Clinical consequences of computer-aided colorectal polyp detection.

BACKGROUND AND AIM: Randomised trials show improved polyp detection with computer-aided detection (CADe), mostly of small lesions. However, operator and selection bias may affect CADe's true benefit. Clinical outcomes of increased detection have not yet been fully elucidated. METHODS: In this multicentre trial, CADe combining convolutional and recurrent neural networks was used for polyp detection. Blinded endoscopists were monitored in real time by a second observer with CADe access. CADe detections prompted reinspection. Adenoma detection rates (ADR) and polyp detection rates were measured prestudy and poststudy. Histological assessments were done by independent histopathologists. The primary outcome compared polyp detection between endoscopists and CADe. RESULTS: In 946 patients (51.9% male, mean age 64), a total of 2141 polyps were identified, including 989 adenomas. CADe was not superior to human polyp detection (sensitivity 94.6% vs 96.0%) but outperformed them when restricted to adenomas. Unblinding led to an additional yield of 86 true positive polyp detections (1.1% ADR increase per patient; 73.8% were <5 mm). CADe also increased non-neoplastic polyp detection by an absolute value of 4.9% of the cases (1.8% increase of entire polyp load). Procedure time increased with 6.6±6.5 min (+42.6%). In 22/946 patients, the additional detection of adenomas changed surveillance intervals (2.3%), mostly by increasing the number of small adenomas beyond the cut-off. CONCLUSION: Even if CADe appears to be slightly more sensitive than human endoscopists, the additional gain in ADR was minimal and follow-up intervals rarely changed. Additional inspection of non-neoplastic lesions was increased, adding to the inspection and/or polypectomy workload.

Botulinum toxin reduces Dysphagia in patients with nonachalasia primary esophageal motility disorders.

BACKGROUND & AIMS: Endoscopic injection of botulinum toxin (BTX) has shown benefits for patients with diffuse esophageal spasm (DES) and nutcracker esophagus (NE) in small uncontrolled trials. We investigated the effect of BTX on symptoms of patients with DES or NE and assessed manometry findings in a prospective, double-blind, randomized, controlled study. METHODS: We assessed 22 patients with dysphagia-predominant, manometry-confirmed DES or NE (6 men; age, 63 ± 2 y) at a tertiary care medical center. Patients were given injections of BTX (8 × 12.5 U) or saline (8 × 0.5 mL) in 4 quadrants, at 2 and 7 cm above the esophagogastric junction. After 1 month, patients crossed over between groups and received endoscopic injections of BTX or saline. When the study began and 4 weeks after each injection, the patients were assessed by esophageal manometry and completed a symptom questionnaire (to determine solid and liquid dysphagia, chest pain, and regurgitation and heartburn; all scored 0-4). Responders were defined based on modified Vantrappen criteria for achalasia. RESULTS: After BTX injections, patients had significant decreases in total symptom scores (sum of solid and liquid dysphagia and chest pain; from 7.6 ± 0.7 to 4.8 ± 0.8; P = .01); this decrease was not observed in patients who received saline injections. Moreover, BTX injection stabilized unintentional weight loss (weight gain of 0.3 ± 0.3 after BTX injection vs further weight loss of 1.6 ± 0.5 kg after saline injection; P = .01). Fifty percent of patients had a response 1 month after BTX injection, compared with 10% after saline injection (P = .04); 30% still had a response 1 year after BTX injection. BTX injection also caused a significant decrease in the mean esophagogastric junction pressure, compared with baseline (15.8 ± 1.7 vs 24.0 ± 2.8 mm Hg; P = .02). CONCLUSIONS: In a prospective controlled study of patients with DES and NE, injections of BTX reduced symptoms and stabilized unintentional weight loss. TRIAL REGISTRY: http://www.targid.eu, ML2669, ML6294.

Pathophysiology, diagnosis and management of postoperative dumping syndrome.

Dumping syndrome is a frequent complication of esophageal, gastric or bariatric surgery. Rapid gastric emptying, with the delivery to the small intestine of a significant proportion of solid food as large particles that are difficult to digest, is a key event in the pathogenesis of this syndrome. This occurrence causes a shift of fluid from the intravascular component to the intestinal lumen, which results in cardiovascular symptoms, release of several gastrointestinal and pancreatic hormones and late postprandial hypoglycemia. Early dumping symptoms comprise both gastrointestinal and vasomotor symptoms. Late dumping symptoms are the result of reactive hypoglycemia. Besides the assessment of clinical alertness and endoscopic or radiological imaging, a modified oral glucose tolerance test might help to establish a diagnosis. The first step in treating dumping syndrome is the introduction of dietary measures. Acarbose can be added to these measures for patients with hypoglycemia, whereas several studies advocate guar gum or pectin to slow gastric emptying. Somatostatin analogs are the most effective medical therapy for dumping syndrome, and a slow-release preparation is the treatment of choice. In patients with treatment-refractory dumping syndrome, surgical reintervention or continuous enteral feeding can be considered, but the outcomes of such approaches are variable.