Presenter Type
UNO Graduate Student (Doctoral)
Major/Field of Study
Biomechanics
Author ORCID Identifier
https://orcid.org/0000-0002-6134-5550
Advisor Information
Alexey Kamenskiy, University of Nebraska at Omaha
Location
MBSC302 - G (Doctoral)
Presentation Type
Oral Presentation
Start Date
24-3-2023 10:30 AM
End Date
24-3-2023 11:45 AM
Abstract
Background: Disease of the lower extremity arteries (Peripheral Arterial Disease, PAD) is associated with high morbidity and mortality. During disease development, the arteries adapt by changing their diameter, wall thickness, and residual deformations, but the effects of demographics and risk factors on this process are not clear.
Methods: Superficial femoral arteries from 736 subjects (505 male, 231 female, 12 to 99 years old, average age 51±17.8 years) and the associated demographic and risk factor variables were used to construct machine learning (ML) regression models that predicted morphological characteristics (diameter, wall thickness, and longitudinal opening angle resulting from the separation of an axial strip) using Support Vector Regression (SVR-RBF kernel), Linear Regression, Ridge, Random Forest, Lasso, Bayesian Ridge, and Gradient Boosting Regressor methods.
Results: Age had the most significant effect on all morphological characteristics, followed by hypertension, sex, and dyslipidemia. Arteries older than 50 years were 27% wider in diameter, 23% thicker, and had 121% wider longitudinal opening angles. Vessels from males were thicker (7%) and wider (19%) than those from females, and had 17% larger longitudinal opening angles. Subjects with hypertension and dyslipidemia had thicker arteries than those without these conditions (13% and 10%, respectively). Smoking, alcohol, and drug abuse disorders did not have a significant effect on any of the morphological characteristics. Patients with Coronary Artery Disease had 7% wider arteries and 21% larger longitudinal opening angles than vessels from healthy subjects. Lasso and ridge regression machine learning techniques could predict most morphometric features with an average R2=0.44 (range 0.11-0.62), with better results for the longitudinal opening angle and lower predictive ability for wall thickness.
Conclusions: Subject demographics and risk factors differentially affect morphological changes in human lower extremity arteries. These data can help better understand PAD pathophysiology and inform the development of novel treatments.
Scheduling
10:45 a.m.-Noon
Included in
Artificial Intelligence and Robotics Commons, Biomechanics Commons, Biomechanics and Biotransport Commons, Biostatistics Commons, Cardiovascular Diseases Commons, Cardiovascular System Commons, Molecular, Cellular, and Tissue Engineering Commons, Other Biomedical Engineering and Bioengineering Commons, Tissues Commons, Vital and Health Statistics Commons
The Effects of Demographics and Risk Factors on the Morphological Characteristics of Human Femoropopliteal Arteries
MBSC302 - G (Doctoral)
Background: Disease of the lower extremity arteries (Peripheral Arterial Disease, PAD) is associated with high morbidity and mortality. During disease development, the arteries adapt by changing their diameter, wall thickness, and residual deformations, but the effects of demographics and risk factors on this process are not clear.
Methods: Superficial femoral arteries from 736 subjects (505 male, 231 female, 12 to 99 years old, average age 51±17.8 years) and the associated demographic and risk factor variables were used to construct machine learning (ML) regression models that predicted morphological characteristics (diameter, wall thickness, and longitudinal opening angle resulting from the separation of an axial strip) using Support Vector Regression (SVR-RBF kernel), Linear Regression, Ridge, Random Forest, Lasso, Bayesian Ridge, and Gradient Boosting Regressor methods.
Results: Age had the most significant effect on all morphological characteristics, followed by hypertension, sex, and dyslipidemia. Arteries older than 50 years were 27% wider in diameter, 23% thicker, and had 121% wider longitudinal opening angles. Vessels from males were thicker (7%) and wider (19%) than those from females, and had 17% larger longitudinal opening angles. Subjects with hypertension and dyslipidemia had thicker arteries than those without these conditions (13% and 10%, respectively). Smoking, alcohol, and drug abuse disorders did not have a significant effect on any of the morphological characteristics. Patients with Coronary Artery Disease had 7% wider arteries and 21% larger longitudinal opening angles than vessels from healthy subjects. Lasso and ridge regression machine learning techniques could predict most morphometric features with an average R2=0.44 (range 0.11-0.62), with better results for the longitudinal opening angle and lower predictive ability for wall thickness.
Conclusions: Subject demographics and risk factors differentially affect morphological changes in human lower extremity arteries. These data can help better understand PAD pathophysiology and inform the development of novel treatments.