Pancreatic cystic lesions (PCLs) are a heterogenous group of lesions ranging from benign to malignant. There has been an increase in PCLs prevalence in recent years, mostly due to advances in imaging techniques, increased awareness of their existence and population aging. Reliable discrimination between neoplastic and non-neoplastic cystic lesions is paramount to ensuring adequate treatment and follow-up. Although conventional diagnostic techniques such as ultrasound (US), magnetic resonance imaging (MRI) and computer tomography (CT) can easily identify these lesions, assessing the risk of malignancy is limited. Endoscopic ultrasound (EUS) is superior to cross-sectional imaging in identifying potentially malignant lesions due to its high resolution and better imaging characteristics, and the advantage of allowing for cyst fluid sampling via fine-needle aspiration (FNA). More complex testing, such as cytological and histopathological analysis and biochemical and molecular testing of the aspirated fluid, can ensure an accurate diagnosis.

Crohn’s disease and ulcerative colitis remain debilitating disorders, characterized by progressive bowel damage and possible lethal complications. The growing number of applications for artificial intelligence in gastrointestinal endoscopy has already shown great potential, especially in the field of neoplastic and pre-neoplastic lesion detection and characterization, and is currently under evaluation in the field of inflammatory bowel disease management. The application of artificial intelligence in inflammatory bowel diseases can range from genomic dataset analysis and risk prediction model construction to the disease grading severity and assessment of the response to treatment using machine learning. We aimed to assess the current and future role of artificial intelligence in assessing the key outcomes in inflammatory bowel disease patients: endoscopic activity, mucosal healing, response to treatment, and neoplasia surveillance.

Background and study aims Current data show that traditional training methods in endoscopic retrograde cholangiopancreatography (ERCP) fall short of producing competent trainees. We aimed to evaluate whether a novel approach to simulator-based training might improve the learning curve for novice endoscopists training in ERCP. Methods We conducted a multicenter, randomized controlled trial using a validated mechanical simulator (the Boškoski-Costamagna trainer). Trainees with no experience in ERCP received either standard cannulation training or motion training before undergoing standard cannulation training on the mechanical simulator. Trainees were timed and graded on their performance in selective cannulation of four different papilla configurations. Results Thirty-six trainees (16 in the motion training group, 20 in the standard group) performed 720 timed attempts at cannulating the bile duct on the simulator. Successful cannulation was achieved in 698 of 720 attempts (96.9 %), with no significant difference between the two study groups (P = 0.37). Trainees in the motion training group had significantly lower median cannulation times compared to the standard group (36 vs. 48 seconds, P = 0.001) and better technical performance on the first papilla type (P = 0.013). Conclusions Our findings suggest that motion training could be an innovative method aimed at accelerating the learning curve of novice trainees in the early phase of their training. Future studies are needed to establish its role in ERCP training programs.

Background Optimal training strategies in endoscopic retrograde cholangiopancreatography (ERCP) remain controversial despite the shift toward competence-based training models, with limited data available on patient safety during training. We aimed to assess whether pre-procedural clinical predictors could identify patients at low risk of developing procedure-related adverse-events (AEs) in a training environment. Methods We performed a prospective, multicenter, cohort study in five training centers. A data collection system documenting indication, clinical data, trainee performance (assessed using a validated competence assessment tool), technical outcomes, and AEs over a 30-day follow-up was utilized. We developed a clinical risk score (Trainee Involvement in ERCP Risk Score [TIERS]) for patients undergoing ERCP and compared the rate of AEs in a training environment between low-risk and high-risk groups. The association between trainee performance and AE rate was also evaluated. Results 1283 ERCPs (409 [31.9 %, 95 %CI 29.3 %–34.4 %] with trainee involvement) performed by 11 trainers and 10 trainees were analyzed. AEs were more frequent in the high-risk compared with the low-risk group: 26.7 % (95 %CI 20.5 %–34.7 %) vs. 17.1 % (95 %CI 12.8 %–22.2 %). TIERS demonstrated a high negative predictive value for AEs (82.9 %, 95 %CI 79.4 %–85.8 %) and was the only predictor of AEs on multivariable analysis (odds ratio 1.38, 95 %CI 1.09–1.75). Suboptimal trainee performance was associated with an increase in AE rates. Conclusion Simple, clinical-based predictive tools could improve ERCP training by selecting the most appropriate cases for hands-on training, with the aim of increasing patient safety.