Development of a nomogram-based model incorporating radiomic features from follow-up longitudinal lung CT images to distinguish invasive adenocarcinoma from benign lesions: a retrospective study

Table 3 Prediction performance of the models in the training and validation sets

	Models	AUC	95%CI	Sensitivity	Specificity
Training set	CR model	0.694	0.630–0.752	0.45	0.85
	T0 model	0.825	0.770–0.871	0.84	0.67
	T1 model	0.858	0.857-0.900	0.71	0.86
	Delta model	0.734	0.673–0.789	0.60	0.80
	Nomogram	0.906	0.881–0.953	0.80	0.88
Validation set	CR model	0.578	0.457–0.658	0.21	0.96
	T0 model	0.789	0.731–0.839	0.80	0.65
	T1 model	0.817	0.749–0.854	0.83	0.75
	Delta model	0.647	0.591–0.716	0.49	0.77
	Nomogram	0.856	0.851–0.933	0.77	0.85

CR model clinicoradiological model, T0 model T0 radiomic model, T1 model T1 radiomic model, Delta model Delta radiomic model.

ISSN: 1471-2466