A Korean research team has made breakthrough progress in diagnosing children with autism using a deep learning artificial intelligence system. By analyzing retinal images of 958 children, the system achieved 100% diagnostic accuracy, providing new possibilities for early intervention and treatment. However, the accuracy of the system in assessing the autism spectrum position in children still needs to be improved, and future research will further explore its application in younger children.
A multi-institutional team in South Korea successfully diagnosed children with autism using a deep learning-based artificial intelligence system. The research team used the system to scan retinal images of 958 children with 100% accuracy. However, the system was less accurate at estimating a child's position on the spectrum. The study could help diagnose autism earlier and provide more help, but its accuracy in younger children requires further study.
Although this research shows the great potential of artificial intelligence in the field of autism diagnosis, it still needs further improvement and verification to ensure the reliability and safety of its widespread application. Future research should focus on improving the accuracy of the system in assessing spectrum position and expanding the sample size, especially for younger children, to ultimately achieve more accurate and earlier diagnosis of autism.