Heart Disease Study π«
We will use the full version of the Heart Disease dataset, as available on the UCI ML repository.
The database is the result of a study for the diagnosis of coronary artery disease, as described in this paper.
The dataset contains data as collected by patients in four different hospitals, in 1988:
- Cleveland Clinic in Cleveland, Ohio (
303
patients); - Hungarian Institute of Cardiology in Budapest, Hungary (
425
patients); - Veterans Administration Medical Center in Long Beach, California (
200
patients) - University Hospitals in Zurich and Basel (
143
patients).
π‘Each hospital will be mapped to a single PySyft Datasite,
hosting their own version of the Heart Study Data
data.
We will pretend that these data were not public - as it is most likely the case
with real medical data. Therefore our main focus in the tutorial
will be to learn how to work with non-public data, while maintaining privacy.
What you will learn π
In this tutorial, you will learn how to…- work remotely with non-public medical data.
- use PySyft to run Machine learning experiments on non-public and distributed medical datasets.
- take advantage of getting access to multiple medical datasets for better Machine learning modelling.
Materials π§βπ»
The tutorial is organised into multiple Jupyter notebooks that will guide you to the different steps of our Machine learning experiment, using PySyft.
-
π§
(Intro) Setup Datasites
- π
1. Compare Demographics
- π€
2. ML Model Training Experiment:
- π
3. ML Model Evaluation Experiment:
- π³οΈ
4. Ensemble Learning Experiment :
Ready to get started ?
Everything you need to start working with the tutorial is available on GitHub! You can start by cloning the repo, and follow the instructions in the README file:
$ git clone https://github.com/openmined/syft-heart-disease-tutorial
Feedback? Always welcome!
If you liked this tutorial, or for any additional question, or feedback you may have, please feel free to use one of the options below:
Star the repository.Open an issue
Reach out in
#support
channel on Slack