This High Schooler Developed an A.I. Tool to Diagnose Autism and ADHD Using the Retina

A 17-year-old high school senior named Edward Kang created RetinaMind, an AI tool that analyzes retinal images to diagnose autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD) with 89% accuracy. Inspired by a 2020 study from the Chinese University of Hong Kong, Kang expanded on the research to refine the diagnostic model, which currently relies on behavioral assessments without physical biomarkers. Autism affects 1 in 54 children in the U.S., while ADHD impacts nearly seven million, both lacking definitive diagnostic tests. Early intervention improves long-term outcomes, but current methods depend on developmental and behavioral evaluations like the DSM-5, ADOS, and Conners Rating Scales. Kang’s tool could accelerate diagnoses, enabling earlier treatment and better quality of life for patients. The project began when Kang, a student at Bergen County Academies in Hackensack, New Jersey, taught himself coding and machine learning. He built RetinaMind by training AI models on retinal images to detect neurological patterns linked to ASD and ADHD. His work highlights a potential breakthrough in using retinal scans as a non-invasive diagnostic method for neurodevelopmental disorders. Kang expressed hope that RetinaMind could reduce diagnostic delays, particularly for women, who are often diagnosed later in life despite similar prevalence rates to men. A 2026 Swedish study found autism occurs equally in both genders but is underdiagnosed in women. The tool’s success could address gaps in early detection and intervention for millions of children worldwide.