DeepMind, a British AI group, has developed a functioning prototype of a device with the potential of diagnosing complicated eye illnesses in real-time, which marks a major move towards the company’s first-ever medical device.
In a recent live demonstration of the company’s AI system, where a patient accepted to be publicly examined, DeepMind conducted a real-time diagnosis and retinal scan of her eye.
The analysis of the scan was done by several algorithms found in Google Cloud, which provided a detailed diagnosis and an urgency score, all in just 30 seconds.
The system can detect a wide variety of eye illnesses, including age-related macular degeneration, diabetic retinopathy, and glaucoma, with a similar degree of accuracy as the leading specialists in the world.
It was created in collaboration with London-based Moorfields Eye Hospital over the last three years.
Details regarding the research are available in Nature Medicine, a scientific journal.
The company has partnered with Moorfields’ team to create a working product, even though it is yet to be granted any regulatory approval.
A spokesperson from DeepMind claimed that if the research findings in a product that undergoes regulatory approvals and clinical trials, doctors working at Moorfields will be in a position to use the particular product free of charge for a starting duration of five years.
“What we’ve been working on really hard is how to take this type of early-stage research system and start to move it into cloud technology, building a prototype of a system really used in practice,” Mr Karthikesalingam said at the Wired Health event in London where the demo took place.
He claimed that the aim of AI tools is figuring out “should someone call a specialist and if so, how urgently and why?”
DeepMind established its health division, as a section of the company’s applied team that is headed by co-founder Mustafa Suleyman, back in 2016.
In November, DeepMind said that it would transfer its health unit’s control to a new California-based Google Health division, an indicator that the company is planning to commercialize and expand its efforts.
“This is likely part of a larger strategy to make Google a reliable outsourced R&D partner. Demonstrating that its applications of AI can have a significant impact on outcomes builds necessary credibility as they move deeper into healthcare, which as a whole could be a significant business for them,” said Nikhil Krishnan, former healthcare analyst at CB Insights.
“However as a business, eye screening alone probably wouldn’t move the needle relative to Google’s core search/ad business, especially considering the risk they’d be taking on it,” he added.
DeepMind says its product will provide diagnoses and explain how it reached its conclusion as well as how sure it is of the findings, which is important for healthcare experts.
“For an ophthalmologist, this is jaw-dropping. What you can see is [the AI] has segmented every single point, about 65m data points in this scan [creating] super-high-resolution images,” said Pearse Keane, a consultant ophthalmologist at Moorfields.
“We have to bring the same levels of rigour [to] how we validate the algorithms that we would with any medical device, but my personal prejudice is that ophthalmology will be the first speciality of medicine that is fundamentally transformed by AI.”