clinicalfair: Algorithmic Fairness Assessment for Clinical Prediction Models

Post-hoc fairness auditing toolkit for clinical prediction models. Unlike in-processing approaches that modify model training, this package evaluates existing models by computing group-wise fairness metrics (demographic parity, equalized odds, predictive parity, calibration disparity), visualizing disparities across protected attributes, and performing threshold-based mitigation. Supports intersectional analysis across multiple attributes and generates audit reports useful for fairness-oriented auditing in clinical AI settings. Methods described in Obermeyer et al. (2019) <doi:10.1126/science.aax2342> and Hardt, Price, and Srebro (2016) <doi:10.48550/arXiv.1610.02413>.

Version:	0.1.0
Depends:	R (≥ 4.1.0)
Imports:	cli (≥ 3.4.0), dplyr (≥ 1.1.0), ggplot2 (≥ 3.4.0), rlang (≥ 1.1.0), stats, tibble (≥ 3.1.0)
Suggests:	knitr, rmarkdown, testthat (≥ 3.0.0), withr
Published:	2026-04-02
DOI:	10.32614/CRAN.package.clinicalfair
Author:	Cuiwei Gao [aut, cre, cph]
Maintainer:	Cuiwei Gao <48gaocuiwei at gmail.com>
BugReports:	https://github.com/CuiweiG/clinicalfair/issues
License:	MIT + file LICENSE
URL:	https://github.com/CuiweiG/clinicalfair
NeedsCompilation:	no
Language:	en-US
Citation:	clinicalfair citation info
Materials:	README, NEWS
CRAN checks:	clinicalfair results

Documentation:

Reference manual:	clinicalfair.html , clinicalfair.pdf
Vignettes:	Algorithmic fairness assessment with clinicalfair (source, R code)

Downloads:

Package source:	clinicalfair_0.1.0.tar.gz
Windows binaries:	r-devel: clinicalfair_0.1.0.zip, r-release: not available, r-oldrel: not available
macOS binaries:	r-release (arm64): clinicalfair_0.1.0.tgz, r-oldrel (arm64): not available, r-release (x86_64): not available, r-oldrel (x86_64): not available

Linking:

Please use the canonical form https://CRAN.R-project.org/package=clinicalfair to link to this page.