differ outside a clinical trial. CONCLUSION: CADx assistance did not result in increased sensitivity of optical diagnosis. Despite a slight increase, the specificity of CADx-assisted diagnosis remained suboptimal. PRIMARY FUNDING SOURCE: Olympus America Corporation served as the clinical study sponsor.

Effect of an online educational module incorporating real-time feedback on accuracy of polyp sizing in trainees: a randomized controlled trial.

BACKGROUND: Although polyp size dictates surveillance intervals, endoscopists often estimate polyp size inaccurately. We hypothesized that an intervention providing didactic instruction and real-time feedback could significantly improve polyp size classification. METHODS: We conducted a multicenter randomized controlled trial to evaluate the impact of different components of an online educational module on polyp sizing. Participants were randomized to control (no video, no feedback), video only, feedback only, or video + feedback. The primary outcome was accuracy of polyp size classification into clinically relevant categories (diminutive [1-5mm], small [6-9mm], large [≥10mm]). Secondary outcomes included accuracy of exact polyp size (inmm), learning curves, and directionality of inaccuracy (over- vs. underestimation). RESULTS: 36 trainees from five training programs provided 1360 polyp size assessments. The feedback only (80.1%, P=0.01) and video + feedback (78.9%, P=0.02) groups had higher accuracy of polyp size classification compared with controls (71.6%). There was no significant difference in accuracy between the video only group (74.4%) and controls (P=0.42). Groups receiving feedback had higher accuracy of exact polyp size (inmm) and higher peak learning curves. Polyps were more likely to be overestimated than underestimated, and 29.3% of size inaccuracies impacted recommended surveillance intervals. CONCLUSIONS: Our online educational module significantly improved polyp size classification. Real-time feedback appeared to be a critical component in improving accuracy. This scalable and no-cost educational module could significantly decrease under- and overutilization of colonoscopy, improving patient outcomes while increasing colonoscopy access.

The synergistic role of virtual coaching with simulation-based mastery learning for upper endoscopy.

Introduction: Our simulation-based mastery learning (SBML) curriculum, delivered in person, has been shown to successfully train novices in structured esophagogastroduodenoscopy (EGD). SBML with virtual coaching (VC) has the potential to improve the effectiveness and efficiency of endoscopy training and expand access to trainees from around the world. We share our observations conducting an EGD training course using SBML with VC. Methods: We conducted a 1-week virtual SBML course for novice trainees across seven academic centers in the USA and Asia. The cognitive component was delivered using an online learning platform. For technical skills, a virtual coach supervised hands-on training and local coaches provided assistance when needed. At the end of training, an independent rater assessed simulation-based performance using a validated assessment tool. We assessed the clinical performance of 30 EGDs using the ASGE Assessment of Competency in Endoscopy tool. We compared the trainees' scores to our cohort trained using in-person SBML training using non-inferiority t-tests. Results: We enrolled 21 novice trainees (mean age: 30.8 ± 3.6 years; female: 52%). For tip deflection, the trainees reached the minimum passing standard after 31 ± 29 runs and mastery after 52 ± 37 runs. For structured EGD, the average score for the overall exam was 4.6 ± 0.6, similar to the in-person cohort (4.7 ± 0.5, p = 0.49). The knowledge-based assessment was also comparable (virtual coaching: 81.9 ± 0.1; direct coaching: 78.3 ± 0.1; p = 0.385). Over time, our novice trainees reached clinical competence at a similar rate to our historical in-person control. Conclusions: VC appears feasible and effective for training novice gastroenterology trainees. VC allowed us to scale our SBML course, expand access to experts, and administer SBML simultaneously across different sites at the highest standards.

Varied Trainee Competence in Cold Snare Polypectomy: Results of the COMPLETE Randomized Controlled Trial.

INTRODUCTION: Cold snare polypectomy (CSP) is strongly recommended as the optimal technique for the complete removal of small polyps. Though significant variability in polypectomy technique and quality has been established, the learning curve and impact of targeted training on CSP are unknown. Video feedback has shown promise as an effective pedagogy to improve performance among surgical trainees. We aimed to compare CSP performance between trainees who received video-based feedback and those who received conventional apprentice-based concurrent feedback. We hypothesized that video-based feedback would accelerate competence. METHODS: We conducted a single-blinded, randomized controlled trial on competence for CSP of polyps <1 cm, comparing video-based feedback with conventional feedback. We randomly assigned deidentified consecutively recorded CSP videos to blinded raters to assess using the CSP Assessment Tool. We shared cumulative sum learning curves every 25 CSP with each trainee. The video feedback trainees also received biweekly individualized terminal feedback. Control trainees received conventional feedback during colonoscopy. The primary outcome was CSP competence. We also assessed competence across domains and change over polypectomy volume. RESULTS: We enrolled and randomized 22 trainees, 12 to video-based feedback and 10 to conventional feedback, and evaluated 2,339 CSP. The learning curve was long; 2 trainees (16.7%) in the video feedback achieved competence, after a mean of 135 polyps, and no one in the control ( P = 0.481) achieved competence. Overall and in all steps of CSP, a higher percentage of the video feedback group met competence, increasing 3% every 20 CSP ( P = 0.0004). DISCUSSION: Video feedback aided trainees to competence in CSP. However, the learning curve was long. Our findings strongly suggest that current training methods are not sufficient to support trainees to competency by the completion of their fellowship programs. The impact of new training methods, such as simulation-based mastery learning, should be assessed to determine whether such methods can result in achievement of competence at a faster rate; ClinicalTrials.gov : NCT03115008.

Longitudinal outcomes of the endoscopic resection of nonpolypoid dysplastic lesions in patients with inflammatory bowel disease.

BACKGROUND AND AIMS: Patients with inflammatory bowel disease (IBD) are at risk of developing dysplasia. According to the Surveillance for Colorectal Endoscopic Neoplasia Detection and Management in Inflammatory Bowel Disease Patients: International Consensus Recommendations, "After complete removal of endoscopically resectable nonpolypoid dysplastic lesions, surveillance colonoscopy is suggested rather than colectomy." We sought to add data to the literature and hypothesized that the endoscopic resection of nonpolypoid colorectal dysplasia (NP-CRD) is safe and effective. METHODS: We conducted a retrospective study of a large cohort of patients with IBD at 2 medical centers who underwent colonoscopy between 2007 and 2018. Patients with at least 1 nonpolypoid lesion ≥10 mm were identified. We measured the feasibility of endoscopic resection, incidence of local recurrence, incidence of cancer, need for surgery, and frequency of adverse events. RESULTS: We studied 326 patients who underwent a mean ± standard deviation of 3.6 ± 3.0 (range, 1-16) colonoscopies during a total follow-up of 1208 patient-years. In 36 patients, 161 lesions ≥10 mm were identified, 63 of which were nonpolypoid (mean size, 17.8 ± 8.9 mm; range, 10-45 mm) (prevalence, 7.7%). The majority of nonpolypoid lesions (96.8% [61 of 63]) were managed endoscopically. Four lesions (mean index lesion size, 32.5 ±11.0 mm) had small local recurrences that were successfully retreated with endoscopy. There were no severe adverse events related to IBD or colorectal cancer observed in the follow-up period. CONCLUSIONS: In this IBD cohort, surveillance colonoscopy rather than colectomy was found to be safe and effective in patients with NP-CRD after undergoing endoscopic resection. After complete removal of endoscopically resectable NP-CRD, surveillance colonoscopy should be considered a safe and effective first-line strategy rather than colectomy.

Baseline Characteristics and Longitudinal Outcomes of Traditional Serrated Adenomas: A Cohort Study.

BACKGROUND AND AIMS: Traditional serrated adenomas (TSAs) may confer increased risk for colorectal cancer (CRC). Our objective with this study was to examine clinical characteristics and long-term outcomes associated with TSA diagnosis. METHODS: We conducted a retrospective cohort study of U.S. Veterans ≥18 years of age with ≥1 TSA between 1999 and 2018. Baseline characteristics, colonoscopy findings, and diagnosis of incident and fatal CRC were abstracted. Advanced neoplasia was defined by CRC or adenoma with high-grade dysplasia, villous histology, or size ≥1 cm. Follow-up was through CRC diagnosis, death, or end of study (December 31, 2018). RESULTS: A total of 853 Veterans with a baseline TSA were identified; 74% were ≥60 years of age, 96% were men, 14% were Black, and 73% were non-Hispanic White. About 64% were current or former smokers. Over 2044 total person-years at follow-up, there were 11 incident CRC cases and 1 CRC death. Cumulative CRC incidence was 1.34% (95% confidence interval [CI], 0.67%-2.68%), and cumulative CRC death was 0.12% (95% CI, 0.00%-0.35%). Among the subset of 378 TSA patients with ≥1 surveillance colonoscopy, 65.1% had high-risk neoplasia on follow-up. CRC incidence among TSA patients was significantly higher than in a comparison cohort of patients with normal baseline colonoscopy at baseline (hazard ratio, 3.70; 95% CI, 1.63-8.41) and similar to a comparison cohort with baseline conventional advanced adenoma (hazard ratio, 0.86; 95% CI, 0.45-1.64). CONCLUSION: Individuals with TSA have substantial risk for CRC based on their cumulative CRC incidence, as well as significant risk of developing other high-risk neoplasia at follow-up surveillance colonoscopy. These data underscore importance of current recommendations for close colonoscopy surveillance after TSA diagnosis.

Adenoma Detection Rate and Clinical Characteristics Influence Advanced Neoplasia Risk After Colorectal Polypectomy.

BACKGROUND AND AIMS: Postpolypectomy risk stratification for subsequent metachronous advanced neoplasia (MAN) is imprecise and does not account for colonoscopist adenoma detection rate (ADR). Our aim was to assess association of ADR with MAN and create a prediction model for postpolypectomy risk stratification incorporating ADR and other factors. METHODS: We conducted a retrospective cohort study of individuals with baseline polypectomy and subsequent surveillance colonoscopy from 2004 to 2016 within the U.S. Department of Veterans Affairs (VA). Clinical factors, polyp findings, and baseline colonoscopist ADR were considered for the model. Model performance (sensitivity, specificity, and area under the curve) for identifying individuals with MAN was compared with 2020 U.S. Multi-Society Task Force on Colorectal Cancer (USMSTF) surveillance recommendations. RESULTS: A total of 30,897 individuals were randomly assigned 2:1 into independent model training and validation sets. Increasing age, male sex, diabetes, current smoking, adenoma number, polyp location, adenoma ≥10 mm or with tubulovillous/villous features, and decreasing colonoscopist ADR were independently associated with MAN. A range of 1.48- to 1.66-fold increased risk for MAN was observed for ADR in the lowest 3 quintiles (ADR <19.7%-39.3%) vs the highest quintile (ADR >47.0%). When the final model selected based on the training set was applied to the validation set, improved sensitivity and specificity over 2020 USMSTF risk stratification were achieved (P = .001), with an area under the curve of 0.62 (95% confidence interval, 0.60-0.64). CONCLUSIONS: Colonoscopist ADR is associated with MAN. Combining clinical factors and ADR for risk stratification has potential to improve postpolypectomy risk stratification. Improving ADR is likely to improve postpolypectomy outcomes.

Individualized feedback on colonoscopy skills improves group colonoscopy quality in providers with lower adenoma detection rates.

Background and study aims Colonoscopy inspection quality (CIQ) assesses skills (fold examination, cleaning, and luminal distension) during inspection for polyps and correlates with adenoma detection rate (ADR) and serrated detection rate (SDR). We aimed to determine whether providing individualized CIQ feedback with instructional videos improves quality metrics performance. Methods We prospectively studied 16 colonoscopists who already received semiannual benchmarked reports of quality metrics (ADR, SDR, and withdrawal time [WT]). We randomly selected seven colonoscopies/colonoscopist for evaluation. Six gastroenterologists graded CIQ using an established scale. We created instructional videos demonstrating optimal and poor inspection techniques. Colonoscopists received the instructional videos and benchmarked CIQ performance. We compared ADR, SDR, and WT in the 12 months preceding ("baseline") and following CIQ feedback. Colonoscopists were stratified by baseline ADR into lower (≤ 34 %) and higher-performing (> 34 %) groups. Results Baseline ADR was 38.5 % (range 26.8 %-53.8 %) and SDR was 11.2 % (2.8 %-24.3 %). The proportion of colonoscopies performed by lower-performing colonoscopists was unchanged from baseline to post-CIQ feedback. All colonoscopists reviewed their CIQ report cards. Post-feedback, ADR (40.1 % vs 38.5 %, P  = 0.1) and SDR (12.2 % vs. 11.2 %, P  = 0.1) did not significantly improve; WT significantly increased (11.4 vs 12.4 min, P  < 0.01). Among the eight lower-performing colonoscopists, group ADR (31.1 % vs 34.3 %, P  = 0.02) and SDR (7.2 % vs 9.1 %, P  = 0.02) significantly increased post-feedback. In higher-performing colonoscopists, ADR and SDR did not change. Conclusions CIQ feedback modestly improves ADR and SDR among colonoscopists with lower baseline ADR but has no effect on higher-performing colonoscopists. Individualized feedback on colonoscopy skills could be used to improve polyp detection by lower-performing colonoscopists.

Cecal retroflexion is infrequently performed in routine practice and the retroflexed view is of poor quality.

BACKGROUND: As right colon polyps are challenging to detect, a retroflexed view of right colon (RV) may be useful. However, cecal retroflexion (CR) without a RV to the hepatic flexure (HF) is inadequate. We aimed to determine the frequency of CR and quality of the RV in routine practice. METHODS: This prospective observational study performed at an academic medical center assessed colonoscopy inspection technique of endoscopists who had performed ≥ 100 annual screening colonoscopies. We video recorded ≥ 28 screening/surveillance colonoscopies per endoscopist and randomly evaluated 7 videos per endoscopist. Six gastroenterologists blindly reviewed the videos to determine if CR was performed and HF withdrawal time (cecum to HF time, excluding ileal/polypectomy time). RESULTS: Reviewers assessed 119 colonoscopies performed by 17 endoscopists. The median HF withdrawal time was 3 min and 46 s. CR was performed in 31% of colonoscopies. CR frequency varied between endoscopists with 9 never performing CR and 2 performing CR in all colonoscopies. When performed, nearly half (43%) of RVs did not extend to the HF with median RV duration of 16 s (IQR 9-30 s). Three polyps were identified in the RV (polyp detection rate of 8.1%), all identified prior to a forward view. CONCLUSIONS: CR is performed infrequently in routine practice. When CR is performed, the RV is of low quality with a very short inspection duration and insufficient ascending colon examination. Further education is required to educate endoscopists in optimal technique to improve overall colonoscopy quality.

Practice pattern variability among gastroenterologists in colorectal cancer surveillance and management of colorectal dysplasia in inflammatory bowel disease.

OBJECTIVE: There is debate on the best method of colorectal cancer (CRC) surveillance in inflammatory bowel disease (IBD). We aimed to examine how gastroenterologists around the world practice CRC surveillance and manage dysplastic lesions in IBD. METHODS: A 22-question survey was emailed to gastroenterologists from 34 countries. It included questions on resources for, frequency and mode of CRC surveillance, and management of colorectal dysplasia. Fisher's exact test and logistic regression were used to evaluate the differences among respondents in various domains. RESULTS: There were 217 eligible responses, with most gastroenterologists working in public hospitals (76%), and treating >10 patients with IBD weekly (71%). High-definition white light endoscopy (HDWLE) was available in 93.1% of the centers. The preferred mode of surveillance was HDWLE with dye-spray chromoendoscopy and targeted biopsies (41.2%). Fewer than 50% of physicians reported using chromoendoscopy in >50% of cases, citing time as the limiting factor (73.7%). Of these gastroenterologists 63% infrequently (<25% of cases) performed random biopsies during chromoendoscopy. They would attempt endoscopic mucosal resection for polypoid lesions >10 mm (67.2%), including >20 mm lesions with low grade dysplasia (49.8%), and non-polypoid lesions >10 mm without dysplasia (56.9%). For non-polypoid lesions >20 mm with low- and high-grade dysplasia, referral to expert endoscopists was the preferred option. CONCLUSION: The preferred method of CRC surveillance was HDWLE with chromoendoscopy and targeted biopsies. Random biopsies were infrequently performed. The uptake of chromoendoscopy for surveillance in practice was low. Physicians varied in their approach in removing endoscopically resectable dysplastic lesions.

Adenoma Detection Rate (ADR) Irrespective of Indication Is Comparable to Screening ADR: Implications for Quality Monitoring.

BACKGROUND & AIMS: Adenoma detection rate (ADR) is a key measure of colonoscopy quality. However, efficient measurement of ADR can be challenging because many colonoscopies are performed for non-screening purposes. Measuring ADR without being restricted to screening indication may likely facilitate more widespread implementation of quality monitoring. We hypothesized that the ADR for all colonoscopies, irrespective of the indication, would be equivalent to the ADR for screening colonoscopies. METHODS: We reviewed consecutive colonoscopies at two Veterans Affairs centers performed by 21 endoscopists over 6 months in 2015. We calculated the ADR for screening exams, non-screening (surveillance and diagnostic) exams, and all exams (irrespective of indication), correcting for within-endoscopist correlation. We then performed simulation modeling to calculate the ADRs under 16 hypothetical scenarios of various indication distributions. We simulated 100,000 trials with 3,000 participants, randomly assigned indication (screening, surveillance, diagnostic, and FIT+) from a multinomial distribution, randomly drew adenoma using the observed ADRs per indication, and calculated 95% confidence intervals of the mean differences in ADR of screening and non-screening indications. RESULTS: Among 2628 colonoscopies performed by 21 gastroenterologists, the indication was screening in 28.9%, surveillance in 48.2% and diagnostic in 22.9%. There was no significant difference in the ADR, 50% (95%CI: 45-56%) for all colonoscopies vs 49% (95%CI: 43-56%) for screening exams (p=.55). ADRs were 56% for surveillance and 38% for diagnostic exams. In our simulation modeling, only one out of 16 scenarios (screening 10%, surveillance 70%, diagnostic 10% and FIT+ 10%) resulted in a significant difference between the calculated ADRs for screening and non-screening indications. CONCLUSIONS: In our study, the overall ADR computed from all colonoscopies was not significantly different than the conventional ADR based on screening colonoscopies. Assessing ADR for colonoscopy irrespective of indication may be adequate for quality monitoring, and could facilitate the implementation of quality measurement and reporting. Future prospective studies should evaluate the validity of using overall ADR for quality reporting in other jurisdictions before adopting this method in clinical practice.

Simplifying Measurement of Adenoma Detection Rates for Colonoscopy.

BACKGROUND: Adenoma detection rate (ADR) is the colonoscopy quality metric with the strongest association to interval or "missed" cancer. Accurate measurement of ADR can be laborious and costly. AIMS: Our aim was to determine if administrative procedure codes for colonoscopy and text searches of pathology results for adenoma mentions could estimate ADR. METHODS: We identified US Veterans with a colonoscopy using Current Procedure Terminology (CPT) codes between January 2013 and December 2016 at ten Veterans Affairs sites. We applied simple text searches using Microsoft SQL Server full-text searches to query all pathology notes for "adenoma(s)" or "adenomatous" text mentions to calculate ADRs. To validate our identification of colonoscopy procedures, endoscopists of record, and adenoma detection from the electronic health record, we manually reviewed a random sample of 2000 procedure and pathology notes from the 10 sites. RESULTS: Structured data fields were accurate in identification of colonoscopies being performed (PPV = 0.99; 95% CI 0.99-1.00) and identifying the endoscopist of record (PPV of 0.95; 95% CI 0.94-0.96) for ADR measurement. Simple text searches of pathology notes for adenoma mentions had excellent performance statistics as follows: sensitivity 0.99 (95% CI 0.98-1.00), specificity 0.93 (95% CI 0.92-0.95), NPV 0.99 (95% CI 0.98-1.00), and PPV 0.93 (0.91-0.94) for measurement of ADR. There was no clinically significant difference in the estimates of overall ADR vs. screening ADR (p > 0.05). CONCLUSIONS: Measuring ADR using administrative codes and text searches from pathology results is an efficient method to broadly survey colonoscopy quality.