Title | ||
---|---|---|
Rhythm Classification Of 12-Lead Ecgs Using Deep Neural Networks And Class-Activation Maps For Improved Explainability |
Abstract | ||
---|---|---|
As part of the PhysioNet/Computing in Cardiology Challenge 2020, we developed a model for multilabel classification of 12-lead electrocardiogram (ECG) data according to specified cardiac abnormalities. Our team, LaussenLabs, developed a novel classifier pipeline with 6 core features (1) the addition of r-peak, p-wave, and t-wave features that were input into the model along with the 12-lead data, (2) data augmentation, (3) competition metric hacking, (4) modified WaveNet architecture, (5) Sigmoid threshold tuning, and (6) model stacking. Our approach received a score of 0.63 using 6-fold cross-validation on the full training data. Unfortunately, our model was unable to run on the test dataset due to time constraints, therefore, our model's final test score is undetermined. |
Year | DOI | Venue |
---|---|---|
2020 | 10.22489/CinC.2020.353 | 2020 COMPUTING IN CARDIOLOGY |
DocType | ISSN | Citations |
Conference | 2325-8861 | 0 |
PageRank | References | Authors |
0.34 | 0 | 12 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sebastian D. Goodfellow | 1 | 0 | 0.34 |
Dmitrii Shubin | 2 | 0 | 0.34 |
Robert W. Greer | 3 | 0 | 0.34 |
Sujay Nagaraj | 4 | 0 | 0.34 |
Carson McLean | 5 | 0 | 0.34 |
Will Dixon | 6 | 0 | 0.34 |
Andrew J. Goodwin | 7 | 0 | 0.34 |
Azadeh Assadi | 8 | 0 | 0.34 |
Anusha Jegatheeswaran | 9 | 0 | 0.34 |
Peter C. Laussen | 10 | 0 | 0.34 |
Mjaye Mazwi | 11 | 1 | 0.68 |
Danny Eytan | 12 | 1 | 2.85 |