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

Table 3

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

Model	Accuracy	AUC	Precision	Recall rate	F1-score
DT	0.764	0.930	0.782	0.724	0.752
RF	0.890	0.946	0.847	0.946	0.894
SVC	0.781	0.853	0.761	0.811	0.785
KNN	0.830	0.918	0.777	0.917	0.836
GBM	0.813	0.883	0.788	0.848	0.817
XGBoost	0.879	0.934	0.851	0.915	0.882

AUC, area 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.