Key Features for Prediction of Post-ERCP-Cholecystitis (PEC): A Novel Machine Learning Model and a Public Online Prediction Platform

Abstract

Background: Post-endoscopic retrograde cholangiopancreatography (ERCP) cholecystitis (PEC) is an ignored but serious complication. Methods: A random forest (RF) machine learning method was used to develop a predictive model for PEC. Eligible patients with common bile duct (CBD) stones and gallbladders in-situ were retrospectively enrolled to build the model. Logistic regression analysis was used to compare the predictive value based on sensitivity, specificity, accuracy, and area under the curve (AUC). The predictive value of the RF model was further validated with another 117 patients. This study was registered with ClinicalTrials.gov, NCT04234126 is completed. Findings: A total of 1,117 patients were enrolled (90 PEC, 8.06%) to build the predictive model for PEC. The RF method identified white blood cell (WBC) count, endoscopic papillary balloon dilatation (EPBD), increase in WBC, residual CBD stones after ERCP, serum amylase levels, and mechanical lithotripsy were the top six predictive factors and has a sensitivity (0.822), specificity (0.853), accuracy (0.855), and AUC values (0.890). A separate logistic regression prediction model was built showing a sensitivity, specificity, and AUC of 0.800, 0.801, and 0.864, respectively. An additional 117 patients (11 PEC, 9.40%) were used to validate the RF model, with an AUC of 0.889 compared to an AUC of 0.884 with the logistic regression model (95% CI, 0.783 - 0.986). The web server is available online at http://101.35.163.113/PEC/. Conclusions: The RF model both validated by logistic regression based on the top six risk factors as listed above accurately predicted the occurrence of PEC. Clinical Trial Registration Details: Registered with Clinicaltrial.gov (NCT04234126). Funding Information: This work was supported by National Natural Science Foundation of China (8187103130; 32160255); Gansu Competitive Foundation Projects for Technology Development and Innovation (1602FKDA001); Gansu Province Science and Technology Planning Project (20YF8WA085); Science and Technology Planning Project of Chengguan District in Lanzhou (2020JSCX0043). The Foundation of The First Hospital of Lanzhou University (ldyyyn-2018-16). Declaration of Interests: No conflict of interest was declared by the authors. Ethics Approval Statement: This retrospective study was conducted in the surgical endoscopy center of The First Hospital of Lanzhou University in China, in accordance with the Declaration of Helsinki. The study was approved by the Ethics Committee of The First Hospital of Lanzhou University (LDYYLL2021-257).