Machine learning for the prediction of post-ERCP pancreatitis risk: A proof-of-concept study.

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.

Endoscopic ultrasound-guided rendezvous in benign biliary or pancreatic disorders with a 22-gauge needle and a 0.018-inch guidewire.

Background and study aims The aim of this study was to assess the efficacy and safety of endoscopic ultrasound-guided rendezvous (EUS-RV) for benign biliary or pancreatic disorders with a 22-gauge needle and a 0.018-inch guidewire. Patients and methods Patients who underwent EUS-RV after failed biliary or pancreatic cannulation for benign disorder were candidates for this study. For EUS-RV, a 22-gauge needle and a 0.018-inch guidewire were used. Inclusion criteria were unsuccessful biliary or pancreatic cannulation for therapeutic endoscopic retrograde cholangiopancreatography (ERCP) with benign biliary or pancreatic obstruction. Exclusion criteria included malignant biliary or pancreatic obstruction, inaccessible papilla due to surgically altered upper gastrointestinal anatomy or duodenal stricture, and previous sphincterotomy and/or biliary stent placement. The primary outcome was the technical success rate of biliary or pancreatic cannulation, and the secondary outcome was the rate of adverse events. Results Thirty-one patients were evaluated. The overall technical success rate was 80.6 % (81.5 % in biliary and 75 % in pancreatic cases). Adverse events (AEs) were identified in 12.9 % of patients, including one with biliary peritonitis, one with abdominal pain and one with severe pancreatitis plus pneumomediastinum. Only one of the AEs (3.3 %) was directly related to the rendezvous procedure. Conclusions EUS-RV may be a safe and feasible salvage method for unsuccessful cannulation for benign disorders. Use of a 22-gauge needle with a 0.018-inch guidewire may be the first option for benign pathology.

Over-the-scope clip for acute esophageal variceal bleeding.

Over-the-scope clip (OTSC) has been reported to control non-variceal bleeding; however, the use of this device for acute variceal hemorrhage (AVH) is very limited. We report our experience regarding the use of OTSC in patients with AVH in terms of technical success and safety. A retrospective clinical experience case series study was conducted from October 2017 to June 2019 at two tertiary care centers. Adult patients with AVH as a result of small varices managed with OTSC after endoscopic band ligation (EBL) failure were enrolled. Standard gastroscope and OTSC 'type a' with a cap of 11 mm in diameter were used in all procedures. Total of five patients with chronic liver disease (Child-Pugh score ≤8) and portal hypertension (hepatic venous pressure gradient, mean 14.4 ± 1.3 mmHg) were included. Four of them presented collapse of the bleeding varix, and one had wall disruption associated with fibrosis secondary to prior banding. We were able to stop AVH in all patients without clip-related adverse events during a 30-day follow-up period. Two patients developed solid food dysphagia after 3 months of clip deployment that resolved after removal using a bipolar cutting device. Twin grasper or anchor were not used to aid or facilitate the approximation of opposite edges in any patient. No additional local therapies or new endoscopic session for variceal eradication were required. This case series shows preliminary success controlling AVH with OTSC after EBL failure in patients with small varices. Esophageal dysphagia may appear as a complication during follow up but it can be resolved by clip removal.

EUS-FNA cytological material from pancreatic lesions: the expression of cathepsins and its predictive value of malignancy

Aims: To assess the expression of cathepsins in pancreatic samples obtained by endoscopic ultrasonography and fine needle aspiration (EUS-FNA) and to investigate their relationship with the staging of the pancreatic ductal adenocarcinoma (PDAC). Methods: We prospectively included patients with solid pancreatic masses, in which EUS-FNA were performed. Cathepsins B, L, S and H expression was determined in FNA samples. Results: Seventeen FNA were performed. All cytological material was from PDAC. Expression of cathepsins was predominantly low (B 65%, L 23%, S 76%, and H 41%). We found no correlation between the expression levels and the extension of the neoplasm. Conclusion: Expression of cathepsins in the cytological material of PDAC is diverse but still poor to be useful in the pre-operative diagnosis. There is no correlation between the expression levels of cathepsins and the extension of the PDAC

No disponible

EUS-FNA cytological material from pancreatic lesions: the expression of cathepsins and its predictive value of malignancy.

AIMS: To assess the expression of cathepsins in pancreatic samples obtained by endoscopic ultrasonography and fine needle aspiration (EUS-FNA) and to investigate their relationship with the staging of the pancreatic ductal adenocarcinoma (PDAC). METHODS: We prospectively included patients with solid pancreatic masses, in which EUS-FNA were performed. Cathepsins B, L, S and H expression was determined in FNA samples. RESULTS: Seventeen FNA were performed. All cytological material was from PDAC. Expression of cathepsins was predominantly low (B 65%, L 23%, S 76%, and H 41%). We found no correlation between the expression levels and the extension of the neoplasm. CONCLUSION: Expression of cathepsins in the cytological material of PDAC is diverse but still poor to be useful in the pre-operative diagnosis. There is no correlation between the expression levels of cathepsins and the extension of the PDAC.

Study of the expression of cathepsins in histological material from pancreatic lesions

Background and aims: To assess the expression levels of cathepsins in malignant and premalignant lesions. Methods: We retrospectively included patients who underwent pancreatic surgery on pancreatic solid or cystic masses. The expression of cathepsin H, L, B and S was determined in both types of samples. Lesions were divided into three categories: malignant (pancreatic adenocarcinoma and malignant mucinous neoplasms), premalignant (mucinous neoplasms) and benign (other lesions). Results: Thirty-one surgical resection samples were studied. The expression of cathepsins was significantly higher in malignant lesions than in premalignant and benign lesions (H 75%, 27%, 37% p = 0.05; L 92%, 36%, 37% p = 0.011; B 83%, 36%, 62% p = 0.069; S 92%, 36%, 25% p = 0.004, respectively). Conclusions: Cathepsins are overexpressed in histological samples of malignant lesions compared to premalignant and benign lesions. However, the expression of cathepsins is similar in both premalignant and benign lesions (AU)

No disponible

Study of the expression of cathepsins in histological material from pancreatic lesions.

BACKGROUND AND AIMS: To assess the expression levels of cathepsins in malignant and premalignant lesions. METHODS: We retrospectively included patients who underwent pancreatic surgery on pancreatic solid or cystic masses. The expression of cathepsin H, L, B and S was determined in both types of samples. Lesions were divided into three categories: malignant (pancreatic adenocarcinoma and malignant mucinous neoplasms), premalignant (mucinous neoplasms) and benign (other lesions). RESULTS: Thirty-one surgical resection samples were studied. The expression of cathepsins was significantly higher in malignant lesions than in premalignant and benign lesions (H 75%, 27%, 37% p = 0.05; L 92%, 36%, 37% p = 0.011; B 83%, 36%, 62% p = 0.069; S 92%, 36%, 25% p = 0.004, respectively). CONCLUSIONS: Cathepsins are overexpressed in histological samples of malignant lesions compared to premalignant and benign lesions. However, the expression of cathepsins is similar in both premalignant and benign lesions.

Sedación en endoscopia digestiva. Guía de práctica clínica de la Sociedad Española de Endoscopia Digestiva / Sedation for gastrointestinal endoscopy. Clinical practice guidelines of the Sociedad Española de Endoscopia Digestiva

No disponible

[Safety of propofol administration by the staff of a gastrointestinal endoscopy unit]. / Seguridad de la administración de propofol por el personal de la unidad de endoscopia digestiva.

Deep sedation controlled by the staff of gastrointestinal endoscopy units is currently controversial. In the last few years, numerous studies have provided data supporting the safety of propofol use in these techniques. We present a large series of patients who underwent gastroscopy or colonoscopy under endoscopist-controlled deep sedation. A total of 875 procedures (297 gastroscopies and 578 colonoscopies) were included. In all procedures intravenous propofol with or without intravenous midazolam was administered. In gastroscopies, complications attributable to the sedation were found in only 6.7% of the patients, mostly due to desaturation, which was resolved without the need for intubation. In colonoscopies, complications were found in 11.2%, the most frequent being bradycardia and desaturation, none of which were serious. No association was found between the presence of complications and the propofol dose administered. In the group of patients undergoing colonoscopy, simultaneous midazolam administration allowed reduction of the propofol dose required to achieve deep sedation. In conclusion, propofol shows a good safety profile and excellent tolerance in patients undergoing gastroscopy and colonoscopy and can be administrated by the endoscopy team. At least in the case of colonoscopy, the associated use of midazolam allows the propofol dose to be decreased, thus, theoretically, reducing the drug's adverse effects.

Seguridad de la administración de propofol por el personal de la unidad de endoscopia digestiva / Safety of propofol administration by the staff of a gastrointestinal endoscopy unit

El control por parte del equipo de endoscopia digestiva de la administración de sedación profunda es un tema controvertido en la actualidad. En los últimos años, son numerosos los estudios que apoyan la seguridad de la utilización de propofol para la realización de estas técnicas. Nosotros presentamos una serie amplia de pacientes a los que se les realizó una gastroscopia o colonoscopia con sedación profunda, con control a cargo del propio endoscopista. Se incluyeron 875 exploraciones (297 gastroscopias y 578 colonoscopias) a las que se les administró propofol vía intravenosa (i.v.), asociado o no a midazolam i.v. En las gastroscopias sólo se produjeron complicaciones atribuibles a la sedación en un 6,7% de los pacientes, la mayoría por desaturación, que se resolvió sin necesidad de intubación. En el caso de la colonoscopia, el 11,2% presentó alguna complicación (las más frecuentes fueron la bradicardia y la desaturación), aunque ninguna de carácter grave. No encontramos relación entre la presencia de complicaciones y la dosis de propofol administrada. En el grupo de colonoscopias, la administración simultánea de midazolam permitió una reducción en la dosis de propofol necesaria para alcanzar un nivel de sedación profunda. En conclusión, el propofol es un fármaco con un perfil seguro y una excelente tolerancia en pacientes sometidos a gastroscopias y colonoscopias, que puede ser manejado por el propio equipo de endoscopia. Su asociación con midazolam permite, al menos en el caso de la colonoscopia, disminuir su dosis y así, teóricamente, reducir sus efectos secundarios

Deep sedation controlled by the staff of gastrointestinal endoscopy units is currently controversial. In the last few years, numerous studies have provided data supporting the safety of propofol use in these techniques. We present a large series of patients who underwent gastroscopy or colonoscopy under endoscopist-controlled deep sedation. A total of 875 procedures (297 gastroscopies and 578 colonoscopies) were included. In all procedures intravenous propofol with or without intravenous midazolam was administered. In gastroscopies, complications attributable to the sedation were found in only 6.7% of the patients, mostly due to desaturation, which was resolved without the need for intubation. In colonoscopies, complications were found in 11.2%, the most frequent being bradycardia and desaturation, none of which were serious. No association was found between the presence of complications and the propofol dose administered. In the group of patients undergoing colonoscopy, simultaneous midazolam administration allowed reduction of the propofol dose required to achieve deep sedation. In conclusion, propofol shows a good safety profile and excellent tolerance in patients undergoing gastroscopy and colonoscopy and can be administrated by the endoscopy team. At least in the case of colonoscopy, the associated use of midazolam allows the propofol dose to be decreased, thus, theoretically, reducing the drug's adverse effects