Application of contrast-enhanced CT radiomics in prediction of early recurrence of locally advanced oesophageal squamous cell carcinoma after trimodal therapy

Table 3 The performance of the three constructed models to predict early recurrence of locally advanced oesophageal squamous cell carcinoma

Cohort	Prediction model	AUC	ACC	F1-score	Sen	Spe	PPV	NPV
The training cohort	Integrated model of radiomics and clinical features	0.821	0.730	0.730	0.735	0.725	0.725	0.735
	The radiomics model	0.754	0.682	0.690	0.694	0.662	0.694	0.662
	The clinical model	0.679	0.671	0.671	0.592	0.606	0.652	0.544
The validation cohort	Integrated model of radiomics and clinical features	0.809	0.733	0.778	0.761	0.720	0.718	0.762
	The radiomics model	0.646	0.630	0.631	0.655	0.613	0.613	0.655
	The clinical model	0.658	0.667	0.567	0.417	0.722	0.500	0.650
Notes: AUC, Area under the receiver operating characteristic curve; ACC, Accuracy; Sen, Sensitivity; Spe, Specificity; PPV, Positive predictive value; and NPV, Negative predictive value.

ISSN: 1470-7330