[Retracted] Prediction of Changes in Tumor Regression during Radiotherapy for Nasopharyngeal Carcinoma by Using the Computed Tomography-Based Radiomics

Table 2

Statistics on the diagnostic efficacy of different models in the training and validation groups.

Model	Group	Sensitivity	Specificity	PPV	NPV	Accuracy	F1
Logistic	Training	0.800	0.622	0.721	0.718	0.720	0.759
	Test	0.792	0.350	0.594	0.583	0.591	0.679
Decision tree	Training	0.909	0.711	0.794	0.865	0.820	0.847
	Test	0.917	0.400	0.647	0.800	0.682	0.759
Random forest	Training	1.000	1.000	1.000	1.000	1.000	1.000
	Test	0.875	0.550	0.700	0.786	0.727	0.778
SVM	Training	0.909	0.622	0.746	0.848	0.780	0.820
	Test	0.875	0.250	0.583	0.625	0.591	0.700
AdaBoost	Training	0.782	0.867	0.878	0.765	0.820	0.827
	Test	0.792	0.450	0.633	0.643	0.636	0.704