Table 1.
Comparison of performance of the proposed model against other algorithms on the MIT-BIH AFIB database with the ECG segment of size 5-s.
| Method | Database | Best Performance (%) | |||
|---|---|---|---|---|---|
| Sensitivity | Specificity | Accuracy | AUC | ||
| HAN-ECG3 | AFDB | 99.08 | 98.54 | 98.81 | 99.86 |
| HAN-ECG2 | AFDB | 98.88 | 98.78 | 98.83 | 99.85 |
| HAN-ECG1 | AFDB | 98.87 | 98.62 | 98.74 | 99.84 |
| RNN | AFDB | 98.72 | 98.44 | 98.58 | 99.80 |
| HAN-ECG2f | AFDB | 98.68 | 98.36 | 98.52 | 99.79 |
| Xia et al. (2018) [31] | AFDB | 98.79 | 97.87 | 98.63 | – |
| Asgari et al. (2015) [2] | AFDB | 97.00 | 97.10 | – | – |
| Lee et al. (2013) [14] | AFDB | 98.20 | 97.70 | – | – |
| Jiang et al. (2012) [10] | AFDB | 98.20 | 97.50 | – | – |
| Huang et al. (2011) [9] | AFDB | 96.10 | 98.10 | – | – |
| Babaeizadeh et al. (2009) [3] | AFDB | 92.00 | 95.50 | – | – |
| Dash et al. (2009) [4] | AFDB | 94.40 | 95.10 | – | – |
| Tateno et al. (2001) [30] | AFDB | 94.40 | 97.20 | – | – |
| Petrenas et al. (2015) [21] | AFDB | 97.1 | 98.3 | – | – |
| Zhou et al. (2014)[34] | AFDB | 96.89 | 98.25 | 97.62 | – |