Machine learning (ML) methods for the analysis of electrocardiography (ECG) data are gaining importance, and are supported by the release of large public datasets. However, these datasets lack important derived descriptors such as ECG features, which are critical for cardiologists’ decision processes. To address this issue, we add ECG features from two leading commercial algorithms and an open-source implementation, supplemented by a set of automatic diagnostic statements from a commercial ECG analysis software. This allows the comparison of ML models trained on clinically versus automatically generated label sets. We provide an extensive technical validation of features and diagnostic statements for ML applications, which will enhance the usability of the PTB-XL dataset as a reference dataset for ML methods in the context of ECG data.
Related Posts
