R packages for prospective biomarker validation with time-to-event data developed in collaboration with Yingye Zheng and Tianxi Cai.
R packages
Biomarker evaluation with survival data- Accuracy summary measures: survAccuracyMeasures
Estimate the AUC, TPR(c), FPR(c), PPV(c), and NPV(c) for for a specific timepoint and marker cutoff value c using non-parametric and semi-parametric methods. Bootstrap standard errors and confidence intervals are also computed.
- Competing risk outcome: survCompetingRisk
Evaluate the prognostic accuracy of a marker with multiple competing risk events. Functions to calculate the AUC, ROC, PPV, and NPV are provided. A discrete covariate Z, if available, can be included.
- Incremental value evaluation: survNRI
Calculate the net reclassification index (NRI) statistic for survival data using five different estimators.
- Longitudinal Prediction:partlyconditional
This package provides functions to fit partly conditional (PC) risk models, which are a helpful class of predictive models often used in medical contexts where long-term follow-up is available and interest lies in predicting patients' risks for a future adverse outcome using repeatedly measured predictors over time.
- LongitudinalAccuracy: longsurvAccuracyMeasures
In development
- Two phase design with longitudinal data: longsurvMarkerTwoPhase
In development
- Two phase design with survival data:survMarkerTwoPhase
Evaluate the prognostic accuracy of a marker under two phase designs (case-cohort and nested case control designs).
- Two phase design with survival data (efficient and flexible estimation): AIPWmeasure
AIPWmeasures
Estimate measures of predictive accuracy using augmented inverse probability weights for two-phase biomarker validation studies.
Power Calculations
Shiny web applications to simulate power for prognostic biomarker validation studies with time to event data.