[Skip to Navigation]
[Skip to Navigation Landing]
Views 3,553
Citations 0
Research Letter
September 22/29, 2020

Geographic Distribution of US Cohorts Used to Train Deep Learning Algorithms

Author Affiliations
  • 1Department of Bioengineering, Stanford University, Stanford, California
  • 2Department of Radiology, Stanford University School of Medicine, Stanford, California
JAMA. 2020;324(12):1212-1213. doi:10.1001/jama.2020.12067

Advances in machine learning, specifically the subfield of deep learning, have produced algorithms that perform image-based diagnostic tasks with accuracy approaching or exceeding that of trained physicians. Despite their well-documented successes, these machine learning algorithms are vulnerable to cognitive and technical bias,1 including bias introduced when an insufficient quantity or diversity of data is used to train an algorithm.2,3 We investigated an understudied source of systemic bias in clinical applications of deep learning—the geographic distribution of patient cohorts used to train algorithms.