Noninvasive molecular diagnosis of craniopharyngioma with MRI-based radiomics approach

BMC Neurology

Table 2 Pathological types, BRAF gene and CTNNB1 gene status differentiation performance in different datasets

	Dataset		AUC	ACC	SENS	SPEC	PPV	NPV	MCC	OOB
Pathological types	n = 32	BS	0.69	0.63	0.38	0.79	0.56	0.65	0.19	0.66
	n = 32	AS	0.96	0.91	0.92	0.89	0.86	0.94	0.81	0.91
	n = 44	–	0.89	0.86	0.89	0.85	0.80	0.92	0.73	0.85
BRAF gene	n = 32	BS	0.59	0.69	0.11	0.91	0.33	0.72	0.04	0.63
	n = 32	AS	0.92	0.94	0.89	0.96	0.89	0.96	0.85	0.91
	n = 44	–	0.91	0.93	0.83	0.97	0.91	0.94	0.83	0.93
CTNNB1 gene	n = 32	BS	0.74	0.72	0.73	0.71	0.69	0.75	0.44	0.66
	n = 32	AS	0.95	0.91	0.93	0.88	0.88	0.94	0.81	0.88
	n = 44	–	0.93	0.86	0.86	0.86	0.86	0.86	0.73	0.86

ISSN: 1471-2377