Document Type
Journal Article
Publication Title
American Journal of Emergency Medicine
Volume
92
First Page
172
Last Page
181
Publisher
Elsevier
School
School of Science
Publication Unique Identifier
10.1016/j.ajem.2025.03.029
Abstract
Background: Artificial intelligence (AI) is used increasingly in point-of-care ultrasound (POCUS). However, the true role, utility, advantages, and limitations of AI tools in POCUS have been poorly understood. Aim: to conduct a scoping review on the current literature of AI in POCUS to identify (1) how AI is being applied in POCUS, and (2) how AI in POCUS could be utilized in clinical settings. Methods: The review followed the JBI scoping review methodology. A search strategy was conducted in Medline, Embase, Emcare, Scopus, Web of Science, Google Scholar, and AI POCUS manufacturer websites. Selection criteria, evidence screening, and selection were performed in Covidence. Data extraction and analysis were performed on Microsoft Excel by the primary investigator and confirmed by the secondary investigators. Results: Thirty-three papers were included. AI POCUS on the cardiopulmonary region was the most prominent in the literature. AI was most frequently used to automatically measure biometry using POCUS images. AI POCUS was most used in acute settings. However, novel applications in non-acute and low-resource settings were also explored. AI had the potential to increase POCUS accessibility and usability, expedited care and management, and had a reasonably high diagnostic accuracy in limited applications such as measurement of Left Ventricular Ejection Fraction, Inferior Vena Cava Collapsibility Index, Left-Ventricular Outflow Tract Velocity Time Integral and identifying B-lines of the lung. However, AI could not interpret poor images, underperformed compared to standard-of-care diagnostic methods, and was less effective in patients with specific disease states, such as severe illnesses that limit POCUS image acquisition. Conclusion: This review uncovered the applications of AI in POCUS and the advantages and limitations of AI POCUS in different clinical settings. Future research in the field must first establish the diagnostic accuracy of AI POCUS tools and explore their clinical utility through clinical trials.
DOI
10.1016/j.ajem.2025.03.029
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Comments
Kim, J., Maranna, S., Watson, C., & Parange, N. (2025). A scoping review on the integration of artificial intelligence in point-of-care ultrasound: Current clinical applications. The American Journal of Emergency Medicine, 92, 172-181. https://doi.org/10.1016/j.ajem.2025.03.029