Biotechnology, Medical News, Neurocognitive disorders, Neuroscience

Language recovery in stroke patients can now be predicted using computer models of the brain

A group of researchers at Boston University are trying to figure out how the brain processes language and speech, as well as how to effectively rehabilitate those who have lost their capacity to speak due to brain damage caused by a stroke, trauma, or another sort of brain injury. Aphasia is a long-term neurological illness that affects over a million people in the United States and is caused by impairment to the portion of the brain responsible for language generation and processing.

“It’s a huge problem,” says Swathi Kiran, director of BU’s Aphasia Research Lab, and College of Health & Rehabilitation Sciences: Sargent College associate dean for research and James and Cecilia Tse Ying Professor in Neurorehabilitation. “It’s something our lab is working to tackle at multiple levels.”

Kiran and her colleagues have been studying the brain for the past decade to discover how it changes as people’s language abilities improve with speech therapy. Currently, they are creating new approaches for predicting a person’s capacity to improve before they begin therapy. Kiran and collaborators at BU and the University of Texas at Austin report in a new paper published in Scientific Reports that they have created sophisticated computer models of the brain to predict language recovery in Hispanic patients who speak both English and Spanish fluently — a group of aphasia patients who are particularly at risk of long-term language loss. According to the researchers, the finding could be a game changer for speech therapy and stroke survivors with aphasia.

Hispanic stroke survivors in the United States are roughly two times less likely to be insured than other racial or ethnic groups, according to Kiran, and so have more difficulty getting language therapy. Furthermore, even though patients may speak numerous languages at home, speech therapy is typically only offered in one language, making it difficult for doctors to prioritize which language a patient should receive therapy in.

“This work started with the question, ‘If someone had a stroke in this country and [the patient] speaks two languages, which language should they receive therapy in?'” says Kiran. “Are they more likely to improve if they receive therapy in English? Or in Spanish?”

This novel technology answers these questions by simulating the brain of a bilingual individual who is language handicapped, as well as their brain’s response to therapy in English and Spanish, using complex neural network models. The model can then choose the best language to target during treatment and anticipate how well a person would regain their language skills following therapy. They discovered that the models effectively predicted treatment effects in the treated language, indicating that these computational tools could greatly aid healthcare practitioners prescribe the optimal rehabilitation strategy feasible.

“There is more recognition with the pandemic that people from different populations–whether [those be differences of] race, ethnicity, different disability, socioeconomic status–don’t receive the same level of [healthcare],” says Kiran. “The problem we’re trying to solve here is, for our patients, health disparities at their worst; they are from a population that, the data shows, does not have great access to care, and they have communication problems [due to aphasia].”

The team is looking at how recovery in one language affects recovery in the other. For example, would learning the word “dog” in English lead to a patient recalling the word “perro,” the Spanish term for dog?

“If you’re bilingual you may go back and forth between languages, and what we’re trying to do [in our lab] is use that as a therapy piece,” says Kiran.

Clinical studies employing this technology are currently ongoing, and will offer a clearer picture of how the models may be used in hospital and clinical settings in the near future.

“We are trying to develop effective therapy programs, but we also try to deal with the patient as a whole,” Kiran says. “This is why we care deeply about these health disparities and the patient’s overall well-being.”

One thought on “Language recovery in stroke patients can now be predicted using computer models of the brain

Leave a Reply