Collaborative and privacy-preserving workflows on a clinical data warehouse: an example developing natural language processing pipelines to detect medical conditions

Study

This repositoy contains the computer code that has been used for the article:

@unpublished{petitjean2023nlp,
author = {Thomas Petit-Jean and Christel Gerardin and Emmanuelle Berthelot and Gilles Chatellier and Marie Frank and Xavier Tannier and Emmanuelle Kempf and Romain Bey},
title = {Collaborative and privacy-preserving workflows on a clinical data warehouse: an example developing natural language processing pipelines to detect medical conditions},
note = {Manuscript submitted for publication},
year = {2023}
}

The code has been executed on the database of the Greater Paris University Hospitals

⚠️ This repository is not maintained. It contains computer code that is specific to a research study.

Version 1.0.0

• Code of article after review.

Repository description

• edsml: library developped to facilitate the development of the qualification algorithms. Based on pytorch and pytorch-lightning.
• ecci_qualifier: source code of the machine-learning based qualification algorithm.
• ecci: code used during training for document selection, CLAIM pipeline or annotation process.
• analysis: code used to generate results for the paper

Acknowledgement

We would like to thank Assistance Publique – Hôpitaux de Paris and AP-HP Foundation for funding this project.