AI Can Diagnose Childhood Autism From Eye Photos With ‘100% Accuracy’
New artificially intelligent (AI) technology can now diagnose childhood autism from photos of children’s eyes with 100% accuracy.
According to a study published in JAMA Network Open this month, researchers took photographs of children’s retinas and screened them using a deep learning AI algorithm to diagnose autism.
To test the algorithm, the researchers recruited 958 participants, all with an average age of 7.8 years. They then photographed their retinas for a total of 1,890 images.
The study says that half of the participants had already been diagnosed with autism spectrum disorder (ADS) and that half were age- and sex-matched control participants.
The AI system was then trained on 85% of the retina images, along with symptom severity scores, to help it construct models on which to base its diagnosis. The other 15% of the photographs of eyes were kept for testing by the researchers.
The screening relies on a new method that scientists came up with, which allows them to access information about the brain by looking at the back of the eye, where the retina and optic nerve connect to the optic disc. This method has allowed scientists to develop a non-invasive means of rapidly diagnosing concussions by shining eye-safe lasers onto the retina.
During this test phase of the study, the AI algorithm was able to diagnose participants with childhood autism with 100 accuracy.
In this case, the researchers limited the training data to children and adolescents between the ages of 4 and 18, but they think that it could work on even younger kids in future studies as well.
The findings support using AI technology as an objective screening tool for early diagnosis of autism, especially when access to a specialist child psychiatrist is limited.
Science Alert reports that around one in 36 people are believed to be autistic, based on prevalence among eight-year-olds. Therefore, being aware of that diagnosis as early as possible can make a huge difference in young people understanding themselves and making their way through the world.
“The findings of this study suggest that retinal photographs may serve as a viable candidate for an objective method to screen for autism and possibly for symptom severity,” the researchers write.
Image credits: Header photo licensed via Depositphotos.