Batch Bayesian optimization design for optimizing a neurostimulator

Recently, spinal epidural neurostimulation is being considered for rehabilitation of persons suffering from partial spinal-cord injury. The neurostimulator must be programmed by a neurosurgeon, yet little work has been done to develop rigorous methods for optimally programming the device. We propose an adaptive design to efficiently optimize programming of the neurostimulator based on specified interim evaluations of patient reported preferences. Preferences for the eligible device configurations are estimated after each interim analysis through a conditionally autoregressive model that assumes preference for one configuration is related to preferences for neighboring configurations. Using the adaptively updated preferences, a group of configurations is programmed into the device for the patient to evaluate during the next follow-up period. This selection is based on a balance of device exploration and preference maximization. We repeat this process until a specified stopping rule or the calibration end is reached. We show simulation studies to evaluate the overall quality of the adaptive calibration for various configuration selection strategies and the effects of stopping it early.