Applying LASSO logistic regression for the prediction of biliary complications after ex vivo liver resection and autotransplantation in patients with end-stage hepatic alveolar echinococcosis.

ABSTRACT

BACKGROUND: The purpose of this study was to explore the relevant risk factors associated with biliary complications (BCs) in patients with end-stage hepatic alveolar echinococcosis (HAE) following ex vivo liver resection and autotransplantation (ELRA) and to establish and visualize a nomogram model. METHODS: This study retrospectively analysed patients with end-stage HAE who received ELRA treatment at the First Affiliated Hospital of Xinjiang Medical University between August 1, 2010 and May 10, 2023. The least absolute shrinkage and selection operator (LASSO) regression model was applied to optimize the feature variables for predicting the incidence of BCs following ELRA. Multivariate logistic regression analysis was used to develop a prognostic model by incorporating the selected feature variables from the LASSO regression model. The predictive ability, discrimination, consistency with the actual risk, and clinical utility of the candidate prediction model were evaluated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA). Internal validation was performed by the bootstrapping method. RESULTS: The candidate prediction nomogram included predictors such as age, hepatic bile duct dilation, portal hypertension, and regular resection based on hepatic segments. The model demonstrated good discrimination ability and a satisfactory calibration curve, with an area under the ROC curve (AUC) of 0.818 (95% CI 0.7417-0.8958). According to DCA, this prediction model can predict the risk of BCs occurrence within a probability threshold range of 9% to 85% to achieve clinical net benefit. CONCLUSIONS: A prognostic nomogram with good discriminative ability and high accuracy was developed and validated to predict BCs after ELRA in patients with end-stage HAE.