Public COVID-19 reference data have been used for the following Shiny App to generate synthetic data via the SASC algorithm. Here, a comparison through the Kaplan-Meier plots is provided so that the parameters chosen for the virtual cohort can be checked against the real-world data.
- Data - PreSurv data can be found here
- Shiny App - Click the binder icon on the top to run the current SASC version application.
- Packages used - Check the environment file in the binder folder for these following details.
TO NOTE: The app is heavy on server side, and it can be slow - be patient.
In the app, one can compare the Kaplan-Meier plots for each parameter (found in the cohort) for the virtual cohort and real-world data
If you have difficulties using the app, please open an issue at our bug-tracker on GitHub.
SASC is a scientific application that has been developed in an academic capacity and thus comes with no warranty or guarantee of maintenance, support, or back-up of data.
If you use our work, please cite our paper:
Khorchani, Takoua, et al. "SASC: A Simple Approach to Synthetic Cohorts for Generating Longitudinal Observational Patient Cohorts from COVID-19 Clinical Data." Available at SSRN 3942844. https://doi.org/10.1016/j.patter.2022.100453