Hemostatic gene polymorphisms in severe acute pancreatitis

Application Value of the Automated Machine Learning Model Based on Modified Computed Tomography Severity Index Combined With Serological Indicators in the Early Prediction of Severe Acute Pancreatitis

BACKGROUND AND AIMS

Machine learning (ML) algorithms are widely applied in building models of medicine due to their powerful studying and generalizing ability. To assess the value of the Modified Computed Tomography Severity Index (MCTSI) combined with serological indicators for early prediction of severe acute pancreatitis (SAP) by automated ML (AutoML).

PATIENTS AND METHODS

The clinical data, of the patients with acute pancreatitis (AP) hospitalized in Hospital 1 and hospital 2 from January 2017 to December 2021, were retrospectively analyzed. Serological indicators within 24 hours of admission were collected. MCTSI score was completed by noncontrast computed tomography within 24 hours of admission. Data from the hospital 1 were adopted for training, and data from the hospital 2 were adopted for external validation. The diagnosis of AP and SAP was based on the 2012 revised Atlanta classification of AP. Models were built using traditional logistic regression and AutoML analysis with 4 types of algorithms. The performance of models was evaluated by the receiver operating characteristic curve, the calibration curve, and the decision curve analysis based on logistic regression and decision curve analysis, feature importance, SHapley Additive exPlanation Plot, and Local Interpretable Model Agnostic Explanation based on AutoML.

RESULTS

A total of 499 patients were used to develop the models in the training data set. An independent data set of 201 patients was used to test the models. The model developed by the Deep Neural Net (DL) outperformed other models with an area under the receiver operating characteristic curve (areas under the curve) of 0.907 in the test set. Furthermore, among these AutoML models, the DL and gradient boosting machine models achieved the highest sensitivity values, both exceeding 0.800.

CONCLUSION

The AutoML model based on the MCTSI score combined with serological indicators has good predictive value for SAP in the early stage.

Meta-analysis and field synopsis of genetic variants associated with the risk and severity of acute pancreatitis

Background

Genetic risk factors can provide insight into susceptibility for acute pancreatitis (AP) and disease progression towards (infected) necrotizing pancreatitis and persistent organ failure. The aim of the study was to undertake a systematic review of the genetic evidence for AP.

Methods

Online databases (MEDLINE, Embase, BIOSIS, Web of Science, Cochrane Library) were searched to 8 February 2018. Studies that reported on genetic associations with AP susceptibility, severity and/or complications were eligible for inclusion. Meta‐analyses were performed of variants that were reported by at least two data sources. Venice criteria and Bayesian false‐discovery probability were applied to assess credibility.

Results

Ninety‐six studies reporting on 181 variants in 79 genes were identified. In agreement with previous meta‐analyses, credible associations were established for SPINK1 (odds ratio (OR) 2·87, 95 per cent c.i. 1·89 to 4·34), IL1B (OR 1·23, 1·06 to 1·42) and IL6 (OR 1·64, 1·15 to 2·32) and disease risk. In addition, two novel credible single‐nucleotide polymorphisms were identified in Asian populations: ALDH2 (OR 0·48, 0·36 to 0·64) and IL18 (OR 1·47, 1·18 to 1·82). Associations of variants in TNF, GSTP1 and CXCL8 genes with disease severity were identified, but were of low credibility.

Conclusion

Genetic risk factors in genes related to trypsin activation and innate immunity appear to be associated with susceptibility to and severity of AP.

Prediction of mortality and organ failure based on coagulation and fibrinolysis markers in patients with acute pancreatitis: A retrospective study

This study explored the predictive value of coagulation and fibrinolysis markers with acute pancreatitis (AP)-related mortality and organ failure.We retrospectively reviewed and analyzed coagulation and fibrinolysis markers and clinical outcomes of the patients with AP.A total of 273 patients with AP were enrolled, 7 patients died and 28 patients suffered from organ failure. Uni- and multivariate logistic regression identified the differences of all of the coagulation and fibrinolysis markers as risk factors for AP-related mortality. The differences of APTT value, TT value, D-dimmer level, FDP level, and AT III level were risk factors for organ failure. Furthermore, the OR of the differences of platelet, PT, APTT, TT, fibrinogen, D-dimmer, FDP, and AT III was substantially improved by grouping with intervals of 10 × 10/L, 2 seconds, 5 seconds, 3 seconds, 0.5 g/L, 3 mg/L FEU, 5 mg/L and 10%, respectively. The risk of mortality can increase up to 1.62, 5.17, and 5.60 fold for every 10 × 10/L, 2 seconds and 5 seconds of increase in platelet, PT and APTT, respectively. There is approximate 2-fold increase in risk of organ failure for every 2 seconds of TT increase. In receiver operating characteristic analysis, there is no difference in the predictive power of bedside index for severity in acute pancreatitis (BISAP) with them in mortality or organ failure.In patients with AP, the dynamic changes of coagulation and fibrinolysis markers are good predictors for AP-related mortality and organ failure, especially platelet, PT and APTT in mortality and TT in organ failure.

Serum Concentrations of Angiopoietin-2 and Soluble fms-Like Tyrosine Kinase 1 (sFlt-1) Are Associated with Coagulopathy among Patients with Acute Pancreatitis

In severe acute pancreatitis (SAP), systemic inflammation leads to endothelial dysfunction and activation of coagulation. Thrombotic disorders in acute pancreatitis (AP) include disseminated intravascular coagulation (DIC). Recently, angiopoietin-2 and soluble fms-like tyrosine kinase 1 (sFlt-1) were proposed as markers of endothelial dysfunction in acute states. Our aim was to assess the frequency of coagulation abnormalities in the early phase of AP and evaluate the relationships between serum angiopoietin-2 and sFlt-1 and severity of coagulopathy. Sixty-nine adult patients with AP were recruited: five with SAP, 15 with moderately severe AP (MSAP) and 49 with mild AP. Six patients were diagnosed with DIC according to International Society on Thrombosis and Haemostasis (ISTH) score. All patients had at least one abnormal result of routine tests of hemostasis (low platelet count, prolonged clotting times, decreased fibrinogen, and increased D-dimer). The severity of coagulopathy correlated with AP severity according to 2012 Atlanta criteria, bedside index of severity in AP and duration of hospital stay. D-dimers correlated independently with C-reactive protein and studied markers of endothelial dysfunction. Angiopoietin-2, D-dimer, and ISTH score were best predictors of SAP, while sFlt-1 was good predictor of MSAP plus SAP. In clinical practice, routine tests of hemostasis may assist prognosis of AP.

Utility of clot formation and lysis assay to monitor global coagulation state of patients with severe acute pancreatitis

BACKGROUND

Systemic inflammation affects hemostasis during severe acute pancreatitis (SAP). A hypercoagulable state occurs more frequently in SAP, which is not fully detected by traditional coagulation testing.

AIMS

The aim of this study was to evaluate the contribution of clot formation and lysis (CloFAL) assay to improve monitoring of global coagulation in patients with SAP.

METHODS

Twenty-five patients with SAP who were treated from December 2009 to April 2011 were studied. Plasma was collected at the time of admission, and CloFAL was measured using the CloFAL analyzer. The parameters evaluated include coagulation time (CT), fibrinolysis time (FT), and maximum amplitude (MA), from which the accelerating coagulation extent (ACE, MA/CT), accelerating fibrinolytic extent (AFE, MA/FT), and balance level exponent (BLE, ACE/AFE) were calculated. In addition, laboratory values for the traditional coagulation testing were measured. Values were compared to a control group of 20 healthy subjects.

RESULTS

The MA, FT, ACE, and BLE values of the CloFAL assay were significantly increased in the SAP group compared to the control group (p\0.05 for all measurements). For the traditional coagulation testing, fibrinogen, plasminogen, and D-dimer levels were higher in patients in the SAP group compared to the control group (p\0.05).

CONCLUSIONS

Our findings using the CloFAL analyzer indicate that the hypercoagulable state was due to increased fibrin generation and invariable fibrinolysis in patients with SAP. CloFAL assay is a simple and useful global coagulation assay to monitor hypercoagulable states during SAP.