AI at UCSD accurately diagnoses eye diseases, pneumonia

Researchers at University of California, San Diego (UCSD) have developed an artificial intelligence (AI) system that may improve how potentially blinding eye diseases are diagnosed through scanning retinal images, according to a recent article by The San Diego Union-Tribune.  

The new machine learning system can identify macular degeneration and diabetic macular edema in 30 seconds with 90 percent accuracy, Kang Zhang, MD, lead author of the study published Feb. 22 in the journal Cell, explained to the Union-Tribune.  

"The AI system made retinal disease diagnoses based on data from hundreds of thousands of images and disease data from patients and the system also included in its diagnoses the pertinent section of an image, giving doctors an understanding of how they were made," according to the article.

Zhang is also a professor of ophthalmology at UCSD’s Shiley Eye Institute and founding director of the Institute for Genomic Medicine at UC San Diego School of Medicine.

“The goal is that you take a picture, upload it to the cloud and within 10 seconds will give you a diagnosis anywhere in the world,” Zhang told the Union-Tribune. 

Read the full story below:

""

A recent graduate from Dominican University (IL) with a bachelor’s in journalism, Melissa joined TriMed’s Chicago team in 2017 covering all aspects of health imaging. She’s a fan of singing and playing guitar, elephants, a good cup of tea, and her golden retriever Cooper.

Around the web

GE HealthCare said the price of iodine contrast increased by more than 200% between 2017 to 2023. Will new Chinese tariffs drive costs even higher?

These risks appear to be present regardless of a person's age or health at the time of infection.

Agfa and Sectra both performed well with end-user satisfaction scores in the 2025 Best in KLAS list of radiology IT systems.