This teen won $175,000 for an AI that scans eyes for autism

Edward Kang’s science project earned him second place and a $175,000 prize at the 2026 Regeneron Science Talent Search, one of the United States’ most prestigious competitions for young scientists.

The 17-year-old, a senior at Bergen County Academies in Hackensack, New Jersey, built an AI tool called RetinaMind that screens for autism spectrum disorder and attention-deficit/hyperactivity disorder by analysing photographs of the back of the eye. The competition recognised both the technical sophistication of the model and its effort to combine computer science with biological research.

Kang began working on RetinaMind in 2023 after reading research suggesting the retina could offer clues about neurological conditions, since the retina and brain develop from the same embryonic tissue. He trained the AI using publicly available retinal image datasets, and unlike many AI models that function as ‘black boxes,’ RetinaMind produces explainable heat maps highlighting which areas of the retina influenced its prediction.

In initial testing, the tool achieved 89% diagnostic accuracy, though that figure comes from public research datasets rather than real-world hospital settings. Large-scale clinical trials are still needed before RetinaMind could be considered for routine medical use, and experts emphasise it is not a replacement for clinical diagnosis.

Image: Wikimedia Commons/by OptometrusPrime