BMC Medical Imaging

Table 3 The value of Different Clinical-Radiomics Models in Training cohort and Validation cohort

From: Radiomics analysis based on CT for the prediction of pulmonary metastases in ewing sarcoma

	Train							Validation
	AUC	ACC	95%CI	Sensitivity	Specificity			AUC	ACC	95%CI	Sensitivity	Specificity
CT _ clinical
GP	0.887	0.824	0.833–0.933	0.820	0.831			0.795	0.793	0.635–0.923	0.867	0.714
LR	0.862	0.833	0.798–0.914	0.885	0.774			0.810	0.724	0.639–0.916	0.800	0.643
PLS-DA	0.848	0.781	0.782–0.903	0.770	0.792			0.800	0.724	0.636–0.914	0.733	0.714
CTE _ clinical
GP	0.840	0.781	0.773–0.896	0.820	0.736			0.843	0.828	0.697–0.952	0.867	0.786
LR	0.835	0.798	0.760–0.894	0.787	0.811			0.843	0.793	0.692–0.949	0.733	0.857
PLS-DA	0.795	0.772	0.717–0.860	0.770	0.773			0.824	0.793	0.657–0.938	0.867	0.714
ComB _ clinical
GP	0.872	0.798	0.812–0.919	0.738	0.868			0.824	0.759	0.676–0.929	0.800	0.714
LR	0.869	0.781	0.811–0.919	0.803	0.736			0.833	0.793	0.688–0.938	0.800	0.786
PLS-DA	0.852	0.763	0.789–0.905	0.738	0.717			0.843	0.828	0.697–0.952	0.800	0.857

Note. AUC area under the receiver-operating characteristic curve, ACC accuracy, GP gaussian process, LR logistic regression, PLS-DA partial least-squares discrimination analysis, CT computed tomography, CTE CT-enhanced, ComB, the combination of CT_clinical and CTE_clinical models

Back to article page

ISSN: 1471-2342

Contact us

General enquiries: journalsubmissions@springernature.com