Skip to main content

Table 3 The performance of the different prediction models on T2D readmission

From: The 30-days hospital readmission risk in diabetic patients: predictive modeling with machine learning classifiers

Groups

Models

Avg. AUC

30 days readmission

(over-sampling)

Random Forest

0.64

Naive Bayes

0.619

Tree Ensemble

0.634

30 days readmission

(down-sampling)

Random Forest

0.661

Naive Bayes

0.633

Tree Ensemble

0.659

Future readmission

Random Forest

0.686

Naive Bayes

0.652

Tree Ensemble

0.685

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us