Table 3 Model performances of difference machine learning algorithms.

From: Development and implementation of patient-level prediction models of end-stage renal disease for type 2 diabetes patients using fast healthcare interoperability resources

Model

LR

RF

SVM

XGB

AUPRC

AUROC

AUPRC

AUROC

AUPRC

AUROC

AUPRC

AUROC

count

9.000

9.000

9.000

9.000

9.000

9.000

9.000

9.000

mean

0.783

0.942

0.792

0.943

0.765

0.929

0.792

0.947

SD

0.012

0.002

0.015

0.005

0.011

0.007

0.009

0.004

ci_low

0.775

0.940

0.782

0.939

0.759

0.924

0.786

0.945

ci_high

0.790

0.943

0.800

0.946

0.772

0.933

0.797

0.950

  1. ci_low Lowest 95% confidence interval of experiments, ci_high Highest 95% confidence interval of experiments, SD Standard Deviation, AUPRC Area Under Precision-Recall Curve, AUROC Area Under Receiver-Operator Characteristics.
Back to article page