Google wants to contribute to the health sector with its technology. The search-engine giant and its health-tech subsidiary, Verily, have developed a new way to assess human heart condition by just scanning the eyes using AI algorithms.
The company’s ambitious plan was explained in a paper published in Nature’s Biomedical Engineering Journal (PDF).
How Will the AI identify heart disease?
According to the paper, the Verily-Google’s method to predict risks of heart diseases is done by scanning the rear interior wall of your eye, known as the Fundus. A Fundus is chock-full of blood vessels that reflect body’s overall health. Having said that, the machine learning read this part to accurately deduce data, including an individual’s age, blood pressure, cholesterol levels, and whether or not they smoke.
The data can then be used to predict the state of the patient’s heart. It is said that the technology produces the same accurate result as other contemporary methods. Moreover, the algorithm-based prediction is going to be quicker and easier for doctors to analyze a patient’s heart disease, without any blood tests.
Before announcing, Verily scientists used the AI-based heart disease detection technology on the medical dataset of nearly 300,000 patients. The information included the eye scans as well as general medical data.
The machine learning was able to scan the retinal images of two candidates – one who had suffered a cardiovascular event in the past five years, and who did not – and correctly identify them 70 percent of the time. The end result was close to contemporary health detection system.
The technology is promising in identifying cardiovascular diseases without any delay and hassle. But don’t get too excited as the AI-based heart disease detection process is still in its initial stages and requires a lot of work before it gets ready for prime time.