AI pitfalls and what not to do: mitigating bias in AI.

Journal: The British journal of radiology
Published Date: Sep 12, 2023

Abstract

Various forms of artificial intelligence (AI) applications are being deployed and used in many healthcare systems. As the use of these applications increases, we are learning the failures of these models and how they can perpetuate bias. With these new lessons, we need to prioritize bias evaluation and mitigation for radiology applications; all the while not ignoring the impact of changes in the larger enterprise AI deployment which may have downstream impact on performance of AI models. In this paper, we provide an updated review of known pitfalls causing AI bias and discuss strategies for mitigating these biases within the context of AI deployment in the larger healthcare enterprise. We describe these pitfalls by framing them in the larger AI lifecycle from problem definition, data set selection and curation, model training and deployment emphasizing that bias exists across a spectrum and is a sequela of a combination of both human and machine factors.

Authors

  • Judy Wawira Gichoya
    Department of Interventional Radiology, Oregon Health & Science University, Portland, Oregon; Department of Radiology and Imaging Sciences, Emory University, Atlanta, Georgia.
  • Kaesha Thomas
    Department of Radiology, Emory University, Atlanta, GA, USA.
  • Leo Anthony Celi
    Massachusetts Institute of Technology, Cambridge, MA, USA.
  • Nabile Safdar
    Department of Radiology, Medical College of Georgia at Augusta University, 1120 15th St, Augusta, GA 30912 (Y.T.); and Department of Radiology, Emory University, Atlanta, Ga (B.V., E.K., A.P., J.G., N.S., H.T.).
  • Imon Banerjee
    Mayo Clinic, Department of Radiology, Scottsdale, AZ, USA.
  • John D Banja
    Department of Rehabilitation Medicine, Emory University, Atlanta, Georgia; Center for Ethics, Emory University, Atlanta, Georgia.
  • Laleh Seyyed-Kalantari
    Computer Science, University of Toronto, Toronto, Ontario, Canada2Vector Institute, Toronto, Ontario, Canada* Corresponding author, laleh@cs.toronto.edu.
  • Hari Trivedi
    Department of Radiology, Medical College of Georgia at Augusta University, 1120 15th St, Augusta, GA 30912 (Y.T.); and Department of Radiology, Emory University, Atlanta, Ga (B.V., E.K., A.P., J.G., N.S., H.T.).
  • Saptarshi Purkayastha
    Indiana University School of Informatics and Computing, Indianapolis, IN, United States.

Keywords

External Resources

Popular Topics
Recent Journals