A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: a retrospective analysis of electronic medical records data

Table 5 10-fold CV Results

	AUC mean ± sd	Accuracy mean ± sd	Precision mean ± sd	Recall mean ± sd	f1 mean ± sd
Logistic regression	0.664 ± 0.015	0.626 ± 0.020	0.336 ± 0.014	0.616 ± 0.029	0.435 ± 0.012
Gradient boosting	0.650 ± 0.011	0.612 ± 0.013	0.325 ± 0.008	0.615 ± 0.032	0.425 ± 0.010
Maxout networks	0.695 ± 0.016	0.645 ± 0.016	0.354 ± 0.016	0.631 ± 0.016	0.454 ± 0.016
DUNs (proposed)	0.705 ± 0.015	0.646 ± 0.018	0.360 ± 0.015	0.652 ± 0.036	0.464 ± 0.013

ISSN: 1472-6947