BMC Pulmonary Medicine

Table 4 Operating characteristic of linear and non-linear models to classify IPF versus control status in the test set

From: Circulating matrix metalloproteinases and tissue metalloproteinase inhibitors in patients with idiopathic pulmonary fibrosis in the multicenter IPF-PRO Registry cohort

Model	AUC	Sensitivity	Specificity	Accuracy	Kappa
PLS	0.88	0.99	0.60	0.89	0.67
PLR	0.89	0.99	0.60	0.89	0.67
LDA	0.88	0.99	0.64	0.90	0.70
SVM	0.87	0.93	0.64	0.86	0.61
KNN	0.83	0.95	0.52	0.84	0.52
RPART	0.72	0.84	0.48	0.75	0.32
RF	0.87	0.96	0.64	0.88	0.65

AUC area under the curve, KNN K-nearest neighbors, LDA linear discriminant analysis, PLR penalized logistic regression, PLS partial least squares, RF random forests, RPART recursive partitioning; SVM, support vector machines

Back to article page

ISSN: 1471-2466

Contact us

Submission enquiries: bmcpulmonarymedicine@biomedcentral.com
General enquiries: ORSupport@springernature.com