A Wide and Deep Transformer Neural Network for 12-Lead ECG Classification

• Published in: 2020 Computing in Cardiology pp. 1 - 4
• Main Authors: Natarajan, Annamalai, Chang, Yale, Mariani, Sara, Rahman, Asif, Boverman, Gregory, Vij, Shruti, Rubin, Jonathan
• Format: Conference Proceeding
• Language: English
• Published: Creative Commons; the authors hold their copyright 13.09.2020
• Subjects: Cardiology; Classification algorithms; Electrocardiography; Measurement; Neural networks
• ISSN: 2325-887X
• DOI: 10.22489/CinC.2020.107

Cardiac abnormalities are a leading cause of death and their early diagnosis are of importance for providing timely interventions. The goal of 2020 PhysioNetlCinC 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-ioN etlCinC challenge placed 1st 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.