Table 2.

Performance of prognostic models built by machine learning algorithms in the training and test sets (area under the ROC curve)

	1-year survival	3-year survival	5-year survival
Training set
XGBoost	0.771	0.763	0.807
LR	0.758	0.756	0.753
SVM	0.703	0.687	0.686
RF	0.761	0.760	0.754
KNN	0.746	0.744	0.786
ID3	0.762	0.752	0.748
Test set
XGBoost	0.782	0.749	0.740
LR	0.750	0.740	0.708
SVM	0.734	0.739	0.715
RF	0.779	0.753	0.718
KNN	0.631	0.607	0.586
ID3	0.750	0.718	0.699

ROC receiver operating characteristic curve; XGBoost extreme gradient boosting; LR logistic regression; SVM support vector machine; RF random forest; KNN K-nearest neighbor; ID3 decision tree