Researchers have developed an AI model that accurately predicts which keratoconus patients require treatment by analyzing OCT eye scans and clinical data.
Key Details
- 1Study presented at the 43rd Congress of the European Society of Cataract and Refractive Surgeons (ESCRS).
- 2AI analyzed 36,673 OCT images from 6,684 patients with keratoconus.
- 3Algorithm could stratify two-thirds of patients as low-risk and one-third as high-risk for disease progression using data from a single visit.
- 4Including data from a second visit increased prediction accuracy to up to 90% of patients correctly categorized.
- 5Cross-linking treatment prevents vision loss and corneal transplantation in most cases if given early.
- 6Algorithm will undergo further safety testing before clinical deployment; researchers plan to expand to other eye conditions.
Why It Matters
Accurate early prediction of keratoconus progression through AI-augmented imaging could enable timely intervention, reduce unnecessary monitoring, and optimize healthcare resources, potentially preventing vision loss in young patients. This approach showcases the growing clinical impact of AI in ophthalmic imaging and patient stratification.
Source
EurekAlert
Related News
•EurekAlert
Imaging Reveals Skull Changes and Immune Impact in Glioblastoma
Advanced imaging uncovers that glioblastoma affects the skull and immune system, not just the brain.
•EurekAlert
AI-Based CT Analysis Predicts Outcomes in Fibrotic Lung Disease
AI analysis of one-year CT changes predicts disease progression and survival in fibrotic interstitial lung disease.
•EurekAlert
AI and Multiphoton Microscopy Achieve 96% Accuracy in Pancreatic Tumor Detection
University of Arizona researchers combined label-free multiphoton microscopy with neural networks to accurately classify pancreatic neuroendocrine neoplasms in tissue samples.