Neural Record Captioning (NRC)

This repository contains code from the paper Natural Language Generation for Electronic Health Records.

Overview

what's included

1. Keras code for the NRC model.
2. Training and testing scripts for the model.
3. Example scripts for preprocessing EHR data to be used in the model.

getting started

1. Install the necessary Python modules (list below)
2. Use preprocessing/sparisfy.py to convert the discrete variables in your EHRs to sparse format
3. Use preprocessing/words_to_integers.py to convert your free text field to integers
4. Train the autoencoder on the sparse records with ae_training.py
5. Train the NRC model with caption_training.py
6. Generate text with caption_testing.py

required software

1. Python 3.x
2. Keras with the TensorFlow backend
3. Pandas, NumPy, h5py, and scikit-learn

hot tips

The default hyperparameters worked well for the data used in our paper, but they might not for yours, so feel free to experiment! Also, we recommend a GPU for training the captioning model. We used a single NVIDIA Titan X for our experiments, and training with ~2 million records took around 6 hours.

Public Domain Standard Notice

This repository constitutes a work of the United States Government and is not subject to domestic copyright protection under 17 USC § 105. This repository is in the public domain within the United States, and copyright and related rights in the work worldwide are waived through the CC0 1.0 Universal public domain dedication. All contributions to this repository will be released under the CC0 dedication. By submitting a pull request you are agreeing to comply with this waiver of copyright interest.

License Standard Notice

The repository utilizes code licensed under the terms of the Apache Software License and therefore is licensed under ASL v2 or later.

This source code in this repository is free: you can redistribute it and/or modify it under the terms of the Apache Software License version 2, or (at your option) any later version.

This source code in this repository is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the Apache Software License for more details.

You should have received a copy of the Apache Software License along with this program. If not, see http://www.apache.org/licenses/LICENSE-2.0.html

The source code forked from other open source projects will inherit its license.

Privacy Standard Notice

This repository contains only non-sensitive, publicly available data and information. All material and community participation is covered by the Disclaimer and Code of Conduct. For more information about CDC's privacy policy, please visit http://www.cdc.gov/privacy.html.

Contributing Standard Notice

Anyone is encouraged to contribute to the repository by forking and submitting a pull request. (If you are new to GitHub, you might start with a basic tutorial.) By contributing to this project, you grant a world-wide, royalty-free, perpetual, irrevocable, non-exclusive, transferable license to all users under the terms of the Apache Software License v2 or later.

All comments, messages, pull requests, and other submissions received through CDC including this GitHub page are subject to the Presidential Records Act and may be archived. Learn more at http://www.cdc.gov/other/privacy.html.

Records Management Standard Notice

This repository is not a source of government records, but is a copy to increase collaboration and collaborative potential. All government records will be published through the CDC web site.

Additional Standard Notices

Please refer to CDC's Template Repository for more information about contributing to this repository, public domain notices and disclaimers, and code of conduct.