Fine-Gray Regression via Forward-Backward Scan

In competing risks regression, the proportional subdistribution hazards (PSH) model is popular for its direct assessment of covariate effects on the cumulative incidence function. This package allows for both penalized and unpenalized PSH regression in linear time using a novel forward-backward scan. Penalties include Ridge, Lease Absolute Shrinkage and Selection Operator (LASSO), Smoothly Clipped Absolute Deviation (SCAD), Minimax Concave Plus (MCP), and elastic net .

Introduction

fastcmprsk is an R package for performing Fine-Gray regression via a forward-backward scan algorithm.

Official CRAN release is available here.

NOTE TO USERS: We plan to make monthly/quarterly updates to the package!

What’s New in Version 1.24.10?

1. Made modification to allow for more than one competing risk.

Features

• Scalable Fine-Gray parameter estimation procedure for large-scale competing risks data.
• Currently supports unpenalized and penalized (LASSO, ridge, SCAD, MCP, elastic-net) regression.
• Can perform CIF estimation with interval/band estimation via bootstrap.

Implementation

fastcmprsk in an R package with most functionality implemented in C. The package uses cyclic coordinate descent to optimize the likelihood function.

Installation

To install the latest development version, install from GitHub.

install.packages("devtools")
devtools::install_github(“erickawaguchi/fastcmprsk”)

System Requirements

Requires R (version 4.4.0 or higher).

User Documentation

• Package manual: Currently unavailable.
• Please cite Kawaguchi et al. (2021).

License

fastcmprsk is licensed under GPL-3.

Development

fastcmprsk is being developed in R Studio.