BMC Medical Informatics and Decision Making

Table 3 Pairwise statistical significance tests between model performances (MCC values) of the models with and without RFE on the validation data

From: Creating sparser prediction models of treatment outcome in depression: a proof-of-concept study using simultaneous feature selection and hyperparameter tuning

	MCC		z	p
	RFE	No RFE	z	p
Clinical data (N = 205)
LR	0.425	0.350	0.888	0.375
RF	0.237	0.224	0.138	0.890
SVC	0.403	0.365	0.448	0.654
Simulated data (N = 200)
LR	0.718	0.719	− 0.021	0.984
RF	0.700	0.724	− 0.483	0.629
SVC	0.709	0.688	0.407	0.684

LR, logistic regression; MCC, Matthews correlation coefficient; RF, random forest classifier; RFE, recursive feature elimination; SVC, support vector classifier

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com