Medica Magazine Overview (Alemanha)

Portable device can be used to diagnose eye disease remotely

Publicado em 26 junho 2019

A portable device connected to a smartphone makes precise images of the retina to detect back-of-the-eye (fundus) disease at a far lower cost than conventional methods. Created by Phelcom Technologies, a startup based at São Carlos in São Paulo State, Brazil, the Eyer can be used for remote diagnosis by an ophthalmologist via telemedicine.

The plant currently turns out 30 units per month. Production is set to reach 100 units by end-2019. The Eyer is shipped with a high-quality smartphone and costs approximately US$5,000. The most widely used conventional ophthalmoscope has to be connected to a computer and costs some US$30,000.

An optical device designed to light up and image the retina is connected to the smartphone's camera, and an app sends the images over the internet to Eyer Cloud, which stores and manages patient files.

If the user does not have Wi-Fi or access to a 3G or 4G network, the images are stored in the smartphone and sent to the cloud when an internet connection becomes available.

"We invested significantly in optics and in design. One challenge was producing a portable version of a device that is typically very large. Another was enabling nonmydriatic operation so that high-quality images of the retina can be captured without the need for pupil dilation," Phelcom CEOJosé Augusto Stuchitold.

Eyer Cloud is an innovation designed by the team to store all the data acquired in retinopathy exams and organize it in a database. Most ophthalmoscopes in current use have to be connected to a computer to save data to a hard disk and are not web-enabled.

Users of the Eyer set up an account to which images can automatically be saved. "We had to make sure data privacy would be guaranteed and develop a means of transmitting images at high speed to the cloud, so that they can be viewed online regardless of the device's location," Stuchi said.

The latter factor is key to enabling telemedicine. The Eyer lets a trained technician or general medical practitioner produce the images, while an ophthalmologist who specializes in retinopathy can then analyze them and write an expert report at another location.

Phelcom is currently partnering with ophthalmologists to develop the reporting part of the system. Payment is by monthly subscription. Each report costs between US$5.00 and US$ 10.00, depending on the number of reports issued.

In addition to representing a new service, the medical reports are fed into a database that can be used to "teach" a computer to find patterns associated with ocular fundus diseases, especially diabetic retinopathy.

The firm currently has images of more than 10,000 retinas and plans soon to have the largest database of its kind in the world. The partners expect to examine 50,000 patients next year alone.

The last year saw the first approval of an artificial intelligence (AI) diagnostics algorithm by the United States Food and Drug Administration (FDA). Called IDx-DR, the software program uses AI to analyze images of the eye taken with a retinal camera to detect diabetic retinopathy, the leading cause of vision impairment and blindness among working-age adults in the US.

In Brazil, 7.6% of people living in cities and aged 30-69 are estimated to have diabetes. Approximately half of these patients probably have diabetic retinopathy.

"The diagnostic use of AI is a growing global trend. Computers process the data, and physicians make decisions," Stuchi said.

The accuracy of Phelcom's system in detecting diabetic retinopathy without human intervention is currently close to 80%, he added. As its database expands, accuracy should reach 95%, and at that point, the app can be marketed. The accuracy of IDx-DR is currently rated at 89.5%.

Phelcom expects to sell 150 Eyers in Brazil in the next 12 months, earning R$3 million in revenue. The partners now want to extend sales to other Latin American countries and then to the US and Europe.; Source:São Paulo Research Foundation

More about FAPESP at: