Learn R Programming

rinet (version 0.1.0)

Clinical Reference Interval Estimation with Reference Interval Network (RINet)

Description

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" .

Copy Link

Version

Install

install.packages('rinet')

Version

0.1.0

License

MIT + file LICENSE

Maintainer

Jack LeBien

Last Published

January 29th, 2026

Functions in rinet (0.1.0)

.correlation_to_covariance

Convert correlation to covariance matrix
predict_rinet_1d

Predict statistics of the underlying reference distribution from 1D mixture distributions using RINet
predict_rinet

Predict statistics of the underlying reference distribution from mixture distributions using RINet
predict_rinet_2d

Predict statistics of the underlying reference distribution from 2D mixture distributions using RINet
.extract_features

Extract histogram features from standardized data
.load_scaler

Internal function to load scaler
rinet-package

RINet: Predict Clinical Reference Intervals from Mixture Distributions
.load_model

Internal function to load model and scaler