Read more

January 20, 2020
1 min read
Save

Ophthalmology a prime specialty for AI integration

You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com.

Judy E. Kim at Hawaiian Eye 2020
Judy E. Kim

KOLOA, Hawaii — Radiology, pathology, dermatology and ophthalmology are specialties primed to use artificial intelligence because they all have one thing in common.

“They are all image based,” Judy E. Kim, MD, said at Retina 2020. “AI is very good at image recognition. It’s also very good at voice recognition, but because we use lots of images we are primed for the use of AI. Secondly, we are primed to use AI because there are diseases that affect our patients all over the world, like diabetes. Almost 400 million people around the world have diabetes.”

AI already plays a part in automated detection of diabetic retinopathy. IDx-DR (IDx) was FDA approved in 2018 to detect more than mild levels of diabetic retinopathy, Kim said.

Potential application of AI in management of age-related macular degeneration would come in the form of patient-operated home OCT, she said.

Notal Vision’s home-based OCT is a compact spectral domain OCT that provides cross-sectional images of the central 10° of the macula, taking about 10 seconds per eye, with the data uploaded to the cloud.

“Because of this potential ... disruptive medicine, the FDA has granted a breakthrough designation to help facilitate FDA approvals,” she said.

Because home OCT has the capability to provide 88 B-scan images per eye per day for multiple patients, the burden of data processing falls to the Notal OCT Analyzer (NOA), which is an AI-based algorithm that analyzes the OCT output. NOA identifies, quantifies and ranks lesion activity.

“[AI] gives opportunity to individualize or personalize wet AMD management,” Kim said. “And it may reduce treatment burden by sorting out who needs more frequent injections vs. those who may not need such frequent injections.” – by Patricia Nale, ELS

Reference: Kim JE. AI and imaging in retinal diseases. Presented at: Retina 2020; Jan. 19-24, 2020; Koloa, Hawaii.

Disclosure: Kim reports financial disclosures with Adverum, Alimera, Allergan, Bausch + Lomb, EyePoint, Gemini, Genentech, Heidelberg, Kodiak, Lineage, Notal Vision, Optos and Orbit.