https://github.com/mp2893/medgan

Generative adversarial network for generating electronic health records.
https://github.com/mp2893/medgan

Last synced: about 2 months ago
JSON representation

Generative adversarial network for generating electronic health records.

• Host: GitHub
• URL: https://github.com/mp2893/medgan
• Owner: mp2893
• License: bsd-3-clause
• Created: 2017-03-19T17:26:17.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2019-08-19T17:50:15.000Z (about 5 years ago)
• Last Synced: 2024-04-08T02:26:41.349Z (5 months ago)
• Language: Python
• Size: 29.3 KB
• Stars: 263
• Watchers: 15
• Forks: 90
• Open Issues: 11
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-data-synthesis - MedGAN - medGAN is a generative adversarial network for generating multi-label discrete patient records. It can generate both binary and count variables (i.e. medical codes such as diagnosis codes, medication codes or procedure codes) - [Paper](https://arxiv.org/abs/1703.06490) (Data-driven methods / Tabular)

README

        
medGAN

=========================================

medGAN is a generative adversarial network for generating multi-label discrete patient records. It can generate both binary and count variables (i.e. medical codes such as diagnosis codes, medication codes or procedure codes).

#### Relevant Publications

medGAN implements the algorithm introduced in the following [paper](https://arxiv.org/abs/1703.06490):

	Generating Multi-label Discrete Patient Records using Generative Adversarial Networks

	Edward Choi, Siddharth Biswal, Bradley Malin, Jon Duke, Walter F. Stewart, Jimeng Sun  

	Machine Learning for Healthcare (MLHC) 2017

#### Code Description

This code trains a generative adversarial network to generate patient records. This work currently can handle patient records that are aggregated over time, hence represented as a matrix where a row corresponds to a patient, and a column to a specific medical code (e.g. diagonsis code, medication code, or procedure code). The value of the matrix could either be binary (i.e. a specific medical code occurred in the longitudinal patient record or not) or count (i.e. how many times a specific medical code occurred in the longitudinal patient record).

	

#### Running GRAM

**STEP 1: Installation**  

1. medGAN was implemented to run on [TensorFlow](https://www.python.org/) 1.2. TensorFlow can be easily installed in Ubuntu as suggested [here](https://www.tensorflow.org/install/install_linux)

2. Download/clone the medGAN code

**STEP 2: Fast way to test medGAN with MIMIC-III**  

This step describes how to train medGAN, with minimum number of steps using MIMIC-III.

0. You will first need to request access for [MIMIC-III](https://mimic.physionet.org/gettingstarted/access/), a publicly avaiable electronic health records collected from ICU patients over 11 years. 

1. You can use "process_mimic.py" to process MIMIC-III dataset and generate a suitable training dataset for medGAN. 

Place the script to the same location where the MIMIC-III CSV files are located, and run the script.

The execution command is `python process_mimic.py ADMISSIONS.csv DIAGNOSES_ICD.csv  <"binary"|"count">`.

Note that the last argument decides whether you construct a binary matrix or a count matrix.

The above command will extract ICD9 diagnosis codes from MIMIC-III. 

Mind that this script will use only 3 digits of the ICD9 diagnosis code. If you want to use all 5 digits, please see the source code of "process_mimic.py".

2. Run medGAN using the ".matrix" file generated by process_mimic.py. The command is:

`python medgan.py   --data_type=["binary", "count"]`.

3. After the training, if you want to generate synthetic records, use this command :

`python medgan.py   --model_file= --generate_data=True --data_type=["binary", "count"]`.

Note that `` is not actually used for generating synthetic records, so it is just a dummy input.