Background and aims Artificial intelligence has been shown to increase adenoma detection rate (ADR) as the main surrogate outcome parameter of colonoscopy quality. To which extent this effect may be related to physician experience is not known. We performed a randomised trial with colonoscopists in their qualification period (AID-2) and compared these data with a previously published randomised trial in expert endoscopists (AID-1). Methods In this prospective, randomised controlled non-inferiority trial (AID-2), 10 non-expert endoscopists (<2000 colonoscopies) performed screening/surveillance/diagnostic colonoscopies in consecutive 40–80 year-old subjects using high-definition colonoscopy with or without a real-time deep-learning computer-aided detection (CADe) (GI Genius, Medtronic). The primary outcome was ADR in both groups with histology of resected lesions as reference. In a post-hoc analysis, data from this randomised controlled trial (RCT) were compared with data from the previous AID-1 RCT involving six experienced endoscopists in an otherwise similar setting. Results In 660 patients (62.3±10 years; men/women: 330/330) with equal distribution of study parameters, overall ADR was higher in the CADe than in the control group (53.3% vs 44.5%; relative risk (RR): 1.22; 95% CI: 1.04 to 1.40; p<0.01 for non-inferiority and p=0.02 for superiority). Similar increases were seen in adenoma numbers per colonoscopy and in small and distal lesions. No differences were observed with regards to detection of non-neoplastic lesions. When pooling these data with those from the AID-1 study, use of CADe (RR 1.29; 95% CI: 1.16 to 1.42) and colonoscopy indication, but not the level of examiner experience (RR 1.02; 95% CI: 0.89 to 1.16) were associated with ADR differences in a multivariate analysis. Conclusions In less experienced examiners, CADe assistance during colonoscopy increased ADR and a number of related polyp parameters as compared with the control group. Experience appears to play a minor role as determining factor for ADR. Trial registration number NCT:04260321.

Artificial intelligence computer-aided detection (CADe) of colorectal neoplasia during colonoscopy may increase adenoma detection rates (ADRs) and reduce adenoma miss rates, but it may increase overdiagnosis and overtreatment of nonneoplastic polyps. To quantify the benefits and harms of CADe in randomized trials. Systematic review and meta-analysis. (PROSPERO: CRD42022293181). Medline, Embase, and Scopus databases through February 2023. Randomized trials comparing CADe-assisted with standard colonoscopy for polyp and cancer detection. Adenoma detection rate (proportion of patients with ≥1 adenoma), number of adenomas detected per colonoscopy, advanced adenoma (≥10 mm with high-grade dysplasia and villous histology), number of serrated lesions per colonoscopy, and adenoma miss rate were extracted as benefit outcomes. Number of polypectomies for nonneoplastic lesions and withdrawal time were extracted as harm outcomes. For each outcome, studies were pooled using a random-effects model. Certainty of evidence was assessed using the GRADE (Grading of Recommendations Assessment, Development and Evaluation) framework. Twenty-one randomized trials on 18 232 patients were included. The ADR was higher in the CADe group than in the standard colonoscopy group (44.0% vs. 35.9%; relative risk, 1.24 [95% CI, 1.16 to 1.33]; low-certainty evidence), corresponding to a 55% (risk ratio, 0.45 [CI, 0.35 to 0.58]) relative reduction in miss rate (moderate-certainty evidence). More nonneoplastic polyps were removed in the CADe than the standard group (0.52 vs. 0.34 per colonoscopy; mean difference [MD], 0.18 polypectomy [CI, 0.11 to 0.26 polypectomy]; low-certainty evidence). Mean inspection time increased only marginally with CADe (MD, 0.47 minute [CI, 0.23 to 0.72 minute]; moderate-certainty evidence). This review focused on surrogates of patient-important outcomes. Most patients, however, may consider cancer incidence and cancer-related mortality important outcomes. The effect of CADe on such patient-important outcomes remains unclear. The use of CADe for polyp detection during colonoscopy results in increased detection of adenomas but not advanced adenomas and in higher rates of unnecessary removal of nonneoplastic polyps. European Commission Horizon 2020 Marie Skłodowska-Curie Individual Fellowship.

Background Endoscopic ultrasound (EUS)-guided biliary drainage is becoming an option for palliation of malignant biliary obstruction. Lumen-apposing metal stents (LAMS) are replacing self-expandable metal stents (SEMS). The aim of this meta-analysis was to evaluate the efficacy and safety of LAMS and SEMS for EUS-guided choledochoduodenostomy (EUS-CDS). Methods A meta-analysis was performed using PRISMA protocols. Electronic databases were searched for studies on EUS-CDS. The primary outcome was clinical success. Secondary outcomes were technical success, reintervention, and adverse events. We used the random effects model with the DerSimonian–Laird estimation, and the results were depicted using forest plots. Subgroup analyses were also performed with data stratified by selected variable. Results Overall, 31 studies (820 patients) were included. The pooled rates of clinical and technical success were 93.6 % (95 % confidence interval [CI] 88.6 %–96.5 %) and 94.8 % (95 %CI 90.2 %–97.3 %) for LAMS, and 91.7 % (95 %CI 88.1 %–94.2 %) and 92.7 % (95 %CI 89.9 %–94.9 %) for SEMS, respectively. The pooled rates of adverse events were 17.1 % (95 %CI 12.5 %–22.8 %) for LAMS and 18.3 % (95 %CI 14.3 %–23.0 %) for SEMS. The pooled rates of reintervention were 10.9 % (95 %CI 7.7 %–15.3 %) for LAMS and 13.9 % (95 %CI 9.6 %–19.7 %) for SEMS. Subgroup analyses confirmed these results. Conclusions This meta-analysis showed that LAMS and SEMS are comparable in terms of efficacy for EUS-CDS. Clinical and technical success, post-procedure adverse events, and reintervention rates were similar between LAMS and SEMS use; however, adverse events require further investigation.

Background Endoscopic ultrasound-guided hepaticogastrostomy (EUS-HGS) is a valid option for EUS-guided biliary drainage that has been increasingly used in the last decade. The aims of this study were to provide a systematic review with meta-analysis and meta-regression of the features and outcomes of this procedure. Methods The MEDLINE, Scopus, Web of Science, and Cochrane databases were searched for literature pertinent to EUS-HGS. Meta-analysis of the proportions and meta-regression of potential modifiers of the main outcome measures were applied. The main outcome was technical success; secondary outcomes were clinical success and procedure-related adverse events (AEs). Results 33 studies, including 1644 patients, were included in the meta-analysis. Malignant biliary obstruction (MBO) was the underlying cause in almost all cases (99.6%); the main indications for EUS-HGS were duodenal/papillary invasion (34.8%), surgically altered anatomy (18.4%), and hilar stenosis (16.0%). The pooled technical success of EUS-HGS was 97.7% (95%CI 96.1%–99.0%; I 2 = 0%), the intention-to-treat clinical success rate was 88.1% (95%CI 84.7%–91.2%; I 2 = 33.9%), and procedure-related AEs occurred in 12.0% (95%CI 9.8%–14.5%; I 2 = 20.4%), with cholangitis/sepsis (2.8%) and bleeding (2.3%) the most frequent. The rate of procedure-related AEs was lower with the use of dedicated stents on univariable meta-regression analysis. Meta-regression showed that technical success and clinical success rates were modified by the centers’ experience (>4/year). Conclusions EUS-HGS represents an effective and safe procedure for EUS-guided biliary drainage in patients with MBO. Future studies should address the impact of center experience, patient selection, and the use of dedicated stents to improve performance of this technique.