Pulse field ablation (PFA) has recently received significant attention as a non-thermal energy-based therapy for treating cardiac arrhythmias. During PFA, the arrhythmogenic tissue responsible for generating and propagating arrhythmias is destroyed through the mechanism of irreversible tissue electroporation by delivering a sequence of high-amplitude electrical pulses of microsecond duration [1,2]. Despite PFA’s higher safety and efficacy compared to other thermal ablative therapies, as reported in the initial clinical studies, there is no consensus on the pulse train parameters, electrode type, and the electric field strength needed to attain successful irreversible electroporation. Here, a novel framework integrating the computational modelling, design of experiments, and machine learning approaches has been reported to better understand cardiac tissue response to PFA parameters. A three-dimensional coupled electro-thermo-fluids model has been developed to investigate the effect of several intrinsic and extrinsic factors on the efficacy of PFA. Data generated from the computational simulations of the coupled model through different combinations of the factors utilizing the design of experiments approach is subsequently employed to train machine learning models that can serve as accurate surrogate models with enhanced predictive capabilities. Different machine learning models, such as linear, support vector machine, tree, Gaussian, and neural networks, are compared based on mean absolute error and R-squared values in both the training and testing phases. The findings indicate that pulse amplitude is the most statistically significant variable associated with ablation volume among pulse train parameters. Further, electrode insertion depth positively correlates with the ablation volume, while blood flow minimally impacts the ablation volume. The reported framework integrating computational modelling, statistical design, and machine learning approaches will lead to patient-specific PFA system design and protocol development, ultimately improving treatment outcomes for cardiac arrhythmias.