Aortic & peripheral vascular disease
Thoracic Aortic Aneurysm Risk Assessment: A Machine Learning Approach
Authors' conclusion
A preliminary set of models demonstrated the ability of a ML algorithm to improve prediction of the mechanical function of TAA tissue.
Study context
- Population
- Patients undergoing surgery for thoracic aortic aneurysm (resected tissue biaxial tensile testing), incl. healthy controlsincl
- Participants
- 158 patients
- Comparison
- Machine learning (ML) model vs aortic diameter and indexed aortic size as correlates of thoracic aortic aneurysm (TAA) tissue energy loss
- Outcome
- Correlation with energy loss of TAA tissue (biomechanical function)
Main finding
As reported in the abstract
Correlation with energy loss (R2)
| Group | R2 |
|---|---|
| ML model | 0.63 |
| Aortic diameter | 0.26 |
| Indexed aortic size | 0.32 |
R2
ML model0.63
Aortic diameter0.26
Indexed aortic size0.32
Further findings
Adding echocardiogram-derived stiffness metric as input (subcohort n = 67)
- Correlative performance improved from R2 = 0.46 to R2 = 0.62
Original publication
Thoracic Aortic Aneurysm Risk Assessment: A Machine Learning Approach. JACC Adv. Published 28 September 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →