Uncertainty-Aware Multi-view Arrhythmia Classification from ECG
This work addresses arrhythmia classification for medical diagnosis, offering incremental improvements in accuracy and robustness to noise in ECG data.
The paper tackles arrhythmia classification from ECG by proposing an uncertainty-aware multi-view deep neural architecture that learns 1D and 2D views to capture different information and fuses them to reduce conflicts from noise, resulting in improved performance and better robustness compared to state-of-the-art methods on two real-world datasets.
We propose a deep neural architecture that performs uncertainty-aware multi-view classification of arrhythmia from ECG. Our method learns two different views (1D and 2D) of single-lead ECG to capture different types of information. We use a fusion technique to reduce the conflict between the different views caused by noise and artifacts in ECG data, thus incorporating uncertainty to obtain stronger final predictions. Our framework contains the following three modules (1) a time-series module to learn the morphological features from ECG; (2) an image-space learning module to learn the spatiotemporal features; and (3) the uncertainty-aware fusion module to fuse the information from the two different views. Experimental results on two real-world datasets demonstrate that our framework not only improves the performance on arrhythmia classification compared to the state-of-the-art but also shows better robustness to noise and artifacts present in ECG.