Explore the vast range of titles available.

The incidence and medical costs of acute pancreatitis (AP) are on the rise, and severe cases still have a 30% mortality rate. We aimed to evaluate hypoalbuminemia as a risk factor and the prognostic value of human serum albumin in AP. Data from 2461 patients were extracted from the international, prospective, multicentre AP registry operated by the Hungarian Pancreatic Study Group. Data from patients with albumin measurement in the first 48 h (n = 1149) and anytime during hospitalization (n = 1272) were analysed. Multivariate binary logistic regression and Receiver Operator Characteristic curve analysis were used. The prevalence of hypoalbuminemia (< 35 g/L) was 19% on admission and 35.7% during hospitalization. Hypoalbuminemia dose-dependently increased the risk of severity, mortality, local complications and organ failure and is associated with longer hospital stay. The predictive value of hypoalbuminemia on admission was poor for severity and mortality. Severe hypoalbuminemia (< 25 g/L) represented an independent risk factor for severity (OR 48.761; CI 25.276–98.908) and mortality (OR 16.83; CI 8.32–35.13). Albumin loss during AP was strongly associated with severity (p < 0.001) and mortality (p = 0.002). Hypoalbuminemia represents an independent risk factor for severity and mortality in AP, and it shows a dose-dependent relationship with local complications, organ failure and length of stay.

Rapid and accurate identification of high-risk acute gastrointestinal bleeding (GIB) patients is essential. We developed two machine-learning (ML) models to calculate the risk of in-hospital mortality in patients admitted due to overt GIB. We analyzed the prospective, multicenter Hungarian GIB Registry’s data. The predictive performance of XGBoost and CatBoost machine-learning algorithms with the Glasgow-Blatchford (GBS), pre-endoscopic Rockall and ABC scores were compared. We evaluated our models using five-fold cross-validation, and performance was measured by area under receiver operating characteristic curve (AUC) analysis with 95% confidence intervals (CI). Overall, we included 1,021 patients in the analysis. In-hospital death occurred in 108 cases. The XGBoost and the CatBoost model identified patients who died with an AUC of 0.84 (CI:0.76–0.90; 0.77–0.90; respectively) in the internal validation set, whereas the GBS and pre-endoscopic Rockall clinical scoring system’s performance was significantly lower, AUC values of 0.68 (CI:0.62–0.74) and 0.62 (CI:0.56–0.67), respectively. ABC score had an AUC of 0.77 (CI:0.71–0.83). The XGBoost model had a specificity of 0.96 (CI:0.92–0.98) at a sensitivity of 0.25 (CI:0.10–0.43) compared with the CatBoost model, which had a specificity of 0.74 (CI:0.66–0.83) at a sensitivity of 0.78 (CI:0.57–0.95). XGBoost and the CatBoost models evaluate the mortality risk of acute GI bleeding better, than the conventional risk assessment tools.

Both acute kidney injury and chronic kidney disease are risk factors for many outcomes of gastrointestinal bleeding (GIB). These are associated with higher mortality, longer hospitalisation, and greater need for transfusion in case of overt GIB. Our study aimed to further evaluate the role of kidney function in several clinical outcomes of GIB patients. The Hungarian Gastrointestinal Bleeding Registry collected data on all-cause GIB between 2019 and 2022. A multi-level data-validation system provided high-quality data, which was retrospectively analysed. Numerous primary (in-hospital mortality, discharge, need for endoscopic intervention, in-hospital rebleeding, length of hospitalisation, need for emergency surgery, need for endoscopic examination and need for intensive care unit) and secondary (detection of Helicobacter pylori ( H. pylori ), recognition of cancer as the source of bleeding, need for any kind of transfusion or clotting factor, anticoagulation therapy) outcomes were observed. Descriptive statistical tools were used to summarize our data. Among others, estimated glomerular filtration rate (eGFR) (ml/min/1.73 m 2 ) was used as continuous variable, mean, standard deviation, median, interquartile range and minimum/maximum values were calculated. Reduced kidney function was associated with in-hospital mortality (eGFR: 42.63 ± 28.78 ml/min/1.73 m 2 vs. 57.08 ± 26.62 ml/min/1.73 m 2 , p < 0.001), need for red blood cells (RBC) transfusion (eGFR: 51.98 ± 27.90 ml/min/1.73 m 2 vs. 60.11 ± 25.06 ml/min/1.73 m 2 , p < 0.001) and clotting factor supplementation (eGFR: 47.40 ± 27.41 ml/min/1.73 m 2 vs. 56.68 ± 27.02 ml/min/1.73 m 2 , p < 0.001). Better eGFR values at admission were associated with discharge home after proper treatment, compared to any other outcome of the admission (eGFR: 58.12 ± 25.56 ml/min/1.73 m 2 vs. 50.23 ± 29.69 ml/min/1.73 m 2 , p < 0.001), H. pylori positivity (eGFR: 59.63 ± 25.24 ml/min/1.73 m 2 vs. 52.76 ± 25.44 ml/min/1.73 m 2 , p = 0.021) and the need for endoscopic intervention (eGFR: 58.65 ± 26.61 ml/min/1.73 m 2 vs. 54.31 ± 27.64 ml/min/1.73 m 2 , p = 0.008). At admission, patients with better eGFR than 36.64 ml/min/1.73 m 2 were discharged to their homes, mortality was higher with eGFR worse than 25.96 ml/min/1.73 m 2 , more RBC transfusion was needed if eGFR was lower than 49.61 ml/min/1.73 m 2 . Regulation of anticoagulation was examined extensively. Impaired kidney function at admission results higher in-hospital mortality in overt all-cause GIB and increases the need of RBC transfusion.

Patients with gastrointestinal bleeding (GIB) exhibit varying tolerances to acute blood loss. We aimed to investigate the effect of relative Hb decrease (ΔHb%) on GIB outcomes. Participants enrolled in the Hungarian GIB Registry between 2019 and 2022 were analyzed. The primary outcome, defined as a composite endpoint, included in-hospital bleeding-related mortality and the need for urgent intervention. Four groups were created based on the lowest Hb measured during hospitalization (nadirHb), along with four subgroups categorized by ΔHb%. Regardless of the nadirHb, participants with higher ΔHb% had a higher probability of reaching the composite endpoint. A 30–40% ΔHb% decrease to a nadirHb of 80–90 g/L resulted in a similar likelihood of reaching the primary endpoint as a 0–10% ΔHb% to 70–80 g/L or 60–70 g/L, respectively (10% vs. 12%, p  = 1.00; 10% vs. 10%, p  = 1.00). Our results showed that a higher Hb decrease in GIB is associated with an increased untoward outcome rate even when the lowest hemoglobin exceeds the recommended transfusion thresholds. New randomized controlled trials investigating transfusion thresholds should consider ΔHb% as a potential key variable and risk factor.

IntroductionAcute gastrointestinal bleeding (GIB) is a life-threatening emergency with a critical economic burden. As a result of bleeding, anaemia often requires intravenous or oral iron supplementation. Elderly patients are even more prone to untoward outcomes after hospital discharge if iron supplementation is inefficient. There is a gap in current guidelines on which supplementation route clinicians should choose. We aim to investigate the effect of one dose of intravenous iron therapy versus 3-month oral iron administration on anaemia in an elderly population.Methods and analysisThe FIERCE study is an open-label, randomised controlled, two-armed trial. At least 48 hours after the acute non-variceal GIB treatment, patients will be recruited in participating centres. A random sequence generator will allocate the participants to group A (intravenous ferric carboxymaltose, 1000 mg) or group B (oral ferrous sulfate (FS), ca. 200 mg every day) with an allocation ratio of 1:1 on the day of the planned discharge from the hospital. Randomisation will be stratified for participating centres and the need for transfusion within the same hospitalisation before recruitment to the trial. Quality of life assessment, functional measurement and laboratory tests will be performed at baseline, 1 and 3 months±7 days after enrolment to the trial. The primary endpoint is a composite endpoint, including all-cause mortality, anaemia-associated unplanned emergency visit and anaemia-associated unplanned hospital admission within 3 months of enrolment in the trial.Ethics and disseminationThe study has been approved by the relevant organisation, the Scientific and Research Ethics Committee of the Hungarian Medical Research Council (46395-5/2021/EÜIG). We will disseminate our results to the medical community and will publish our results in peer-reviewed journals.Trial registrationThe trial has been registered at ClinicalTrials.gov (NCT05060731).

Background: Acute pancreatitis (AP) is a life-threatening disease. We aimed to explore the prognostic relevance of renal function based on estimated glomerular filtration rate (eGFR). Methods: A prospective registry of AP patients was established by the Hungarian Pancreatic Study Group. Data of 1,224 consecutive patients were collected between 2012 and 2017. Patients were divided into 3 groups according to their eGFR measured within 24 h of hospitalization: normal renal function: >90 mL/min, mild to moderate renal functional impairment : 30–90 mL/min and severe renal dysfunction : <30 mL/min. Associations of eGFR with outcome (survival, length of hospitalization, AP severity, blood glucose), inflammatory markers (erythrocyte sedimentation rate, white blood cell count), anemia and organ failure (heart, kidney, liver) were analyzed. Results: Death, longer hospitalization and severe AP, but not the cause of AP, were significantly associated with lower eGFR. The inflammatory markers (CRP, WBC count) but not anemia (Hb, Htk) were closely associated with severe renal dysfunction. Renal function was associated with heart and renal failure but not with other complications of AP such as respiratory failure, local pancreatic complications, diabetes or peptic ulcer. eGFR was not associated with liver damage (ALAT, γ-GT) or liver function (serum bilirubin) although biliary complications, alcohol and metabolic syndrome were the most common etiologies of AP. Conclusions: Our study suggests a useful prognostic value of initial eGFR in AP patients. Even mild eGFR reduction predicted mortality, severity of AP and the length of hospitalization. Thus, precise evaluation of renal function should be considered for assessing AP severity and outcome.

IntroductionAcute pancreatitis (AP) is an inflammatory disease with no specific treatment. Mitochondrial injury followed by ATP depletion in both acinar and ductal cells is a recently discovered early event in its pathogenesis. Importantly, preclinical research has shown that intracellular ATP delivery restores the physiological function of the cells and protects from cell injury, suggesting that restoration of energy levels in the pancreas is therapeutically beneficial. Despite several high quality experimental observations in this area, no randomised trials have been conducted to date to address the requirements for energy intake in the early phase of AP.Methods/designThis is a randomised controlled two-arm double-blind multicentre trial. Patients with AP will be randomly assigned to groups A (30 kcal/kg/day energy administration starting within 24 hours of hospital admission) or B (low energy administration during the first 72 hours of hospital admission). Energy will be delivered by nasoenteric tube feeding with additional intravenous glucose supplementation or total parenteral nutrition if necessary. A combination of multiorgan failure for more than 48 hours and mortality is defined as the primary endpoint, whereas several secondary endpoints such as length of hospitalisation or pain will be determined to elucidate more detailed differences between the groups. The general feasibility, safety and quality checks required for high quality evidence will be adhered to.Ethics and disseminationThe study has been approved by the relevant organisation, the Scientific and Research Ethics Committee of the Hungarian Medical Research Council (55961-2/2016/EKU). This study will provide evidence as to whether early high energy nutritional support is beneficial in the clinical management of AP. The results of this trial will be published in an open access way and disseminated among medical doctors.Trial registrationThe trial has been registered at the ISRCTN (ISRTCN 63827758).

Pancreatic necrosis is a consistent prognostic factor in acute pancreatitis (AP). However, the clinical scores currently in use are either too complicated or require data that are unavailable on admission or lack sufficient predictive value. We therefore aimed to develop a tool to aid in necrosis prediction. The XGBoost machine learning algorithm processed data from 2387 patients with AP. The confidence of the model was estimated by a bootstrapping method and interpreted via the 10th and the 90th percentiles of the prediction scores. Shapley Additive exPlanations (SHAP) values were calculated to quantify the contribution of each variable provided. Finally, the model was implemented as an online application using the Streamlit Python-based framework. The XGBoost classifier provided an AUC value of 0.757. Glucose, C-reactive protein, alkaline phosphatase, gender and total white blood cell count have the most impact on prediction based on the SHAP values. The relationship between the size of the training dataset and model performance shows that prediction performance can be improved. This study combines necrosis prediction and artificial intelligence. The predictive potential of this model is comparable to the current clinical scoring systems and has several advantages over them.

In gastrointestinal emergency situations we have to face countless difficulties and challenges. Many of the situation require immediate surgical interventions or intensive care unit (ICU) admission, and for most of them, special scoring systems were defined, to detect the severity of the disease or the worsening condition of the patient.Acute, severe gastrointestinal (GI) bleeding has previously required predominantly surgical care. Following the introduction and expansion of gastrointestinal endoscopy, the number of cases requiring surgery has dropped significantly. The incidence of upper nonvariceal bleeding and the need for operative intervention has been steadily declining since 1993. Although endoscopic modalities have undergone significant development, it can be said that we have not been able to achieve a significant improvement in the mortality of gastrointestinal bleeding in the last decades [1]. Possible reasons are the significant increase in the average age of the population and fatal outcomes due to the many comorbidities associated mostly with old age. It is often seen that GI bleeding can be stopped in a patient, yet the outcome is fatal. Accordingly, a reduction in mortality rates in the future will be possible if patient management, independent of endoscopic techniques can be improved. The key is to have a proper risk assessment and to pay more attention to the treatment of vulnerable patients (early, accurate risk assessment, closer observation, multi-parameter monitoring). There are several risk assessment and outcome predictor scoring systems, most of which rely on clinical parameters typical of the acute phase of bleeding. The Rockall scoring system calculates outcome based on comorbidities, however, e.g. in terms of renal failure, the stages are not properly defined [2].Acute pancreatitis (AP) is a leading cause of hospital admissions worldwide [3,4]. The disease can be traced back to various causes, which can vary in severity [5,6]. According to the severity of the disease, we distinguish between mild, moderate and severe cases. Mortality in severe cases is much higher, approximately 30% [7]. As the mortality of severe cases is high, the disease has been in the focus of research in recent decades [8]. As a result, there is a significant improvement in mortality, but it is still high. Different scoring systems try to predict the outcome of cases with more or less success. Subsequent complications are not taken into account by these scoring systems. Accordingly, they do not clarify the effect of the case on the outcome. The modified Marshall scoring system takes multiple organ system dysfunctions into account, which are strongly correlated with mortality and ICU admission [9]. Three major organ systems are highlighted i.e., renal, cardiovascular, and respiratory failure formation are the most frequently researched and articles on topics, while neurological complications and regular use of the Glasgow Coma Scale (GCS) have been pushed into the background. In clinical practice, patients hospitalized for acute pancreatitis may have or may be formed neurological symptoms such as alcohol withdrawal syndrome, confusion and delirium. Disorder of consciousness means the development of spatial and temporal disorientation, it often occurs in hospitalized patients, especially the elderly. The currently used prognostic score systems do not take into account the disturbances of consciousness developed during hospital admission, so they cannot estimate their effect on the course of the disease. Treatment of AP is predominantly supportive, accordingly, if complications can be reduced with adequate patient care, it can also improve the outcome.

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. The EASY prediction score is a practical tool for identifying patients at a greater risk for severe acute pancreatitis shortly after hospital admission. The explanation of the impact of features on the prediction helps physicians understand the decision of the machine learning model. The easy‐to‐use web application is available for clinicians and contributes to the improvement of the model.