Skip to main content

Table 2 Performances in discrimination and calibration of the three models

From: Comparison of discrimination and calibration performance of ECG-based machine learning models for prediction of new-onset atrial fibrillation

 

CNN

XGB

LR

AUC

0.799 (0.794, 0.805)

0.738 (0.732, 0.744)

0.683 (0.678, 0.688)

ICI

0.014 (0.01, 0.018)

0.008 (0.006, 0.01)

0.014 (0.013, 0.015)

Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us