In a paper (PDF) published today in the Nature journal Biomedical Engineering, researchers explained their method: An AI algorithm evaluated eye scans and, after refining its model with machine learning, was able to predict cardiovascular risk factors like age, gender and blood pressure. By studying the appearance algorithms can predict heart disease. "In addition to detecting eye disease, images of the eye can very accurately predict other indicators of CV health".
"In summary, we have provided evidence that deep learning may uncover additional signals in retinal images that will allow for better cardiovascular risk stratification".
LEFT: image of the back of the eye showing the macula (dark spot in the middle), optic disc (bright spot at the right), and blood vessels (dark red lines arcing out from the bright spot on the right).
In case you're wondering why Google and Verily chose retinal imaging for this breakthrough medical advancement, the rear interior wall of an eye called the fundus is jammed with blood vessels that reflect the body's overall health.
However, despite the success of their experiment, Google said that more research has to be done.
This is a big step forward scientifically, Google AI officials said, because it is not imitating an existing diagnostic but rather using machine learning to uncover a surprising new way to predict these problems. Eye scans and medical data are combined with deep learning analysis, neural networks and then scanned for patterns for cardiovascular risk. "Given the retinal image of one patient who (up to 5 years) later experienced a major CV event (such as a heart attack) and the image of another patient who did not, our algorithm could pick out the patient who had the CV event 70 per cent of the time. However, we don't precisely know in a particular individual how these factors add up, so in some patients, we may perform sophisticated tests ... to help better stratify an individual's risk for having a cardiovascular event such as a heart attack or stroke", declared study co-author Dr. Michael McConnell, a medical researcher at Verily.
"This performance approaches the accuracy of other [cardiovascular] risk calculators that require a blood draw to measure cholesterol", Peng wrote.
One of the exciting aspects of this study is the generation of "attention maps" to show which aspects of the retina contributed most to the algorithm, thus providing a window into the "black box" often associated with machine learning.
"However, with medical images, observing and quantifying associations can often be hard because of the wide variety of features, patterns, colours, values and shapes that are present in real data".
Essentially Google has taken a diagnosis method with an established history, found new ways to analyze the data and sped it up significantly.