TY - JOUR
T1 - FDA Review of Radiologic AI Algorithms
T2 - Process and Challenges
AU - Zhang, Kuan
AU - Khosravi, Bardia
AU - Vahdati, Sanaz
AU - Erickson, Bradley J.
N1 - Publisher Copyright:
© RSNA, 2024.
PY - 2024/1
Y1 - 2024/1
N2 - A Food and Drug Administration (FDA)–cleared artificial intelligence (AI) algorithm misdiagnosed a finding as an intracranial hemorrhage in a patient, who was finally diagnosed with an ischemic stroke. This scenario highlights a notable failure mode of AI tools, emphasizing the importance of human-machine interaction. In this report, the authors summarize the review processes by the FDA for software as a medical device and the unique regulatory designs for radiologic AI/machine learning algorithms to ensure their safety in clinical practice. Then the challenges in maximizing the efficacy of these tools posed by their clinical implementation are discussed.
AB - A Food and Drug Administration (FDA)–cleared artificial intelligence (AI) algorithm misdiagnosed a finding as an intracranial hemorrhage in a patient, who was finally diagnosed with an ischemic stroke. This scenario highlights a notable failure mode of AI tools, emphasizing the importance of human-machine interaction. In this report, the authors summarize the review processes by the FDA for software as a medical device and the unique regulatory designs for radiologic AI/machine learning algorithms to ensure their safety in clinical practice. Then the challenges in maximizing the efficacy of these tools posed by their clinical implementation are discussed.
UR - http://www.scopus.com/inward/record.url?scp=85181632562&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85181632562&partnerID=8YFLogxK
U2 - 10.1148/radiol.230242
DO - 10.1148/radiol.230242
M3 - Review article
C2 - 38165243
AN - SCOPUS:85181632562
SN - 0033-8419
VL - 310
JO - Radiology
JF - Radiology
IS - 1
M1 - e230242
ER -