Search

The peroral endoscopic myotomy (POEM) procedure, as described over 10 years ago, is a submucosal endoscopy procedure that allows access to the muscle layers throughout the gastrointestinal (GI) tract. With this access, and ability to cut the muscle fibers, POEM can be performed not only for motility disorders but for structural pathology as well, such as Zenker diverticulum. Regardless of the location, there are 4 steps to the procedure: mucosotomy, submucosal tunneling, myotomy, and mucostomy closure. This review outlines these key components as well as variations in techniques for POEM throughout the GI tract.

This ESGE Position Statement defines the expected value of artificial intelligence (AI) for the diagnosis and management of gastrointestinal neoplasia within the framework of the performance measures already defined by ESGE. This is based on the clinical relevance of the expected task and the preliminary evidence regarding artificial intelligence in artificial or clinical settings. Main recommendations: (1) For acceptance of AI in assessment of completeness of upper GI endoscopy, the adequate level of mucosal inspection with AI should be comparable to that assessed by experienced endoscopists. (2) For acceptance of AI in assessment of completeness of upper GI endoscopy, automated recognition and photodocumentation of relevant anatomical landmarks should be obtained in ≥90% of the procedures. (3) For acceptance of AI in the detection of Barrett’s high grade intraepithelial neoplasia or cancer, the AI-assisted detection rate for suspicious lesions for targeted biopsies should be comparable to that of experienced endoscopists with or without advanced imaging techniques. (4) For acceptance of AI in the management of Barrett’s neoplasia, AI-assisted selection of lesions amenable to endoscopic resection should be comparable to that of experienced endoscopists. (5) For acceptance of AI in the diagnosis of gastric precancerous conditions, AI-assisted diagnosis of atrophy and intestinal metaplasia should be comparable to that provided by the established biopsy protocol, including the estimation of extent, and consequent allocation to the correct endoscopic surveillance interval. (6) For acceptance of artificial intelligence for automated lesion detection in small-bowel capsule endoscopy (SBCE), the performance of AI-assisted reading should be comparable to that of experienced endoscopists for lesion detection, without increasing but possibly reducing the reading time of the operator. (7) For acceptance of AI in the detection of colorectal polyps, the AI-assisted adenoma detection rate should be comparable to that of experienced endoscopists. (8) For acceptance of AI optical diagnosis (computer-aided diagnosis [CADx]) of diminutive polyps (≤5 mm), AI-assisted characterization should match performance standards for implementing resect-and-discard and diagnose-and-leave strategies. (9) For acceptance of AI in the management of polyps ≥ 6 mm, AI-assisted characterization should be comparable to that of experienced endoscopists in selecting lesions amenable to endoscopic resection.

Background and Aims: Dye-based chromoendoscopy (DBC) could be effective in increasing the adenoma detection rate (ADR) in patients undergoing colonoscopy, but the technique is time-consuming and its uptake is limited. We aimed to assess the effect of DBC on ADR based on available randomized controlled trials (RCTs). Methods: Four databases were searched up to April 2022 for RCTs comparing DBC with conventional colonoscopy (CC) in terms of ADR, advanced ADR, and sessile serrated adenoma detection rate as well as the mean adenomas per patient and non-neoplastic lesions. Relative risk (RR) for dichotomous outcomes and mean difference (MD) for continuous outcomes were calculated using random-effect models. The I2 test was used for quantifying heterogeneity. Risk of bias was evaluated with the Cochrane tool. Results: Overall, 10 RCTs (5334 patients) were included. Indication for colonoscopy was screening or surveillance (3 studies) and mixed (7 studies). Pooled ADR was higher in the DBC group versus the CC group (95% CI, 48.1% [41.4%-54.8%] vs 39.3% [33.5%-46.4%]; RR, 1.20 [1.11-1.29]), with low heterogeneity (I2 = 29%). This effect was consistent for advanced ADR (RR, 1.21 [1.03-1.42]; I2 = .0%), sessile serrated adenomas (6.1% vs 3.5%; RR, 1.68 [1.15-2.47]; I2 = 9.8%), and mean adenomas per patient (MD, .24 [.17-.31]) overall and in the right-sided colon (MD, .28 [.14-.43]). A subgroup analysis considering only trials using high-definition white-light endoscopy reduced the heterogeneity while still showing a significant increase in adenoma detection with DBC: 51.6% (95% confidence interval [CI], 47.1%-56.1%) and 59.1% (95% CI, 54.7-63.3%), RR = 1.14 (95% CI, 1.06-1.23), P = .0004, I2 = .0%, P = .50. Conclusions: Meta-analysis of RCTs showed that DBC increases key quality parameters in colonoscopy, supporting its use in everyday clinical practice.

Background The advantage of using the macroscopic on-site evaluation (MOSE) technique during endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB) performed with 22G Franseen needles has not been investigated. We aimed to compare EUS-FNB with MOSE vs. EUS-FNB performed with three needle passes. Methods This randomized trial involved 10 Italian referral centers. Consecutive patients referred for EUS-FNB of pancreatic or nonpancreatic solid lesions were included in the study and randomized to the two groups. MOSE was performed by gross visualization of the collected material by the endoscopists and considered adequate when a white/yellowish aggregate core longer than 10 mm was retrieved. The primary outcome was diagnostic accuracy. Secondary outcomes were specimen adequacy, number of needle passes, and safety. Results 370 patients with 234 pancreatic lesions (63.2 %) and 136 nonpancreatic lesions (36.8 %) were randomized (190 EUS-FNB with MOSE and 180 with standard EUS-FNB). No statistically significant differences were found between EUS-FNB with MOSE and conventional EUS-FNB in terms of diagnostic accuracy (90.0 % [95 %CI 84.8 %–93.9 %] vs. 87.8 % [95 %CI 82.1 %–92.2 %]; P = 0.49), sample adequacy (93.1 % [95 %CI 88.6 %–96.3 %] vs. 95.5 % [95 %CI 91.4 %–98 %]; P = 0.31), and rate of adverse events (2.6 % vs. 1.1 %; P = 0.28). The median number of passes was significantly lower in the EUS-FNB with MOSE group (1 vs. 3; P Conclusions The accuracy of EUS-FNB with MOSE is noninferior to that of EUS-FNB with three needle passes. MOSE reliably assesses sample adequacy and reduces the number of needle passes required to obtain the diagnosis with a 22G Franseen needle.

Early detection of pancreatic cancer has long eluded clinicians because of its insidious nature and onset. Often metastatic or locally invasive when symptomatic, most patients are deemed inoperable. In those who are symptomatic, multi-modal imaging modalities evaluate and confirm pancreatic ductal adenocarcinoma. In asymptomatic patients, detected pancreatic lesions can be either solid or cystic. The clinical implications of identifying small asymptomatic solid pancreatic lesions (SPLs) of2 cm are tantamount to a better outcome. The accurate detection of SPLs undoubtedly promotes higher life expectancy when resected early, driving the development of existing imaging tools while promoting more comprehensive screening programs. An imaging tool that has matured in its reiterations and received many image-enhancing adjuncts is endoscopic ultrasound (EUS). It carries significant importance when risk stratifying cystic lesions and has substantial diagnostic value when combined with fine needle aspiration/biopsy (FNA/FNB). Adjuncts to EUS imaging include contrast-enhanced harmonic EUS and EUS-elastography, both having improved the specificity of FNA and FNB. This review intends to compile all existing enhancement modalities and explore ongoing research around the most promising of all adjuncts in the field of EUS imaging, artificial intelligence.

Background and study aims Artificial intelligence (AI) is set to impact several fields within gastroenterology. In gastrointestinal endoscopy, AI-based tools have translated into clinical practice faster than expected. We aimed to evaluate the status of research for AI in gastroenterology while predicting its future applications. Methods All studies registered on Clinicaltrials.gov up to November 2021 were analyzed. The studies included used AI in gastrointestinal endoscopy, inflammatory bowel disease (IBD), hepatology, and pancreatobiliary diseases. Data regarding the study field, methodology, endpoints, and publication status were retrieved, pooled, and analyzed to observe underlying temporal and geographical trends. Results Of the 103 study entries retrieved according to our inclusion/exclusion criteria, 76 (74 %) were based on AI application to gastrointestinal endoscopy, mainly for detection and characterization of colorectal neoplasia (52/103, 50 %). Image analysis was also more frequently reported than data analysis for pancreaticobiliary (six of 10 [60 %]), liver diseases (eight of nine [89 %]), and IBD (six of eight [75 %]). Overall, 48 of 103 study entries (47 %) were interventional and 55 (53 %) observational. In 2018, one of eight studies (12.5 %) were interventional, while in 2021, 21 of 34 (61.8 %) were interventional, with an inverse ratio between observational and interventional studies during the study period. The majority of the studies were planned as single-center (74 of 103 [72 %]) and more were in Asia (45 of 103 [44 %]) and Europe (44 of 103 [43 %]). Conclusions AI implementation in gastroenterology is dominated by computer-aided detection and characterization of colorectal neoplasia. The timeframe for translational research is characterized by a swift conversion of observational into interventional studies.

Since it was first described in 2001, endoscopic ultrasonography-guided biliary drainage (EUS-BD) has emerged as an alternative procedure for achieving an endoscopic internal drainage in case of endoscopic retrograde cholangiopancreatography (ERCP) failure. Biliary drainage can be achieved by either a transduodenal extrahepatic approach through EUS-guided choledochoduodenostomy (EUS-CDS), or a transgastric intrahepatic approach, namely EUS-guided hepaticogastrostomy (EUS-HGS) which already holds a remarkable place in the treatment of patients with malignant biliary obstruction.For this review we did a comprehensive search of PubMed/MEDLINE from inception to May 31, 2021 for papers with a significant sample size (at least 20 patients enrolled) dealing with EUS-HGS. Data on technical success, clinical success and rate of adverse events were collected.A total of 22 studies with different design, comprising 874 patients, were included. Technical success was achieved in about 96% of cases (ranging from 65% to 100%). Clinical success was obtained in almost 91% of cases (ranging from 76% to 100%). Overall rate of adverse events was 19% (ranging from 0% to 35%). Abdominal pain, self-limiting pneumoperitoneum, bile leak, cholangitis, bleeding, perforation and intraperitoneal migration of the stent were the most common.Despite both safety and efficacy profile, at the moment HGS still remains a challenging procedure at every single step and must therefore be conducted by a very experienced endoscopist in interventional EUS and ERCP procedures, who is able to deal with the possible severe adverse events of this procedure. A rapid introduction in clinical practice of dedicated devices is desiderable.

Introduction In this study, we review long-term outcomes of gastric endoscopic submucosal dissection [ESD] in western setting in light of the latest Japanese indication criteria, and examine predictors of outcomes and complications. Methods Data was collected on consecutive patients referred for gastric ESD in four participating centres from 2009 to 2021. Retrospective analysis of data with logistic regression and survival analysis was performed. Results A total of 415 patients were included. Mean age was 71.7 years, 56.4% were males. Absolute indication criteria [2018 guidelines] were fulfilled in 75.3% of patients. Median follow-up was 52 months. Post-resection histology was adenocarcinoma, HGD and LGD in 49.9%, 22.7% and 17.1% respectively. Perforation, early bleeding and delayed bleeding occurred in 2.4%, 4.3% and 3.4% respectively. En-bloc, R0 and recurrence on first endoscopic follow-up were 94.7%, 83.4% and 2.7% respectively. Relative indication [2018 Guidelines] for ESD was associated with R1 outcome [P-value 0.002]. Distal location [P-value 0.002] and increased procedure time [P-value 0.04] were significantly associated with bleeding risk, whereas scarring [P-value 0.009] and increased procedure duration [P-value 0.003] were associated with perforation. Recurrence-free survival at 2 years and 5 years was 94% and 83% respectively. Conclusion This is the largest multicenter western cohort suggesting gastric ESD is safe and effective in the western setting. A quarter of our patients fell outside of the new absolute indications for ESD, suggesting that western practice involves more advanced lesions. We identified the predictors of adverse outcomes in western practice. This should inform future practice and research.

Background: Endoscopic Ultrasound (EUS) is widely used for the diagnosis of bilio-pancreatic and gastrointestinal (GI) tract diseases, for the evaluation of subepithelial lesions, and for sampling of lymph nodes and solid masses lo-cated next to the GI tract. The role of Artificial Intelligence in healthcare in growing. This review aimed to provide an overview of the current state of AI in EUS from imaging to pathological diagnosis and training. Methods: AI algorithms can assist in lesion detection and characterization in EUS by analysing EUS images and identifying suspicious areas that may require further clinical evaluation or biopsy sampling. Deep learning tech-niques, such as convolutional neural networks (CNNs), have shown great potential for tumour identification and subepithelial lesion (SEL) evaluation by extracting important features from EUS images and using them to classify or segment the images. Results: AI models with new features can increase the accuracy of diagnoses, provide faster diagnoses, identify subtle differences in disease presentation that may be missed by human eyes, and provide more information and in-sights into disease pathology. Conclusions: The integration of AI in EUS images and biopsies has the potential to improve the diagnostic accura-cy, leading to better patient outcomes and to a reduction of repeated procedures in case of non-diagnostic biopsies.

Many tumors may secondarily involve the pancreas; however, only retrospective autopic and surgical series are available. We retrospectively collected data from all consecutive patients with histologically confirmed secondary tumors of the pancreas referred to five Italian centers between 2010 and 2021. We described clinical and pathological features, therapeutic approach and treatment outcomes. EUS characteristics of the lesions and the tissue acquisition procedures (needle, passages, histology) were recorded. A total of 116 patients (males/females 69/47; mean age 66.7) with 236 histologically confirmed pancreatic metastases were included; kidney was the most common primary site. EUS was performed to confirm the diagnosis in 205 lesions which presented as predominantly solitary (59), hypoechoic (95) and hypervascular (60), with a heterogeneous (n = 54) pattern and well-defined borders (n = 52). EUS-guided tissue acquisition was performed in 94 patients with an overall accuracy of 97.9%. Histological evaluation was possible in 88.3% of patients, obtaining final diagnosis in all cases. When cytology alone was performed, the final diagnosis was obtained in 83.3% of cases. A total of 67 patients underwent chemo/radiation therapy, and surgery was attempted in 45 (38.8%) patients. Pancreatic metastases are a possible event in the natural history of solid tumors, even long after the diagnosis of the primary site. EUS-guided fine needle biopsy may be suggested to implement the differential diagnosis.

Nutritional support is essential in patients who have a limited capability to maintain their body weight. Therefore, oral feeding is the main approach for such patients. When physiological nutrition is not possible, positioning of a nasogastric, nasojejunal tube, or other percutaneous devices may be feasible alternatives. Creating a percutaneous endoscopic gastrostomy (PEG) is a suitable option to be evaluated for patients that need nutritional support for more than 4 wk. Many diseases require nutritional support by PEG, with neurological, oncological, and catabolic diseases being the most common. PEG can be performed endoscopically by various techniques, radiologically or surgically, with different outcomes and related adverse events (AEs). Moreover, some patients that need a PEG placement are fragile and are unable to express their will or sign a written informed consent. These conditions highlight many ethical problems that become difficult to manage as treatment progresses. The aim of this manuscript is to review all current endoscopic techniques for percutaneous access, their indications, postprocedural follow-up, and AEs.

Background Optical diagnosis of colonic polyps is poorly reproducible outside of high volume referral centers. The present study aimed to assess whether real-time artificial intelligence (AI)-assisted optical diagnosis is accurate enough to implement the leave-in-situ strategy for diminutive (≤ 5 mm) rectosigmoid polyps (DRSPs). Methods Consecutive colonoscopy outpatients with ≥ 1 DRSP were included. DRSPs were categorized as adenomas or nonadenomas by the endoscopists, who had differing expertise in optical diagnosis, with the assistance of a real-time AI system (CAD-EYE). The primary end point was ≥ 90 % negative predictive value (NPV) for adenomatous histology in high confidence AI-assisted optical diagnosis of DRSPs (Preservation and Incorporation of Valuable endoscopic Innovations [PIVI-1] threshold), with histopathology as the reference standard. The agreement between optical- and histology-based post-polypectomy surveillance intervals (≥ 90 %; PIVI-2 threshold) was also calculated according to European Society of Gastrointestinal Endoscopy (ESGE) and United States Multi-Society Task Force (USMSTF) guidelines. Results Overall 596 DRSPs were retrieved for histology in 389 patients; an AI-assisted high confidence optical diagnosis was made in 92.3 %. The NPV of AI-assisted optical diagnosis for DRSPs (PIVI-1) was 91.0 % (95 %CI 87.1 %–93.9 %). The PIVI-2 threshold was met with 97.4 % (95 %CI 95.7 %–98.9 %) and 92.6 % (95 %CI 90.0 %–95.2 %) of patients according to ESGE and USMSTF, respectively. AI-assisted optical diagnosis accuracy was significantly lower for nonexperts (82.3 %, 95 %CI 76.4 %–87.3 %) than for experts (91.9 %, 95 %CI 88.5 %–94.5 %); however, nonexperts quickly approached the performance levels of experts over time. Conclusion AI-assisted optical diagnosis matches the required PIVI thresholds. This does not however offset the need for endoscopistsʼ high level confidence and expertise. The AI system seems to be useful, especially for nonexperts.

Background Computer-aided detection (CADe) increases adenoma detection in primary screening colonoscopy. The potential benefit of CADe in a fecal immunochemical test (FIT)-based colorectal cancer (CRC) screening program is unknown. This study assessed whether use of CADe increases the adenoma detection rate (ADR) in a FIT-based CRC screening program. Methods In a multicenter, randomized trial, FIT-positive individuals aged 50–74 years undergoing colonoscopy, were randomized (1:1) to receive high definition white-light (HDWL) colonoscopy, with or without a real-time deep-learning CADe by endoscopists with baseline ADR > 25 %. The primary outcome was ADR. Secondary outcomes were mean number of adenomas per colonoscopy (APC) and advanced adenoma detection rate (advanced-ADR). Subgroup analysis according to baseline endoscopists’ ADR (≤ 40 %, 41 %–45 %, ≥ 46 %) was also performed. Results 800 individuals (median age 61.0 years [interquartile range 55–67]; 409 men) were included: 405 underwent CADe-assisted colonoscopy and 395 underwent HDWL colonoscopy alone. ADR and APC were significantly higher in the CADe group than in the HDWL arm: ADR 53.6 % (95 %CI 48.6 %–58.5 %) vs. 45.3 % (95 %CI 40.3 %–50.45 %; RR 1.18; 95 %CI 1.03–1.36); APC 1.13 (SD 1.54) vs. 0.90 (SD 1.32; P = 0.03). No significant difference in advanced-ADR was found (18.5 % [95 %CI 14.8 %–22.6 %] vs. 15.9 % [95 %CI 12.5 %–19.9 %], respectively). An increase in ADR was observed in all endoscopist groups regardless of baseline ADR. Conclusions Incorporating CADe significantly increased ADR and APC in the framework of a FIT-based CRC screening program. The impact of CADe appeared to be consistent regardless of endoscopist baseline ADR.

Colorectal cancer is the third most common cancer worldwide. Because of the slow progression of the precancerous precursors, an efficient endoscopic surveillance strategy may be expected. It seems that around one-fourth of colorectal malignancies are still missed during colonoscopy. Several endoscopic technologies have been introduced, without radical changes. Interest in the development of artificial intelligence applications in the medical field has grown in the past decade. Artificial intelligence can help to highlight a specific region of interest that needs closer examination for the identification of polyps. The aim of this review is to report the first clinical experiences with the first US FDA-approved, real-time, deep-learning, computer-aided detection system (GI Genius™, Medtronic).Prevention of colorectal cancer through the diagnosis of its precursors is one of the greatest aims of an endoscopist. In this way we can avoid the development of a serious disease from lesions, which at early presentation don't have malignant aspects and could be removed during a colonoscopy. Identification of these lesions could be challenging and is based on the experiences and abilities of physicians, but this could lead to huge differences in the detection of polyps among the population. In the last decade, to improve the ability to detect the aforementioned lesions, which in endoscopy terms are defined as polyps, different systems of detection guided by artificial intelligence have been designed. This technology has been shown to be very helpful and, so, the more lesions that are recognized, the more colorectal cancer could be prevented. This article presents the first system of polyp detection guided by artificial intelligence approved by one of the world's regulatory agencies, the US FDA.

Barrett's esophagus (BE) is a well-established risk factor for esophageal adenocarcinoma. It is recommended that patients have regular endoscopic surveillance, with the ultimate goal of detecting early-stage neoplastic lesions before they can progress to invasive carcinoma. Detection of both dysplasia or early adenocarcinoma permits curative endoscopic treatments, and with this aim, thorough endoscopic assessment is crucial and improves outcomes. The burden of missed neoplasia in BE is still far from being negligible, likely due to inappropriate endoscopic surveillance. Over the last two decades, advanced imaging techniques, moving from traditional dye-spray chromoendoscopy to more practical virtual chromoendoscopy technologies, have been introduced with the aim to enhance neoplasia detection in BE. As witnessed in other fields, artificial intelligence (AI) has revolutionized the field of diagnostic endoscopy and is set to cover a pivotal role in BE as well. The aim of this commentary is to comprehensively summarize present evidence, recent research advances, and future perspectives regarding advanced imaging technology and AI in BE; the combination of computer-aided diagnosis to a widespread adoption of advanced imaging technologies is eagerly awaited. It will also provide a useful step-by-step approach for performing high-quality endoscopy in BE, in order to increase the diagnostic yield of endoscopy in clinical practice.

Sporadic non-ampullary duodenal adenomas (SNDAs) are often referred to tertiary centers because of the challenges in endoscopic resection. There is a paucity of data on both technical and clinical outcomes. The aim of our study was to evaluate the efficacy and safety of endoscopic resection for the treatment of SNDA in two western centers.This is a retrospective study reporting data of a cohort of patients referred for resection of SNDA between 2013 and 2017. Patients with familial adenomatous polyposis or ampullary lesions were excluded from present analysis. Outcomes considered for this study were technical success, adverse events, recurrence and need for surgery.120 patients (mean age 66 ± 11.9 years, 64male) were enrolled in the study. Mean size of the lesions was 23.3 mm (range 5-80). Fifty-six en-bloc endoscopic mucosal resection (EMR) (46.6%), 41 piecemeal EMR (pEMR) and 23 endoscopic submucosal dissection were performed. Intra-procedural perforation was observed in 4 patients (3.3%). Fourteen post-procedural (11.6%) adverse events were recorded. All post-procedural perforations occurred in lesions 30 mm. Recurrence was observed in 11 patients (9.5%) during a mean follow-up of 29 months. All recurrences were successfully managed endoscopically. 119 patients were still alive at last follow-up.Endoscopic resection can be successfully carried out in majority of patients. Size 30 mm seems to be the predictor of high adverse events risk.

Background and study aims The role of endoscopic submucosal dissection (ESD) for colorectal lesions in Western communities is unclear and its adoption is still limited. The aim of this study is to assess the long-term outcomes of a large cohort of patients treated with colorectal ESD in a tertiary Western center. Patients and methods A retrospective analysis was conducted on patients treated by ESD for superficial colorectal lesions between February 2011 and November 2019. The primary outcome was the recurrence rate. Secondary outcomes were en-bloc and R0 resection rates, procedural time, adverse events (AEs), and need for surgery. The curative resection rate was assessed for submucosal invasive lesions. Results A total of 327 consecutive patients, median age 69 years (IQR 60–76); 201 men (61.5 %) were included in the analysis. Of the lesions, 90.8 % were resected in an en-bloc fashion. The rate of R0 resection was 83.1 % (217/261) and 44.0 % (29/66) for standard and hybrid ESD techniques, respectively. Submucosal invasion and piecemeal resection independently predicted R1 resections. A total of 18(5.5 %) intra-procedural AEs (perforation:11, bleeding:7) and 12(3.7 %) post-procedural AEs occurred (perforation:2, bleeding: 10). Eighteen adenoma recurrences per 1,000 person-years (15cases, 5.6 %) were detected after a median follow-up time of 36 months. All recurrences were detected within 12 months. No carcinoma recurrences were observed. R1 resection status and intra-procedural AEs independently predicted recurrences with seven vs 150 recurrences per 1,000 person-years in the R0 vs R1 group, respectively. Conclusions Colorectal ESD is a safe and effective option for managing superficial colorectal neoplasia in a Western setting, with short and long-terms outcomes comparable to Eastern studies. En-bloc R0 resection and absence of intra-procedural AEs are associated with reduced risk of recurrence.

Summary Background Computer-aided detection (CADe) techniques based on artificial intelligence algorithms can assist endoscopists in detecting colorectal neoplasia. CADe has been associated with an increased adenoma detection rate, a key quality indicator, but the utility of CADe compared with existing advanced imaging techniques and distal attachment devices is unclear. Methods For this systematic review and network meta-analysis, we did a comprehensive search of PubMed/Medline, Embase, and Scopus databases from inception to Nov 30, 2020, for randomised controlled trials investigating the effectiveness of the following endoscopic techniques in detecting colorectal neoplasia: CADe, high definition (HD) white-light endoscopy, chromoendoscopy, or add-on devices (ie, systems that increase mucosal visualisation, such as full spectrum endoscopy [FUSE] or G-EYE balloon endoscopy). We collected data on adenoma detection rates, sessile serrated lesion detection rates, the proportion of large adenomas detected per colonoscopy, and withdrawal times. A frequentist framework, random-effects network meta-analysis was done to compare artificial intelligence with chromoendoscopy, increased mucosal visualisation systems, and HD white-light endoscopy (the control group). We estimated odds ratios (ORs) for the adenoma detection rate, sessile serrated lesion detection rate, and proportion of large adenomas detected per colonoscopy, and calculated mean differences for withdrawal time, with 95% CIs. Risk of bias and certainty of evidence were assessed with the Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach. Findings 50 randomised controlled trials, comprising 34 445 participants, were included in our main analysis (six trials of CADe, 18 of chromoendoscopy, and 26 of increased mucosal visualisation systems). HD white-light endoscopy was the control technique in all 50 studies. Compared with the control technique, the adenoma detection rate was 7·4% higher with CADe (OR 1·78 [95% CI 1·44–2·18]), 4·4% higher with chromoendoscopy (1·22 [1·08–1·39]), and 4·1% higher with increased mucosal visualisation systems (1·16 [1·04–1·28]). CADe ranked as the superior technique for adenoma detection (with moderate confidence in hierarchical ranking); cross-comparisons of CADe with other imaging techniques showed a significant increase in the adenoma detection rate with CADe versus increased mucosal visualisation systems (OR 1·54 [95% CI 1·22–1·94]; low certainty of evidence) and with CADe versus chromoendoscopy (1·45 [1·14–1·85]; moderate certainty of evidence). When focusing on large adenomas (≥10 mm) there was a significant increase in the detection of large adenomas only with CADe (OR 1·69 [95% CI 1·10–2·60], moderate certainty of evidence) when compared to HD white-light endoscopy; CADe ranked as the superior strategy for detection of large adenomas. CADe also seemed to be the superior strategy for detection of sessile serrated lesions (with moderate confidence in hierarchical ranking), although no significant increase in the sessile serrated lesion detection rate was shown (OR 1·37 [95% CI 0·65–2·88]). No significant difference in withdrawal time was reported for CADe compared with the other techniques. Interpretation Based on the published literature, detection rates of colorectal neoplasia are higher with CADe than with other techniques such as chromoendoscopy or tools that increase mucosal visualisation, supporting wider incorporation of CADe strategies into community endoscopy services. Funding None.

Colonoscopy is a fundamental tool in colorectal cancer (CRC) prevention. Nevertheless, one-fourth of colorectal neoplasms are still missed during colonoscopy, potentially being the main reason for post-colonoscopy colorectal cancer (PCCRC). Adenoma detection rate (ADR) is currently known as the best quality indicator correlating with PCCRC incidence.We performed a literature review in order to summarize evidences investigating key factors affecting ADR: endoscopists education and training, patient management, endoscopic techniques, improved navigation (exposition defect), and enhanced lesions recognition (vision defect) were considered.'Traditional' factors, such as split dose bowel preparation, adequate withdrawal time, and right colon second view, held a significant impact on ADR. Several devices and technologies have been developed to promote high-quality colonoscopy, however artificial intelligence may be considered the most promising tool for ADR improvement, provided that endoscopists education and recording are guaranteed.