FDA-reviewed artificial intelligence-enabled products applicable to emergency medicine
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.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Recent work has provided insights into subsets of devices, but a comprehensive characterization of FDA-authorized AI-enabled devices is currently lacking.
“Recent work has provided insights into subsets of devices6–11, but a comprehensive characterization of FDA-authorized AI-enabled devices is currently lacking.”
From How AI is used in FDA-authorized medical devices: a taxonomy across 1,016 authorizations (2025) · cites this paper as [10]
Cites
Joshi, G., Jain, A., Araveeti, S. R., Adhikari, S., Garg, H., & Bhandari, M. (2024) · Electronics · doi:10.3390/electronics13030498 · Cited by 294 · see citing works
Harvey, H. B., & Gowda, V. (2020) · Academic Radiology · doi:10.1016/j.acra.2019.09.017 · Cited by 112 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
How AI is used in FDA-authorized medical devices: a taxonomy across 1,016 authorizations
Singh, R., Bapna, M., Diab, A. R., Ruiz, E. S., & Lotter, W. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01800-1 · Cited by 61 · see citing works
- Authors
- Morey, J., Schupbach, J., Jones, D., Walker, L., Lindor, R., Loufek, B., Mullan, A., & Cabrera, D.
- Affiliations
- Mayo Clinic (US)
- Corresponding author
- Morey, Jacob
- ORCID
- Venue
- The American Journal of Emergency Medicine
- Publisher
- Elsevier BV
- Published
- 2025-03
- Volume
- 89
- Pages
- 241-246
- ISSN
- 0735-6757 (ISSN-L)
- OpenAlex
- W4405775009
- Cited by
- 9
- References
- 2
- Citations by year
- 2026: 3 · 2025: 6
- FWCI
- 0.84
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- The American Journal of Emergency Medicine (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Technology and Human Factors in Education and Health
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- artificial intelligence, emergency medicine, AI-enabled medical devices, artificial intelligence in radiology, net health benefit, clinical translation of AI
- MeSH terms
- Artificial Intelligence, Emergency Medicine, Humans, United States, United States Food and Drug Administration
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review