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
Max net savings ($M)
Accuracy
DUNs (proposed)
3.403 ± 0.536
0.764 ± 0.014
Maxout networks
3.241 ± 0.561
0.754 ± 0.014
Logistic regression
2.173 ± 0.357
0.750 ± 0.018
Gradient boosting
1.787 ± 0.428
0.739 ± 0.016