Google Algorithms Can Tell Heart Disease Risk from Eye Scans

AI looks into your eyes to predict cardio risk

AI looks into your eyes to predict cardio risk Feb 20 2018

The opportunity to one day readily understand the health of a patient's blood vessels, key to cardiovascular health, with a simple retinal image could lower the barrier to engage in critical conversations on preventive measures to protect against a cardiovascular event.

Given that the algorithm could accurately predict risk factors, the scientists also trained the algorithm to predict the onset of a major cardiovascular event, such as a heart attack within five years.

"Traditionally, medical discoveries are made by observing associations, making hypotheses from them and then designing and running experiments to test the hypotheses", reads the preamble to a paper published today on Nature Biomedical Engineering.

People Keep Running Into the Fancy Glass at Apple Park
Apple's new futuristic, nearly all-glass, Cupertino, Calif. campus may be handsome , but it's causing some problems for employees. In 2012, an 83-year-old woman sued Apple after walking into a see-through door at an Apple Store and breaking her nose .

Google researchers fed images scanned from the retinas of more than 280,000 patients across the United States and United Kingdom into its intricate pattern-recognizing algorithms, known as neural networks.

Eye scans using deep learning technique are all that one may soon need to gauge whether he or she is prone to heart ailments in near future, according to a study by scientists at Google Research, Verily Life Sciences and Stanford School of Medicine. In future studies, the researchers said they plan to explore the effects of interventions such as lifestyle changes or medications on risk predictions. Their results indicate that their predictions are accurate 70% of the time. Discovering that we could do this is a good first step.

Google said that its algorithm used the entire image to quantify the association between the image and the risk of heart attack or stroke.

U.S. airstrike killed 'dozens' of Russian contractors in Syria
The US responded with airstrikes that killed about 100 of the attackers, according to the coalition, with the rest retreating. The US response showed that Washington "was taking under its control economic assets belonging to Syria ", Moscow said.

While doctors can typically distinguish between the retinal images of patients with severe high blood pressure and normal patients, the algorithm could go further to predict the systolic blood pressure within 11mm Hg on average for patients overall, including those with and without high blood pressure. The green traces are the pixels used to predict the risk factors.

For example, the algorithm paid more attention to blood vessels for making predictions about blood pressure, as shown in the image above. Through mass aggregation and deep learning, an AI program was able to accomplish this feat, and will only continue to improve as it is further trained, tested, and perhaps eventually used in the real world. "We hope researchers in other places will take what we have and build on it". DeepMind, the London-based AI-development firm bought by Google in 2014 that often operates autonomously, released research earlier this month showing similar algorithms could help detect signs of glaucoma and other eye diseases.

Penn State shocks No. 8 Ohio State
All three of Penn State's remaining regular season games give the team opportunities to boost its NCAA Tournament resume. With the victory, Penn State now has two quality wins on their tournament resume, both courtesy of Ohio State.

Latest News