Related Experiment Video
Updated: Apr 6, 2026
08:44
An In Vitro Hemodynamic Loop Model to Investigate the Hemocytocompatibility and Host Cell Activation of Vascular Medical Devices
Published on: August 21, 2020
8.0K
Multi-objective optimization of pulsatile ventricular assist device hemocompatibility based on neural networks and a
Zihao Xu1, Ming Yang, Xianghui Wang
11 Department of Instrument Science and Engineering, Shanghai Jiao Tong University, Shanghai - China.
The International Journal of Artificial Organs
|August 6, 2015
Summary
This study introduces a novel multi-objective optimization method to improve ventricular assist device (VAD) hemocompatibility. The new approach enhances device performance by optimizing geometry for reduced hemolysis, platelet activation, and deposition.
Area of Science:
- Biomedical Engineering
- Computational Fluid Dynamics
- Medical Device Design
Background:
- Pulsatile ventricular assist devices (VADs) are crucial for mechanical circulatory support, but their clinical use is limited by poor hemocompatibility.
- Current methods for improving VAD hemocompatibility often rely on inefficient trial-and-error computational fluid dynamics (CFD) analysis.
Purpose of the Study:
- To develop and apply a multi-objective optimization method integrating neural networks and NSGA-II with FSI simulation to enhance pulsatile VAD hemocompatibility.
- To optimize VAD geometry by considering key hemocompatibility indices: hemolysis, platelet activation, and platelet deposition.
Main Methods:
- Parameterized the VAD blood chamber geometry and defined hemocompatibility indices as goal functions.
- Utilized neural networks to model the relationship between geometrical parameters and hemocompatibility indices.
- Employed NSGA-II for multi-objective optimization to identify Pareto optimal solutions, followed by fuzzy membership approach for selecting the best compromise solution.
Main Results:
- The optimized VAD design achieved acceptable levels for hemolysis, platelet activation, and platelet deposition indices.
- Relative errors between predicted and simulated hemocompatibility indices were less than 5%.
Conclusions:
- The proposed multi-objective optimization method shows significant potential for improving pulsatile VAD hemocompatibility.
- This approach may be applicable to the optimization of other blood-wetted medical devices.
