TY - JOUR
T1 - AI IN IMAGING AND THERAPY
T2 - INNOVATIONS, ETHICS, AND IMPACT: REVIEW ARTICLE AI pitfalls and what not to do: mitigating bias in AI
AU - Gichoya, Judy Wawira
AU - Thomas, Kaesha
AU - Celi, Leo Anthony
AU - Safdar, Nabile
AU - Banerjee, Imon
AU - Banja, John D.
AU - Seyyed-Kalantari, Laleh
AU - Trivedi, Hari
AU - Purkayastha, Saptarshi
N1 - Publisher Copyright:
© 2023 The Authors.
PY - 2023/10
Y1 - 2023/10
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85174038992&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174038992&partnerID=8YFLogxK
U2 - 10.1259/bjr.20230023
DO - 10.1259/bjr.20230023
M3 - Review article
C2 - 37698583
AN - SCOPUS:85174038992
SN - 0007-1285
VL - 96
JO - British Journal of Radiology
JF - British Journal of Radiology
IS - 1150
M1 - 20230023
ER -