Artificial Intelligence for Diabetes-related Complications: The Eye as a Window to the Systemic Health

Abstract

Diabetes mellitus (DM) is a global pandemic that is one of the fastest growing chronic diseases and the top cause of blindness in the working population. The eye provides a direct visualization to the body's vasculature and systemic health, allowing it to be a minimally invasive tool to evaluate DM and its micro- and macrovascular complications, including diabetic retinopathy, corneal neuropathy, cardiovascular disease, chronic kidney disease and cerebrovascular disease. With the rapid rate of disease burden, there is an unmet public health need to identify these diseases at an early stage to implement timely management. Artificial intelligence (AI), in particular deep learning, has been widely explored for disease segmentation, classification, and prediction. Despite the advances in AI for optimizing the screening and management of DM, future work is warranted to address the issues such as interpretability, cost, and acceptance of AI systems by patients and healthcare workers.