SAFE-OPT: A Bayesian optimization algorithm for learning optimal deep brain stimulation parameters with safety constraints

To treat neurological and psychiatric diseases with deep brain stimulation, a trained clinician must select parameters for each patient by monitoring their symptoms and side-effects in a months-long trial-and-error process, delaying optimal clinical outcomes. Bayesian optimization has been proposed...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:bioRxiv
Hlavní autoři: Cole, Eric R, Connolly, Mark, Ghetiya, Mihir, Sendi, Mohammad, Kashlan, Adam, Eggers, Thomas, Robert Elkan Gross
Médium: Paper
Jazyk:angličtina
Vydáno: Cold Spring Harbor Cold Spring Harbor Laboratory Press 16.02.2024
Cold Spring Harbor Laboratory
Vydání:1.1
Témata:
Algorithms
Bayesian analysis
Bioengineering
Deep brain stimulation
Learning
Mental disorders
Mental task performance
Optimization algorithms
Patient safety
Safety
Side effects
Spatial memory
hippocampus
real-time
optimization
data-driven
Neuromodulation
ISSN:2692-8205, 2692-8205
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:To treat neurological and psychiatric diseases with deep brain stimulation, a trained clinician must select parameters for each patient by monitoring their symptoms and side-effects in a months-long trial-and-error process, delaying optimal clinical outcomes. Bayesian optimization has been proposed as an efficient method to quickly and automatically search for optimal parameters. However, conventional Bayesian optimization does not account for patient safety and could trigger unwanted or dangerous side-effects. In this study we develop SAFE-OPT, a Bayesian optimization algorithm designed to learn subject-specific safety constraints to avoid potentially harmful stimulation settings during optimization. We prototype and validate SAFE-OPT using a rodent multielectrode stimulation paradigm which causes subject-specific performance deficits in a spatial memory task. We first use data from an initial cohort of subjects to build a simulation where we design the best SAFE-OPT configuration for safe and accurate searching in silico. We then deploy both SAFE-OPT and conventional Bayesian optimization in new subjects in vivo, showing that SAFE-OPT can find an optimally high stimulation amplitude that does not harm task performance with comparable sample efficiency to Bayesian optimization and without selecting amplitude values that exceed the subject-specific safety threshold. The incorporation of safety constraints will provide a key step for adopting Bayesian optimization in real-world applications of deep brain stimulation.Competing Interest StatementThe authors have declared no competing interest.
Bibliografie:SourceType-Working Papers-1
ObjectType-Working Paper/Pre-Print-1
content type line 50
Competing Interest Statement: The authors have declared no competing interest.
ISSN:2692-8205
2692-8205
DOI:10.1101/2024.02.13.580142