Note: The default ITS GitLab runner is a shared resource and is subject to slowdowns during heavy usage.
You can run your own GitLab runner that is dedicated just to your group if you need to avoid processing delays.

Commit bff6cc82 authored by Xuefei Zhang's avatar Xuefei Zhang
Browse files

Update README.md

parent ee585340
# TVC project
This gitlab page contains code and sample dataset for paper Adapted time-varying covariates Cox model for predicting cirrhosis development performs well among patients with hepatitis C with and without antiviral treatment (authors: Lauren A Beste*; Xuefei Zhang*; Grace Su; Tony Van; George N Ioannou; Monica Tincopa; Boang Liu; Amit G Singal; Ji Zhu; Akbar K. Waljee)
The files include
1. process_trainData_Kyear_outcome.R
Process training dataset to predict outcome in K years. This processing includes redefining outcome and merging all labs files, treatment variable, demographic variables, and outcome for all patients into a data frame that can be directly used for TVC model training.
2. process_testData_Kyear_outcome_L_year_predictor.R
Process test dataset such that the trained K year prediction model can be applied for testing. This processing includes redefining outcome on test dataset and erging all labs files, treatment variable, demographic variables, and outcome for all patients into a data frame that be directly used for TVC model testing.
3. fit_Kyear_outcome_Lyear_predictor_v1_XZ.R
Fit models that predict K years outcome and evaluate the model performance on test dataset using first L year predictors. Model fitting and evaluation are done over 30 training/testing random splits.
4. ./sample_data/
This folder contains sampled dataset that specify the format of inputs of data processing files process_trainData_Kyear_outcome.R and process_testData_Kyear_outcome_L_year_predictor.R. The dataset is made up, mostly randomly generated from `runif()` function in R and does not contain any identifiable information about patients.
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment