Skip to main content

Table 3 The results for the eight candidate models between before and after NCR treatment

From: A stacking-based model for predicting 30-day all-cause hospital readmissions of patients with acute myocardial infarction

Model

AUC

Sensitivity

Before

After

Before

After

DT

0.665 ± 0.03

0.664 ± 0.02

0.287 ± 0.09

0.385 ± 0.08*

SVM

0.621 ± 0.01

0.662 ± 0.02*

0.161 ± 0.02

0.393 ± 0.03*

RF

0.700 ± 0.02

0.701 ± 0.02

0.338 ± 0.04

0.444 ± 0.03*

ET

0.705 ± 0.02

0.709 ± 0.02

0.289 ± 0.04

0.453 ± 0.03*

GB

0.698 ± 0.02

0.702 ± 0.02

0.338 ± 0.04

0.460 ± 0.04*

ADB

0.684 ± 0.03

0.680 ± 0.03

0.351 ± 0.04

0.424 ± 0.04*

Bagging

0.700 ± 0.02

0.705 ± 0.02

0.399 ± 0.04

0.498 ± 0.04*

XGB

0.702 ± 0.02

0.706 ± 0.02

0.371 ± 0.04

0.468 ± 0.03*

  1. Font bold: the better values; *: there is a statistically significant difference between before and after NCR treatment (p-value < 0.05). DT Decision tree, SVM Support vector machine, RF Random forest, ET Extra trees, GBDT Gradient boosting decision tree, ADB AdaBoost, Bagging Bootstrap aggregating, XGB Extreme gradient boosting
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us