Use of artificial intelligence algorithms to predict systemic diseases from retinal images

Abstract

The rise of non-invasive, rapid, and widely accessible quantitative high-resolution imaging methods, such as modern retinal photography and optical coherence tomography (OCT), has significantly impacted ophthalmology. These techniques offer remarkable accuracy and resolution in assessing ocular diseases and are increasingly recognized for their potential in identifying ocular biomarkers of systemic diseases. The application of artificial intelligence (AI) has been demonstrated to have promising results in identifying age, gender, systolic blood pressure, smoking status, and assessing cardiovascular disorders from the fundus and OCT images. Although our understanding of eye–body relationships has advanced from decades of conventional statistical modeling in large population-based studies incorporating ophthalmic assessments, the application of AI to this field is still in its early stages. In this review article, we concentrate on the areas where AI-based investigations could expand on existing conventional analyses to produce fresh findings using retinal biomarkers of systemic diseases. Five databases—Medline, Scopus, PubMed, Google Scholar, and Web of Science were searched using terms related to ocular imaging, systemic diseases, and artificial intelligence characteristics. Our review found that AI has been employed in a wide range of clinical tests and research applications, primarily for disease prediction, finding biomarkers and risk factor identification. We envisage artificial intelligence-based models to have significant clinical and research impacts in the future through screening for high-risk individuals, particularly in less developed areas, and identifying new retinal biomarkers, even though technical and socioeconomic challenges remain. Further research is needed to validate these models in real-world setting.