Fig. 4From: Multiphase CT-based prediction of Child-Pugh classification: a machine learning approachConfusion matrix for the prediction of low disease severity (Child-Pugh class A) and advanced disease severity (Child-Pugh class ≥ B). Linear regression (LR), random forest (RF), convolution neural network (CNN), and experienced radiologists (ERs). Values in brackets are relative to the numbers of patient in the ground truth Child-Pugh class.Back to article page