EHR-QC is a complete end-to-end pipeline to standardise and preprocess Electronic Health Records (EHR) for downstream integrative machine learning applications. This utility has two distinct modules;
- Standardisation
- Pre-processing
Both the modules can be run as a single end-to-end pipeline or individual components can be run in a standalone manner.
This utility is primarily focussed to provide a domain specific toolset for performing commmon standardisation and pre-processing tasks while handling the healthcare data. A command line interface is designed to provide an abstraction over the internal implementation details while at the same time being easy to use for anyone with basic Linux skills.
git clone git@github.com:ryashpal/EHRQC.gitpython -m venv .venv
source .venv/bin/activatepip install -r requirements.txtFor the most up-to-date documentation about installation, configuration, running, and use cases please refer to the EHR-QC Documantation page.
If you use this library for your research, please cite our paper:
Yashpal Ramakrishnaiah, Nenad Macesic, Geoffrey I. Webb, Anton Y. Peleg, Sonika Tyagi,
EHR-QC: A streamlined pipeline for automated electronic health records standardisation and preprocessing to predict clinical outcomes, Journal of Biomedical Informatics,
Volume 147, 2023, 104509, ISSN 1532-0464,
https://doi.org/10.1016/j.jbi.2023.104509.
(https://www.sciencedirect.com/science/article/pii/S1532046423002307)
BibTeX:
@article{RAMAKRISHNAIAH2023104509,
title = {EHR-QC: A streamlined pipeline for automated electronic health records standardisation and preprocessing to predict clinical outcomes},
journal = {Journal of Biomedical Informatics},
volume = {147},
pages = {104509},
year = {2023},
issn = {1532-0464},
doi = {https://doi.org/10.1016/j.jbi.2023.104509},
url = {https://www.sciencedirect.com/science/article/pii/S1532046423002307},
author = {Yashpal Ramakrishnaiah and Nenad Macesic and Geoffrey I. Webb and Anton Y. Peleg and Sonika Tyagi},
keywords = {Digital health, Electronic health records, EHR, Clinical outcome prediction, Machine learning},
}
Our special thanks to;
