Classifying Cardiac Abnormalities in 12-Lead ECG Using Wide and Deep Transformer Neural Networks

A talk by Jonathan Rubin
Senior Scientist, Philips Research

Register to watch this content

By submitting your email you agree to the Terms of Service and Privacy Statement
Watch this content now

Stages covered by this talk

About this talk

Cardiac abnormalities are a leading cause of death and their early diagnosis is important for providing timely interventions. The performance of modern, automated algorithms for classifying cardiac abnormalities from 12-lead ECG data was recently investigated at the 2020 PhysioNet / Computing in Cardiology Challenge. As part of the 2020 challenge the world’s largest open access database of 12-lead ECGs was released, which was drawn from three continents with diverse and distinctly different populations. In this talk, I will present our winning entry to the 2020 PhysioNet Challenge that combines both traditional hand-crafted ECG features, together with a novel deep learning architecture that learns discriminative feature representations.

Have you got yours yet?

Our All-Access Passes are a must if you want to get the most out of this event.

Check them out

Proudly supported by

Want to sponsor this event? contact us.