Machine Learning for Predicting Distant Metastasis of Medullary Thyroid Carcinoma Using the SEER Database

Table 4

Comparison of prediction performance between different models constructed from undersampling data.

Model	Accuracy	AUC	Precision	Recall rate	F1-score
DT	0.803	0.751	0.827	0.800	0.813
RF	0.732	0.769	0.741	0.766	0.754
SVC	0.750	0.784	0.750	0.800	0.774
KNN	0.714	0.789	0.750	0.700	0.760
GBM	0.785	0.814	0.781	0.833	0.806
XGBoost	0.767	0.768	0.774	0.800	0.786

AUC, are under the receiver operating characteristic curve; DT, decision tree; SVM, support vector machine; RF, random forest; KNN, k-nearest neighbors; XGBoost, extreme gradient boosting; GBM, gradient boosting machine.