A multi-layer cascaded binary classifier achieved an overall F1-score of 0.83 on the Physionet 2017 hidden test dataset for classifying normal, atrial fibrillation, and other abnormal ECG rhythms.
A two-layer cascaded binary classifier effectively identifies normal, AF, and other abnormal rhythms from short single-lead ECG recordings with high F1-scores.
In this paper, we present a methodology for classifying normal, atrial fibrillation (AF), non-AF related other abnormal heart rhythms and noisy recordings by analysing single lead ECG signal of short duration. In a two layer binary cascaded approach proposed in our methodology, an unlabelled recording is initially classified into one of the two intermediate classes ('normal+others' and 'AF+noisy') at the first layer before actual classification at the second layer. The Physionet Challenge 2017 dataset containing more than 8500 ECG recordings are used for creation of training models and interval validation. The proposed methodology yields an average F1-score of 0.91, 0.79 and 0.77 respectively in classifying normal, AF and other rhythms on the training dataset using 5-fold cross validation. Results also show that, the said methodology, when applied on a hidden test set maintained by the challenge organisers yields F1-score values of 0.92, 0.86 and 0.74 in classifying the same.
Datta et al. (2017) studied Atrial Fibrillation and other abnormal ECG rhythms (n=8,528). Cascaded binary classifier was evaluated on Overall F1-score on hidden test dataset. A multi-layer cascaded binary classifier achieved an overall F1-score of 0.83 on the Physionet 2017 hidden test dataset for classifying normal, atrial fibrillation, and other abnormal ECG rhythms.