Search

Publisher Copyright: © 2022, The Author(s). 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.

Background Currently, no consensus on the use of blood tests for monitoring disease recurrence in patients with resected melanoma exists. The only meta-analysis conducted in 2008 found that elevated serum S100B levels were associated with significantly worse survival in melanoma patients. Serum LDH is an established prognostic factor in patients with advanced melanoma. Objective To compare the discriminative and prognostic ability of serum S100B with that of serum LDH in patients with melanoma. Methods This systematic review and meta-analysis were reported in accordance with the PRISMA Statement. The study protocol was registered in the International Prospective Register of Systematic Reviews (PROSPERO; CRD42019137138). Results A quantitative analysis of data from 6 eligible studies included 1,033 patients with cutaneous melanoma. The discriminative ability of serum S100B at identifying disease relapse [pooled Area Under the ROC (AUROC) 78.64 (95% CI 70.28; 87.01)] was significantly greater than the discriminative ability of serum LDH [AUROC 64.41 (95% CI 56.05; 7278)] (p=0.013). Ten eligible studies with 1,987 patients were included in the risk of death analysis. The prognostic performance of serum S100B [pooled estimate of adjusted hazard ratio (HR) 1.78 (95% CI 1.38; 2.29)] was independent but not superior to that of serum LDH [HR 1.60 (95% CI 1.36; 2.29)]. Limitations A relatively small number of articles were eligible and there was considerable heterogeneity across the included studies. Conclusions Serum biomarkers may provide relevant information on melanoma patient status and should be further researched. Serum S100B is a valid marker for diagnosis of melanoma recurrence. Systematic Review Registration The study protocol was registered in the International Prospective Register of Systematic Reviews (PROSPERO; CRD42019137138).

Supplemental material, sj-pdf-1-tag-10.1177_1756284820965324 for Accuracy of the Helicobacter pylori diagnostic tests in patients with peptic ulcer bleeding: a systematic review and network meta-analysis by Nóra Vörhendi, Alexandra Soós, Marie Anne Engh, Benedek Tinusz, Zsolt Szakács, Dániel Pécsi, Alexandra Mikó, Patrícia Sarlós, Péter Hegyi and Bálint Eröss in Therapeutic Advances in Gastroenterology

Supplemental material, sj-pdf-1-tag-10.1177_1756284820965324 for Accuracy of the Helicobacter pylori diagnostic tests in patients with peptic ulcer bleeding: a systematic review and network meta-analysis by Nóra Vörhendi, Alexandra Soós, Marie Anne Engh, Benedek Tinusz, Zsolt Szakács, Dániel Pécsi, Alexandra Mikó, Patrícia Sarlós, Péter Hegyi and Bálint Eröss in Therapeutic Advances in Gastroenterology