UCSD researchers develop AI to predict, diagnose eye diseases

Researchers at Shiley Eye Institute at UC San Diego Health and University of California, San Diego School of Medicine have developed an artificial intelligence (AI) tool capable of screening patients with common but blinding retinal diseases for improved detection and treatment. Findings were published online Feb. 22 in Cell.

In this study, researchers focused on macular degeneration and diabetic macular edema—two common causes of permanent blindness that are treatable if caught early. In the paper, researchers used an AI-based convolutional neural network to review more than 200,000 eye scans.

“AI has huge potential to revolutionize disease diagnosis and management by doing analyses and classifications involving immense amounts of data that are difficult for human experts—and doing them rapidly,” said senior author Kang Zhang, MD, PhD, a professor of ophthalmology at Shiley Eye Institute and founding director of the Institute for Genomic Medicine at UC San Diego School of Medicine.

Following the transfer learning into the AI, researchers added occlusion testing that give the computer the ability to identify areas in each image that are of interest and the basis of its conclusion. In testing the AI's ability to detect preventable causes of blindness, researchers compared the diagnosis made by the AI with those from five ophthalmologists. Results found the AI could generate decision on if a patient needed to be referred to treatment within 30 seconds at 95 percent accuracy.

“Machine learning is often like a black box where we don’t know exactly what is happening,” Zhang said. “With occlusion testing, the computer can tell us where it is looking in an image to arrive at a diagnosis, so we can figure out why the system got the result it did. This makes the system more transparent and increases our trust in the diagnosis. The future is more data, more computational power and more experience of the people using this system so that we can provide the best patient care possible, while still being cost-effective.”