Observational analysis categorized aortic regurgitation severity in patients using automated hemodynamic indicators, suggesting efficient evaluation methods.
Motivation: Current standards for quantitative evaluation of chronic aortic regurgitation (AR) are confounded by variability in measurement/analysis techniques. Establishing automated assessment methods for AR would help standardize clinical evaluation. Goal(s): Thus study sought to identify hemodynamic quantifications indicative of AR severity using completely-automated analysis methods. Approach: A fully-automated 4D flow analysis pipeline, with machine-learning networks replacing manual intervention, was applied to MRI from AR patients to quantify aortic flow. These quantifications were compared to clinical AR grades to evaluate their ability to classify severe vs. non-severe. Results: Completely-automated reverse flow measurements in standardized descending aorta locations showed strong predictive performance for severe AR (area-under-curve>0.8). Impact: This study offers a template for completely automated assessment of aortic regurgitation and shows reverse flow in the proximal descending aorta is most predictive of aortic regurgitation severity. This may support standards for clinical evaluation of aortic regurgitation by CMR.
No takes yet. Share an insight, caveat, or question.
Johnson et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: