Table 3.

Summary of the abovementioned comparisons with regard to the classifications applied.

Classification	Sample size	Data collection	Feature selection	Validation	Model	Accuracy
Common	12-40	1 site	Spectral analysis	Often missing	SVMa	Typically >95% or 99%
Recommended	>50-100	Multiple sites/collaborative (possible extraction from MRIb sets)	Nonlinear analysis	Internal plus external validation on unseen data	LASOc, embedded regularization	ROCd curve application/more realistic results

^aSVM: support vector machine.

^bMRI: magnetic resonance imaging.

^cLASO: the name of the algorithm; a type of linear regression that uses shrinkage.

^dROC: receiver operating characteristic.