Scientists at Google and its healthcare research subsidiary, Verily have documented a new artificial intelligence based preventive diagnosis process for assessing the risk of cardiovascular diseases in patients.
Training deep-learning models on data from more than a quarter of a million patients, the scientists were able to predict the cardiovascular risk factors that were not previously thought to be present in retinal fundus images.
The researchers trained deep learning algorithms on data from thousands of patients recorded in a massive United Kingdom study, which was used with retinal scans to produce a program that can identify risk factors from the scan information alone. Tests of the idea have proven as effective as current methods, and the eye test is faster and less invasive than traditional blood tests used to perform the same tests. Moreover, the rear of our eyes houses a ton of blood vessels, the changes in which are indicative of a variety of parameters like blood pressure, patient's age, smoking habits etc. When comparing the eyes of different patients, the software was able to accurately recognize which patient was healthy and which one had suffered from a cardiovascular disease 70 percent of the time.
Study coauthor Dr Michael McConnell, a medical researcher at Verily, said: 'Cardiovascular disease is the leading cause of death globally. Predicting the factors that put a person at risk of a heart attack or stroke was an offshoot of the original research.
The results were similar to those achieved via testing methods that require blood be drawn to measure a patient's cholesterol, which are typically 72 per cent accurate.
Siegel added that early detection is "hugely important" because it can help prevent heart attacks.
The algorithm used scans of a patient's eye to build a picture of their general health, a technique which is already used in medical research. The interior surface of the eye, known as the fundus, is an area full of blood vessels that reflect the overall health of your body and that provides important medical information.
Lily Peng, a doctor and lead researcher on the project, says Google was surprised by the results.