BMC Medical Informatics and Decision Making

Table 3 Comparison of 10-fold Cross-validation Model Performance (mean±std)

From: Enhancing heart failure treatment decisions: interpretable machine learning models for advanced therapy eligibility prediction using EHR data

	Accuracy	F1	AUC	AUPRC	Cohen’s D (\(S\vert P\))
S-LTR	0.832 (0.044)	0.708 (0.086)	0.903 (0.047)	0.836 (0.11)
P-LTR	0.826 (0.055)	0.670 (0.12)	0.869 (0.087)	0.839 (0.11)
LR	0.828 (0.049)	0.642 (0.15)	0.841 (0.11)	0.811 (0.13)	\(0.733\ \vert \ 0.282\)
SVM	0.837 (0.052)	0.657 (0.15)	0.823 (0.091)	0.792 (0.13)	\(1.104\ \vert \ 0.517\)
Gaussian NB	0.744 (0.066)	0.603 (0.13)	0.795 (0.10)	0.747 (0.15)	\(1.382\ \vert \ 0.790\)
RF	0.844 (0.041)	0.656 (0.14)	0.829 (0.096)	0.803 (0.13)	\(0.979\ \vert \ 0.437\)

* S-LTR Standard LTR, P-LTR Personalized LTR, Cohen’s D (\(S\vert P\)): Cohen’s D is computed by comparing the AUC values of various models with those of S-LTR and P-LTR model

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com