Skip to main content

Table 5 Summary of the results for the baseline model on test set using the same inputs (TSS, demographics, and severity scores) as fed to the proposed model

From: Prediction of unplanned 30-day readmission for ICU patients with heart failure

Models

AUROC

AUROC 95% CI

Precision

Sensitivity

Accuracy

F-score

RF

0.841

[0.793–0.864]

0.820

0.803

0.830

0.771

XGBoost

0.832

[0.748–0.843]

0.812

0.792

0.813

0.773

CatBoost

0.830

[0.779–0.859]

0.780

0.801

0.829

0.763

SVM

0.801

[0.763–0.843]

0.775

0.802

0.829

0.765

Decision tree

0.820

[0.740–0.851]

0.802

0.751

0.718

0.737

KNN

0.821

[0.737–0.853]

0.810

0.803

0.823

0.761

  1. RF, random forest; SVM, support vector machine; KNN, K-nearest neighbors
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us