Dr. Christine Dollaghan, a professor at the Callier Center for Communication Disorders and UT Dallas’ School of Behavioral and Brain Sciences, has contributed to two recent articles related to evaluating children’s language impairment.
She is sole author of a paper that appeared in the October edition of the Journal of Speech, Language, and Hearing Research. For that project, Dollaghan evaluated scores from more than 600 six-year-old children, some of whom had specific language impairment (SLI) and others who had normal language skills. She wanted to find out whether children with SLI appear to represent a qualitatively distinct group, or simply the children whose language skills fall at the lower end of the normal curve. The results showed that the children with SLI did not have qualitatively different language skills from their peers, suggesting that treatment approaches for SLI should be tailored to individual children rather than to a diagnostic label.
Article: “Taxometric Analyses of Specific Language Impairment in 6-Year-Old Children”
Dollaghan also is a co-author of an article in the November edition of Artificial Intelligence in Medicine with colleagues from UT Dallas’ Erik Jonsson School of Engineering and Computer Science, K. Gabani, T. Solorio, Y. Liu, and K. Hassanali. The study explored the use of automated computer-based methods, including natural language processing and machine learning, to identify children with SLI based on 15-minute conversation samples. The automated methods performed well, suggesting that future collaborations between computer science and communication disorders are likely to be useful.
Article: “Exploring a corpus-based approach for detecting language impairment in monolingual English-speaking children”