Mayo, Google Research develops a new AI algorithm to improve brain stimulation devices to treat disease

[ad_1]

Newswise – ROCHESTER, Minnesota For millions of people with epilepsy and movement disorders such as Parkinson’s disease, electrical brain stimulation is already expanding treatment options. In the future, electrical stimulation could help people with psychiatric illness and direct brain injuries, such as stroke.

However, studying how brain networks interact with each other is complicated. Brain networks can be explored by delivering short pulses of electrical current to one area of ​​a patient’s brain while measuring voltage responses in other areas. In principle, one should be able to deduce the structure of brain networks from this data. However, with real-world data, the problem is difficult because the recorded signals are complex and a limited amount of measurements can be made.

To make the problem manageable, Mayo Clinic researchers have developed a series of paradigms, or viewpoints, that simplify comparisons of the effects of electrical stimulation on the brain. Because there was no mathematical technique in the scientific literature to characterize how input assemblies converge in human brain regions, Mayo’s team collaborated with an international expert in artificial intelligence (AI) algorithms to develop a new type of algorithm called ” base profile curve “. identification.”

In a study published in PLOS Computational Biology, a patient with a brain tumor underwent placement of a series of electrocorticographic electrodes to detect seizures and map brain function before the tumor was removed. Each interaction of the electrode resulted in hundreds to thousands of time points being studied using the new algorithm.

“Our results show that this new type of algorithm can help us understand which brain regions interact directly with each other, which in turn can help guide the placement of electrodes to stimulate networked brain disease treatment devices. “says Kai Miller, MD, Ph. D., Mayo Clinic neurosurgeon and first author of the study. “With the emergence of new technologies, this type of algorithm can help us better treat patients with epilepsy, movement disorders such as Parkinson’s disease and psychiatric diseases such as OCD and depression.”

“Neurological data to date is perhaps the most challenging and exciting data for artificial intelligence researchers to model,” says Klaus-Robert Mueller, Ph.D., co-author of the study and member of the Google Research Brain Team. Dr. Mueller is co-director of the Berlin Institute for the Fundamentals of Learning and Data and Director of the Machine Learning Group both at the Technical University of Berlin.

In the study, the authors provide a downloadable code package for others to explore the technique. “Sharing the developed code is a key part of our efforts to aid research reproducibility,” says Dora Hermes, Ph.D., Mayo Clinic biomedical engineer and senior author.

This research was supported by the National Institutes of Health’s National Center for Advancing Translational Science Clinical and Translational Science Award, the National Institute of Mental Health Collaborative Research in Computational Neuroscience, and the Federal Ministry of Education and Research.

###

About Mayo Clinic Mayo Clinic is a nonprofit organization committed to innovating in clinical practice, education and research, and providing compassion, expertise and answers to all those in need of healing. Visit the Mayo Clinic News Network for more Mayo Clinic news. For information on COVID-19, including the Mayo Clinic Coronavirus Map Tracking Tool, which has 14-day forecast of COVID-19 trends, visit the Mayo Clinic COVID-19 Resource Center.

[ad_2]