The machine learning model combining age, HDL-C, ApoB, LVMI and AAoV predicted ascending aortic dilation in bicuspid aortic valve patients with an AUC of 0.825 and accuracy of 74.5%.
Cohort (n=51)
No
Does a machine learning model integrating echocardiography and serum biomarkers accurately predict ascending aorta dilation in patients with bicuspid aortic valve?
A machine learning model integrating echocardiographic hemodynamics and serum lipid markers can accurately predict ascending aorta dilation in patients with bicuspid aortic valve.
Effect estimate: AUC 0.825 (95% CI 0.694–0.933)
p-value: p=<0.05
Objective In order to address the challenge of early detection of ascending aortic dilation (AAD) in patients with bicuspid aortic valve (BAV), a machine learning prediction model integrating ultrasound hemodynamics and serum markers was developed to break through the limitations of traditional anatomical indicators. Methods A total of 51 patients with BAV were prospectively enrolled and divided into ascending aortic dilation group (BAV-D, n = 25) and non-dilated group (BAV-ND, n = 26). Two-dimensional echocardiographic parameters ascending aorta maximum flow rate (AAoV), mean pressure difference (AAoMPG) and blood lipid markers High-Density Lipoprotein Cholesterol (HDL-C), ApoB, etc. were collected, and the key predictors were screened by the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm, and the logistic regression model was constructed and the nomogram was visualized. Leave one cross-validation (LOOCV) was used to evaluate the robustness of the model. Results AAoV, AAoMPG and HDL-C in the BAV-D group were significantly higher than those in the BAV-ND group (all P 0.05). LASSO screened out five core predictors: age, HDL-C, ApoB, left ventricular mass index (LVMI), and AAoV. The AUC of the model was 0.825 (95% CI: 0.694–0.933), the accuracy was 74.5% (sensitivity 72.0%, specificity 76.9%), and the nomogram verification AUC was 0.809. Conclusion The machine learning model constructed by integrating hemodynamics (AAoV) and metabolic markers (HDL-C and ApoB) for the first time can accurately quantify the risk of AAD in BAV patients, and its performance is significantly better than that of a single anatomical parameter, providing a visual decision-making tool for early intervention.
Long et al. (Thu,) conducted a cohort in Adults with bicuspid aortic valve and ascending aortic dilation or non-dilated ascending aorta (n=51). Machine learning predictive model combining 2D echocardiographic parameters and serum lipid biomarkers vs. Standard clinical assessment using traditional anatomical parameters was evaluated on Discrimination accuracy of machine learning model for prediction of ascending aortic dilation in BAV patients (AUC 0.825, 95% CI 0.694–0.933, p=<0.05). The machine learning model combining age, HDL-C, ApoB, LVMI and AAoV predicted ascending aortic dilation in bicuspid aortic valve patients with an AUC of 0.825 and accuracy of 74.5%.