Masked Transformer for Electrocardiogram Classification

no code implementations • 31 Aug 2023 • Ya Zhou, Xiaolin Diao, Yanni Huo, Yang Liu, Xiaohan Fan, Wei Zhao

The experiments demonstrate that the proposed method increases the macro F1 scores by 3. 4%-27. 5% on the Fuwai dataset, 9. 9%-32. 0% on the PTB-XL dataset, and 9. 4%-39. 1% on a multicenter dataset, compared to the alternative methods.

Classification ECG Classification +2