The study involved 958 participants, half of whom had been diagnosed with autism spectrum disorder (ADS). The AI was able to diagnose autism with complete accuracy during the test phase. The researchers believe the technology could be used for early diagnosis of autism, particularly where access to specialist child psychiatrists is limited. They also suggest that the method could be applicable to even younger children in future studies.
Key takeaways:
- New AI technology can diagnose childhood autism from photos of children’s eyes with 100% accuracy.
- The AI system was trained on 85% of the retina images and symptom severity scores, while the remaining 15% were used for testing.
- The method used allows scientists to access information about the brain by looking at the back of the eye, providing a non-invasive means of diagnosis.
- The findings suggest that this AI technology could be used as an objective screening tool for early diagnosis of autism, especially in areas with limited access to specialist child psychiatrists.