AI recognition of patient race in medical imaging: a modelling study.

• Type of Material: Article
• Authors: Judy Gichoya, Emory University; Imon Banerjee, Arizona State University; Ananth Reddy Bhimireddy, Emory University; John L. Burns, Indiana University; Leo Anthony Celi, Massachusetts Institute of Technology; Li-Ching Chen, National Tsing Hua University; Ramon Correa, Arizona State University; Natalie Dullerud, University of Toronto; Marzyeh Ghassemi, Massachusetts Institute of Technology; Shih-Cheng Huang, Stanford University; Po-Chih Kuo, National Tsing Hua University; Matthew P. Lungren, Stanford University; Lyle J. Palmer, University of Adelaide; Brandon J. Price, Florida State University; Saptarshi Purkayastha, Indiana University; Ayis T. Pyrros, Dupage Medical Group; Lauren Oakden-Rayner, University of Adelaide; Chima Okechukwu, Georgia Institute of Technology; Laleh Seyyed-Kalantari, University of Toronto; Hari Trivedi, Emory University; Ryan Wang, National Tsing Hua University; Zachary Zaiman, Emory University; Haoran Zhang, University of Toronto
• Language: English
• Date: 2022-06
• Publisher: Elsevier
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2022 The Author(s). Published by Elsevier Ltd.
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1016/S2589-7500(22)00063-2
• Title of Journal or Parent Work: Lancet Digit Health
• Volume: 4
• Issue: 6
• Start Page: e406
• End Page: e414
• Grant/Funding Information: JWG and ATP are funded by the National Institute of Biomedical Imaging and Bioengineering (NIBIB) MIDRC grant of the National Institutes of Health (75N92020C00008 and 75N92020C00021). JWG and SP are funded by US National Science Foundation (grant number 1928481) from the Division of Electrical, Communication & Cyber Systems. MPL was funded by the National Library of Medicine of the National Institutes of Health (R01LM012966). LAC is funded by the National Institute of Health through a NIBIB grant (R01 EB017205). PK is funded by the Ministry of Science and Technology (Taiwan; MOST109-2222-E-007-004-MY3).
• Keywords: Deep Learning; Early Detection of Cancer; Lung Neoplasms; Artificial Intelligence; Humans; Retrospective Studies

Abstract

BACKGROUND: Previous studies in medical imaging have shown disparate abilities of artificial intelligence (AI) to detect a person's race, yet there is no known correlation for race on medical imaging that would be obvious to human experts when interpreting the images. We aimed to conduct a comprehensive evaluation of the ability of AI to recognise a patient's racial identity from medical images. METHODS: Using private (Emory CXR, Emory Chest CT, Emory Cervical Spine, and Emory Mammogram) and public (MIMIC-CXR, CheXpert, National Lung Cancer Screening Trial, RSNA Pulmonary Embolism CT, and Digital Hand Atlas) datasets, we evaluated, first, performance quantification of deep learning models in detecting race from medical images, including the ability of these models to generalise to external environments and across multiple imaging modalities. Second, we assessed possible confounding of anatomic and phenotypic population features by assessing the ability of these hypothesised confounders to detect race in isolation using regression models, and by re-evaluating the deep learning models by testing them on datasets stratified by these hypothesised confounding variables. Last, by exploring the effect of image corruptions on model performance, we investigated the underlying mechanism by which AI models can recognise race. FINDINGS: In our study, we show that standard AI deep learning models can be trained to predict race from medical images with high performance across multiple imaging modalities, which was sustained under external validation conditions (x-ray imaging [area under the receiver operating characteristics curve (AUC) range 0·91-0·99], CT chest imaging [0·87-0·96], and mammography [0·81]). We also showed that this detection is not due to proxies or imaging-related surrogate covariates for race (eg, performance of possible confounders: body-mass index [AUC 0·55], disease distribution [0·61], and breast density [0·61]). Finally, we provide evidence to show that the ability of AI deep learning models persisted over all anatomical regions and frequency spectrums of the images, suggesting the efforts to control this behaviour when it is undesirable will be challenging and demand further study. INTERPRETATION: The results from our study emphasise that the ability of AI deep learning models to predict self-reported race is itself not the issue of importance. However, our finding that AI can accurately predict self-reported race, even from corrupted, cropped, and noised medical images, often when clinical experts cannot, creates an enormous risk for all model deployments in medical imaging. FUNDING: National Institute of Biomedical Imaging and Bioengineering, MIDRC grant of National Institutes of Health, US National Science Foundation, National Library of Medicine of the National Institutes of Health, and Taiwan Ministry of Science and Technology.