Multi-Class Classification of Pathologies Found on Short ECG Signals

Abstract

The ability to detect several key cardiac pathologies simultaneously, based on ECG signals, is key towards establishing a real-world application of AI models in cardiology. Such a multi-label classification task requires not only well-performing binary classification models, but also a way to combine such models into an overall classification modeling structure. We have approached this task using materials from Classification of 12-1ead ECGs for the PhysioNet/Computing in Cardiology Challenge 2020. Duplicate ECG strips have been removed. An annotation tool for labeling ECG wave points and intervals/templates has been created in MATLAB®, and used for labeling pathological intervals, as well as noisy intervals and inconsistencies between the ECG data and the pre-assigned labels. Several one-vs-rest binary classifiers were built, where morphological features specific to each pathology had been generated from the signals. The binary classifiers were augmented by a multi-class classifier using an Error Correcting Output Codes (ECOC) methodology. Our approach achieved a challenge validation score of 0.616, and full test score of 0.194, placing us 23 (team DSC) out of 41 in the official ranking.