Publication
An AI-driven Clinical Decision Support System for the Treatment of Diabetic Retinopathy and Age-related Macular Degeneration
Robert Leist; Hans-Jürgen Profitlich; Daniel Sonntag
In: Joint Proceedings of the ACM IUI Workshops 2025. Workshop on Intelligent and Interactive Health User Interfaces (HealthIUI-2025), located at IUI-2025, March 24, Cagliary, Italy, Association of Computing Machinery, New York, NY, United States, 5/2025.
Abstract
Diabetic Retinopathy (DR) and Age-related Macular Degeneration (AMD) are among the leading causes of blindness worldwide. Despite the availability of treatments to prevent disease progression, the effectiveness of these interventions is often limited by inefficiencies in existing clinical software. Recent advancements in Artificial Intelligence (AI) offer the potential to enhance Clinical Decision Support Systems (CDSS), streamlining workflows and reducing the burden on healthcare providers. This paper introduces a CDSS designed to assist ophthalmologists in the management of DR and AMD, integrating three AI-driven components. First, we developed a segmentation model for automated analysis of medical imaging data. Second, we implemented a recommendation algorithm to guide treatment decisions. Finally, we utilized a time series forecasting model to enable predictive medicine. Our models were trained using real-world clinical data from 913 patients with AMD and 461 patients with DR. The system demonstrates promising performance, underscoring the importance of high-performing AI models in advancing CDSS for ophthalmology. The code for our CDSS is available here: https://github.com/DFKI-Interactive-Machine-Learning/ophthalmo-cdss.