Cardiac arrest & resuscitation
Artificial intelligence-based evaluation of carotid artery compressibility via point-of-care ultrasound in determining the return of spontaneous circulation during cardiopulmonary resuscitation
Authors' conclusion
RealCAC-Net enabled precise CAC quantification for ROSC determination during cardiopulmonary resuscitation.
Study context
- Population
- Adults with cardiac arrest undergoing cardiopulmonary resuscitation, South Korean ED, 2022–2023161 training, 134 test cases
- Comparison
- RealCAC-Net vs baseline model
- Outcome
- Accuracy of return of spontaneous circulation (ROSC) classification from carotid artery compressibility (dice similarity coefficient, intersection-over-union, precision, recall, F1 score)
Methodological detailssingle emergency department, artificial intelligence (AI) model development and testing, 11,958 training images from 161 cases; 15,080 test images from 134 cases
- Single emergency department
- AI model development and testing
- 11,958 training images from 161 cases; 15,080 test images from 134 cases
Performance
As reported in the abstract
ROSC classification performance
| Test or model | Cross-validation average dice similarity coefficient | Cross-validation intersection-over-union | Cross-validation classification accuracy | Test set classification accuracy | Test set F1 score |
|---|---|---|---|---|---|
| RealCAC-Net | 0.90 | 0.84 | 0.96 | 0.96 | 0.97 |
RealCAC-Net
Cross-validation average dice similarity coefficient0.90
Cross-validation intersection-over-union0.84
Cross-validation classification accuracy0.96
Test set classification accuracy0.96
Test set F1 score0.97
Original publication
Artificial intelligence-based evaluation of carotid artery compressibility via point-of-care ultrasound in determining the return of spontaneous circulation during cardiopulmonary resuscitation. Resuscitation. Published 5 July 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →