Diabetic Screening

New Zealand tech company develops tool to detect diseases like diabetes

New Zealand tech company develops tool to detect diseases like diabetes 768 512 Toku Eyes

Around 280,000 New Zealanders have diabetes, with the disease almost three times more common in Māori than non-Māori. And mortality rates for the disease are nine times higher for Māori aged 43-64 years than non-Māori.

Health experts say early screening is essential, but the problem is that just 35 percent of Māori opt-in for these checkups.

But a New Zealand tech company is hoping to help curb the problem as well as other diseases using its artificial intelligence platform THEIA.

Feast your eyes on THEIA, the latest eye imaging diagnostic device.

It’s a way to detect eye diseases and other diseases like diabetes.

With a retinal photo, the software uses hundreds of thousands of data points to give risk predictions, whereas currently to get that sort of diagnosis you need to go through multiple tests and doctor visits.

“I truly believe we can change eye care first and general health care second,” THEIA founder and CEO Dr Ehsan Vaghefi said.

That’s because the eye is the only external part of the body where we can photograph the blood vessels that feed vital organs. Combine this with THEIA and it’s a game-changer.

“We can look at the risk of diabetes in the eye and high cholesterol in the eye, and suddenly an image of your eye can tell us a lot about your general health and not just the eye,” Dr Vaghefi said.

Auckland ophthalmologist Dr David Squirell has been part of Aotearoa’s diabetic screening for over 15 years.

He said the technology is about as accurate as he can be and better than most junior doctors.

He said the artificial intelligence helps to identify those needing help urgently to adjust their lifestyle, diet or medication.

“Technology follows the patient, we want to make it easier for people to be screened because there are multiple barriers and one of them is just physical,” Dr Squirell said.

THEIA has the potential to expand existing screening capacity by around 50 percent and reduce labour costs by 30 percent

But for this Ngāi Tai descendant, it’s about better accessibility for Māori.

Diabetes is almost three times more common in Māori than in non-Māori.

“It’s completely portable and it can be run in any setting, it can be run in iwi community centres and the AI really gives us this ability to give the result without the need of a specialist,” chief commercial officer Francesca Logan said.

“We are having constructive conversations with the Ministry of Health and the Māori Health Authority and we are hoping that by next time that our technology will be accessible in many places across New Zealand,” Dr Vaghefi said.

Rather than a window to the soul, the eye is now the window to the future of your health.

NEWS – Newshub – Te Rina Kowhai
Article originally on www.newshub.co.nz

A multi-center prospective evaluation of THEIA

A multi-center prospective evaluation of THEIA 1024 683 Toku Eyes

A multi-center prospective evaluation of THEIA to detect diabetic retinopathy (DR) and diabetic macular edema (DME) in the New Zealand screening program

Purpose: to assess the efficacy of THEIA, an artificial intelligence for screening diabetic retinopathy in a multi-center prospective study. To validate the potential application of THEIA as clinical decision making assistant in a national screening program.

Methods: 902 patients were recruited from either an urban large eye hospital, or a semi-rural optometrist led screening provider, as they were attending their appointment as part of New Zealand Diabetic Screening programme.

These clinics used a variety of retinal cameras and a range of operators. The de-identified images were then graded independently by three senior retinal specialists, and final results were aggregated using New Zealand grading scheme, which is then converted to referable\non-referable and Healthy\mild\more than mild\vision threatening categories. Results: compared to ground truth, THEIA achieved 100% sensitivity and [95.35%-97.44%] specificity, and negative predictive value of 100%. THEIA also did not miss any patients with more than mild or vision threatening disease. The level of agreement between the clinicians and the aggregated results was (k value: 0.9881, 0.9557, and 0.9175), and the level of agreement between THEIA and the aggregated labels was (k value: 0.9515).

Conclusion: Our multi-centre prospective trial showed that THEIA does not miss referable disease when screening for diabetic retinopathy and maculopathy. It also has a very high level of granularity in reporting the disease level. Since THEIA is being tested on a variety of cameras, operating in a range of clinics (rural\urban, ophthalmologist-led\optometrist-led), we believe that it will be a suitable addition to a public diabetic screening program.

Ehsan Vaghefi, Song Yang, Li Xie, David Han, David Squirrell

Download Paper from Cornell University here