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.

Herbal remedies in gastroenterology.

Complementary and alternative medicine (CAM) is presently not considered to be part of conventional medicine. Nevertheless, an estimated 51% of patients with gastrointestinal disorders have tried some from of CAM. Indeed, 10% of alternative medicines are being used for digestive symptoms. After prayer or spiritual healing, herbal medicine is the second most common CAM therapy. While herbal products make numerous health-related claims, those that have been systematically evaluated are unfortunately few. The modern gastroenterologist must be up to date with the regulations, side effects, and possible benefits of specific herbal products used in patients with gastrointestinal disorders.

Portal hypertensive bleeding.

Portal hypertension bleeding is a common and serious complication of cirrhosis. All patients with cirrhosis should undergo endoscopy and be evaluated for possible causes of current or future portal hypertensive bleeding. Possible causes of bleeding include esophageal varices, gastric varices, and PHG. Patients with esophageal varices at high risk of bleeding should be treated with nonselective beta-blockers for primary prevention of variceal hemorrhage. HVPG measurements represent the optimal way to monitor the success of pharmacologic therapy. EVL may be used in those with high-risk varices who do not tolerate beta-blockers. When active bleeding develops, simultaneous and coordinated attention must be given to hemodynamic resuscitation, prevention and treatment of complications, and active control of bleeding. In cases of acute esophageal variceal (Fig. 5) and PHG bleeding, terlipressin, somatostatin, or octreotide should be started. Endoscopic treatment is provided for those with bleeding esophageal varices. If first-line therapy fails, TIPS or surgery may need to be performed. Unlike esophageal variceal or PHG bleeding, there is no established optimal treatment for gastric variceal bleeding. Individual and specific treatment modalities for acute gastric variceal bleeding must be calculated carefully after considering side effects.