2649

View Abstract / View Presentation

Identification of Hemodynamic Biomarkers for Bicuspid Aortic Valve Patients using Machine Learning

Pamela Franco^1,2,3, Julio Sotelo^1,3,4, Lydia Dux-Santoy⁵, Andrea Guala⁵, Aroa Ruiz-Muñoz⁵, Arturo Evangelista⁵, José Rodríguez-Palomares⁵, and Sergio Uribe^1,3,6
¹Biomedical Imaging Center, School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile, ²Electrical Engineering Department, School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile, ³Millennium Nucleus for Cardiovascular Magnetic Resonance, Santiago, Chile, ⁴School of Biomedical Engineering, Universidad de Valparaíso, Valparaíso, Chile, ⁵Department of Cardiology, Hospital Universitari Vall d’Hebron, Vall d’Hebron Institut de Recerca (VHIR), Universitat Autònoma de Barcelona, Barcelona, Spain, ⁶Radiology Department, School of Medicine, Pontificia Universidad Católica de Chile, Santiago, Chile

The clinical significance of BAV disease justifies the need for improved clinical guidelines. Medical imaging has demonstrated the existence of altered hemodynamics. We present a machine learning method consisting of a feature selection mechanism to classify accurately to identify them.

Figure 1. Features selection using SFS and exhaustive search: (a) Sequential forward selection. There are five selected features, and they correspond to Velocity Angle in AAo, Velocity Angle in AArch, Forward Velocity in AAo, Regurgitation Fraction in pDAo, and Helicity Density in AAo. (b) Feature Space in 3D. The selected features are certain hemodynamic features. We can see that the separability is ‘good’ between both classes (volunteers and BAV patients).

Table 2. Average accuracy and standard deviation of different combinations of classifiers and features. Each experiment was done using 10 group cross-validation and repeated 10 times with confidence interval 95%.