CFD-derived radiomics from hemodynamic maps for quantitative assessment of left atrial flow in atrial fibrillation: a proof-of-concept study - Summary - MDSpire
Advertisement
CFD-derived radiomics from hemodynamic maps for quantitative assessment of left atrial flow in atrial fibrillation: a proof-of-concept study
To evaluate whether radiomics-based quantification of spatial texture patterns can provide reproducible left atrial flow biomarkers for atrial fibrillation classification, emphasizing the importance of reproducibility in clinical settings.
Key Findings:
Five robust features identified, four being Gray-Level Non-Uniformity features from throughflow regions.
The fifth feature was a Dependence Entropy feature from LAA helicity maps.
Classifier achieved 93% accuracy, 95% sensitivity, 90% specificity, and an AUC of 0.92.
Features correlated significantly with left atrial enlargement and mitral regurgitation grade, indicating their clinical relevance.
Interpretation:
Radiomics analysis of CFD-derived hemodynamic maps can effectively quantify complex left atrial flow patterns and identify reproducible flow biomarkers in atrial fibrillation.
Limitations:
Study is a proof-of-concept with a small sample size, which may introduce biases.
External validation in larger multicenter cohorts is needed.
Conclusion:
The framework establishes the feasibility of objective hemodynamic phenotyping with potential applications in atrial fibrillation risk stratification, potentially improving patient outcomes.
In a multicenter registry study, genetic diagnoses were associated with substantially lower cognitive, language, and motor scores; while birth weight, surgical timing, hospitalization burden, and caregiver education were also associated with outcomes.
