Researchers at the Lions Eye Institute are partnering with Google to deliver Australian-first research using artificial intelligence (AI) solutions to detect blindness and eye disease earlier in Indigenous Australians.
Diabetic-induced vision loss is 14 times more common in Indigenous people than non-Indigenous, and diabetes itself is three to five times more common across all ages in the Indigenous population.
A common cause of vision loss is due to diabetic retinopathy – a disease that creates lesions in the back of the retina that can lead to blindness.
With early detection and treatment, blindness can be prevented, but unfortunately this illness can go undetected if patients do not undergo screening. This is a growing health concern, particularly as access to doctors and healthcare services can be limited in rural and remote areas.
In response, the Lions Eye Institute has collaborated with Google to research artificial intelligence (AI) solutions to make screening more accessible and efficient, aiming to detect eye disease earlier for the patient.
Led by Associate Professor Angus Turner, a Western Australian ophthalmologist based at the Lions Eye Institute and the McCusker Director of Lions Outback Vision, the research is working to understand how the technology can be applied in a real-world setting.
The Lions Eye Institute conducted a retrospective study with Derbal Yerrigan Health Service in Western Australia using anonymised data to validate the performance of Google’s AI model to detect diabetic retinopathy within the local Indigenous population.
Retinal cameras with in-built AI were trialed, which had the ability to provide instantaneous results without the need to transfer pictures or wait for human analysis. This also further supported the camera operator to more efficiently interact with the patient and share results for better patient understanding.
The AI is capable of detecting more than just eye problems. It can also pick up issues with the heart and lungs meaning a multitude of diseases can be screened for with one visit. Video telehealth with a specialist can also be initiated immediately if a disease is identified that needs treatment explained and arranged.
A paper on the study was published in the British Journal of Ophthalmology (BJO) in February 2023, which found that the machine learning model performed on-par with a retinal specialist.
Around the world, Google’s AI system is already assisting clinicians and community health workers screen for diabetic retinopathy, and is deployed in India and Thailand.
Moving forward, the Lions Eye Institute team is hoping to fit out two vans with the new retinal cameras to travel to smaller communities in the Pilbara and Kimberley, as these areas are not able to be accessed by the existing large Vision Van due to remoteness and unsealed roads.