Description
Deriving Clinically Interpretable Cutoffs for Disease Biomarkers.
Description
Provides a reproducible pipeline for deriving two clinically meaningful cutoffs for disease biomarkers using a unified two-stage framework. The package integrates finite mixture modeling with risk prediction using biomarker plus clinical features, followed by decision curve analysis to evaluate clinical utility. Outputs include biomarker density plots, risk calibration curves, decision curves, and summary tables of diagnostic performance. Designed for researchers in bio-statistics, neurology, and data science, this package emphasizes reproducibility, transparency, and clear clinical relevance.
README.md
Deriving Clinically Interpretable Cutoffs for Disease Biomarkers
An R package for biomarker evaluation that introduces a two‑stage cutoff framework. Instead of a single threshold, it defines both a rule‑out cutoff (cL) and a rule‑in cutoff (cH), creating three groups: non‑diseased, diseased, and an intermediate gray zone. This approach improves diagnostic interpretability and supports clinical decision‑making.
✨ Features
The TwoCutoff package supports reproducible diagnostic pipelines by integrating:
- 📌 adjust_score() -- Gaussian mixture + confounder‑adjusted XGBoost risk modeling\
- 📊 derive_cutoffs_percentile() -- percentile‑based cutoff derivation\
- 📊 derive_cutoffs_sensspec() -- ROC‑based cutoff derivation\
- 📈 evaluate_performance() -- sensitivity, specificity, PPV, NPV metrics\
- 🔍 compare_performance() -- side‑by‑side comparison of cutoff methods\
- 📉 dca_analysis() -- decision curve analysis for clinical utility\
- 🎨 plot_two_cutoff() -- visualization of cutoffs and confusion matrix
🛠 Installation
# Install from CRAN (when available)
install.packages("TwoCutoff")
# Or install the development version from GitHub:
install.packages("remotes")
remotes::install_github("kumarbhrigu/TwoCutoff")