Abstract
Liver transplantation is one of the most effective treatments for end-stage liver disease, but the demand for livers is much higher than the available donor livers. Model for End-stage Liver Disease (MELD) score is a commonly used approach to prioritize patients, but previous studies have indicated that MELD score may fail to predict well for the postoperative patients. This work proposes to use data-driven approach to devise a predictive model to predict postoperative survival within 30 days based on patient’s preoperative physiological measurement values. We use random forest (RF) to select important features, including clinically used features and new features discovered from physiological measurement values. Moreover, we propose a new imputation method to deal with the problem of missing values and the results show that it outperforms the other alternatives. In the predictive model, we use patients’ blood test data within 1–9 days before surgery to construct the model to predict postoperative patients’ survival. The experimental results on a real data set indicate that RF outperforms the other alternatives. The experimental results on the temporal validation set show that our proposed model achieves area under the curve (AUC) of 0.771 and specificity of 0.815, showing superior discrimination power in predicting postoperative survival.
Highlights
Liver transplantation is one of the most effective treatments in treating acute liver failure, chronic liver cirrhosis and even hepatocellular carcinomas[1]
It is worth mentioning that these features are accessible, and our model focuses on short-term survival after the surgery of liver transplantation
Random forest[29] (RF) is a state-of-the-art algorithm, and it could provide feature importance based on the out-of-bag samples and permutation test, in which informative variables produce a systematic decrease in accuracy when permuted
Summary
Liver transplantation is one of the most effective treatments in treating acute liver failure, chronic liver cirrhosis and even hepatocellular carcinomas[1]. This work proposes to use machine learning to develop a prediction model for the postoperative survival of liver transplantation, since machine learning does not assume the distribution of the underlying data and many state-of-the-art algorithms have been devised over the decades[24,25,26]. A previous study used classification trees to predict a candidate’s 3-month wait-list mortality with Standard Transplant Analysis and Research (STAR) data set, providing more accurate and objective predictions than MELD in prioritizing candidates for liver transplantation[27]. The objective of this research is to use data-driven technique to develop a predictive model to predict postoperative survival within 30 days for the patients who have undergone liver transplantation. We developed the prediction with the derivation set, and validated the model with temporal validation set
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have