Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2023 Jul 18;14:4314. doi: 10.1038/s41467-023-39902-7

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2023

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Fig. 4 — In each panel, replicates are shown as individual points (n = 125), with age mean absolute error (MAE) on the x-axis and separation on the y-axis. Note that increasing values on the x-axis correspond to a reduction in age encoding; increasing values on the y-axis denote worsening fairness. Therefore, a correlation between encoding and unfairness would be observed as a negative correlation. a Original dataset. For this dataset, models which encoded age to a lesser degree (right) tended to be slightly more fair (lower separation), as reflected by a statistically significant Spearman rank correlation (two-sided). b The same analysis for the biased dataset. In this case, the correlation between age encoding and unfairness is markedly strengthened. c Balanced dataset. There was no significant correlation between age encoding and unfairness in this dataset. In all analyses, replicates with unacceptable performance (AUC < 0.8, arbitrary threshold) were excluded (open dots). Source data are provided as a Source Data file.