Key result
An ensemble model of residual neural networks pre-trained on a large institutional dataset and re-trained on challenge data achieved a full test score of 0.141, placing 27th out of 41 teams.
Why the study?
The study was conducted as part of the PhysioNet/Computing in Cardiology Challenge 2020 to build computational methods to identify cardiac abnormalities from 12-lead ECGs.
Does an ensemble model of residual neural networks using transfer learning accurately identify cardiac abnormalities from 12-lead ECGs?
Does an ensemble model of residual neural networks using transfer learning accurately identify cardiac abnormalities from 12-lead ECGs?
Answers are grounded in this paper and cite their sources.
An ensemble residual neural network model utilizing transfer learning demonstrated modest performance in identifying cardiac abnormalities from 12-lead ECGs in a standardized computational challenge.
This article concerns the PhysioNet/Computing in Cardiology Challenge 2020 which focused on building computational methods to identify cardiac abnormalities from 12-lead ECGs. Our team, MCIRCC, utilized a large secondary dataset of 12-lead ECGs obtained from the Section of Electrophysiology at the University of Michigan, called the MUSE dataset, to pre-train multiple residual neural networks that were later re-trained on the challenge dataset. To do so, the diagnosis statements that existed in our dataset were utilized to assign the same labels to our ECGs as the challenge data. After parameter optimization, we selected a subset of top performing models and created an ensemble model that achieved a challenge validation score of 0.616, and full test score of 0.141, placing us 27 th out of 41 teams in the official ranking.
No takes yet. Share an insight, caveat, or question.
Ansari et al. (2020) studied Cardiac abnormalities (n=374,321). Residual Neural Networks and Transfer Learning was evaluated on Challenge full test score. An ensemble model of residual neural networks pre-trained on a large institutional dataset and re-trained on challenge data achieved a full test score of 0.141, placing 27th out of 41 teams.
Synapse has enriched 10 related papers. Consider them for comparative context: