English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent research has shown that artificial intelligence (AI) models canexhibit bias in performance when trained using data that are imbalanced byprotected attribute(s). Most work to date has focused on deep learning models,but classical AI techniques that make use of hand-crafted features may also besusceptible to such bias. In this paper we investigate the potential for racebias in random forest (RF) models trained using radiomics features. Ourapplication is prediction of tumour molecular subtype from dynamic contrastenhanced magnetic resonance imaging (DCE-MRI) of breast cancer patients. Ourresults show that radiomics features derived from DCE-MRI data do containrace-identifiable information, and that RF models can be trained to predictWhite and Black race from these data with 60-70% accuracy, depending on thesubset of features used. Furthermore, RF models trained to predict tumourmolecular subtype using race-imbalanced data seem to produce biased behaviour,exhibiting better performance on test data from the race on which they weretrained.

An Investigation Into Race Bias in Random Forest Models Based on Breast DCE-MRI Derived Radiomics Features