Online Bayesian optimization of vagus nerve stimulation.

Objective.In bioelectronic medicine, neuromodulation therapies induce neural signals to the brain or organs, modifying their function. Stimulation devices capable of triggering exogenous neural signals using electrical waveforms require a complex and multi-dimensional parameter space to control such waveforms. Determining the best combination of parameters (waveform optimization or dosing) for treating a particular patient's illness is therefore challenging. Comprehensive parameter searching for an optimal stimulation effect is often infeasible in a clinical setting due to the size of the parameter space. Restricting this space, however, may lead to suboptimal therapeutic results, reduced responder rates, and adverse effects.Approach. As an alternative to a full parameter search, we present a flexible machine learning, data acquisition, and processing framework for optimizing neural stimulation parameters, requiring as few steps as possible using Bayesian optimization. This optimization builds a model of the neural and physiological responses to stimulations, enabling it to optimize stimulation parameters and provide estimates of the accuracy of the response model. The vagus nerve (VN) innervates, among other thoracic and visceral organs, the heart, thus controlling heart rate (HR), making it an ideal candidate for demonstrating the effectiveness of our approach.Main results.The efficacy of our optimization approach was first evaluated on simulated neural responses, then applied to VN stimulation intraoperatively in porcine subjects. Optimization converged quickly on parameters achieving target HRs and optimizing neural B-fiber activations despite high intersubject variability.Significance.An optimized stimulation waveform was achieved in real time with far fewer stimulations than required by alternative optimization strategies, thus minimizing exposure to side effects. Uncertainty estimates helped avoiding stimulations outside a safe range. Our approach shows that a complex set of neural stimulation parameters can be optimized in real-time for a patient to achieve a personalized precision dosing.

A bounded iterative closest point method for minimally invasive registration of the femur.

This article describes a novel method for image-based, minimally invasive registration of the femur, for application to computer-assisted unicompartmental knee arthroplasty. The method is adapted from the well-known iterative closest point algorithm. By utilising an estimate of the hip centre on both the preoperative model and intraoperative patient anatomy, the proposed 'bounded' iterative closest point algorithm robustly produces accurate varus-valgus and anterior-posterior femoral alignment with minimal distal access requirements. Similar to the original iterative closest point implementation, the bounded iterative closest point algorithm converges monotonically to the closest minimum, and the presented case includes a common method for global minimum identification. The bounded iterative closest point method has shown to have exceptional resistance to noise during feature acquisition through simulations and in vitro plastic bone trials, where its performance is compared to a standard form of the iterative closest point algorithm.