Atrial Fibrillation Detection Using Convolutional Neural Networks

Chandra, B S and Sastry, Challa Subrahmanya and Jana, Soumya and Patidar, S (2017) Atrial Fibrillation Detection Using Convolutional Neural Networks. Comput ing in Cardiology. pp. 1-4. ISSN 2325- 887X

Full text not available from this repository. (Request a copy)

Abstract

As part of the PhysioNet/Computing in Cardiology Challenge 2017, this work focuses on the classification of a single channel short electrocardiogram (ECG) sig- nal into normal, atrial fibrillation (AF), others and noise classes. To this end, we propose a shallow convolutional neural network architecture which learns suitable features pertaining to each class while eliminating the need to ex- tract the traditionally used ad hoc features. In particular, we first developed a robust R-peak detector and stacked sequence of fixed number of detected beats with R-peaks aligned. These stack of beats corresponding to a segment of ECG record are classified into one of the four afore- mentioned classes. To improve the robustness, multiple classifiers were trained to classify these segments. Over- all record classification was then generated using an vot- ing scheme from the classification results of individual seg- ments. Our best submission result during the official phase has a score of 71% with F1 scores of 86%, 73% and 56% respectively for normal, AF and other classes respectively.

[error in script]

IITH Creators: