Bias in vital signs? Machine learning models can learn patients' race or ethnicity from the values of vital signs alone.

Journal: BMJ health & care informatics
Published Date:

Abstract

OBJECTIVES: To investigate whether machine learning (ML) algorithms can learn racial or ethnic information from the vital signs alone.

Authors

  • Bojana Velichkovska
    Ss Cyril and Methodius University in Skopje, Skopje, North Macedonia.
  • Hristijan Gjoreski
    Department of Intelligent Systems, Jožef Stefan Institute, Jožef Stefan International Postgraduate School, Jamova cesta 39, Ljubljana, Slovenia. Electronic address: hristijan.gjoreski@ijs.s.
  • Daniel Denkovski
    Ss Cyril and Methodius University in Skopje, Skopje, North Macedonia.
  • Marija Kalendar
    Ss Cyril and Methodius University in Skopje, Skopje, North Macedonia.
  • Irene Dankwa Mullan
    Milken Institute School of Public Health, George Washington University, Washington, District of Columbia, USA.
  • Judy Wawira Gichoya
    From the American College of Radiology Data Science Institute, Reston, Va (J.R.G.); Department of Radiology, National Jewish Health, 3401 Shore Rd, Fort Collins, CO 80524 (J.R.G.); Mercy University Hospital, Cork, Ireland (A.B.); University of Texas MD Anderson Cancer Center, Houston, Tex (C.C.W.); MIT, Department of Linguistics and Philosophy, Cambridge, Mass (J.S.); Netherlands Cancer Institute, Amsterdam, the Netherlands (E.R.); Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, Alberta, Canada (J.L.J.); Radiology Department-Mayo Clinic, Rochester, Minn (S.G.L.); Lahey Hospital & Medical Center, Burlington, Mass (A.B.K.); Pelvic Pain Support Network, Poole, UK (J.B.); General Counsel, American College of Radiology, Reston, Va (W.F.S.); Center of Law and Internet, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands (R.v.d.H.v.G.); Department of Radiology, University Medical Center, Freiburg, Germany (E.K.); Department of Interventional Radiology, Oregon Health & Science University, Portland, Ore (J.W.G.); Department of Radiology and Imaging Sciences, Emory University, Atlanta, Ga (J.W.G., N.MS.); Department of Radiology, University of Pennsylvania, Philadelphia, Pa (T.S.C.); Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah (M.B.M.); Centre de Recherche du Centre Hospitalier de L'Université de Montréal, Quebec, Canada (A.T.); and Department of Radiology and Biomedical Imaging, UCSF, San Francisco, Calif (M.K.).
  • Nicole Martinez
    Stanford University School of Medicine, Stanford University, Stanford, California, USA.
  • Leo Celi
    Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA, 02139, USA.
  • Venet Osmani
    Fondazione Bruno Kessler Research Institute, Trento, Italy.