Genetic algorithm-based optimization framework for control parameters of ventricular assist devices

Abstract

In this work, a novel, genetic algorithm-based optimization framework (GAOF) has been developed and evaluated to optimize the control parameters of ventricular assist devices (VADs). This framework enables the optimization of complex control structures based on VAD- and patient-specific characteristics by allowing the selection of the numerical model of the human cardiovascular system and the VAD to represent the patient scenario of interest accurately. Additionally, the GAOF can incorporate treatment-specific goals during the definition of the objective functions of the optimization problem and, consequently, promotes the development of treatment-specific VAD controllers. The efficacy of the GAOF was assessed with one- and two-degree-of-freedom physiologic proportional-integral-derivative controllers and a physiologic data-driven iterative learning controller. Two VAD designs and various patient disease scenarios were used to further explore and evaluate the capabilities of the GAOF. The optimized controllers outperformed substantially the hand-tuned controller, which was used as the benchmark, in all the investigated cases. This highlights the potential improvement in the performance of any VAD controller by deploying the GAOF and, consequently, the possibility to increase the survival rates and enhance the quality of life of VAD patients.