Key result
Wide and deep transformer neural network achieves top score classifying 27 cardiac abnormalities.
Why the study?
Cardiac abnormalities are a leading cause of death, making early diagnosis important for timely interventions, motivating the development of algorithms to diagnose multiple abnormalities from 12-lead ECG data.
A wide and deep transformer neural network combining handcrafted and deep features achieved the top score in the 2020 PhysioNet/CinC challenge for classifying 12-lead ECG abnormalities.
Achieves top score in ECG abnormality challenge; leaves open prospective clinical validation before any practice integration.
Cardiac abnormalities are a leading cause of death and their early diagnosis are of importance for providing timely interventions. The goal of 2020 PhysioNet/CinC challenge was to develop algorithms to diagnose multiple cardiac abnormalities using 12-lead ECG data. In this work, we develop a wide and deep transformer neural network to classify each 12-lead ECG sequence into 27 cardiac abnormality classes. Our approach combines handcrafted ECG features, which were determined to be important by a random forest model, and discriminative feature representations that are automatically learned from a transformer neural network. Our entry to the 2020 Phys-ioNet/CinC challenge placed 1 st out of 41 official ranking teams (team name = prna). Using the official generalized weighted accuracy metric for evaluation, we achieved a validation score of 0.587 and top score of 0.533 on the full held-out test set.
No takes yet. Share an insight, caveat, or question.
Natarajan et al. (2020) studied Cardiac abnormalities. Wide and deep transformer neural network vs. Other challenge algorithms was evaluated on Official generalized weighted accuracy metric on the full held-out test set. A wide and deep transformer neural network combining handcrafted features and deep learned representations achieved a top score of 0.533 on the full test set for classifying 27 cardiac abnormalities.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: