Published: Tue, February 20, 2018
Health Care | By Oscar Goodwin

Google AI can spot heart disease by staring into patients' eyes

Google AI can spot heart disease by staring into patients' eyes

Building a slide deck, pitch, or presentation?

The researchers trained the algorithm using machine learning by having it analyze the eye scans and general medical data of around 300,000 patients.

Google Research's deep learning work could represent a new method of scientific discovery. In biology the rear interior wall of the eye is full of blood vessels that reflect the body's overall health. Instead, no one taught Google algorithms that some patterns in the retinas of those people were associated with an elevated risk of heart disease and stroke or high blood pressure. These diseases have remained the leading causes of death globally for the last 15 years, the organization noted. Researchers from Alphabet (Google's parent company) subsidiary Verily discovered this new method by deploying machine learning. The system can also use retinal images to predict risk factors, which Google says includes things like the patient's gender and age.

From Washington to Trump, President's Day in the United States
McCauley said it hasn't always been this way, she believes the change came from the Federal Government taking over the holiday. However, through the years, it has come to be a time to honor the birthdays of all USA presidents - past and present.


However, deep learning techniques can also be used to increase the accuracy of diagnoses for these conditions, Peng wrote.

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

"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".

Iran Aircraft killed 66 On Board, Wreckage Not Confirmed
The Iranian airliner's fleet is very old as it has been prevented from updating for years due to severe sanctions from the West. The organization specialized in flights to remote airfields across the country as well as internationally.


Google and Verily's scientists analyse a medical dataset of almost 300,000 patients. The latest applies machine learning to retinal images to identify the risk factors of cardiovascular disease.

That exceeds the abilities of human doctors, who are usually able to tell the difference between someone with normal or high blood pressure, but not able to estimate the systolic pressure. In another example, when the algorithm processed images of patients who would suffer a heart attack within five years and those who did not, the algorithm could make the correct assessment 70 percent of the time. This could lead to easier and potentially quicker analysis than a blood test with roughly the same accuracy as current methods. Results are most significant when the algorithm was tasked with determining specific risk factors.

As Peng notes, opening the black box to explain how predictions are made should give doctors more confidence in the algorithm. "This could help scientists generate more targeted hypotheses and drive a wide range of future research", researchers added.

Apple just fixed a big text message bug
Receiving the character will crash whatever messaging app sees the character, forcing you to force-close the app. Apple' software updates are called macOS High Sierra 10.13.3 Supplemental Update, watchOS 4.2.3 and tvOS 11.2.6.


The algorithm was fairly accurate at predicting the risk of a cardiovascular event directly, said Peng.

Like this: