Diabetic retinopathy is one of the most frequent ocular diseases and poses a growing challenge due to rising patient numbers, staff shortages and increasing healthcare costs. Automating routine screening processes with artificial intelligence (AI) can reduce the workload of medical specialists and improve efficiency without compromising the quality of care.
The Digital Eye Clinic project, carried out by Stadtspital Zürich and the Spross Research Institute for the Advancement of Ophthalmology, was part of the Canton of Zurich’s Innovation Sandbox for AI. It explored the medical, technological, regulatory and ethical prerequisites for integrating AI diagnostics into clinical workflows.
The project evaluated existing diagnostic providers and platforms within the current legal and technical framework of the city of Zurich. As no commercial vendor met the clinic’s key criteria, the team developed and validated its own AI models based on opensource research frameworks. Alongside technological validation, the project examined critical issues in regulation, data protection and medical ethics.
The results provide practical insights and best practices for hospitals and healthcare providers considering
AI-assisted diagnostics. They emphasise the need for structured selection and implementation processes, open and interoperable architectures, early clinical involvement, and a careful assessment of whether to use open-source models or rely on external vendors. Beyond ophthalmology, the findings offer transferable lessons for the safe and effective adoption of AI in other areas of clinical practice.
You need to load content from reCAPTCHA to submit the form. Please note that doing so will share data with third-party providers.
More InformationYou are currently viewing a placeholder content from Turnstile. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou are currently viewing a placeholder content from Vimeo. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou are currently viewing a placeholder content from YouTube. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou need to load content from reCAPTCHA to submit the form. Please note that doing so will share data with third-party providers.
More Information