Full width home advertisement

Welcome Home


Post Page Advertisement [Top]

Mayo Clinic and Google collaborate to create a new AI algorithm for treating psychiatric illness



In collaboration with Google Research, scientists at the Mayo Clinic have developed a new artificial intelligence (AI) system that can be used to determine which brain regions are directly interconnected with one another. This information can then be used to guide the placement of electrodes for stimulating devices used to treat network brain disorders. Individuals suffering from epilepsy, movement disorders such as Parkinson's disease, and psychological ailments such as obsessive-compulsive disorder and depression may benefit from the use of this algorithm.


It is difficult to figure out how different brain networks communicate with one another. Patients' brain networks can be investigated by delivering brief pulses of electrical current to one area of their brain while simultaneously measuring voltage responses in other areas of the patient's brain. According to the theory, one should be able to infer the structure of brain networks from this type of information. Although the problem is difficult to solve with real-world data, it is made more difficult because the recorded signals are complex and only a limited number of measurements can be made.



Mayo Clinic researchers devised a set of paradigms, or viewpoints, to make comparing the effects of electrical stimulation on the brain more manageable. In addition, because there was no mathematical technique to characterize how assemblies of inputs converge in human brain regions in the scientific literature, the Mayo team collaborated with an international expert in artificial intelligence algorithms to develop a new type of algorithm called basis profile curve identification, which stands for basis profile curve identification.


After being diagnosed with a brain tumor, a patient underwent placement of an electrocorticographic electrode array to locate seizures and map brain function before the tumor was surgically removed, according to a study published in the journal PLOS computational biology. Every electrode interaction resulted in hundreds to thousands of time points that could be analyzed using the new algorithm after the interaction was completed.


“Our findings show that this new type of algorithm may help us understand which brain regions directly interact with one another, which in turn may help guide the placement of electrodes for stimulating devices to treat network brain diseases,” says Kai Miller, M.D., PhD, a Mayo Clinic neurosurgeon and the study's first author. “Our findings show that this new type of algorithm may help us understand which brain regions directly interact with one another,” says Miller. The researchers believe that as new technology is developed, algorithms such as this one could aid in the treatment of patients suffering from epilepsy, movement disorders such as Parkinson's disease, and psychiatric illnesses such as obsessive-compulsive disorder and depression.


According to Klaus-Robert Mueller, PhD, study co-author and member of the Google Research Brain Team, “Neurologic data to date has proven to be some of the most challenging and exciting data to model for AI researchers.” At the Technical University of Berlin, Dr Mueller serves as co-director of the Berlin Institute for the Foundations of Learning and Data as well as director of the Machine Learning Group.


The authors of the study make a downloadable code package available so that others can experiment with the technique. “Sharing the code that has been developed is a critical component of our efforts to improve the reproducibility of research,” says Dora Hermes, PhD, a Mayo Clinic biomedical engineer and senior author of the paper.

No comments:

Post a Comment

Bottom Ad [Post Page]