AI looks into your eyes to predict cardio risk

Ebony Scott
February 20, 2018

As with all deep learning analysis, neural networks were then used to mine this information for patterns, learning to associate telltale signs in the eye scans with the metrics needed to predict cardiovascular risk (e.g., age and blood pressure). And while doctors can usually distinguish between the retinal images of patients with severe high blood pressure and those without, the algorithm could go further, and predict the systolic blood pressure for all patients.

Scientists at Alphabet, Google's parent company, have successfully used artificial intelligence to tell how great a person's risk is of having a heart attack based on his or her retinal scan. This unique method involves analyzing blood vessels in an area of the eye called the retinal fundus. One test showed a 70-percent accuracy, for example, in determining which patient among two had experienced a major cardiovascular event following when the retinal image was taken.

In the era of AI and machine learning, doctors are using patterns, generated by algorithms, to recognise diseases. Learning whether you are prone to heart disease can prevent millions of deaths every year as heart disease is the top killer worldwide.

Using that data, the deep learning system was trained to identify certain health issues and risk factors, such as very high blood pressure or whether the patient is a smoker or non-smoker. This time around they are using technology to impact the world of healthcare. "This performance approaches the accuracy of other CV risk calculators that require a blood draw to measure cholesterol", the blog post noted.

Cerrone stops Medeiros with TKO
Cerrone and Nurmagomedov, to remind, have plenty of history together, having been booked to fight twice in the past to no avail. Donald Cerrone had never lost two fights in a row before falling to Robbie Lawler via unanimous decision at UFC 214 last July.

Robert Mueller charges lawyer with lying in Russian Federation election meddling probe
Some are theorizing that Van Der Zwaan either knows far more than he's telling, or he's a means to an end to snag the oligarch. Mr Trump said the Russian indictments vindicate him as they show there was no collusion between Russians and his campaign.

Welcome to Maharashtra, PM Narendra Modi tells global investors
He said the sector is growing tremendously and thus making quality infrastructure in the aviation sector is important. Modi said projects worth Rs 10 lakh crore are stuck as the previous governments did not finish it on time.

A promising start, this research is still in its early days, with Verily noting that "more work must be done to develop and validate these findings on larger patient cohorts before this can arrive in a clinical setting". Researchers have known that retinal blood vessels provide a clue to overall cardiovascular health for some years now, and Google is acting on that knowledge.

As Peng notes, opening the black box to explain how predictions are made should give doctors more confidence in the algorithm.

Google also used some attention techniques to find out how the algorithm was making its prediction.

The algorithm was fairly accurate at predicting the risk of a cardiovascular event directly, said Peng. In addition, this technique could help generate hypotheses for future scientific investigations into CV risk and the retina.

Other reports by GizPress

Discuss This Article