Researchers test scanning retina with AI to determine cardiovascular risk

(Image credit: Adobe Stock/Senuka Nuwansith)

A team of researchers is reviewing the potential of artificial intelligence (AI) in ophthalmology.

The research has been detailed in a position paper in the Asia-Pacific Journal of Ophthalmology.¹ 

The research is led by Lama Al-Aswad, MD, MPH, a professor of ophthalmology and Irene Heinz Given and John La Porte Given Research Professor of Ophthalmology II, of the Scheie Eye Institute. The effort represents a collaboration among researchers from Penn Medicine, Penn Engineering, the University of Michigan Kellogg Eye Center, St. John Eye Hospital in Jerusalem, and Gyeongsang National University College of Medicine in Korea.²

According to the researchers fundus photography facilitates the visualization of retina at the back of the eye, making the potential of AI in providing systemic disease biomarkers a real possibility. When fundus images are of sufficient quantity and quality, it becomes possible to train AI systems to detect elevated HbA1c levels — an important marker for high blood sugar that is usually secured with blood draws, which indicates an increased risk of diabetes and cardiovascular disease. This process leverages the emerging field of oculomics, which studies ophthalmic biomarkers to gain insights into systemic health.^1,2

In the manuscript, the international consortium of researchers examined the potential of oculomics and highlights pertinent topics for clinicians to consider as ophthalmology moves into an era where AI has the abiity to enhance systemic health through eye care.

Moreover, the researchers’ position is backed by preliminary research results from a pilot study that trained AI models to predict HbA1c levels based on fundus images. In the study, researchers looked at a number of factors — including AI model size and architecture, the presence of diabetes, and patient demographics (age and sex) — as well as their impact on AI performance.

The researchers noted that biased training samples for an oculomics model, such as a pool of predominantly older patients, can degrade model performance. The results of the case study highlight the importance of developing trustworthy AI models for assessing cardiovascular risk factors while addressing the challenges and problems that must be overcome prior to clinical adoption, as well as advancing reliable oculomics technology.¹

"By leveraging AI to analyze retinal images for cardiovascular risk assessment,” Al-Aswad said, “we aim to bridge a crucial gap in early disease detection. This method not only enhances our ability to identify at-risk individuals but also holds promise for transforming how we manage chronic conditions such as diabetes. By focusing on practical applications of this technology, we are advancing towards more personalized and preventative healthcare solutions.”

“While these advancements hold promise, it is also of utmost importance for clinicians and researchers to develop and employ these techniques in a responsible manner, as this will benefit patient care the most in the end,” added Kuk Jin Jang, PhD, a postdoctoral researcher in the Penn Research in Embedded Computing and Integrated Systems Engineering (PRECISE) Center at the University of Pennsylvania.

Joshua Ong, MD, a resident physician at the University of Michigan and PRECISE Center affiliate, lauded the collaboration.

“Our collaboration serves to further understand how we can responsibly leverage this revolutionary technology to benefit patients in the future. It is a testament to the collaborative advances formed when healthcare and engineering come together to work towards responsible AI for patient care,” he said. “I am incredibly grateful for our multidisciplinary team for coming together to bring this paper and topic to the forefront.”

PRECISE Center Director Insup Lee, PhD, also noted the collaboration can open new doors for healthcare.

“This collaboration reflects a deep commitment to advancing healthcare through innovative AI applications,” he said. “By combining our expertise, we are paving the way for significant improvements in patient care and the overall management of long-term health challenges.”

References:

1. Joshua Ong, Kuk Jin Jang, Seung Ju Baek, Dongyin Hu, Vivian Lin, Sooyong Jang, Alexandra Thaler, Nouran Sabbagh, Almiqdad Saeed, Minwook Kwon, Jin Hyun Kim, Seongjin Lee, Yong Seop Han, Mingmin Zhao, Oleg Sokolsky, Insup Lee, Lama A. Al-Aswad, Development of oculomics artificial intelligence for cardiovascular risk factors: A case study in fundus oculomics for HbA1c assessment and clinically relevant considerations for clinicians, Asia-Pacific Journal of Ophthalmology, Volume 13, Issue 4, 2024, 100095, ISSN 2162-0989,https://doi.org/10.1016/j.apjo.2024.100095.

2. Revolutionizing cardiovascular risk assessment with AI. EurekAlert! Published October 4, 2024. Accessed October 8, 2024. https://www.eurekalert.org/news-releases/1060193