A Hong Kong scientist has developed a method to use machine learning and artificial intelligence to scan retinas of children as young as six to detect early autism or the risk of autism and hopes to develop a commercial product this year, reports Reuters.
Retinal eye scanning can help to improve early detection and treatment outcomes for children, said Benny Zee, a professor at the Chinese University of Hong Kong. “The importance of starting early intervention is that they are still growing, they are still developing. So, there is a bigger chance of success,” Zee said.
Reuters reports that his method uses a high-resolution camera with new computer software which analyses a combination of factors including fibre layers and blood vessels in the eye.
The technology can be used to identify children at risk of autism and get them into treatment programmes sooner, said Zee.
Reuters reports that 70 children were tested using the technology, 46 with autism and a control group of 24. The technology was able to identify the children with autism 95.7% of the time. The average age tested was 13, with the youngest being six.
The report says autism specialists welcomed his findings but said there remained a huge stigma, with parents often reluctant to believe their children have autism even when there are clear signs.
“Many times, parents will initially be in denial,” said Dr Caleb Knight, who runs a private autism therapy centre. “If you had a medical test or biological marker like this, it might facilitate parents not going into denial for longer periods and therefore the child would get treatment more quickly.”
Zee is quoted by Reuters as saying that his research is intended to be a supplemental tool to a professional assessment by licensed healthcare professionals.
Study details
A machine learning approach for retinal images analysis as an objective screening method for children with autism spectrum disorder
Maria Lai, Jack Lee, Sally Chiu, Jessie Charm, Wing Yee So, Fung Ping Yuen, Chloe Kwok, Jasmine Tsoi, Yuqi Lin, Benny Zee
Published in EClinical Medicine on 5 November 2020
Abstract
Background
Autism spectrum disorder (ASD) is characterised by many of features including problem in social interactions, different ways of learning, some children showing a keen interest in specific subjects, inclination to routines, challenges in typical communication, and particular ways of processing sensory information. Early intervention and suitable supports for these children may make a significant contribution to their development. However, considerable difficulties have been encountered in the screening and diagnosis of ASD. The literature has indicated that certain retinal features are significantly associated with ASD. In this study, we investigated the use of machine learning approaches on retinal images to further enhance the classification accuracy.
Methods
Forty-six ASD participants were recruited from three special needs schools and 24 normal control were recruited from the community. Among them, 23 age-gender matched ASD and normal control participant-pairs were constructed for the primary analysis. All retinal images were captured using a nonmydriatic fundus camera. Automatic retinal image analysis (ARIA) methodology applying machine-learning technology was used to optimise the information of the retina to develop a classification model for ASD. The model's validity was then assessed using a 10-fold cross-validation approach to assess its validity.
Findings
The sensitivity and specificity were 95.7% (95% CI 76.0%, 99.8%) and 91.3% (95% CI 70.5%, 98.5%) respectively. The area under the ROC curve was 0.974 (95% CI 0.934, 1.000); however, it was noted that the specificity for female participants might not be as high as that for male participants.
Interpretation
Because ARIA is a fully automatic cloud-based algorithm and relies only on retinal images, it can be used as a risk assessment tool for ASD screening. Further diagnosis and confirmation can then be made by professionals, and potential treatment may be provided at a relatively early stage.
[link url="https://www.reuters.com/article/us-health-autism-hongkong/hk-scientist-develops-retinal-scan-technology-to-identify-early-childhood-autism-idUSKBN2B702L"]Full Reuters report (Open access)[/link]
[link url="https://www.thelancet.com/journals/eclinm/article/PIIS2589-5370(20)30332-1/fulltext"]EClinical Medicine study (Open access)[/link]