How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals

A comprehensive overview of medical AI devices approved by the US Food and Drug Administration sheds new light on limitations of the evaluation process that can mask vulnerabilities of devices when they are deployed on patients.

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Nature medicine 2021-04, Vol.27 (4), p.582-584
Hauptverfasser:	Wu, Eric, Wu, Kevin, Daneshjou, Roxana, Ouyang, David, Ho, Daniel E., Zou, James
Format:	Artikel
Sprache:	eng
Schlagworte:	631/114/2413 692/308 706/703 Algorithms Artificial Intelligence Bias Biochemistry & Molecular Biology Biomedical and Life Sciences Biomedicine Cancer Research Case studies Cell Biology Comment Databases as Topic Device Approval Equipment and Supplies Evaluation FDA approval Humans Infectious Diseases Licensing, certification and accreditation Life Sciences & Biomedicine Medical equipment Medicine, Research & Experimental Metabolic Diseases Molecular Medicine Neurosciences Patients Physiological apparatus Pneumothorax Research & Experimental Medicine Science & Technology United States United States Food and Drug Administration
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	A comprehensive overview of medical AI devices approved by the US Food and Drug Administration sheds new light on limitations of the evaluation process that can mask vulnerabilities of devices when they are deployed on patients.
ISSN:	1078-8956 1546-170X
DOI:	10.1038/s41591-021-01312-x