Eyes on early intervention for child autism
Prof. Benny Zee (middle) leads the research study on the application of ARIA technology to assess the risk of autism spectrum disorder.
CUHK has successfully developed a convenient, non-invasive and painless technology that can quickly assess the risk of autism spectrum disorder (ASD) simply by analysing the fundus images of children’s eyes. By offering an objective screening method for autism risk, the new technology helps children with autism to receive early intervention rather than waiting for a long time for diagnosis. The study can be found in the journal EClinicalMedicine published by The Lancet.
The study used the Automatic Retinal Image Analysis (ARIA) method to examine retinal images for the tell-tale signs of autism identified by previous studies, such as the thinning of retinal nerve fibre layer and other machine-learning-based parameters. Based on 46 autism cases from special needs schools, the study concluded that the innovative method could be an effective risk assessment tool for autism screening, with both the sensitivity and specificity of ARIA technology in identifying ASD reaching as high as 90%.
‘Our eyes enclose tremendously important clues and signals to our health. What we need is the right technology for their interpretation,’ says Prof. Benny Zee, Director of the Centre for Clinical Research and Biostatistics, the Jockey Club School of Public Health and Primary Care at CUHK.
An objective screening method
The lack of an objective screening method for autism is a major cause of delayed diagnosis or even misdiagnosis.
Autism is a complex neurodevelopmental disorder that begins at a young age and can affect social interaction, communication, and sensory information. Early intervention is highly recommended, but a diagnosis of autism typically requires lengthy assessment by multi-disciplinary professionals. The lack of an objective screening method is a major cause of delayed diagnosis or misdiagnosis, especially in young children.
With ARIA technology, retinal images can be quickly and easily obtained from young children in a community setting and used to assess their risk of autism. Prof. Zee believes that ARIA technology may provide critical information for the classification of autism and may even contribute to the future development of an objective measure of autism.
Knowledge transfer with social impact
The importance of this study lies not only in scientific and technological advancement but also in revealing how a close collaboration between universities, special needs schools, and community optometrists can generate extensive social capital and create more social impact. As a result, the research team recently received the Outstanding Social Capital Partnership Award and the Social Capital Builder Logo Award from the Hong Kong SAR Government in recognition of its community engagement programmes.
Retinal images provide important clues and signals to our health.
Prof. Zee has devoted himself to the study of ARIA for more than ten years. ARIA technology has previously been applied to assess the risk of stroke (ARIA-stroke risk) and white matter hyperintensities as an early risk factor of dementia (ARIA-WMH). The team is now working on ARIA technology for the risk assessment of undiagnosed diabetes, coronary heart disease, diabetic kidney disease, mood disorders and COVID-19 complications. Prof. Zee foresees ARIA will become a standard risk assessment tool, promoting disease prevention and translating the research results into applications that will substantially impact society.