FDA Review of Radiologic AI Algorithms: Process and Challenges
- 1 January 2024
- journal article
- editorial
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 310 (1) , e230242
Abstract
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.Keywords
This publication has 16 references indexed in Scilit:
- The Need for Medical Artificial Intelligence That Incorporates Prior ImagesRadiology, 2022
- External Validation of Deep Learning Algorithms for Radiologic Diagnosis: A Systematic ReviewRadiology: Artificial Intelligence, 2022
- FDA-regulated AI Algorithms: Trends, Strengths, and Gaps of Validation StudiesAcademic Radiology, 2022
- FDA-approved deep learning software application versus radiologists with different levels of expertise: detection of intracranial hemorrhage in a retrospective single-center studyNeuroradiology, 2022
- Diagnostic Accuracy and Failure Mode Analysis of a Deep Learning Algorithm for the Detection of Cervical Spine FracturesAmerican Journal of Neuroradiology, 2021
- How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvalsNature Medicine, 2021
- Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015–20): a comparative analysisThe Lancet Digital Health, 2021
- Utility of Artificial Intelligence Tool as a Prospective Radiology Peer Reviewer — Detection of Unreported Intracranial HemorrhageAcademic Radiology, 2021
- The Rebirth of CAD: How Is Modern AI Different from the CAD We Know?Radiology: Artificial Intelligence, 2019
- The utility of deep learning: evaluation of a convolutional neural network for detection of intracranial bleeds on non-contrast head computed tomography studies2019