Framework for healthcare ML implementation
Project description
cyclops
is a framework for facilitating research and deployment of ML models
in the health (or clinical) setting. It provides a few high-level APIs namely:
- query API - Querying EHR databases (such as MIMIC-IV)
- process API - Process static and temporal EHR data
- evaluate API - Evaluate models on clinical prediction tasks
- monitor API - Detect data drift relevant for clinical use cases
cyclops
also provides a library of use-cases on clinical datasets. The implemented
use cases include:
- Mortality decompensation prediction
🐣 Getting Started
Installing the core cyclops package using pip
pip install pycyclops
Setup Python virtual environment and install dependencies for development
The development environment has been tested on python = 3.9.7
.
The python virtual environment can be setup using poetry. Hence, make sure it is installed and then run:
poetry install
source $(poetry env info --path)/bin/activate
📚 Documentation
🎓 Notebooks
To use jupyter notebooks, the python virtual environment can be installed and used inside an Ipython kernel. After activating the virtual environment, run:
python3 -m ipykernel install --user --name <name_of_kernel>
Now, you can navigate to the notebook's Kernel
tab and set it as
<name_of_kernel>
.
Tutorial notebooks in tutorials
can be useful to view the
functionality of the framework.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for pycyclops-0.1.4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 087863de842c37466dfa2ca278d61b391f683646f54a3b09d3a4a5677377eec9 |
|
MD5 | e6e51cf42814f20bf9881396c973da31 |
|
BLAKE2b-256 | a59de9b3772e4303bb7de74bfb7138138b12898f0906874b6fc55e125653a26f |