Table 2.

The performance of the support vector machine (SVM) classification obtained by cross-validation for predicting cervical cancer recurrence at four weeks after chemoradiotherapy initiated.

Imaging	Dataset	Sensitivity	Specificity	Accuracy	PPV	NPV	AUC
T2WI	Training	0.80	0.85	0.83	0.71	0.91	0.83
	Testing	0.46	0.76	0.65	0.60	0.71	0.61
ADC	Training	1.00	1.00	1.00	1.00	1.00	0.98
	Testing	0.47	0.87	0.71	0.63	0.74	0.74
T2WI + ADC	Training	0.90	0.91	0.91	0.84	0.96	0.94
	Testing	0.47	0.80	0.68	0.61	0.73	0.73

Note: PPV = positive predictive value; NPV = negative predictive value; AUC = area under the curve; ADC = apparent diffusion coefficient.