Table 7.

Values of AUC obtained when analysing the best texture datasets (without feature selection) with and without including the textures extracted from the additional older patients.

AUC: Mean (SD)	GLRLM FLAIR – WMH		LBP FLAIR – SS		LBP T2W – SS		WCF FLAIR – NAWM		WCF T2W – WMH
	Without older patients	With older patients	Without older patients	With older patients	Without older patients	With older patients	Without older patients	With older patients	Without older patients	With older patients
RF	0.674 (0.108)	0.682 (0.089)a	0.742 (0.100)	0.655 (0.098)	0.680 (0.112)	0.623 (0.078)	0.761 (0.097)	0.645 (0.086)	0.752 (0.097)	0.678 (0.074)
SVM	0.770 (0.089)	0.736 (0.084)	0.751 (0.103)	0.644 (0.106)	0.763 (0.116)	0.670 (0.083)	0.637 (0.121)	0.580 (0.106)	<0.5	<0.5

AUC: area under the curve, RF: random forest classifier, SVM: support vector machine classifier, GLRM: grey–level run length matrix features, GLCM: grey-level co-occurrence matrix features, LBP: local binary patterns features, WCF: wavelet co-occurrence features, WSF: wavelet statistical features, NAWM: normal-appearing white matter, SS: subcortical structures, WMH: white matter hyperintensities.

^aException where the AUC increased after adding older patients.