Suscribirse

FDA-reviewed artificial intelligence-enabled products applicable to emergency medicine - 05/03/25

Doi : 10.1016/j.ajem.2024.12.062 
Jacob Morey a, , John Schupbach a, Derick Jones a, Laura Walker a, Rachel Lindor a, Brenna Loufek b, Aidan Mullan a, Daniel Cabrera a
a Department of Emergency Medicine, Mayo Clinic, Rochester, MN, USA 
b Center for Digital Health, Mayo Clinic, Rochester, MN, USA 

Corresponding author at: Department of Emergency Medicine, Mayo Clinic, 200 1st St SW, Rochester, MN 55905, USA.Department of Emergency MedicineMayo Clinic200 1st St SWRochesterMN55905USA

Abstract

Objective

To identify and assess artificial intelligence (AI)-enabled products reviewed by the U.S. Food and Drug Administration (FDA) that are potentially applicable to emergency medicine (EM).

Methods

The FDA AI-enabled products website was accessed to identify all marketed products as of March 2024. Board-certified EM physicians analyzed all products for applicability to EM practice. Inclusion criteria included products used by EM physicians directly or non-EM physicians participating directly in the evaluation and management of patients in an acute care setting. The Clinical and Economic Review (ICER) Evidence Rating Matrix was used to rate the net health benefit of applicable products.

Results

A total of 882 AI-enabled products have been reviewed by the FDA from 1995 to 2024. There were 272 products that were updates of prior products that were excluded, leaving 610 unique products. Products were most commonly evaluated by Radiology (454/610), Cardiovascular (59/610), and Neurology (25/610) panels. We found 154 (25 %) products applicable to EM that were approved through Radiology (121/154), Cardiovascular (24/154), Neurology (5/154), Anesthesiology (3/154), and Ophthalmology (1/154) panels. There were 30 products that were rated as having a comparable or incremental net health benefit with moderate certainty (a C+ rating).

Conclusion

An increasing number of AI-enabled products are available and regulated by the FDA. We have identified 154 that are applicable to EM, primarily related to assisting with diagnosis on various imaging modalities. There remain many opportunities for EM to assist in product reviews and meaningful translation of products into clinical practice.

El texto completo de este artículo está disponible en PDF.

Keywords : Artificial intelligence, Machine learning, FDA, Emergency medicine


Esquema


© 2024  Elsevier Inc. Reservados todos los derechos.
Añadir a mi biblioteca Eliminar de mi biblioteca Imprimir
Exportación

    Exportación citas

  • Fichero

  • Contenido

Vol 89

P. 241-246 - mars 2025 Regresar al número
Artículo precedente Artículo precedente
  • Pre-to-post COVID-19 pandemic trends in time from emergency department arrival to inpatient floor arrival: Door to floor time
  • Andrew J. Loza, Rohit B. Sangal, Katherine A. Gielissen, Edward R. Melnick, Christopher Sankey, Sharon Ostfeld-Johns
| Artículo siguiente Artículo siguiente
  • Clinical observation of 4 cases of cerebral infarction caused by left ventricular noncompaction
  • Yu Shufeng, Zhong Changyang, Jin Yi, Wu Cong, Wang Peng

Bienvenido a EM-consulte, la referencia de los profesionales de la salud.
El acceso al texto completo de este artículo requiere una suscripción.

¿Ya suscrito a @@106933@@ revista ?

@@150455@@ Voir plus

Mi cuenta


Declaración CNIL

EM-CONSULTE.COM se declara a la CNIL, la declaración N º 1286925.

En virtud de la Ley N º 78-17 del 6 de enero de 1978, relativa a las computadoras, archivos y libertades, usted tiene el derecho de oposición (art.26 de la ley), el acceso (art.34 a 38 Ley), y correcta (artículo 36 de la ley) los datos que le conciernen. Por lo tanto, usted puede pedir que se corrija, complementado, clarificado, actualizado o suprimido información sobre usted que son inexactos, incompletos, engañosos, obsoletos o cuya recogida o de conservación o uso está prohibido.
La información personal sobre los visitantes de nuestro sitio, incluyendo su identidad, son confidenciales.
El jefe del sitio en el honor se compromete a respetar la confidencialidad de los requisitos legales aplicables en Francia y no de revelar dicha información a terceros.


Todo el contenido en este sitio: Copyright © 2025 Elsevier, sus licenciantes y colaboradores. Se reservan todos los derechos, incluidos los de minería de texto y datos, entrenamiento de IA y tecnologías similares. Para todo el contenido de acceso abierto, se aplican los términos de licencia de Creative Commons.