A CT-based radiomics nomogram for distinguishing between benign and malignant bone tumours

Cancer Imaging

Table 5 Results of radiomics nomogram, radiomics signature, and the clinical model predictive ability for distinguishing between malignant and benign bone tumour

Variables	Group	AUC (95% CI)	Accuracy	Sensitivity	Specificity	PPV	NPV
Clinical model	Train	0.858 (0.799–0.917)	0.813	0.876	0.727	0.780	0.814
Clinical model	Validation	0.815 (0.696–0.934)	0.745	0.586	0.955	0.944	0.636
Radiomics signature	Train	0.892 (0.842–0.942)	0.832	0.854	0.803	0.854	0.803
Radiomics signature	Validation	0.781 (0.643–0.918)	0.804	0.793	0.818	0.852	0.750
Radiomics nomogram	Train	0.917 (0.871–0.963)	0.871	0.854	0.894	0.916	0.819
Radiomics nomogram	Validation	0.823 (0.686–0.959)	0.863	0.931	0.773	0.844	0.895

AUC Area under the curve, CI Confidence interval, PPV Positive predictive value, NPV Negative predictive value

ISSN: 1470-7330