This repository is meant to be a useful resource library for getting started with deep learning work using electrocardiograms.
Scripts and tutorial for extracting raw ECG waveforms from GE Muse or PDFs of ECGs. It also includes examples of how to display and review your ECG data.
Generate your own synthetic electrocardiograms. Comes with the ability to alter many different aspects of the waveform to test different hypotheses.
Key preprocessing steps for cleaning and normalizing ECG data.
Different example models we've built to showcase approaches that work for electrocardiograms, in pytorch and tensorflow/keras.
A framework built on PyTorch Ignite using Optuna to allow for rapid experimentation and displaying your results using Tensorboard
See the notebooks we used for generating our figures and key results on our valvular heart disease model published in JACC.
For more details, see the accompanying paper,
Deep Learning Electrocardiographic Analysis for Detection of Left-Sided Valvular Heart Disease
Pierre Elias, Timothy J. Poterucha, Vijay Rajaram, Luca Matos Moller, Victor Rodriguez, Shreyas Bhave, Rebecca T. Hahn, Geoffrey Tison, Sean A. Abreau, Joshua Barrios, Jessica Nicole Torres, J. Weston Hughes, Marco V. Perez, Joshua Finer, Susheel Kodali, Omar Khalique, Nadira Hamid, Allan Schwartz, Shunichi Homma, Deepa Kumaraiah, David J. Cohen, Mathew S. Maurer, Andrew J. Einstein, Tamim Nazif, Martin B. Leon, and Adler J. Perotte. Journal of the American College of Cardiology, August 1, 2022. https://www.jacc.org/doi/10.1016/j.jacc.2022.05.029?utm_medium=email_newsletter&utm_source=jacc&utm_campaign=toc&utm_content=20220801#mmc1
Lead Developers:
-Pierre Elias
-Adler Perotte
Contributors:
-Vijay Rajaram
-Shengqing Xia
-Alex Wan
-Junyang Jiang
-Yuge Shen
-Han Wang