"Using deep learning algorithms trained on data from 284,335 patients, we were able to predict CV risk factors from retinal images with surprisingly high accuracy for patients from two independent data sets of 12,026 and 999 patients", Lily Peng, MD, product manager and a lead on these efforts within Google AI, wrote in the Google AI official blog. It can then accurately estimate the person's age, blood pressure, and whether they smoke or not. Using its algorithms to predict which patient within five years would actually have a heart attack or other major cardiovascular event, and which patient would not.
By gathering this information, Verily said, it can determine whether the patient is at severe risk of having a heart attack, just as much as a series of tests using traditional methods could. However, it still needs to be tested thoroughly before being implemented in a real world setting. "However, with medical images, observing and quantifying associations can be hard because of the wide variety of features, patterns, colors, values and shapes that are present in real images", researchers noted in a paper (PDF) published in the Nature journal Biomedical Engineering on Tuesday.
The search giant said that it is looking forward to developing and testing the algorithm on larger and more comprehensive datasets to make it more useful for patients and doctors. Apart from the retina scans they also recorded the medical data of these individuals. "They're taking data that's been captured for one clinical reason and getting more out of it than we now do", said Oakden-Rayner.
Now it does seem a bit odd that eye-scanning could be a way to judge the health of your heart, but this is based on established research where the rear interior wall of your eye is packed with blood vessels that can reflect your body's overall health.
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). "This performance approaches the accuracy of other CV risk calculators that require a blood draw to measure cholesterol". Using this data, the algorithm could predict which patients would eventually develop cardiovascular disease with a 70 percent accuracy rate.
While it might seem odd to look into a person's eyes to determine their heart health, it's actually not unusual and the eyes are actually a good place to check for the first signs of many health conditions. He added that artificial intelligence had the potential to speed up existing forms of medical analysis, but cautioned that the algorithm would need to be tested further before it could be trusted.
- Killed in New Regime Attacks in Syria's E. Ghouta
- Alleged HTC Desire 12 Retail Box Confirms Some Of Its Specs
- Virginia's House Republicans finally put their weight behind Medicaid expansion
- MI gas prices fall more than 10 cents in the past week
- Fortnite: Battle Royale's Season 3 Battle Pass Adds Space-Themed Loot
- Fact check: Trump roars on Twitter about Russian Federation probe
- Jennifer Lawrence Explains Why Her On-Set Nudity Made People 'Uncomfortable'
- Consumers Energy: No Coal Use by 2040
- Syria facing 'new wave' of U.S. intervention, Iran's Zarif says
- Mob storms police station, drags rape accused out, lynches them