Dataset Information

Pleuropulmonary pathologies in the early phase of acute pancreatitis correlate with disease severity.

ABSTRACT:

Background

Respiratory failure worsens the outcome of acute pancreatitis (AP) and underlying factors might be early detectable.

Aims

To evaluate the prevalence and prognostic relevance of early pleuropulmonary pathologies and pre-existing chronic lung diseases (CLD) in AP patients.

Methods

Multicentre retrospective cohort study. Caudal sections of the thorax derived from abdominal contrast enhanced computed tomography (CECT) performed in the early phase of AP were assessed. Independent predictors of severe AP were identified by binary logistic regression analysis. A one-year survival analysis using Kaplan-Meier curves and log rank test was performed.

Results

358 patients were analysed, finding pleuropulmonary pathologies in 81%. CECTs were performed with a median of 2 days (IQR 1-3) after admission. Multivariable analysis identified moderate to severe or bilateral pleural effusions (PEs) (OR = 4.16, 95%CI 2.05-8.45, p<0.001) and pre-existing CLD (OR = 2.93, 95%CI 1.17-7.32, p = 0.022) as independent predictors of severe AP. Log rank test showed a significantly worse one-year survival in patients with bilateral compared to unilateral PEs in a subgroup.

Conclusions

Increasing awareness of the prognostic impact of large and bilateral PEs and pre-existing CLD could facilitate the identification of patients at high risk for severe AP in the early phase and thus improve their prognosis.

SUBMITTER: Luiken I

PROVIDER: S-EPMC8820650 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Pleuropulmonary pathologies in the early phase of acute pancreatitis correlate with disease severity.

Luiken Ina I Eisenmann Stephan S Garbe Jakob J Sternby Hanna H Verdonk Robert C RC Dimova Alexandra A Ignatavicius Povilas P Ilzarbe Lucas L Koiva Peeter P Penttilä Anne K AK Regnér Sara S Dober Johannes J Wohlgemuth Walter A WA Brill Richard R Michl Patrick P Rosendahl Jonas J Damm Marko M

PloS one 20220207 2

<h4>Background</h4>Respiratory failure worsens the outcome of acute pancreatitis (AP) and underlying factors might be early detectable.<h4>Aims</h4>To evaluate the prevalence and prognostic relevance of early pleuropulmonary pathologies and pre-existing chronic lung diseases (CLD) in AP patients.<h4>Methods</h4>Multicentre retrospective cohort study. Caudal sections of the thorax derived from abdominal contrast enhanced computed tomography (CECT) performed in the early phase of AP were assessed. ...[more]

PMID: 35130290

Similar Datasets

Project description:BackgroundMachine learning (ML) algorithms are widely applied in building models of medicine due to their powerful studying and generalizing ability. This study aims to explore different ML models for early identification of severe acute pancreatitis (SAP) among patients hospitalized for acute pancreatitis.MethodsThis retrospective study enrolled patients with acute pancreatitis (AP) from multiple centers. Data from the First Affiliated Hospital and Changshu No. 1 Hospital of Soochow University were adopted for training and internal validation, and data from the Second Affiliated Hospital of Soochow University were adopted for external validation from January 2017 to December 2021. The diagnosis of AP and SAP was based on the 2012 revised Atlanta classification of acute pancreatitis. Models were built using traditional logistic regression (LR) and automated machine learning (AutoML) analysis with five types of algorithms. The performance of models was evaluated by the receiver operating characteristic (ROC) curve, the calibration curve, and the decision curve analysis (DCA) based on LR and feature importance, SHapley Additive exPlanation (SHAP) Plot, and Local Interpretable Model Agnostic Explanation (LIME) based on AutoML.ResultsA total of 1,012 patients were included in this study to develop the AutoML models in the training/validation dataset. An independent dataset of 212 patients was used to test the models. The model developed by the gradient boost machine (GBM) outperformed other models with an area under the ROC curve (AUC) of 0.937 in the validation set and an AUC of 0.945 in the test set. Furthermore, the GBM model achieved the highest sensitivity value of 0.583 among these AutoML models. The model developed by eXtreme Gradient Boosting (XGBoost) achieved the highest specificity value of 0.980 and the highest accuracy of 0.958 in the test set.ConclusionsThe AutoML model based on the GBM algorithm for early prediction of SAP showed evident clinical practicability.

Dataset Information

Pleuropulmonary pathologies in the early phase of acute pancreatitis correlate with disease severity.

Background

Aims

Methods

Results

Conclusions

Publications

Pleuropulmonary pathologies in the early phase of acute pancreatitis correlate with disease severity.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets