Skip to main content

Table 5 10-fold CV Results

From: 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

  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