EASY-APP: An artificial intelligence model and application for early and easy prediction of severity in acute pancreatitis.

BACKGROUND: Acute pancreatitis (AP) is a potentially severe or even fatal inflammation of the pancreas. Early identification of patients at high risk for developing a severe course of the disease is crucial for preventing organ failure and death. Most of the former predictive scores require many parameters or at least 24 h to predict the severity; therefore, the early therapeutic window is often missed. METHODS: The early achievable severity index (EASY) is a multicentre, multinational, prospective and observational study (ISRCTN10525246). The predictions were made using machine learning models. We used the scikit-learn, xgboost and catboost Python packages for modelling. We evaluated our models using fourfold cross-validation, and the receiver operating characteristic (ROC) curve, the area under the ROC curve (AUC), and accuracy metrics were calculated on the union of the test sets of the cross-validation. The most critical factors and their contribution to the prediction were identified using a modern tool of explainable artificial intelligence called SHapley Additive exPlanations (SHAP). RESULTS: The prediction model was based on an international cohort of 1184 patients and a validation cohort of 3543 patients. The best performing model was an XGBoost classifier with an average AUC score of 0.81 ± 0.033 and an accuracy of 89.1%, and the model improved with experience. The six most influential features were the respiratory rate, body temperature, abdominal muscular reflex, gender, age and glucose level. Using the XGBoost machine learning algorithm for prediction, the SHAP values for the explanation and the bootstrapping method to estimate confidence, we developed a free and easy-to-use web application in the Streamlit Python-based framework (http://easy-app.org/). CONCLUSIONS: The EASY prediction score is a practical tool for identifying patients at high risk for severe AP within hours of hospital admission. The web application is available for clinicians and contributes to the improvement of the model.

Elevated Serum Triglyceride Levels in Acute Pancreatitis: A Parameter to be Measured and Considered Early.

BACKGROUND: The value of serum triglycerides (TGs) related to complications and the severity of acute pancreatitis (AP) has not been clearly defined. Our study aimed to analyze the association of elevated levels of TG with complications and the severity of AP. METHODS: The demographic and clinical data of patients with AP were prospectively analyzed. TG levels were measured in the first 24 h of admission. Patients were divided into two groups: one with TG values of<200 mg/dL and another with TG≥200 mg/dL. Data on the outcomes of AP were collected. RESULTS: From January 2016 to December 2019, 247 cases were included: 200 with TG<200 mg/dL and 47 with TG≥200 mg/dL. Triglyceride levels≥200 mg/dL were associated with respiratory failure (21.3 vs. 10%, p=0.033), renal failure (23.4 vs. 12%, p=0.044), cardiovascular failure (19.1 vs. 7.5%, p=0.025), organ failure (34 vs. 18.5%, p=0.02), persistent organ failure (27.7 vs. 9.5%, p=0.001), multiple organ failure (19.1 vs. 8%, p=0.031), moderately severe and severe AP (68.1 vs. 40.5%, p=0.001), pancreatic necrosis (63.8 vs. 34%, p<0.001), and admission to the intensive care unit (27.7 vs. 9.5%, p=0.003). In the multivariable analysis, a TG level of≥200 mg/dL was independently associated with respiratory, renal, and cardiovascular failure, organ failure, persistent organ failure, multiple organ failure, pancreatic necrosis, severe pancreatitis, and admission to the intensive care unit (p<0.05). CONCLUSIONS: In our cohort, TG≥200 mg/dL was related to local and systemic complications. Early determinations of TG levels in AP could help identify patients at risk of complications.

Robotic abdominal resection of tailgut cysts - A technical note with step-by-step description.

AIM: Here, we describe a step-by-step standardized technique for tailgut cyst resection using a single-docking robotic approach. METHOD: Each step of the technique is illustrated using a composite collection of four operative patient videos to demonstrate the advantages and feasibility of this technique. The robot platform utilised is Da Vinci Xi. RESULTS: Five female patients have undergone this operation in our unit. The size of tumours ranged from 12 to 45 mm. Median operating time was 100 min (range 90-150). Mean blood loss in all the patients was less than 50 ml. There were no major intraoperative complications. One patient had a postoperative presacral collection which required radiological drainage. Length of stay in all patients was one day. CONCLUSIONS: This technique using a single-docking robotic approach appears safe and feasible. The robotic approach results in improved dexterity and more accurate dissection, better retraction and excellent vision which improves the ease of operating in the pelvis. Therefore, this approach can be replicated for use in a wide variety of patients with tailgut cysts.

Lower gastrointestinal bleeding due to colonic fistula caused by a gossypiboma: Case report and literature review.

INTRODUCTION: Even in modern surgery, human mistakes cannot be totally avoided. Retained surgical items are among the most feared ones. Forgotten sponges inside patients can cause a wide range of complications due to the foreign body reaction, called gossypiboma. The incidence of gossypibomas in the literature is probably underreported due to its legal implications; however, we must know its consequences and highlight the importance of the prevention strategies. We present a case where only preventive measures would have avoided its fatal outcome. PRESENTATION OF CASE: An 85-year-old male, previous left nephrectomy 12 years before, came to the emergency room with hematochezia and hemodynamic instability. An emergent angio-CT revealed a 12 cm mass due to a gossypiboma near the descending colon; the presence of air suggested an infection and/or fistulization to the bowel. It was decided not to perform invasive procedures, resulting in the patient's death. DISCUSSION: Gossypibomas can remain asymptomatic for years, being diagnosed when causing an obstruction, malabsorption, septic symptoms or even spontaneously. This may lead to high morbidity and mortality rates. In order to prevent it, different strategies have been described, with the objective to intensify surveillance. When diagnosed, laparotomy, laparoscopic and even endoscopic procedures have been performed successfully. CONCLUSION: We suggest putting all our efforts in identifying high risk patients and surgeries, training the OR team and enhancing protocols and checklists to minimize any preventable errors.

Fístula duodeno-cava tras tratamiento con bevacizumab / Duodenocaval fistula after treatment with bevacizumab

No disponible