Published: Tue, February 20, 2018
Health Care | By Alice Shelton

Google is using retinal images to assess cardiovascular risk factors

Google is using retinal images to assess cardiovascular risk factors

After analyzing data from over a quarter million patients, the neural network can predict the patient's age (within a 4-year range), gender, smoking status, blood pressure, body mass index, and risk of cardiovascular disease. 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 a study published on Monday in the journal Nature Biomedical Engineering, Google AI researchers described how deep learning algorithms can be trained to predict heart disease symptoms by looking at retinal images.

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.

In this case, Google's Verily is using eye scans to accurately predict an individual's age, blood pressure, and whether or not they smoke.

Ajit Pai's Sinclair Connections Now Under FCC Internal Investigation
The FCC officials told the aides that they would open an investigation, according to four people with knowledge of the meetings. Several other actions by Pai have also raised suspicions that he is acting to "improperly benefit" Sinclair.

Traditionally, medical discoveries are often made through a sophisticated form of guess and test making hypotheses from observations and then designing and running experiments to test the hypotheses. "We think that the accuracy of this prediction will go up a little bit more as we kind of get more comprehensive data". As well as eyes scans, this also included general medical data. According to the team, they were able to quantify the association between the retinal vessels and cardiovascular risks identified by researchers from previous medical studies. Lily Peng, a doctor and lead researcher on the project said that it was early and they were working with small data sets. "But we need to validate". While the link between the eyes and the heart may be somewhat well-known, no human could ever hope to study enough pairs of peepers to actually figure out what all of the different properties of the eye meant as far as heart disease risk.

For the study, the scientists developed deep learning models using retinal fundus images of almost 3, 00,000 people available from two countries; the United Kingdom and the U.S. and validated them using those from another 13,000 patients. All of these factors are important predictors of cardiovascular health. In the future, doctors will be able to screen for the number one killer worldwide much more easily, and they will be doing it without causing us any physical discomfort.

"To make this useful for patients, we will be seeking to understand the effects of interventions such as lifestyle changes or medications on our risk predictions and we will be generating new hypotheses and theories to test", Peng said.

Like this: