Skip to main content
. 2021 Jun 17;11:12818. doi: 10.1038/s41598-021-92172-5

Figure 2.

Figure 2

Multiclass ROC curves with deep neural networks applied in the internal and external datasets. The micro-average and macro-average AUC derived from the ROC curve of the AI algorithm is calculated during the internal and external validations (0.78 [95% CI 0.76–0.80], 0.79 [95% CI 0.78–0.80] for internal validation dataset; 0.75 [95% CI 0.74–0.76], 0.75 [95% CI 0.74–0.76] for external validation dataset). ROC receiver operating characteristic; AUC area under the ROC curve. Class 0: healthy-NSR, Class 1: PAF-NSR.