Home Mathematics A safe-ML model for assessing head loss in a subject-specific human femoral arterial network
Chapter
Licensed
Unlicensed Requires Authentication

A safe-ML model for assessing head loss in a subject-specific human femoral arterial network

  • Debismita Nayak and T. S. L. Radhika
Become an author with De Gruyter Brill
Applied Engineering Mathematics
This chapter is in the book Applied Engineering Mathematics

Abstract

Head loss in arteries refers to the energy or pressure drop in blood flow caused by resistance, blood viscosity, or obstructions. An increased head loss may signal arterial problems such as blockages (e. g., atherosclerosis), reduced vascular flexibility, or turbulent flow. Therefore, accurately assessing head loss is crucial for early disease detection, treatment planning, surgical evaluation, and overall vascular health management. Hence, the prime objective of our study is head-loss evaluation in one of the important human arteries, the femoral arteryfemoral artery, an artery that transports blood and nutrients to the lower body. We chose to work on a subject-specific image for which a CFD model was developed using the COMSOL Multiphysics software. We simulated the model using the available clinical data on various model parameters to define various physiological conditions in the artery. The average blood velocities were computed in the three components of the femoral arteryfemoral artery: the common femoral arteryfemoral artery, superficial femoral arteryfemoral artery, and deep femoral arteryfemoral artery, and we calculated the head loss in each segment using established formulae. Our next objective was to see if there were any patterns in the simulated data generated for a wide range of the model parameters’ values. For this, we employed clustering techniques, and further, we developed machine learning (ML)machine learning models for each cluster to predict the head loss for a given set of input parameters. Safe-ML techniques were also integrated into our work to ensure the robustness and reliability of the results.

Abstract

Head loss in arteries refers to the energy or pressure drop in blood flow caused by resistance, blood viscosity, or obstructions. An increased head loss may signal arterial problems such as blockages (e. g., atherosclerosis), reduced vascular flexibility, or turbulent flow. Therefore, accurately assessing head loss is crucial for early disease detection, treatment planning, surgical evaluation, and overall vascular health management. Hence, the prime objective of our study is head-loss evaluation in one of the important human arteries, the femoral arteryfemoral artery, an artery that transports blood and nutrients to the lower body. We chose to work on a subject-specific image for which a CFD model was developed using the COMSOL Multiphysics software. We simulated the model using the available clinical data on various model parameters to define various physiological conditions in the artery. The average blood velocities were computed in the three components of the femoral arteryfemoral artery: the common femoral arteryfemoral artery, superficial femoral arteryfemoral artery, and deep femoral arteryfemoral artery, and we calculated the head loss in each segment using established formulae. Our next objective was to see if there were any patterns in the simulated data generated for a wide range of the model parameters’ values. For this, we employed clustering techniques, and further, we developed machine learning (ML)machine learning models for each cluster to predict the head loss for a given set of input parameters. Safe-ML techniques were also integrated into our work to ensure the robustness and reliability of the results.

Chapters in this book

  1. Frontmatter I
  2. Preface V
  3. Contents VII
  4. Love wave propagation in layered piezoelectric structures for sensor-based applications 1
  5. A safe-ML model for assessing head loss in a subject-specific human femoral arterial network 11
  6. Fluid dynamics of transportation of viscoelastic fluids through inclined circular cylindrical tubes and its application in biological systems 31
  7. Numerical computation of Crane-type MHD Casson (blood type) stagnation point fluid flow past a stretching sheet 45
  8. Bioconvective MHD Casson fluid flow with motile microorganisms on a moving flat plate embedded in a porous medium 59
  9. Stability analysis of convection in rotating fluid layers with triple diffusion 73
  10. Groundwater contamination in heterogeneous semi-infinite aquifers for 1-D flow 85
  11. Convection in the boundary layer with uniform heat flux from a rectangular cavity’s side walls enclosed by porous lining 99
  12. Natural convection in a rectangular cavity bounded by porous lining 113
  13. Analysis of delayed mosquito life-cycle model 127
  14. Reflection and transmission of plane waves between two initially stressed rotating nonlocal orthotropic microstretch thermoelastic half-spaces with imperfect interface 137
  15. Nonlocal thermoelasticity of Klein–Gordon type: constitutive modelling in a piezoelectric microbeam resonator with memory effect 159
  16. Mathematical perspectives on biomechanical signal processing 179
  17. Numerical simulation of thermal performance in a hybrid nanofluid filled chamber with a heat producing element 221
  18. Non-Darcian flow of bioconvective viscoelastic fluid in a convectively heated elongating surface with variable heat source and energy activation 239
  19. Finite element analysis of biological systems 255
  20. Numerical analysis of free convective heat-transfer characteristics of a non-Newtonian (Casson) fluid in a heated permeable cavity under the effects of thermal radiation 279
  21. Graph-theoretical insights into resting-state EEG: a mathematical approach to psychiatric disorder analysis 289
  22. Index 317
Downloaded on 31.10.2025 from https://www.degruyterbrill.com/document/doi/10.1515/9783111638782-002/html?lang=en
Scroll to top button