Subpopulation-specific machine learning prognosis for underrepresented patients with double prioritized bias correction
Afrose, Song et al. highlight deficiencies in the widely accepted one-machine-learning-model-fits-all approach. The authors develop a bias correction method that produces specialized machine learning-based prognostication models for underrepresented racial and age groups.
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-09-01
|
Series: | Communications Medicine |
Online Access: | https://doi.org/10.1038/s43856-022-00165-w |