Translational Psychiatry

Table 5 Classification between individuals with schizophrenia and TD.

From: Machine-learning classification using neuroimaging data in schizophrenia, autism, ultra-high risk and first-episode psychosis

		Schizophrenia and TD
		(Subcortical)			(Surface area)			(Cortical thickness)			(All features)
Classifier	Score (%)	Schi	ASD	All	Schi	ASD	All	Schi	ASD	All	Schi	ASD	All
Logistic regression	Mean accuracy			64.7						67.6			70.5
	Recall score	65.2	63.6					69.5	63.6		69.5	72.7
	Precision score	78.9	46.6					80.0	50.0		84.2	53.3
	F1/F2 scores	71.4/67.5	53.8/59.3					74.4/71.4	56.0/60.3		76.1/72.0	61.5/67.7
Support vector machine	Mean accuracy			67.6
	Recall score	73.9	54.5
	Precision score	77.2	50.0
	F1/ F2 scores	75.5/74.5	52.1/53.5
Random forest	Mean accuracy			76.4
	Recall score	82.6	63.6
	Precision score	82.6	63.6
	F1/F2 scores	82.6	63.6
AdaBoost	Mean accuracy			73.5
	Recall score	73.9	72.7
	Precision score	85.0	57.1
	F1/F2 scores	79.0/75.8	64.0/68.9
Decision tree	Mean accuracy									70.5
	Recall score							73.9	63.6
	Precision score							80.9	53.8
	F1/F2 scores							77.2/75.2	58.3/61.4

ASD autism spectrum disorder, TD typically developing, Schi schizophrenia, All whole brain or all features combined.

Back to article page

Search

Advanced search

Quick links