|
a |
|
b/README.md |
|
|
1 |
DeepBeat: Multi-task deep learning for cardiac rhythm detection in wearable devices |
|
|
2 |
------------------------------------------------------------------------------ |
|
|
3 |
|
|
|
4 |
DeepBeat is a deep learning model for |
|
|
5 |
1) classification of Atrial Fibrillation (AF) from photoplethysmography (PPG) signals and |
|
|
6 |
2) signal quality estimation |
|
|
7 |
|
|
|
8 |
Dataset |
|
|
9 |
------- |
|
|
10 |
We share a deidentified train, validate and test partition that were used for training DeepBeat. These deidentified signal are shared with a non-commerical data use agreement and can be found at synapase, ID:syn21985690. |
|
|
11 |
|
|
|
12 |
|
|
|
13 |
Examples |
|
|
14 |
------- |
|
|
15 |
We have included juypter notebooks and trained models for reproduciblility. |