Digital Clinical Decision Support System for Screening of Eye Diseases

Eye diseases are a major cause of blindness, primarily affecting elderly individuals, especially in developing nations. Among various eye diseases, glaucoma, age-related macular degeneration, and cataracts are the most prevalent in sub-Saharan African nations. Many of these eye conditions are preventable or treatable if detected early. Unfortunately, in low-resource settings, due to a lack of screening mechanisms and poorly organized healthcare structures, people do not often seek early checkups before the disease progresses. Furthermore, most eye diseases do not exhibit clear symptoms in the early stages and may be irreversible. Developing countries’ health facilities lack modern and high-quality screening technologies and specialized experts. In addition, conventional eye screening methods are reliant on physicians’ expertise and knowledge, which can lead to misdiagnosis. This study proposes a digital eye disease diagnosis support system that integrates image acquisition, enhancement, retinal vessel extraction, machine learning-based segmentation, and cup-to-disk ratio determination with intraocular pressure measurement for automated eye disease screening. Our experimental results indicate that this proposed system has the potential to be utilized as a decision support system for eye disease diagnosis, particularly in resource-limited settings.