misdiagnosisofathleteecg
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.4%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: ShaunKyle
- License: mit
- Language: Jupyter Notebook
- Default Branch: main
- Size: 6.35 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Classification of 12-lead ECG recordings from athletes
Investigating reduced deep learning model performance on athletic patient cohorts
Running 12-Lead ECG classification models from the 2020 George B. Moody PhysioNet Challenge on someone else's computer with a bigger GPU than mine.
In addition to the original datasets used in the 2020 PhysioNet Challenge, this project also tests the models on a unique patient cohort: professional athletes.
Results are published to https://shaunkyle.github.io/MisdiagnosisOfAthleteECG - Misclassification of athlete ECG by GE Marquette SL12 algorithm - TODO: Measuring shift in population between datasets - TODO: Verify model performance on 2020 PhysioNet Challenge datasets - TODO: Reduced model performance on athletic datasets
Setup
Create python virtual environment inside the .venv directory.
sh
uv venv --python 3.10
Activate the virutal environment in shell (prepend .venv/bin to PATH)
```sh
On MacOS, Linux, or other POSIX
source .venv/bin/activate
On Windows
.venv\Scripts\activate ```
Install (or update) dependencies
```sh
On computer with CUDA 11.6
uv pip install -U -r requirements-CUDA.txt
On other computers (uses CPU)
uv pip install -U -r requirements-CPU.txt ```
Documentation website
```sh
Preview website locally
quarto preview
Update documentation website (gh-pages branch)
quarto publish gh-pages ```
Citation
Citation metadata is provided by CITATION.cff. For convenience, a BibTex citation is provided below.
bibtex
@software{Kyle_Classification_of_12-lead,
author = {Kyle, Shaun},
title = {{Classification of 12-lead ECG recordings from athletes}},
url = {https://github.com/ShaunKyle/PhysioNetChallenge2020}
}
Owner
- Login: ShaunKyle
- Kind: user
- Repositories: 1
- Profile: https://github.com/ShaunKyle
Citation (CITATION.cff)
# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0
title: Classification of 12-lead ECG recordings from athletes
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Shaun
family-names: Kyle
email: s.kyle@student.unsw.edu.au
affiliation: UNSW
url: "https://github.com/ShaunKyle/PhysioNetChallenge2020"
GitHub Events
Total
- Push event: 36
- Create event: 1
Last Year
- Push event: 36
- Create event: 1
Dependencies
- torch ==1.13.1
- torchaudio ==0.13.1
- torchvision ==0.14.1
- torch ==1.13.1
- torchaudio ==0.13.1
- torchvision ==0.14.1
- requests *