Dataset Information

A Novel 5-Cytokine Panel Outperforms Conventional Predictive Markers of Persistent Organ Failure in Acute Pancreatitis.

ABSTRACT:

Introduction

Existing laboratory markers and clinical scoring systems have shown suboptimal accuracies for early prediction of persistent organ failure (POF) in acute pancreatitis (AP). We used information theory and machine learning to select the best-performing panel of circulating cytokines for predicting POF early in the disease course and performed verification of the cytokine panel's prognostic accuracy in an independent AP cohort.

Methods

The derivation cohort included 60 subjects with AP with early serum samples collected between 2007 and 2010. Twenty-five cytokines associated with an acute inflammatory response were ranked by computing the mutual information between their levels and the outcome of POF; 5 high-ranking cytokines were selected. These cytokines were subsequently measured in early serum samples of an independent prospective verification cohort of 133 patients (2012-2016), and the results were trained in a Random Forest classifier. Cross-validated performance metrics were compared with the predictive accuracies of conventional laboratory tests and clinical scores.

Results

Angiopoietin 2, hepatocyte growth factor, interleukin 8, resistin, and soluble tumor necrosis factor receptor 1A were the highest-ranking cytokines in the derivation cohort; each reflects a pathologic process relevant to POF. A Random Forest classifier trained the cytokine panel in the verification cohort and achieved a 10-fold cross-validated accuracy of 0.89 (area under the curve 0.91, positive predictive value 0.89, and negative predictive value 0.90), which outperformed individual cytokines, laboratory tests, and clinical scores (all P ≤ 0.006).

Discussion

We developed a 5-cytokine panel, which accurately predicts POF early in the disease process and significantly outperforms the prognostic accuracy of existing laboratory tests and clinical scores.

SUBMITTER: Langmead C

PROVIDER: S-EPMC8104185 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Neutrophil to lymphocyte ratio (NLR) has frequently been reported as a significant indicator of systemic inflammation in various medical conditions. The association underlying NLR and outcomes in patients with acute pancreatitis (AP) has not been evaluated after the publication of revised Atlanta classification.This was a single-center retrospective diagnostic accuracy study and a cohort outcome study. From 2009 to 2015, Asian Chinese patients with a diagnosis of AP presented within 72?hours from symptom onset and underwent neutrophil, lymphocyte assessment at presentation were included in this study. The outcomes were the occurrence of persistent organ failure (POF), intensive care unit (ICU) stay >7 days, and in-hospital mortality. The relationships of baseline neutrophil, lymphocyte count, and NLR with outcomes were assessed with multivariate Cox regression model.A total of 974 consecutive AP patients were clinically eligible. The mean neutrophils, lymphocytes, and NLR for the entire population were 10.23?±?4.76??×?10/L, 1.05?±?0.49??×?10/L, and 12.88?±?11.25. Overall, 223 (22.9%) of the patients developed with POF, 202 (20.7%) spent more than 7 days in ICU, and 58 (6.0%) died during hospitalization. The NLR had a superior predictive performance than neutrophils and lymphocytes. Using an NLR cutoff of 11, the area under the curves (AUC) were 0.76 for POF, 0.74 for longer ICU stay, and 0.79 for death during hospitalization. After multivariate analysis, NLR???11 was further identified as an independent prognostic factor (hazard ratio [HR] 1.37, 95% confidence interval [CI] 1.00-1.89; HR 1.44, 95% CI 1.03-2.00; HR 2.75, 95% CI 1.12-6.76; all P value?<?0.05). Following stratification according to quartiles of NLR, positive trends for the association across increasing NLR quartiles and the 3 outcomes were observed (P values for trends across quartiles were 0.007, 0.016, and 0.028, respectively). The adjusted HRs for highest NLR quartile versus the lowest were 2.80 (95% CI 1.42-5.51) (POF), 2.79 (95% CI 1.37-5.70) (ICU?>?7 days), and 2.22 (95% CI 0.49-10.05) (mortality), respectively.Our data show for the first time that an increased NLR is an independent risk factor for POF, longer ICU stay, and in-hospital mortality in AP.