Early Language Prediction Technology

Overview

Linguistic and Paediatric researchers at The Chinese University of Hong Kong have developed a test to predict infants’ future language ability using electroencephalography (EEG). The test measures how an infant’s nervous system encodes and differentiates different Chinese speech sounds, and makes a prediction of an infant’s language abilities on a continuum of functions via machine learning.

  • Early Language Prediction Technology 0
  • Early Language Prediction Technology 1
Research completion
2021
Commercialisation opportunities
Service licensing agreement
Problem addressed

Poor language skills can place a long-term burden on both individual and society. Language development remains remarkably stable without intervention. Early detection and forecasting of language development in children would be crucial to indicate to parents at the earliest time point that intervention may be needed to reduce the severity of potential impairment in children.

Innovation
  • A novel and objective approach using an EEG test and prediction algorithms to provide prognostic indications of language developmental outcome for individuals at the earliest possible time point, which substantially outperforms predictive models constructed using tradition clinical factors such as birth weight and gestational age.
  • The predictive models used in this technology were constructed using machine-learning techniques with the application of cross validation. The data was based on a group of healthy infants who underwent an EEG procedure at infancy, and were later measured on language and communication outcomes. 
  • The prediction algorithm is precise enough to make prediction of language development at the level of the individual child using neural measures, with sensitivity and specificity up to 86.8% and 88.6% respectively. 
Key impact
  • Since infants cannot talk, behavioral tests are not reliable to access their language development. An EEG test would be a more objective and prefereable method to forecast language development outcomes.
  • A prognostic tool that could predict future language abilities at the earliest time point allows caregivers and clinicians to plan for early intervention, minimizing both the severity and the economic burden of a potential language impairment, as the nervous sytem is at its most plastic in the early years.
  • Auditory-evoked EEG is already being used for hearing screening and diagnosis of newborns in the form of an auditory brainstem reponse assessment. The prognostic tool extended the potential of this simple, safe and easy to administer test to predict infant language development.
  • Since a regression model is used to statistically adjust the neural input to the prediction model, infants can be tested at any convenient time during the first year of life without compromising the predictive performance of the tool.
Application
  • Incorporate the predictive technology into a standard ABR hearing screening test for newborns at hospitals
  • Medical clinics and health centres (paediatrics)

Patent

  • Pending PRC invention patent (202010692253.5)
The Chinese University of Hong Kong (CUHK)

Founded in 1963, The Chinese University of Hong Kong (CUHK) is a forward-looking comprehensive research university with a global vision and a mission to combine tradition with modernity, and to bring together China and the West. CUHK teachers and students hail from all around the world. Four Nobel laureates are associated with the university, and it is the only tertiary institution in Hong Kong with recipients of the Nobel Prize, Turing Award, Fields Medal and Veblen Prize sitting as faculty in residence. CUHK graduates are connected worldwide through an extensive alumni network. CUHK undertakes a wide range of research programmes in many subject areas, and strives to provide scope for all academic staff to undertake consultancy and collaborative projects with industry. 

Enquiry