AI Diagnoses Autism with 100% Accuracy

Researchers from Yonsei University College of Medicine in South Korea have developed a method to diagnose autism spectrum disorder (ASD) and assess symptom severity in children using retinal images screened by a deep learning AI algorithm. The study involved 958 participants, half of whom were diagnosed with ASD, and half were age- and sex-matched controls.

The AI algorithm, trained on 85% of the retinal images and symptom severity scores, achieved 100% accuracy in ASD screening on the test set of images, with a mean area under the receiver operating characteristic curve of 1.00. The mean area under the curve for symptom severity was 0.74. The researchers suggest that their AI-based model could serve as an objective screening tool for ASD from the age of four.