For inpatients with cirrhosis, a machine learning (ML) model using random forest (RF) analysis is superior for prediction of ...

ROC curves and AUC statistics were produced using the ROCR package 39. To construct the ROC curves, the 1:1 subpool P -values were the true-negative group for each differential ratio ROC curve.

A model using age, family history, and the 11 risk SNPs had an AUC of 0.65, better than the 0.50 level that represents chance alone and similar to the 0.68 for PSA.

The mean overall cost was determined to be $44,953. The prediction models had ROC AUC statistics of 0.82 at the first time point and 0.89 at the second time point in training set, ...