Diagnostic accuracy of point-of-care ultrasound with artificial intelligence-assisted assessment of left ventricular ejection fraction
Source check: Source checked. Not independent scientific confirmation.
Finding: In a prospective multicentre study, EchoNous KOSMOS point-of-care ultrasound estimated left-ventricular ejection fraction in 424 participants and was compared with transthoracic echocardiography. Agreement was high (overall ICC 0.904); AUC was 0.98 for abnormal ejection fraction (<50%) and 0.99 for severe dysfunction (<30%). This diagnostic-accuracy study does not show improved patient outcomes.
Technology: EchoNous KOSMOS AI-assisted left-ventricular-ejection-fraction assessment
Family Kosmos: profile · models page
Publication: Peer-reviewed paper · Test context: prospective or independent check. Catalog categories, not an evidence grade.
- AI contribution
- The KOSMOS device's AI interprets point-of-care ultrasound images for LVEF assessment; in 424 prospective multicentre participants, estimates were compared with comprehensive echocardiography.
- Test and result
- Prospective multicentre comparison of AI-assisted point-of-care estimates with comprehensive transthoracic echocardiography in 424 participants. Overall ICC was 0.904; AUC was 0.98 for LVEF <50% and 0.99 for LVEF <30%.
- Limitation / still unknown
- The study reports diagnostic agreement, not whether AI-assisted estimates changed care or improved patient outcomes; transport to settings outside the participating centres is not established.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.nature.com/articles/s41746-023-00945-1 · https://europepmc.org/articles/PMC10613290 · https://pubmed.ncbi.nlm.nih.gov/37898711/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 4/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.