Artificial intelligence-enhanced retinal imaging as a biomarker for systemic diseases

Area of Science:

• Oculomics and AI in healthcare
• Biomarker discovery through retinal imaging
• Translational medicine and disease prediction

Background:

• Retinal imaging offers non-invasive visualization of vasculature and neural networks.
• Oculomics leverages the eye's connection to systemic health for disease insights.
• Artificial intelligence (AI), especially deep learning, enhances retinal analysis capabilities.

Purpose of the Study:

• To review AI-enhanced retinal imaging for systemic disease prediction.
• To highlight advancements and opportunities in AI-driven oculomics.
• To discuss challenges and future directions in AI and big data for healthcare.

Main Methods:

• Analysis of digital color fundus photographs, optical coherence tomography (OCT), OCT angiography, and ultra-wide field imaging.
• Application of deep learning and other AI technologies for retinal image analysis.
• Review of studies demonstrating AI's potential in predicting various systemic diseases.

Main Results:

• AI-based retinal analysis shows promise in detecting cardiovascular, CNS, kidney, metabolic, endocrine, and hepatobiliary diseases.
• AI facilitates early detection, risk stratification, and personalized prognostication of systemic conditions.
• Significant progress in AI-enhanced retinal imaging for disease prediction has been achieved.

Conclusions:

• AI-powered retinal imaging is a transformative tool for systemic disease screening and management.
• Further research and careful consideration of AI, big data, and generative AI are crucial.
• Integration of AI in clinical practice holds immense potential for improving patient outcomes.