Interpreting Deep Neural Networks for Single-Lead ECG Arrhythmia Classification
This addresses the need for interpretability in deep learning models for ECG diagnosis, which is crucial for clinical adoption but is incremental as it builds on existing methods.
The authors tackled the problem of interpreting deep neural networks for single-lead ECG arrhythmia classification by proposing two methods, Grad-CAM and input deletion masks, to visualize model saliency, with results aligning with medical literature.
Cardiac arrhythmia is a prevalent and significant cause of morbidity and mortality among cardiac ailments. Early diagnosis is crucial in providing intervention for patients suffering from cardiac arrhythmia. Traditionally, diagnosis is performed by examination of the Electrocardiogram (ECG) by a cardiologist. This method of diagnosis is hampered by the lack of accessibility to expert cardiologists. For quite some time, signal processing methods had been used to automate arrhythmia diagnosis. However, these traditional methods require expert knowledge and are unable to model a wide range of arrhythmia. Recently, Deep Learning methods have provided solutions to performing arrhythmia diagnosis at scale. However, the black-box nature of these models prohibit clinical interpretation of cardiac arrhythmia. There is a dire need to correlate the obtained model outputs to the corresponding segments of the ECG. To this end, two methods are proposed to provide interpretability to the models. The first method is a novel application of Gradient-weighted Class Activation Map (Grad-CAM) for visualizing the saliency of the CNN model. In the second approach, saliency is derived by learning the input deletion mask for the LSTM model. The visualizations are provided on a model whose competence is established by comparisons against baselines. The results of model saliency not only provide insight into the prediction capability of the model but also aligns with the medical literature for the classification of cardiac arrhythmia.