v1xerunt / adacare

Source code for AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration

AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration

The source code for AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration

Visualization

Welcome to test the prototype of our visualization tool. The clinical hidden status is built by our latest representation learning model ConCare https://github.com/Accountable-Machine-Intelligence/concare and AdaCare. The internationalised multi-language support will be available soon.

Requirements

• Install python, pytorch. We use Python 3.7.3, Pytorch 1.1.
• If you plan to use GPU computation, install CUDA

Data preparation

We do not provide the MIMIC-III data itself. You must acquire the data yourself from https://mimic.physionet.org/. Specifically, download the CSVs. To run decompensation prediction task on MIMIC-III bechmark dataset, you should first build benchmark dataset according to https://github.com/YerevaNN/mimic3-benchmarks/.

After building the decompensation dataset, please save the files in decompensation directory to data/ directory.

Fast way to test AdaCare with MIMIC-III

1. We provide the trained weights in ./saved_weights/AdaCare. You can obtain the reported performance in our paper by simply load the weights to the model.

2. You need to run train.py in test mode and input the data directory. For example,

   $ python train.py --test_mode=1 --data_path='./data/'

Training AdaCare

1. The minimum input you need to train AdaCare is the dataset directory and file name to save model. For example,

   $ python train.py --data_path='./data/' --file_name='trained_model'

2. You can also specify batch size --batch_size <integer> , learning rate --lr <float> and epochs --epochs <integer>

3. Additional hyper-parameters can be specified such as the dimension of RNN, dropout rate, etc. Detailed information can be accessed by

   $ python train.py --help

4. When training is complete, it will output the performance of AdaCare on test dataset.

adacare's Issues

cross- validation strategy: how to split dataset into train\valid\test?

Hi, good work! I wonder how to split dataset into train\valid\test set after building the decompensation/in-hospital-mortality datasets to reproduce your results?