Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive Thresholding

Automatic electrocardiogram (ECG) classification is a promising technology for the early screening and follow-up management of cardiovascular diseases. It is, by nature, a multi-label classification task owing to the coexistence of different kinds of diseases, and is challenging due to the large number of possible label combinations and the imbalance among categories. Furthermore, the task of multi-label ECG classification is cost-sensitive, a fact that has usually been ignored in previous studies on the development of the model. To address these problems, in this work, we propose a novel deep learning model-based learning framework and a thresholding method, namely category imbalance and cost-sensitive thresholding (CICST), to incorporate prior knowledge about classification costs and the characteristic of category imbalance in designing a multi-label ECG classifier. The learning framework combines a residual convolutional network with a class-wise attention mechanism. We evaluate our method with a cost-sensitive metric on multiple realistic datasets. The results show that CICST achieved a cost-sensitive metric score of 0.641 & PLUSMN; 0.009 in a 5-fold cross-validation, outperforming other commonly used thresholding methods, including rank-based thresholding, proportion-based thresholding, and fixed thresholding. This demonstrates that, by taking into account the category imbalance and predefined cost information, our approach is effective in improving the performance and practicability of multi-label ECG classification models.

Automated summary

This study proposes a novel deep learning model-based learning framework and thresholding method for designing multi-label ECG classifiers, and evaluates the method on multiple realistic datasets with a cost-sensitive metric, showing superior performance in cost sensitivity.