Brain MRI, AI predict deaf children's capacity to learn language

Researchers from The Chinese University of Hong Kong and Ann & Robert H. Lurie Children's Hospital of Chicago have combined international expertise and two types of technology to predict how well a deaf child can learn language after receiving cochlear implant surgery in a study published in the Proceedings of the National Academy of Sciences.  

The brain and the ear play equal roles in hearing and language development and hearing loss at a young age can cause abnormal brain develop due to the lack of auditory stimulation in areas of the brain. Since approved by the FDA in 1991, cochlear implants have helped children as early as being infants to hear clearer and understand better, however many still lag behind developmentally compared to their peers.  

Researchers from the Chinese University of Hong Kong and Ann & Robert H. Lurie Children's Hospital of Chicago have two types of technology to predict how well a deaf child can learn language after receiving cochlear implant surgery. 

“Since the brain underlies all human ability, the methods we have applied to children with hearing loss could have widespread use in predicting function and improving the lives of children with a broad range of disabilities,” said co-author of the study Patrick C. M. Wong, PhD, a cognitive neuroscientist, professor and director of the Brain and Mind Institute at The Chinese University of Hong Kong to WTTW Chicago Tonight.  

Provided through a machine learning algorithm that utilizes both MRI exams of the brain and artificial intelligence, researchers have contributed to a better understanding of how the brains structure in children with developmental challenges impacts learning language.  

"The ability to predict language development is important because it allows clinicians and educators to intervene with therapy to maximize language learning for the child," said Wong in a press release. "Since the brain underlies all human ability, the methods we have applied to children with hearing loss could have widespread use in predicting function and improving the lives of children with a broad range of disabilities."  

According to Nancy M. Young, MD, medical director of audiology and cochlear implant programs at Lurie Children's and a surgeon and professor at Northwestern University Feinberg School of Medicine, there has been no reliable methods to predict which children are at risk to develop poorer language skills. The study, she explains, is the first of its kind to "provide clinicians and caregivers with concrete information about how much language improvement can be expected given the child's brain development immediately before surgery" and eventually provide customized, precision hearing, speech and music therapy for pediatric patients.  

"We used MRI to capture these abnormal patterns before cochlear implant surgery and constructed a machine-learning algorithm for predicting language development with a relatively high degree of accuracy, specificity and sensitivity," Wong explained. "Although the current algorithm is built for children with hearing impairment, research is being conducted to also predict language development in other pediatric populations. A one-size-fits-all intensive therapy approach is impractical and may not adequately address the needs of those children most at risk to fall behind."