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.

Air-gas exchange reevaluated: clinically important results of a computer simulation.

PURPOSE: The primary aim of this study was to evaluate the efficiency of air-gas exchange techniques and the factors that influence the final concentration of an intraocular gas tamponade. Parameters were varied to find the optimum method of performing an air-gas exchange in ideal circumstances. METHODS: A computer model of the eye was designed using 3D software with fluid flow analysis capabilities. Factors such as angular distance between ports, gas infusion gauge, exhaust vent gauge and depth were varied in the model. Flow rate and axial length were also modulated to simulate faster injections and more myopic eyes, respectively. The flush volume of gas required to achieve a 97% intraocular gas fraction concentration were compared. RESULTS: Modulating individual factors did not reveal any clinically significant difference in the angular distance between ports, exhaust vent size, and depth or rate of gas injection. In combination, however, there was a 28% increase in air-gas exchange efficiency comparing the most efficient with the least efficient studied parameters in this model. The gas flush volume required to achieve a 97% gas fill also increased proportionately at a ratio of 5.5 to 6.2 times the volume of the eye. CONCLUSIONS: A 35-mL flush is adequate for eyes up to 25 mm in axial length; however, eyes longer than this would require a much greater flush volume, and surgeons should consider using two separate 50-mL gas syringes to ensure optimal gas concentration for eyes greater than 25 mm in axial length.