Classification of Cancer Using Administrative Data

Classifies the type of cancer using routinely collected data commonly found in cancer registries from pathology reports. The package implements the International Classification of Diseases for Oncology, 3rd Edition site (topography), histology (morphology), and behaviour codes of neoplasms to classify cancer type < https://www.who.int/standards/classifications/other-classifications/international-classification-of-diseases-for-oncology>. Classification in children utilize the International Classification of Childhood Cancer by Steliarova-Foucher et al. (2005) . Adolescent and young adult cancer classification is based on Barr et al. (2020) .

cancerR

• Overview
• Features
• Installation
• Get started
• Upcoming features
• Citation
• Contributing
• References

Overview

cancerR is designed to use administrative data to classify different cancer subtypes using data commonly collected by cancer registries. This package is meant for researchers and data scientists who work with cancer data and need to classify the type of cancer using the information available in pathology reports which have been coded using the International Classification of Diseases for Oncology (ICD-O).

Features

The main purpose of cancerR is to use information gathered using the standardized collection system of the ICD-O classification system of tumors to classify the type of cancer. Depending on the age of the patient, users of the package can classify the type of cancer according to

The package provides functionality to:

• convert and validate tumor site (a.k.a. topography) codes
• classify childhood cancer according to the International Classification of Childhood Cancer
• assign adolescent and young adult cancers using the AYA Site from the Surveillance, Epidemiology, and End Results (SEER) program or the published AYA classification by Barr et al

Installation

You can install the released version of cancerR from CRAN with:

## Install < cancerR > from CRAN ----
install.packages("cancerR")

or you can install the development version from GitHub with:

## Install < remotes > package (if not already installed) ----
if (!requireNamespace("remotes", quietly = TRUE)) {
  install.packages("remotes")
}

## Install < cancerR > from GitHub ----
remotes::install_github("giancarlodigi/cancerR")

Then you can attach the package cancerR:

library("cancerR")

Getting started

For an overview of the main features of cancerR, please read the Get started vignette. This vignette provides a brief introduction to the package and its implementation for classifying cancer using administrative data.

Upcoming features

The package is under active development and planning to add the following features:

• adult cancer classification according to the ICD-O
• implementing conversion and classification of cancers using ICD-O-2 codes

Citation

Please cite cancerR as:

Di Giuseppe Giancarlo (2026) cancerR: An R package to classify cancer using administrative data. R package version 0.1.1. https://github.com/giancarlodigi/cancerR/

Contributing

All types of contributions are encouraged and valued. For more information, please reach out to the maintainer of the package.

Please note that the cancerR project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.

References

Barr RD, Ries LAG, Trama A, et al. A system for classifying cancers diagnosed in adolescents and young adults. Cancer. 2020;126(21):4634-4659. doi: 10.1002/cncr.33041.

Steliarova-Foucher E, Stiller C, Lacour B, Kaatsch P. International Classification of Childhood Cancer, third edition. Cancer. 2005;103(7):1457-1467. doi: 10.1002/cncr.20910.

National Cancer Institute. Surveillance, Epidemiology, and End Results Program. Adolescent and Young Adult Site Recode ICD-O-3/WHO 2008. 2021. Available here.

World Health Organization. International Classification of Diseases for Oncology (ICD-O) - 3rd Edition, 1st Revision; 2013. Document manual found here