Machine-Learning for Optimization of Electrodes and Waveforms for Electroporation

The adoption of high-frequency irreversible electroporation in a variety of medical treatments is more and more frequent. Unfortunately, a large number of parameters can influence the efficiency and effectiveness of the electroporation procedures: suitable choices of electrodes and of the stimulating signals being some important examples. In this paper, we demonstrate that machine-learning strategies based on Neural Networks are an appropriate approach to optimize the choice of the electrode characteristics, and we discuss the extension of alternative Machine Learning approaches to the optimization of the stimulating waveforms.