Objective The use of endoscopic submucosal dissection (ESD) is gradually expanding for treatment of neoplasia in Barrett’s esophagus (BE). We aimed to report outcomes of all ESDs for BE neoplasia performed inNL. Design We retrospectively assessed ESD outcomes in NL, where treatment for BE neoplasia is centralized in 9 expert centers with jointly trained endoscopists and pathologists, and treatment/follow-up data collected in a joint database. ESD is restricted for selected cases. Results During median 121 minutes (p25-p75 90-180), 130 complete ESDs were performed with 97% (126/130) removed en-bloc. Pathology was HGD (5%), T1a-EAC (43%) or T1b-EAC (52%; 19%sm1, 33%≥sm2). The combined en-bloc and R0 rate was 87% [95%-CI 77-94%] for HGD/T1a-EAC and 49% [37-62%] for T1b-EAC. Upon R1 resection, 29% had residual cancer, in all cases detected at first follow-up endoscopy, while the remaining 71% had no residual cancer in esophagectomy specimen (n=6) or during median 9 months endoscopic FU (p25-p75 4-22) (n=18). Upon R0 resection, local recurrence rate during median 17 months (8-30) was 0% [0-5%]. Adverse events: 1% perforation [0-4%], 3% post-procedural bleeding [1-7%], 13% strictures [8-20%]. Conclusion In expert hands, ESD is safe and allows for removal of bulky intraluminal neoplasia and submucosal cancer. ESD of the latter is, however, associated with a positive deep resection margin in half of the patients, yet only one third had actual persisting neoplasia at endoscopic FU. To better stratify R1-patients with an indication for additional surgery, repeat endoscopy after healing of the ESD wound may help in predicting residual cancer.

Colorectal cancer (CRC) screening with colonoscopy is commonly used in patients who are candidates for liver transplantation. We initiated this study to define the risk‐benefit ratio of performing screening colonoscopy in this population. A retrospective observational study of all consecutive patients undergoing colonoscopy during pre–liver transplantation screening between 2004 and 2017 was conducted. Endoscopic and pathological findings and clinical events potentially related to the colonoscopy in the 30 days after the procedure were registered and compared with a 30‐day inpatient control time frame. A total of 858 colonoscopies were performed in 808 patients (65% male; median age, 55 years [interquartile range (IQR), 47‐62]; median model for end‐stage liver disease (MELD) score, 15 [IQR, 11‐18]). CRC was found in 2 patients (0.2%), and advanced adenomas were found in 44 patients (5.4%). The only independent risk factor for an advanced neoplasm was age (odds ratio, 1.072 per year; 95% confidence interval, 1.031‐1.115; P < 0.001). During the 30‐day postprocedure period, 178 clinical events occurred in 128 patients compared with 101 clinical events in 72 patients in the control time frames ( P < 0.001). After colonoscopy, there was a significantly increased risk for renal failure ( P = 0.001) and gastrointestinal (GI) bleeding ( P = 0.023). Presence of ascites and MELD score were identified as independent risk factors for acute renal failure and GI bleeding. During the study observation period, 53.5% of the screened population actually underwent liver transplantation. Conclusion : CRC screening in pre–liver transplantation patients is associated with a relatively low prevalence of CRC and an increased risk of postcolonoscopy complications such as acute renal failure and GI bleeding, especially in patients with advanced liver disease. Because the risk‐benefit ratio of standard performance of a screening colonoscopy in this population appears questionable, alternative screening strategies should be considered.

<b><i>Background:</i></b> Over the past decade, several artificial intelligence (AI) systems are developed to assist in endoscopic assessment of (pre-)cancerous lesions of the gastrointestinal (GI) tract. In this review, we aimed to provide an overview of the possible indications of AI technology in upper GI endoscopy and hypothesize about potential challenges for its use in clinical practice. <b><i>Summary:</i></b> Application of AI in upper GI endoscopy has been investigated for several indications: (1) detection, characterization, and delineation of esophageal and gastric cancer (GC) and their premalignant conditions; (2) prediction of tumor invasion; and (3) detection of <i>Helicobacter pylori</i>. AI systems show promising results with an accuracy of up to 99% for the detection of superficial and advanced upper GI cancers. AI outperformed trainee and experienced endoscopists for the detection of esophageal lesions and atrophic gastritis. For GC, AI outperformed mid-level and trainee endoscopists but not expert endoscopists. <b><i>Key Messages:</i></b> Application of artificial intelligence (AI) in upper gastrointestinal endoscopy may improve early diagnosis of esophageal and gastric cancer and may enable endoscopists to better identify patients eligible for endoscopic resection. The benefit of AI on the quality of upper endoscopy still needs to be demonstrated, while prospective trials are needed to confirm accuracy and feasibility during real-time daily endoscopy.

Background During endoscopic submucosal dissection (ESD), normal mucosa is cut under constant optical control. We studied whether a positive horizontal resection margin after a complete en bloc ESD predicts local recurrence. Methods In this European multicenter cohort study, patients with a complete en bloc colorectal ESD were selected from prospective registries. Cases were defined by a horizontal resection margin positive or indeterminate for dysplasia (HM1), whereas controls had a free resection margin (HM0). Low-risk lesions with submucosal invasion (T1) and margins free of carcinoma were analysed seperately. The main outcome was local recurrence. Results From 928 consecutive ESDs (2011-2020), 354 patients (40% female, mean age 67 years, median follow-up 23.6 months) were included concerning 308 non-invasive lesions and 46 T1 lesions. Recurrence rate for non-invasive lesions was 1/212 (0.5%; 95%CI 0.02-2.6%) for HM0 vs. 2/96 (2.1%; 95%CI 0.57-7.3%) for HM1. Recurrence rate for T1 was 1/38 (2.6%; 95%CI 0.14-13.5%) for HM0 vs. 2/8 (25%; 95%CI 7.2-59%) for HM1. Conclusion A positive horizontal resection margin after an en bloc ESD for non-invasive lesions is associated with a marginal non-significant increase of the local recurrence rate, equal to an ESD with clear horizontal margins. This could not be confirmed for T1 lesions.