Collaborative Graph Learning with Auxiliary Text for Temporal Event Prediction in Healthcare

• python 3
• numpy
• sklearn
• pandas
• nltk
• tensorflow

1. Install all required softwares and packages.

pip install -r requirements.txt

2. In the python console, download the stopwords and punkt corpus required by nltk.

import nltk


nltk.download('stopwords')
nltk.download('punkt')

Go to https://mimic.physionet.org/ for access. Once you have the authority for the dataset, download the dataset and extract the csv files to data/mimic3/raw/ in this project.

python run_preprocess.py

1. For the medical code prediction task.

python train_codes.py

2. For the heart failure prediction task.

python train_hf.py