Personalized home based neurostimulation via AI optimization augments sustained attention

Area of Science:

• Neuroscience and Artificial Intelligence
• Cognitive Enhancement Technologies

Background:

• Brain-based augmentation technologies struggle with personalization and real-world application.
• Existing methods lack tailored neurostimulation for at-home cognitive enhancement.

Purpose of the Study:

• To develop an AI-driven personalized Bayesian optimization algorithm for remote neurostimulation parameter adjustment.
• To enhance sustained attention in individuals within their home environment.
• To ensure scalability and real-world translation of cognitive enhancement techniques.

Main Methods:

• Utilized an AI-driven personalized Bayesian optimization algorithm.
• Remotely adjusted neurostimulation parameters based on individual baseline ability and head anatomy.
• Validated the approach through in silico modeling and a double-blind, sham-controlled study.

Main Results:

• The AI algorithm successfully personalized neurostimulation for enhanced sustained attention.
• The approach demonstrated alignment with MRI-based models and neurobiological theories.
• Efficacy was maximized, showing potential for scalable, real-world cognitive enhancement.

Conclusions:

• AI-driven personalized neurostimulation offers a viable solution for at-home cognitive enhancement.
• The developed algorithm enables scalable and effective cognitive therapy in real-world settings.
• This approach overcomes key challenges in personalization and translation for brain-based technologies.