Search

Background: Predicting Post-Endoscopic Retrograde Cholangiopancreatography (ERCP) pancreatitis (PEP) risk can be determinant in reducing its incidence and managing patients appropriately, however studies conducted thus far have identified single-risk factors with standard statistical approaches and limited accuracy. Aim: To build and evaluate performances of machine learning (ML) models to predict PEP probability and identify relevant features. Methods: A proof-of-concept study was performed on ML application on an international, multicenter, prospective cohort of ERCP patients. Data were split in training and test set, models used were gradient boosting (GB) and logistic regression (LR). A 10-split random cross-validation (CV) was applied on the training set to optimize parameters to obtain the best mean Area Under Curve (AUC). The model was re-trained on the whole training set with the best parameters and applied on test set. Shapley-Additive-exPlanation (SHAP) approach was applied to break down the model and clarify features impact. Results: One thousand one hundred and fifty patients were included, 6.1% developed PEP. GB model outperformed LR with AUC in CV of 0.7 vs 0.585 (p-value=0.012). GB AUC in test was 0.671. Most relevant features for PEP prediction were: bilirubin, age, body mass index, procedure time, previous sphincterotomy, alcohol units/day, cannulation attempts, gender, gallstones, use of Ringer's solution and periprocedural NSAIDs. Conclusion: In PEP prediction, GB significantly outperformed LR model and identified new clinical features relevant for the risk, most being pre-procedural.

Background Difficult biliary cannulation in endoscopic retrograde cholangiopancreatography (ERCP) increases the risk of post-ERCP pancreatitis (PEP). The purpose of this prospective, randomized, multicenter study was to compare two advanced rescue methods, transpancreatic biliary sphincterotomy (TPBS) and a double-guidewire (DGW) technique, in difficult common bile duct (CBD) cannulation. Methods Patients with native papilla and planned CBD cannulation were recruited at eight Scandinavian hospitals. An experienced endoscopist attempted CBD cannulation with wire-guided cannulation. If the procedure fulfilled the definition of difficult cannulation and a guidewire entered the pancreatic duct, randomization to either TPBS or to DGW was performed. If the randomized method failed, any method available was performed. The primary end point was the frequency of PEP and the secondary end points included successful cannulation with the randomized method. Results In total, 1190 patients were recruited and 203 (17.1 %) were randomized according to the study protocol (TPBS 104 and DGW 99). PEP developed in 14/104 patients (13.5 %) in the TPBS group and 16/99 patients (16.2 %) in the DGW group (P = 0.69). No difference existed in PEP severity between the groups. The rate of successful deep biliary cannulation was significantly higher with TPBS (84.6 % [88/104]) than with DGW (69.7 % [69/99]; P = 0.01). Conclusions In difficult biliary cannulation, there was no difference in PEP rate between TPBS and DGW techniques. TPBS is a good alternative in cases of difficult cannulation when the guidewire is in the pancreatic duct.

Introduction: Risk of post-ERC pancreatitis (PEP) in patients with primary sclerosing cholangitis (PSC) is 1-7.8%. PSC is often associated with inflammatory bowel disease and autoimmune hepatitis, which are usually treated with thiopurines. The role of thiopurines in PEP risk is still unclear. Aims and methods: We evaluated the thiopurine use in PEP. The data of 354 PSC patients who underwent 985 ERCs between 2009 and 2018 were collected. 177 patients treated with thiopurines (study group, SG) and 177 controls (CG) were matched with a propensity score (PSM). Odds ratios (ORs) with 95% confidence interval (95% CI) were calculated. Multivariable logistic regression analysis and generalized linear mixed model were performed. The P-value < 0.05 was significant. Results: In matched data, 472 ERCs were performed in SG and 513 in CG. Thiopurines were used in 373/472 (79.0%) ERCs in SG. The PEP rate was 5.3% in SG and 5.7% in CG ( p = 0.889). Unintentional pancreatic duct cannulation (OR 1.28, 95%CI 1.07-1.51, p = 0.004), and periampullary diverticulum (OR 4.87, 95%CI 1.72-11.98, p = 0.001) increased the risk of PEP. Conclusion: Prior or present thiopurine use did not increase the risk of PEP. (c) 2021 The Author(s). Published by Elsevier Ltd on behalf of Editrice Gastroenterologica Italiana S.r.l. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )

Background Transpancreatic biliary sphincterotomy (TPBS) is an advanced cannulation method for accessing common bile duct (CBD) in endoscopic retrograde cholangiopancreatography (ERCP). If CBD cannulation is difficult, an endoscopist can open the septum between the pancreatic and biliary duct with a sphincterotome to gain access. Long-term results of this procedure are unclear. We wanted to evaluate the short- and long-term complications of TPBS on patients with native papilla and benign indication for ERCP. Patients and Methods ERCPs performed in Helsinki University Hospital between 2007 and 2013 were reviewed. The study group comprised 143 consecutive patients with TPBS and 140 controls (CG). Data were collected from patient records and a phone survey was performed as a follow-up ≥ 4 years after the index ERCP. Results Post-ERCP pancreatitis (PEP) developed in seven patients (4.9%) in TPBS and one patient (0.7%) in CG (p = 0.067). The rates of other acute complications were similar between the groups. ERCP ended with no access to CBD in four cases (2.8%) in TPBS. The median length of follow-up was 6 years in TPBS and 7 years in CG. During this period, three patients (2.1%) in TPBS and six patients (4.3%) in CG suffered from acute pancreatitis (AP) (p = 0.238). One (0.7%) patient in CG and none in TPBS developed chronic pancreatitis (CP). Abdominal pain was suffered by ten patients (6.9%) in TPBS and twelve patients (8.6%) in CG daily, whereas by six patients (4.2%) in TPBS and twelve patients (8.6%) in CG weekly. Conclusion TPBS is a useful procedure, with acceptable complication rates. No significant difference occurred between the groups when evaluating the short-term or long-term complications with a follow-up period of four to 10 years. Additionally, no significant differences occurred in upper abdominal pain, episodes of AP, or development of CP.

Objectives: Post-endoscopic retrograde cholangiopancreatography (ERCP) acute pancreatitis (PEP) is a frequent complication of this endoscopic procedure. Chronic statin intake has been linked to lower incidence and severity of acute pancreatitis (AP). Periprocedural rectal administration of non-steroidal anti-inflammatory drugs is protective against PEP, but the role of chronic acetylsalicylic acid (ASA) treatment is unclear. We aimed to investigate whether statins and chronic ASA intake are associated with lower risk of PEP. Methods: An international, multicenter, prospective cohort study. Consecutive patients undergoing ERCP in seven European centers were included. Patients were followed-up to detect those with PEP. Multivariate analysis by means of binary logistic regression was performed, and adjusted odds ratios (aORs) were calculated. Results: A total of 1150 patients were included, and 70 (6.1%) patients developed PEP. Among statins users, 8.1% developed PEP vs. 5.4% among non-users (P=0.09). Multivariate analysis showed no association between statin use and PEP incidence (aOR 1.68 (95% CI 0.94–2.99, P=0.08)). Statin use had no effect on severity of PEP, being mild in 92.0% of statin users vs. 82.2% in non-statin users (P=0.31). Chronic ASA use was not associated with PEP either (aOR 1.02 (95% CI 0.49–2.13), P=0.96). Abuse of alcohol and previous endoscopic biliary sphincterotomy were protective factors against PEP, while >1 pancreatic guidewire passage, normal bilirubin values, and duration of the procedure >20minutes, were risk factors. Conclusions: The use of statins or ASA is not associated with a lower risk or a milder course of PEP.