Scientists from Google and its health-tech subsidiary Verily have found a new way to evaluate a person’s risk of heart disease using machine learning just by looking at their eyes.

The software scans and analyzes the back of a person`s eye to figure out metrics like age, blood pressure, and if someone smokes or not.

This assists them to predict if people are at a risk of a heart disease, for the rear wall of the eye can work as a display case for cardiovascular health.

The rear interior wall of the eye, called the fundus, comprise of numerable blood vessels that have the capacity to reflect a person`s overall health actually. When studied closely for informer factors, someone`s cardiovascular health can be evaluated through the eyes to a great extent.

The AI was equipped with eye scans of 300,000 patients. The scientists first used machine learning to study a sample size and develop the AI Algorithm. They analyzed the eye scans and general medical data by examining the patients.

After compiling the data, the scientists used neural networks to encode this information for patterns. By doing so, the deep learning analysis began to associate particular eye scans with corresponding metrics like age and blood pressure to give cardiovascular risks.

The Google AI software showed an accuracy of 70%. To test the algorithm effectively, the AI engine was again and again given with retinal images of two patients, one with the history of a cardiovascular disease and one without, and as a surprise, it came that the software was quite accurate in discovering the diseases.

Remarkably, the traditional method SCORE used for evaluating cardiovascular risk by doctors, which requires needs patients blood test, has an accuracy rate of 72%.

Admiring Verily`s efforts, medical researcher Luke Oakden-Rayner said, "They`re taking data that`s been captured for one clinical reason and getting more out of it than we currently do. Rather than replacing doctors, it`s trying to extend what we can actually do."