AI-driven ADHD screening using eye images developed in Korea

Article Analysis:
The article discusses a new study from South Korea that explores the use of AI models to diagnose and stratify attention deficit hyperactivity disorder (ADHD) by analyzing eye images.

Highlights:
1. AI Diagnosis: Researchers from Yonsei University Health System utilized four machine learning models and the AutoMorph deep learning pipeline to analyze retinal fundus photographs from children with ADHD and typical development, achieving high accuracy rates of up to 96.9%.

2. Identification of Symptoms: The study identified representative symptoms of ADHD through key retinal features analysis, including increased vascular density, decreased arterial vessel width, and changes in the optic disc structure.

3. Rapid Screening Tool: The researchers highlight the potential of retinal images as an ADHD biomarker and a rapid screening tool, with fundus examinations taking less than five minutes, allowing for effective monitoring of ADHD treatments.

Summary:
The study showcases the successful implementation of AI models in diagnosing and stratifying ADHD through the analysis of eye images, providing a quick and efficient screening method that could potentially revolutionize ADHD diagnosis and treatment monitoring.

Editorial content by NewsSIP AI