Skip to content

reAIM-Lab/PSE-Pulse-Oximetry

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Overview

This repo contains the implementation for "Path-specific effects for pulse-oximetry guided decisions in critical care".

Installation

Create a conda virtual environment and install the dependencies. All the experiments were performed on one NVIDIA RTX 6000 GPU, 32 CPU cores, 256GB of system RAM, running Ubuntu 22.04 with CUDA 12.2.

conda env create -f environment.yml

Data Preparation

Navigate to the corresponding dataset directory in data/eicu or data/mimic-iv and run the preprocess.sh and process.py scripts. For the eICU dataset, separate queries for the ventilation outcomes and Charlson Comorbidity Scores in Google BigQuery are included the notebook eicu_ventilation_charlson.ipynb.

Validate all datasets by navigating to experiments and running datasets.py.

Training

Train all models by navigating to experiments and running main.py. The results for each experiment will be stored in a separate csv file in experiments/results.

Plotting and analysis

Plot all experiment results by navigating to experiments and running plot.py. For the dataset analysis, navigate to data and run viz.py.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors