Development and validation of a prediction model for deep vein thrombosis in older non-mild acute pancreatitis patients

Analysis of factors influencing onset and survival of patients with severe acute pancreatitis: A clinical study

OBJECTIVES

Acute pancreatitis (AP) is an inflammatory disease of the pancreas, and the prognosis of severe AP (SAP) is poor. The study aimed to identify promising biomarkers for predicting the occurrence and survival outcome of SAP patients.

MATERIALS AND METHODS

Two hundred and forty AP patients were retrospectively recruited, in which 72 cases with SAP. Blood test was done for collection of laboratory indicators. After treatment, the mortality of patients was recorded.

RESULTS

Patients in the SAP group had higher intensive care unit admissions and longer hospital stays (p < .001). Among laboratory parameters, significantly high values of C-reactive protein (CRP), triglycerides and glucose (TyG) index, Von willebrand factor antigen (vWF:Ag) and D-dimer were found in SAP groups relative to non-SAP ones. Receiver operating characteristic curve indicated the good performance of CRP, TyG index, vWF:Ag and D-dimer in SAP diagnosis. Among all SAP cases, 51 survived while 21 died. TyG index (odds ratio [OR] = 6.914, 95% confidence interval [CI] = 1.193-40.068, p = .028), vWF:Ag (OR = 7.441, 95% CI = 1.236-244.815, p = .028), and D-dimer (OR = 7.987, 95% CI = 1.251-50.997, p = .028) were significantly related to survival outcome of SAP patients by multiple logistic regression analysis. Both TyG index and vWF showed favorable efficiency in predicting overall prognosis. The area under the curve for the multivariate model (PRE = -35.908 + 2.764 × TyG + 0.021 × vWF:Ag) was 0.909 which was greater than 0.9, indicating its excellent performance in prognosis prediction.

CONCLUSION

CRP, TyG index, vWF:Ag, and D-dimer values on admission may be potential clinical predictors of the development of SAP. Moreover, TyG index and vWF:Ag may be helpful to predict survival outcome.

Construction and validation of a clinical prediction model for deep vein thrombosis in patients with digestive system tumors based on a machine learning

This study developed a deep vein thrombosis (DVT) risk prediction model based on multiple machine learning methods for patients with digestive system tumors undergoing surgical treatment. Data of 1048 patients with digestive system tumors admitted to Shanxi Provincial People's Hospital (College of Shanxi Medical University) from January 2020 to January 2023 were retrospectively analyzed, and 845 cases were screened according to the inclusion and exclusion criteria. The patients were divided into a training group (586 patients), and a validation group (259 patients), then feature selection was performed using six models, including Lasso regression, XGBoost, Random Forest, Decision Tree, Support Vector Machine, and Logistics. Predictive models were subsequently constructed from column-line plots, and the predictive validity of the models was assessed using receiver operating characteristic curves, precision-recall curves, and decision-curve analysis. In the model comparison, the XGBoost model showed the largest area under the curve (AUC) on the validation set (P < 0.05), demonstrating excellent predictive performance and generalization ability. We selected the common characteristic factors in the six models to further develop the column line plots to assess the DVT risk. The model performed well in clinical validation and effectively differentiated high-risk and low-risk patients. The differences in BMI, procedure time, and D-dimer were statistically significant between patients in the thrombus group and those in the non-thrombus group (P < 0.05). However, the AUC of the Xgboost model was found to be greater than that of the column chart model by the Delong test (P < 0.05). BMI, procedure time, and D-dimer are critical predictors of DVT risk in patients with digestive system tumors. Our model is an adequate assessment tool for DVT risk, which can help improve the prevention and treatment of DVT.

Acute pancreatitis induces a transient hypercoagulable state in murine models

BACKGROUND/OBJECTIVES

Although understudied, risk of venous thromboembolism (VTE) appears to be increased during acute pancreatitis (AP). We aimed to further characterize a hypercoagulable state associated with AP utilizing thromboelastography (TEG), a readily available, point of care test.

METHODS

AP was induced in C57/Bl6 mice using l-arginine and caerulein. TEG was performed with citrated native samples. The maximum amplitude (MA) and coagulation index (CI), a composite marker of coagulability, were evaluated. Platelet aggregation was assessed using whole blood collagen-activated platelet impedance aggregometry. Circulating tissue factor (TF), the initiator of extrinsic coagulation, was measured with ELISA. A VTE model using IVC ligation followed by measurement of clot size and weight was evaluated. After IRB approval and consent, blood samples from patients hospitalized with a diagnosis of AP were evaluated by TEG.

RESULTS

Mice with AP displayed a significant increase in MA and CI, consistent with hypercoagulability. Hypercoagulability peaked at 24 h after induction of pancreatitis, then returned to baseline by 72 h. AP resulted in significantly increased platelet aggregation and elevated circulating TF. Increased clot formation with AP was observed in an in vivo model of deep vein thrombosis. In a proof of concept, correlative study, over two thirds of patients with AP demonstrated an elevated MA and CI compared to the normal range, consistent with hypercoagulability.

CONCLUSIONS

Murine acute pancreatitis results in a transient hypercoagulable state that can be assessed by TEG. Correlative evidence for hypercoagulability was also demonstrated in human pancreatitis. Further study to correlate coagulation measures to incidence of VTE in AP is warranted.

Predictive value of the C-reactive protein/albumin ratio in severity and prognosis of acute pancreatitis

Aim

To investigate the predictive value of C-reactive protein (CRP) to serum albumin (ALB) ratio in the severity and prognosis of acute pancreatitis (AP), and compare the predictive value of the CRP/ALB ratio with the Ranson score, modified computed tomography severity index (MCTSI) score, and Bedside Index of Severity in Acute Pancreatitis (BISAP) score.

Methods

This cohort study retrospectively analyzed clinical data of AP patients from August 2018 to August 2020 in our hospital. Logistic regression analysis was utilized to determine the effects of CRP/ALB ratio, Ranson, MCTSI, and BISAP score on severe AP (SAP), pancreatic necrosis, organ failure, and death. The predictive values of CRP/ALB ratio, Ranson, MCTSI, and BISAP score were examined with the area under the curve (AUC) of the receiver operator characteristic (ROC) curve analysis. DeLong test was used to compare the AUCs between CRP/ALB ratio, Ranson, MCTSI, and BISAP score.

Results

Totally, 284 patients were included in this study, of which 35 AP patients (12.32%) developed SAP, 29 (10.21%) organ failure, 30 (10.56%) pancreatic necrosis and 11 (3.87%) died. The result revealed that CRP/ALB ratio on day 2 was associated with SAP [odds ratio (OR): 1.74, 95% confidence interval (CI): 1.32 to 2.29], death (OR: 1.73, 95%CI: 1.24 to 2.41), pancreatic necrosis (OR: 1.28, 95%CI: 1.08 to 1.50), and organ failure (OR: 1.43, 95%CI: 1.18 to 1.73) in AP patients. Similarly, CRP/ALB on day 3 was related to a higher risk of SAP (OR: 1.50, 95%CI: 1.24 to 1.81), death (OR: 1.8, 95%CI: 1.34 to 2.65), pancreatic necrosis (OR: 1.22, 95%CI: 1.04 to 1.42), and organ failure (OR: 1.21, 95%CI: 1.04 to 1.41). The predictive value of CRP/ALB ratio for pancreatic necrosis was lower than that of MCTSI, for organ failure was lower than that of Ranson and BISAP, and for death was higher than that of MCTSI.

Conclusion

The CRP/ALB ratio may be a novel but promising, easily measurable, reproducible, non-invasive prognostic score that can be used to predict SAP, death, pancreatic necrosis, and organ failure in AP patients, which can be a supplement of Ranson, MCTSI, and BISAP scores.

Automated Machine Learning for the Early Prediction of the Severity of Acute Pancreatitis in Hospitals

Background

Machine 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.

Methods

This 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.

Results

A 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.

Conclusions

The AutoML model based on the GBM algorithm for early prediction of SAP showed evident clinical practicability.