Efficiently searching through large tACS parameter spaces using closed-loop Bayesian optimization

Brain Stimulation

Ricardo P. Monti¹  Laura E. Simmons²  Joy L. Arthur³  Ilkka Laakso³  Ines R. Violante⁴  Robert Leech⁵  Severin Limal⁶  Romy Lorenz⁷ 

[1] Corresponding author. MRC Cognition and Brain Sciences Unit, University of Cambridge, Cambridge, CB2 7EF, UK.;Max-Planck Institute for Human Cognitive and Brain Sciences, Leipzig, 04303, Germany;Computational, Cognitive and Clinical Neuroscience Laboratory, Department of Medicine, Imperial College London, London, W12 0NN, UK;Department of Electrical Engineering and Automation, Aalto University, Espoo, 02150, Finland;Department of Physiology, Anatomy and Genetics, University of Oxford, Oxford, OX1 3PT, UK;Gatsby Computational Neuroscience Unit, University College London, London, W1T 4JG, UK;MRC Cognition and Brain Sciences Unit, University of Cambridge, Cambridge, CB2 7EF, UK;

关键词: Transcranial alternating current stimulation;    Experimental design;    Machine-learning;    Bayesian optimization;    Real-time;    Phosphenes;   

DOI  :  

来源: DOAJ

【 摘 要 】

Background: Selecting optimal stimulation parameters from numerous possibilities is a major obstacle for assessing the efficacy of non-invasive brain stimulation. Objective: We demonstrate that Bayesian optimization can rapidly search through large parameter spaces and identify subject-level stimulation parameters in real-time. Methods: To validate the method, Bayesian optimization was employed using participants’ binary judgements about the intensity of phosphenes elicited through tACS. Results: We demonstrate the efficiency of Bayesian optimization in identifying parameters that maximize phosphene intensity in a short timeframe (5 min for >190 possibilities). Our results replicate frequency-dependent effects across three montages and show phase-dependent effects of phosphene perception. Computational modelling explains that these phase effects result from constructive/destructive interference of the current reaching the retinas. Simulation analyses demonstrate the method's versatility for complex response functions, even when accounting for noisy observations. Conclusion: Alongside subjective ratings, this method can be used to optimize tACS parameters based on behavioral and neural measures and has the potential to be used for tailoring stimulation protocols to individuals.

【 授权许可】

Unknown