Performance of a point-of-care ultrasound platform for artificial intelligence-enabled assessment of pulmonary B-lines
This study demonstrated excellent interrater reliability of B-line counts from experts but poor agreement with the AI software embedded in a major vendor system, primarily due to overcounting. Our findings indicate that further development is needed to increase the accuracy of AI tools in LUS.
Authors
- J. G. Smith (ORCID: https://orcid.org/0000-0001-6285-9935)
- Annika Ingvarsson (ORCID: https://orcid.org/0000-0003-1968-8880)
- Ashkan Labaf (ORCID: https://orcid.org/0000-0001-5522-2119)
- Anna Werther Evaldsson (ORCID: https://orcid.org/0000-0001-9509-7199)
- Linda Åhman-Persson
- Leo Silvén Husu
Institutions
- Lund University (SE)
- Skåne University Hospital (SE)
- University of Gothenburg (SE)
Publication Details
- Journal
- Cardiovascular Ultrasound
- Published
- 2025-03-02
- DOI
- https://doi.org/10.1186/s12947-025-00338-2
- Citations
- 3
- Primary Topic
- Ultrasound in Clinical Applications
- Type
- article
- Field-Weighted Citation Impact
- 4.64
Funders
- Lunds Universitet