Introduction of CSTE (ver 1.0.0)

CSTE provides a uniform statistical inferential tool for estimating individualized treatment rule.

CSTE estimates differences of average outcomes between different treatment groups conditional on patients characteristics and provides the corresponding simultaneous confidence bands. Based on the CSTE curve and the simultaneous confidence bands, one can decide the subgroups of patients that benefit from each treatment and then make individualized treatment selections.

The current CSTE can analyze the following types of datasets:

  • Datasets with binary outcomes, 2-arm treatments, and single or multiple (even high-dimensional) covariates.[1-2]

  • Datasets with right censored time-to-event outcomes, multi-arm treatments, and a single covariate of the biomarker.[3-4]

CSTE will consider more types of datasets in the future.

R package

CSTE: Covariate Specific Treatment Effect (CSTE) Curve (https://CRAN.R-project.org/package=CSTE)

References

[1] Han K, Zhou X, Liu B. CSTE curve for selection of the optimal treatment when outcome is binary. SCIENTIA SINICA Mathematica. 2017;47(4):497–514.

[2] Guo W, Zhou XH, Ma S. Estimation of optimal individualized treatment rules using a covariate-specific treatment effect curve with high-dimensional covariates. Journal of the American Statistical Association. 2021;116(533):309–21. https://doi.org/10.1080/01621459.2020.1865167

[3] Zhou XH, Ma Y. BATE curve in assessment of clinical utility of predictive biomarkers. Science China Mathematics. 2012 Aug 18;55(8):1529–52. http://link.springer.com/10.1007/s11425-012-4473-0

[4] Ma Y, Zhou XH. Treatment selection in a randomized clinical trial via covariate-specific treatment effect curves. Statistical Methods in Medical Research. 2017 Feb;26(1):124–41. http://journals.sagepub.com/doi/10.1177/0962280214541724

Contact

yzhou_at_pku.edu.cn

Release history

Date Version Details
2023-09-30 0.9.0 First release
2024-05-02 1.0.0 Update

Results

  • CSTE Curve: the estimated CSTE curve
  • Predicted CSTE Curve: the CSTE curve predicted based on the new patients' data

CSTE Estimates

CSTE curve

Kernel bandwidth for B-spline method in the confidence intervals
Significant level for confidence interval
Set the range for y-axis
Set the range for x-axis

The predicted location of x-axis for new subject

Predicted CSTE curve

Set the range for y-axis
Set the range for x-axis

Data preview

Results

  • CSTE Curve: the estimated CSTE curve
  • CSTE Dynamic Curve: the estimated CSTE curve shown in dynamic plot
  • Estimates: the estimated CSTE with confidence bands