Fundus images predict risk of hypertension and other systemic diseases
Researchers from Skoltech, the Z-union AI Technologies Consortium, Sber AI Lab and other research centers have proposed an artificial intelligence-based approach for the preventive screening of 15 diseases based on fundus photography—medical images of the rear of the eye.
Researchers from Skoltech, Z-union AI Technologies Consortium, Sber AI Lab and other institutions have developed an AI-powered system for early disease detection using fundus photography—images of the back of the eye. The system can predict 15 diseases, both eye-related and systemic, such as hypertension, lupus, and AIDS, based on these images.
Fundus photography is a routine procedure in eye clinics, where a photograph of the retina is taken when a patient complains of eye pain. By analyzing these images, the AI model can provide a probability score for each of the 15 diseases, with an impressive accuracy of 0.997. This non-invasive screening method could enable earlier detection of diseases, allowing for timely treatment and improved patient outcomes.
The dataset used to train the model consists of over 20,000 annotated fundus images, including rare pathologies, making it a valuable resource for future research. The study, published in Frontiers in Medicine, suggests that adopting this AI-based approach could enhance medical practice and improve patient quality of life.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
