New Zealand-based AI healthcare firm Toku Eyes has brought its retina-based AI health screening platform to the United States.

Its latest offering, the ORAiCLE, can assess and calculate a person's cardiovascular risk through a retinal scan. Still pending a patent, the AI technology uses an image of the back of a user's eye taken from a retinal camera. The platform spots minute changes in blood vessels, capillaries, arteries and other indicators to predict a user's risk of having a stroke or heart attack in the next five years.

Toku Eyes has already established local partnerships with EyeCheq, which is building a nationwide network of self-service retinal image kiosks, and Unified Imaging, a provider of image management platforms for eye care clinics.

The company targets to bring its platform to more than 1,500 locations across the US by 2025, subject to regulatory clearances.

WHY IT MATTERS

More than 80% of heart attacks are said to be preventable if high-risk cases can be identified early. However, traditional methods in determining high-risk patients have been "inaccurate, costly, and invasive" with 40% of diabetic and prediabetic people unable to access critical screening, according to Toku Eyes.

The company has come up with the ORAiCLE platform which is said to be more cost-effective and easily accessible in locations such as pharmacies and self-service retinal photo kiosks. Toku Eyes also claims its technology can work accurately with low-quality images compared to Google's similar technology.

"It is often unknown that the cardiovascular system is able to be photographed through the eye," it said. 

John Marshall, who invented the excimer technology for correcting eye refractive errors, said that "[u]sing the eye as a diagnostic device for conditions outside the eye makes it so now ophthalmologists can begin to talk to the cardiovascular surgeon". 

"This has huge potential that will ramify throughout medicine," he claimed.

THE LARGER TREND

Toku Eyes' AI platform has been used as part of diabetic screening services in public and private health facilities in New Zealand. The technology has also been live in 20 clinics in India, where the company intends to bring it to 50 more clinics by yearend.

In other news,  a research project in Thailand has seen a deep learning algorithm being used to accurately detect diabetic retinopathy in diabetic patients. The Google-backed study ran fundus photographs of over 7,500 patients on the algorithm whose reading was found to be on par with retina specialists. 

ON THE RECORD

"By looking inside the eyes, we get an in-depth view of what is happening inside the entire body to better assess the risk factors of each individual and identify high-risk individuals before their condition worsens. Our goal is to make health screening simple and easy to access for the entire population so we can get in front of underlying health risks and improve patient outcomes," Toku Eyes CEO and co-founder Ehsan Vaghefi said.