Table 8.

Sample classification after LDA to discriminate between CSF samples from patients with Relapse–remitting multiple sclerosis (RRMS) and non-inflammatory diseases of the CNS (N-INF) based on the identified protein spots

	Classification resultsb,c
	Disease	Predicted Group Membership		Total
		RRMS	N-INF
Original
Count	RRMS	67	2	69
	N-INF	12	30	42
%	RRMS	97.1	2.9	100
	N-INF	28.6	71.4	100
Cross-validateda
Count	RRMS	67	2	69
	N-INF	14	28	42
%	RRMS	97.1	2.9	100
	N-INF	33.3	66.7	100

^aCross validation is done only for those cases in the analysis. In cross validation, each sample is classified by the functions derived from all samples other than the one under analysis

^b87.4% of original grouped cases correctly classified

^c85.6% of cross-validated grouped cases correctly classified