Cardiac arrest & resuscitation
Artificial intelligence (AI)-driven carotid artery compressibility assessment via point-of-care ultrasound for blood pressure estimation in critically ill and post-resuscitation patients: a prospective observational study
Authors' conclusion
This proof-of-concept study demonstrated potential diagnostic utility of carotid artery compressibility for blood pressure estimation in critically ill and post-ROSC patients with hypotensive conditions.
Study context
- Population
- Critically ill and post-ROSC patients in the ED372 ultrasound clips
- Participants
- 56 participants
- Exposure
- AI-quantified carotid artery compressibility (CAC) on point-of-care ultrasound (POCUS) vs concurrently measured blood pressure (BP)
- Outcome
- Diagnostic performance of the model for identifying hypotension
Methodological detailsdiagnostic and regression analyses, AI-derived (deep learning, RealCAC-Net)
- Diagnostic and regression analyses
- AI-derived (deep learning, RealCAC-Net)
Main finding
As reported in the abstract
AUC for SBP < 60 mmHg
0.90
95% CI 0.87–0.93
AUC for mean BP < 40 mmHg
0.91
95% CI 0.88–0.94
Observational data: associations, not effects.
Further findings
Continuous BP estimation (regression models)
- Root mean squared errors as low as (mmHg)
- 8.3
- Model performed best in hypotensive ranges
Original publication
AI-driven carotid artery compressibility assessment via point-of-care ultrasound for blood pressure estimation in critically ill and post-resuscitation patients: a prospective observational study. Crit Care. Published 28 November 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →