BME Frontiers / 2022 / Article / Tab 2

Research Article

Automatic Detection of Atrial Fibrillation from Single-Lead ECG Using Deep Learning of the Cardiac Cycle

Table 2

Comparison of performance of different AF detection algorithms evaluated on Physionet Challenge data. For our approaches, average -score, sensitivity, specificity, PPV, area under the ROC curve (AUC), and accuracy (ACC) of 10-fold cross-validation are presented with the standard deviation. values marked with are estimated from the corresponding sensitivity and PPV reported in the literature.

MethodSensitivitySpecificityPPVAUCACC

DHB+RNN
P-DHB+RNN
S-DHB+RNN
DHB+avg
P-DHB+avg
S-DHB+Avg
MS-CNN [20]90.589.798.891.497.8
AliveCor [20]85.090.0
VGGNet [20]86.5787.998.185.396.9
CNN [36]58.459.993.456.989.1