Codes, models and synthesized data for paper "Learning from past respiratory infections to predict COVID-19 Outcomes: A retrospective study"

<a href="https://embed.stanford.edu/iframe/?url=https%3A%2F%2Fpurl.stanford.edu%2Fvg665fp4193" class="su-underline">Show Content</a>

Abstract/Contents

Abstract: This repository contains the codes and synthesized data for our paper "Learning from past respiratory infections to predict COVID-19 Outcomes: A retrospective study". In this paper we proposed a framework that used COVID-like cohorts (you can find the description in our paper) to train machine learning models and validated them on the COVID-19 population.If you just want to test the model on synthetic COVID dataset, you could run the predict_COVID.py directly, or if you want to train the model by your own data, you could run the "training_models.py" file.The file descriptions are:directory: contains the test data. is the data template we used.directory: contains the trained models by COVID-like patients.is used to predict intubation within 48 hours.is used to load test data from test data file.is used to train the modelsProcess:1) Input the command "pip install -r requirements.txt" to install the environment2) Using python command to train the model: python training_models.py3) Using python command to run the model: python predict_COVID.pyThe output is a score file in the "result" directory.

Author	Sang, Shengtian	https://orcid.org/0000-0003-0851-9520 (unverified)
Advisor	Hernandez-Boussard, Tina	https://orcid.org/0000-0001-6553-3455 (unverified)

Subject	Stanford University. School of Medicine
Subject	COVID-19 program
Genre	Software/code

Related item	Preferred citation Sang S, Sun R, Coquet J, Carmichael H, Seto T, Hernandez-Boussard T. Learning From Past Respiratory Infections to Predict COVID-19 Outcomes: Retrospective Study. J Med Internet Res 2021;23(2):e23026. https://doi.org/10.2196/23026
DOI	https://doi.org/10.25740/vg665fp4193
Location	https://purl.stanford.edu/vg665fp4193

Use and reproduction: User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
License: This work is licensed under a Creative Commons Attribution Non Commercial No Derivatives 4.0 International license (CC BY-NC-ND).

Preferred citation: Sang, Shengtian and Hernandez-Boussard, Tina. (2020). Codes, models and synthesized data for paper "Learning from past respiratory infections to predict COVID-19 Outcomes: A retrospective study". Stanford Digital Repository. Available at: https://purl.stanford.edu/vg665fp4193 https://doi.org/10.25740/vg665fp4193

Stanford Research Data

Loading usage metrics...