At Boston University, a team of researchers is working to better understand how language and speech are processed in the brain and how to better rehabilitate people who have lost their ability to communicate due to brain damage caused by a stroke. , a trauma or other type of brain injury. This type of language loss is called aphasia, a long-term neurological disorder caused by damage to the part of the brain responsible for the production and processing of language that affects more than one million people in the United States.
“It’s a huge problem,” says Swathi Kiran, director of the BU Aphasia Research Laboratory and the College of Health and Rehabilitation Sciences: research dean at Sargent College and professor of Neurorehabilitation at James and Cecilia Tse Ying. “It’s something our lab is working on to address at various levels.”
Over the past decade, Kiran and his team have been studying the brain to see how it changes as people language skills improve with speech therapy. More recently, they have developed new methods to predict a person’s ability to improve even before starting therapy. In a new article published in Scientific reports, Kiran, and collaborators from BU and the University of Texas at Austin report that they can predict language recovery in Hispanic patients who speak both English and Spanish fluently — a group of patients with aphasia, especially at risk of long-term language loss — through sophisticated computer models of the brain. They say the breakthrough could change the game of the field of speech therapy and stroke survivors affected by aphasia.
“That [paper] uses computational models to predict rehabilitation outcomes in a population of neurological disorders that are really underutilized, “says Kiran. In the United States, Hispanic stroke survivors are nearly twice as likely to be insured as the rest of racial or ethnic groups, ”says Kiran, and In addition, speech therapy is often only available in one language, although patients can speak several languages at home, making it difficult for doctors to prioritize in which language a patient should receive therapy. .
“This work began with the question,” If anyone had a stroke in this country and [the patient] speaks two languages, in which language should they receive therapy? “says Kiran.” Are they more likely to improve if they receive therapy in English? Or in Spanish? “
This first such technology addresses these needs through the use of sophisticated neural network models that simulate the brain of a bilingual person with a language disability and their brain’s response to therapy in English and Spanish. The model can then identify the optimal language to target during treatment and predict the outcome after therapy to predict the extent to which a person will regain their language skills. They found that the models accurately predicted the effects of treatment on treated language, meaning that these computational tools could guide health care providers in prescribing the best possible rehabilitation plan.
“There is more recognition with the pandemic than people from different populations, either [those be differences of] race, ethnicity, different disability, socioeconomic status; they do not receive the same level of [healthcare]”says Kiran.” The problem we are trying to solve here is, for our patients, health disparities at their worst; they come from a population that, according to the data, does not have great access to care and has communication problems [due to aphasia]. “
As part of this work, the team examines how recovery in one language affects recovery in another. Will learning the word “dog” in English make a patient remember the word “dog,” the word dog in Spanish?
“If you are bilingual, you can go back and forth between languages and what we are trying to do [in our lab] it’s a use as a piece of therapy, ”Kiran says.
Clinical trials using this technology are already underway, which will soon provide an even clearer picture of how models can be implemented in the hospital and clinical settings.
“We’re trying to develop effective therapy programs, but we’re also trying to deal with the patient in general,” Kiran says. “That’s why we are deeply concerned about these health disparities and the overall well-being of the patient.”
Uli Grasemann et al, Prediction of the response to language treatment in bilingual aphasia using neural network-based patient models, Scientific reports (2021). DOI: 10.1038 / s41598-021-89443-6
Citation: Computer simulations of the brain can predict language recovery in stroke survivors (2021, June 4) retrieved June 4, 2021 at https://medicalxpress.com/news/2021-06-simulations- brain-language-recovery-survivors.html
This document is subject to copyright. Apart from any fair treatment for private study or research purposes, no part may be reproduced without written permission. Content is provided for informational purposes only.