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

The Lancet Digital Health - Tập 4 Số 6 - Trang e406-e414 - 2022
Judy Wawira Gichoya1, Imon Banerjee2, Ananth Reddy Bhimireddy1, James MacGregor Burns3, Leo Anthony Celi4,5, Li-Ching Chen6, Ramón Correa2, Natalie Dullerud7, Marzyeh Ghassemi8,5, Shih-Cheng Huang9, Po‐Chih Kuo6, Matthew P. Lungren9, Lyle J. Palmer10,11, Brandon J. Price12, Saptarshi Purkayastha3, Ayis Pyrros13, Luke Oakden‐Rayner10, Chima Okechukwu14, Laleh Seyyed-Kalantari7,15,16, Hari Trivedi1, Ryan Wang6, Zachary Zaiman17, Haoran Zhang7
1Department of Radiology, Emory University, Atlanta, Ga. USA
2School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ, USA
3School of Informatics and Computing, Indiana University–Purdue University, Indianapolis, IN, USA
4Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA.
5Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA, USA
6Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan
7Department of Computer Science, University of Toronto, Toronto, ON, Canada
8Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA
9Stanford University School of Medicine, Palo Alto, CA USA
10Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
11School of Public Health, University of Adelaide, Adelaide, SA, Australia
12Florida State University College of Medicine, Tallahassee, FL, USA
13Dupage Medical Group, Hinsdale, IL, USA
14Department of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA
15Lunenfeld-Tanenbaum Research Institute, Sinai Health, Toronto, ON, Canada
16Vector Institute for Artificial Intelligence, Toronto, ON, Canada
17Department of Computer Science, Emory University, Atlanta, GA, USA

Tóm tắt

Từ khóa


Tài liệu tham khảo

Bender

Angwin

Koenecke, 2020, Racial disparities in automated speech recognition, Proc Natl Acad Sci USA, 117, 7684, 10.1073/pnas.1915768117

Buolamwini, 2018, Gender shades: intersectional accuracy disparities in commercial gender classification, PMLR, 81, 77

Adamson, 2018, Machine learning and health care disparities in dermatology, JAMA Dermatol, 154, 1247, 10.1001/jamadermatol.2018.2348

Navarrete-Dechent, 2018, Automated dermatological diagnosis: hype or reality?, J Invest Dermatol, 138, 2277, 10.1016/j.jid.2018.04.040

Sarkar, 2021, Performance of intensive care unit severity scoring systems across different ethnicities in the USA: a retrospective observational study, Lancet Digit Health, 3, e241, 10.1016/S2589-7500(21)00022-4

Obermeyer, 2019, Dissecting racial bias in an algorithm used to manage the health of populations, Science, 366, 447, 10.1126/science.aax2342

Seyyed-Kalantari, 2021, Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations, Nat Med, 27, 2176, 10.1038/s41591-021-01595-0

Seyyed-Kalantari, 2020, CheXclusion: fairness gaps in deep chest X-ray classifiers, arXiv

Yi, 2021, Radiology “forensics”: determination of age and sex from chest radiographs using deep learning, Emerg Radiol, 28, 949, 10.1007/s10140-021-01953-y

Eng, 2021, Artificial intelligence algorithm improves radiologist performance in skeletal age assessment: a prospective multicenter randomized controlled trial, Radiology, 301, 692, 10.1148/radiol.2021204021

Rim, 2020, Prediction of systemic biomarkers from retinal photographs: development and validation of deep-learning algorithms, Lancet Digit Health, 2, e526, 10.1016/S2589-7500(20)30216-8

Munk, 2021, Assessment of patient specific information in the wild on fundus photography and optical coherence tomography, Sci Rep, 11, 10.1038/s41598-021-86577-5

Poplin, 2018, Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning, Nat Biomed Eng, 2, 158, 10.1038/s41551-018-0195-0

Greenland, 1986, Identifiability, exchangeability, and epidemiological confounding, Int J Epidemiol, 15, 413, 10.1093/ije/15.3.413

Greenland, 1999, Confounding and collapsibility in causal inference, SSO Schweiz Monatsschr Zahnheilkd, 14, 29

Wawira Gichoya, 2021, Equity in essence: a call for operationalising fairness in machine learning for healthcare, BMJ Health Care Inform, 28, 10.1136/bmjhci-2020-100289

Tariq, 2020, Current clinical applications of artificial intelligence in radiology and their best supporting evidence, J Am Coll Radiol, 17, 1371, 10.1016/j.jacr.2020.08.018

Benjamens, 2020, The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database, NPJ Digit Med, 3, 118, 10.1038/s41746-020-00324-0

Tadavarthi, 2020, The State of radiology AI: considerations for purchase decisions and current market offerings, Radiol Artif Intell, 2, 10.1148/ryai.2020200004

Krieger, 1987, Shades of difference: theoretical underpinnings of the medical controversy on black/white differences in the United States, 1830–1870, Int J Health Serv, 17, 259, 10.2190/DBY6-VDQ8-HME8-ME3R

Cooper, 1986, The biological concept of race and its application to public health and epidemiology, J Health Polit Policy Law, 11, 97, 10.1215/03616878-11-1-97

Johnson, 2019, MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports, Sci Data, 6, 317, 10.1038/s41597-019-0322-0

Irvin, 2019, CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison, AAAI, 33, 590, 10.1609/aaai.v33i01.3301590

Wagner, 2000, Measures of body composition in blacks and whites: a comparative review, Am J Clin Nutr, 71, 1392, 10.1093/ajcn/71.6.1392

del Carmen, 2007, Mammographic breast density and race, AJR Am J Roentgenol, 188, 1147, 10.2214/AJR.06.0619

Graham, 2015, Disparities in cardiovascular disease risk in the United States, Curr Cardiol Rev, 11, 238, 10.2174/1573403X11666141122220003

Ettinger, 1997, Racial differences in bone density between young adult black and white subjects persist after adjustment for anthropometric, lifestyle, and biochemical differences, J Clin Endocrinol Metab, 82, 429

Hochberg, 2007, Racial differences in bone strength, Trans Am Clin Climatol Assoc, 118, 305

DeGrave, 2021, AI for radiographic COVID-19 detection selects shortcuts over signal, Nat Mach Intell, 3, 610, 10.1038/s42256-021-00338-7

Jabbour, 2020, Deep learning applied to chest X-rays: exploiting and preventing shortcuts, PMLR, 126, 750

Ioannidis, 2021, Recalibrating the use of race in medical research, JAMA, 325, 623, 10.1001/jama.2021.0003

Vyas, 2020, Hidden in plain sight—reconsidering the use of race correction in clinical algorithms, N Engl J Med, 383, 874, 10.1056/NEJMms2004740

Brown, 2021, The algorithm audit: scoring the algorithms that score us, Big Data Soc, 10.1177/2053951720983865

Pierson, 2021, An algorithmic approach to reducing unexplained pain disparities in underserved populations, Nat Med, 27, 136, 10.1038/s41591-020-01192-7

Seyyed-Kalantari, 2021, Medical imaging algorithms exacerbate biases in underdiagnosis, Research Square

Thông tin
Thông tin xuất bản

The Lancet Digital Health

Tập 4 Số 6

e406-e414

Thông tin tác giả