Montargil

Hydroxychloroquine (HCQ) is widely prescribed for various conditions, including autoimmune diseases like systemic lupus erythematosus. However, long-term use of HCQ can lead to retinal toxicity, which is challenging to detect early and can continue to worsen even after stopping the drug. This condition has become a public health concern due to the increasing number of patients using HCQ. Screening for HCQ-related retinal damage currently relies on subjective interpretation of tests such as optical coherence tomography (OCT), autofluorescence imaging, and visual field exams. The study evaluates a deep learning technology called RETINAI to automate the detection and prediction of HCQ maculopathy using OCT scans and fundus photography. Participants will be divided into two groups: those with signs of retinopathy and control patients. Both groups will undergo OCT scans analyzed by the RETINAI algorithm to identify features of toxicity. The goal is to develop an automated screening method that could improve early detection compared to current manual reading techniques. Participants with more than 10 years of HCQ use will be involved in the study. Researchers will collect imaging data and apply the algorithm while validating results with blinded readers. The primary outcome is to create an automated screening tool based on OCT features, assessed over one year. This approach aims to reduce the burden on ophthalmology services and potentially improve patient outcomes by detecting retinal toxicity earlier and more objectively.