Improving the Specificity of EEG for Diagnosing Alzheimer's Disease

Table 1

LDA results, for WTFR and Bump amplitude. LOO = Leave-one-out validation error (classification error). SEN = sensitivity. SPE = specificity. In both cases, the best discriminating frequency range is in the theta range. Classification, sensitivity, and specificity are improved by bump modeling.

	𝜃 (3.5–7.5 Hz)	𝛼1 (7.5–9.5 Hz)	𝛼2 (9.5–12.5 Hz)	𝛽 (12.5–25 Hz)
WTFR	LOO = 33.3%	LOO = 46.7%	LOO = 81.7%	LOO = 48.3%
	SEN = 50.0%	SEN = 27.3%	SEN = 18.2%	SEN = 59.1%
	SPE = 76.3%	SPE = 68.4%	SPE = 18.4%	SPE = 47.4%
Bumps	LOO = 21.7%	LOO = 76.7%	LOO = 51.7%	LOO = 41.7%
	SEN = 72.3%	SEN = 18.2%	SEN = 40.9%	SEN = 68.2%
	SPE = 81.6%	SPE = 26.3%	SPE = 52.6%	SPE = 52.6%