AGA Clinical Practice Update on the Role of Artificial Intelligence in Colon Polyp Diagnosis and Management: Commentary

DESCRIPTION

The purpose of this American Gastroenterological Association (AGA) Institute Clinical Practice Update (CPU) is to review the available evidence and provide expert commentary on the current landscape of artificial intelligence in the evaluation and management of colorectal polyps.

METHODS

This CPU was commissioned and approved by the AGA Institute Clinical Practice Updates Committee (CPUC) and the AGA Governing Board to provide timely guidance on a topic of high clinical importance to the AGA membership and underwent internal peer review by the CPUC and external peer review through standard procedures of Gastroenterology. This Expert Commentary incorporates important as well as recently published studies in this field, and it reflects the experiences of the authors who are experienced endoscopists with expertise in the field of artificial intelligence and colorectal polyps.

Patients Prescribed Direct-Acting Oral Anticoagulants Have Low Risk of Postpolypectomy Complications

BACKGROUND & AIMS

Use of direct-acting oral anticoagulants (DOACs) is increasing, but little is known about the associated risks in patients undergoing colonoscopy with polypectomy. We aimed to determine the risk of post-polypectomy complications in patients prescribed DOACs.

METHODS

We performed a retrospective analysis using Optum's de-identified Clinformatics Data Mart Database (2003-2016) (a de-identified administrative database from a large national insurance provider) to identify adults who underwent colonoscopy with polypectomy or endoscopic mucosal resection (EMR) from January 1, 2011, through December 31, 2015. We collected data from 11,504 patients prescribed antithrombotic agents (1590 DOAC, 3471 warfarin, and 6443 clopidogrel) and 599,983 patients not prescribed antithrombotics of interest (controls). We compared 30-day post-polypectomy complications, including gastrointestinal bleeding (GIB), cerebrovascular accident (CVA), myocardial infarction (MI), and hospital admissions, of patients prescribed DOACs, warfarin, or clopidogrel vs controls.

RESULTS

Post-polypectomy complications were uncommon but occurred in a significantly higher proportion of patients receiving any antithrombotic vs controls (P < .001). The percentage of patients in the DOAC group with GIB was 0.63% (95% CI, 0.3%-1.2%) vs 0.2% (95% CI, 0.2%-0.3%) in controls. The percentage of patients with CVA in the DOAC group was 0.06% (95% CI, 0.01%-0.35%) vs 0.04% (95% CI, 0.04%-0.05%) in controls. After we adjusted for bridge anticoagulation, EMR, Charlson comorbidity index (CCI), and CHADS2 (congestive heart failure, hypertension, age over 75, diabetes, stroke [double weight]) score, patients prescribed DOACs no longer had a statistically significant increase in the odds of GIB (odds ratio [OR], 0.90; 95% CI, 0.44-1.85), CVA (OR, 0.45; 95% CI, 0.06-3.28), MI (OR, 1.07; 95% CI, 0.14-7.72), or hospital admission (OR, 0.86; 95% CI, 0.64-1.16). Clopidogrel, warfarin, bridge anticoagulation, higher CHADS2, CCI, and EMR were associated with increased odds of complications.

CONCLUSION

In our retrospective analysis of a large national dataset, we found that patients prescribed DOACs did not have significantly increased adjusted odds of post-polypectomy GIB, MI, CVA, or hospital admission. Bridge anticoagulation, higher CHADS2 score, CCI, and EMR were risk factors for GIB, MI, CVA, and hospital admissions. Studies are needed to determine the optimal peri-procedural dose for high-risk patients.

AGA White Paper: Training and Implementation of Endoscopic Image Enhancement Technologies

Endoscopic image-enhancement technologies provide opportunities to visualize normal and abnormal tissues within the gastrointestinal (GI) tract in a manner that complements conventional white light endoscopic imaging. The additional information that is obtained enables the endoscopist to better identify, delineate, and characterize lesions and can facilitate targeted biopsies or, in some cases, eliminate the need to send samples for histologic analysis. Some of these technologies have been available for more than a decade, but despite this fact, there is limited use of these technologies by endoscopists. Lack of formalized training in their use and a scarcity of guidelines on implementation of these technologies into clinical practice are contributing factors. In November 2014, the American Gastroenterological Association's Center for GI Innovation and Technology conducted a 2-day workshop to discuss endoscopic image-enhancement technologies. This article represents the third of 3 separate documents generated from the workshop and discusses the published literature pertaining to training and outlines a proposed framework for the implementation of endoscopic image-enhancement technologies in clinical practice. There was general agreement among participants in the workshop on several key considerations. Training and competency assessment for endoscopic image-enhancement technologies should incorporate competency-based education paradigms. To facilitate successful training, multiple different educational models that can cater to variations in learning styles need to be developed, including classroom-style and self-directed programs, in-person and web-based options, image and video atlases, and endoscopic simulator programs. To ensure safe and appropriate use of these technologies over time, refresher courses, skill maintenance programs, and options for competency reassessment should be established. Participants also generally agreed that although early adopters of novel endoscopic image-enhancement modalities can successfully implement these technologies by pursuing training and ensuring self-competency, widespread implementation is likely to require support from GI societies and buy-in from other key stakeholders including payors/purchasers and patients. Continued work by manufacturers and the GI societies in providing training programs and patient education, working with payors and purchasers, and creating environments and policies that motivate endoscopists to adopt new practices is essential in creating widespread implementation.

Real-Time Characterization of Diminutive Colorectal Polyp Histology Using Narrow-Band Imaging: Implications for the Resect and Discard Strategy

BACKGROUND & AIMS

Narrow-band imaging (NBI) allows real-time histologic classification of colorectal polyps. We investigated whether endoscopists without prior training in NBI can achieve the following thresholds recommended by the American Society for Gastrointestinal Endoscopy: for diminutive colorectal polyps characterized with high confidence, a ≥90% negative predictive value for adenomas in the rectosigmoid and a ≥90% agreement in surveillance intervals.

METHODS

Twenty-six endoscopists from 2 tertiary care centers underwent standardized training in NBI interpretation. Endoscopists made real-time predictions of diminutive colorectal polyp histology and surveillance interval predictions based on NBI. Their performance was evaluated by comparing predicted with actual findings from histologic analysis. Multilevel logistic regression was used to assess predictors of performance. Cumulative summation analysis was used to characterize learning curves.

RESULTS

The endoscopists performed 1451 colonoscopies and made 3012 diminutive polyp predictions (74.3% high confidence) using NBI. They made 898 immediate post-procedure surveillance interval predictions. An additional 505 surveillance intervals were determined with histology input. The overall negative predictive value for high-confidence characterizations in the rectosigmoid was 94.7% (95% confidence interval: 92.6%-96.8%) and the surveillance interval agreement was 91.2% (95% confidence interval: 89.7%-92.7%). Overall, 97.0% of surveillance interval predictions would have brought patients back on time or early. High-confidence characterization was the strongest predictor of accuracy (odds ratio = 3.42; 95% confidence interval: 2.72-4.29; P < .001). Performance improved over time, however, according to cumulative summation analysis, only 7 participants (26.9%) identified adenomas with sufficient sensitivity such that further auditing is not required.

CONCLUSIONS

With standardized training, gastroenterologists without prior expertise in NBI were able to meet the negative predictive value and surveillance interval thresholds set forth by the American Society for Gastrointestinal Endoscopy. The majority of disagreement in surveillance interval brought patients back early. Performance improves with time, but most endoscopists will require ongoing auditing of performance. ClinicalTrials.gov ID NCT02441998.

Association of endotoxins and colon polyp: a case-control study

Endotoxins are known to be associated with the occurrence of various chronic diseases. This study was conducted to investigate the role of endotoxins in the pathogenesis of colon polyps through a case-control study. A total of 145 subjects (74 subjects in the polyp group and 71 subjects in the control group) had undergone a colonoscopy. Age, body mass index (BMI) and endotoxin levels were found to be significantly higher in the polyp group than in the control group. The endotoxin level was still significantly higher in the polyp group than in the control group, even after age and BMI had been adjusted (polyp group 0.108 ± 0.007 EU/mL, control group 0.049 ± 0.008 EU/mL, P < 0.001). In subgroup analysis, the endotoxin level significantly increased in accordance with the number of colon polyps (one-polyp group, 0.088 ± 0.059 EU/mL; two-polyp group, 0.097 ± 0.071 EU/mL; three-or-more-polyp group, 0.149 ± 0.223 EU/mL). The endotoxin levels also significantly increased in groups with tubular adenoma with high-grade dysplasia (hyperplastic polyp group, 0.109 ± 0.121 EU/mL; tubular adenoma with low grade dysplasia group, 0.103 ± 0.059 EU/mL; tubular adenoma with high grade dysplasia group, 2.915 ± 0.072 EU/mL). In conclusion, the serum level of endotoxins is quantitatively correlated with colon polyps.

Clinical significance of colonic diverticulosis associated with bowel symptoms and colon polyp

This study was done to evaluate prospectively the clinical significance of colonic diverticulosis. In the 1,030 consecutive outpatients undergoing colonoscopy, the information on the demographics, the patterns of bowel symptoms, and the prevalence of colon polyp were analyzed according to the presence of colonic diverticulosis. The mean age of 1,030 patients were 52.2 yr and 59.3% were male. The prevalence of diverticulosis was 19.7% (203/1,030). Of 203 diverticulosis patients 85.2% were in proximal group, 5.4% in distal group and 9.4% in both group. Six (3.0%) patients were found to have diverticulitis. Multivariate logistic regression analysis showed that an old age, diabetes and the presence of polyp were significant factors associated with proximal or both diverticulosis. A significant difference was demonstrated between the patients of distal diverticular group and the controls for the symptom frequency scores within the previous 4 weeks. The items, which showed difference, were hard stool, urgency, flatus, chest discomfort and frequent urination. In conclusion, old age, diabetes and the presence of colon polyp were associated with proximal diverticulosis. The temporal symptoms were more frequent in distal diverticulosis than in proximal diverticulosis in the study subjects.