Peer-Reviewed Publication
Ophthalmol Ther2026July 18, 2026Journal Article
Predictive Modeling of Coronary Artery Disease Using Color Fundus Photography-Based Features of Retinal Vasculature.
Natasa Jeremic1,2, Emese Sükei2, Azin Zarghami1, Michael Apata2, Meltem Esengönül2, Maximilian Pawloff1, Andreas Pollreisz1, Reinhard Windhager3, Matthias Hasun4, Alexander Niessner5, Stefan Sacu6, Hrvoje Bogunovic7, Ursula Schmidt-Erfurth2
1Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria.
2Laboratory for Ophthalmic Image Analysis (OPTIMA), Center for Cancer Research, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria.
3Department of Orthopedics and Trauma-Surgery, Medical University of Vienna, Vienna, Austria.
4Division of Cardiology, Department of Internal Medicine II, Clinic Landstraße, Juchgasse 30, 1030, Vienna, Austria.
5Division of Cardiology, Department of Internal Medicine II, Clinic Landstraße, Juchgasse 30, 1030, Vienna, Austria. alexander.niessner@gesundheitsverbund.at.
6Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria. Stefan.Sacu@meduniwien.ac.at.
7Institute of Artificial Intelligence, Center for Medical Data Science, Medical University of Vienna, Vienna, Austria.
Abstract
INTRODUCTION: Coronary artery disease (CAD) remains the leading cause of death and current screening methods are limited. Color fundus photography (CFP) has been explored in literature mostly on the basis of associations and exploratory deep learning approaches with only indirect end points. In this explorative study, we aimed to assess the predictive abilities and limitations of explainable CFP-b…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans