Machine Learning-Based Algorithms for the Prediction of 90-Day Survival in Patients with Liver Failure Receiving Artificial Liver Therapy

Liver failure is associated with high short-term mortality, and the predictive value of clinical factors for patients undergoing artificial liver therapy is uncertain. We aim to develop prognostic models using several machine learning algorithms to predict 90-day survival in patients with liver failure undergoing artificial liver therapy. We retrospectively enrolled hospitalized patients with liver failure who received artificial liver therapy in our center between December 2017 and December 2021. Prognostic characteristics were chosen by the least absolute shrinkage and selection operator (LASSO) regression and independent predictors by multivariable logistic regression analysis. Four machine learning algorithms—logistic regression, random forest, support vector machine, and k-nearest neighbor—were used to build and validate models to predict 90-day survival following ALSS. Model performance was assessed by the area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. A total of 197 patients were included in this study. LASSO regression identified 14 prognostic features, and subsequent multivariate logistic regression analysis determined that age, total bilirubin, liver failure type, alpha-fetoprotein, and thrombin time were independent predictors. Among the four machine learning models, LR achieved the highest predictive performance with an AUC of 88.2%, accuracy of 78.3%, sensitivity of 78.7%, specificity of 76.9%, PPV of 92.5%, NPV of 51.2%, and F1-score of 0.798, followed by RF(AUC = 0.869), SVM (AUC = 85.8%), and KNN (AUC = 82.0%). Machine learning models showed promising performance in predicting 90-day survival in liver failure patients receiving artificial liver support therapy, potentially supporting individualized prognostic assessment.