rinet: Clinical Reference Interval Estimation with Reference Interval Network (RINet)

Predicts statistics of a reference distribution from a mixture of raw clinical measurements (healthy and pathological). Uses pretrained CNN models to estimate the mean, standard deviation, and reference fraction from 1D or 2D sample data. Methods are described in LeBien, Velev, and Roche-Lima (2026) "RINet: synthetic data training for indirect estimation of clinical reference distributions" <doi:10.1016/j.jbi.2026.104980>.

Version:	0.2.0
Depends:	R (≥ 3.5.0)
Imports:	torch, stats
Published:	2026-10-20
DOI:	10.32614/CRAN.package.rinet
Author:	Jack LeBien [aut, cre]
Maintainer:	Jack LeBien <jlebien at abartyshealth.com>
BugReports:	https://github.com/jackgle/rinet_r_package/issues
License:	MIT + file LICENSE
URL:	https://github.com/jackgle/rinet_r_package
NeedsCompilation:	no
Materials:	NEWS
CRAN checks:	rinet results

Documentation:

Reference manual:

rinet.html , rinet.pdf

Downloads:

Package source:	rinet_0.2.0.tar.gz
Windows binaries:	r-devel: rinet_0.1.1.zip, r-release: rinet_0.1.1.zip, r-oldrel: rinet_0.1.1.zip
macOS binaries:	r-release (arm64): rinet_0.2.0.tgz, r-oldrel (arm64): rinet_0.2.0.tgz, r-release (x86_64): rinet_0.2.0.tgz, r-oldrel (x86_64): rinet_0.2.0.tgz
Old sources:	rinet archive

Linking:

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