antonior92/automatic-ecg-diagnosis
Scripts and modules for training and testing neural network for ECG automatic classification. Companion code to the paper "Automatic diagnosis of the 12-lead ECG using a deep neural network".
Implements a ResNet-based architecture in TensorFlow/Keras that processes 10-second 12-lead ECG signals (4096 samples at 400Hz) to predict six cardiac abnormalities (1st-degree AV block, bundle branch blocks, bradycardia, atrial fibrillation, and tachycardia) as independent multi-label probabilities. Pre-trained weights and the CODE dataset subset are provided for reproducibility, with modular scripts for training (`train.py`), inference (`predict.py`), and benchmarking against the Nature Communications publication results.
437 stars. No commits in the last 6 months.
Stars
437
Forks
137
Language
Python
License
MIT
Category
Last pushed
Mar 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/antonior92/automatic-ecg-diagnosis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
DeepPSP/torch_ecg
Deep learning ECG models implemented using PyTorch
im-ethz/flirt
Are you ready to FLIRT with your wearable data?
Edoar-do/HuBERT-ECG
A self-supervised foundation ECG model for broad and scalable cardiac applications
bowang-lab/ecg-fm
An electrocardiogram analysis foundation model.
AmbiqAI/heartkit
Perform AI-based heart monitoring tasks