Google’s scientists working under its health subsidiary Verily have found a revolutionary new way of diagnosing the risks of heart attack among individuals. The new machine learning technology can analyze scans of the patient’s eye and deduce important data that can be used to assess a person’s risk of suffering a heart attack.
The Google algorithm is able to deduce accurate pieces of data such as the patient’s age, their blood pressure, or whether they smoke or not. Google says that the technology is very accurate in determining the risk of heart attacks and it’s even better compared to other leading methods used in medical care.
There are also other advantages. The time it takes for the technology to diagnose the risk of heart attack is way less compared to the traditional methods. This could potentially help doctors detect such risks faster without the need for any blood test. However, the technology is not ready yet for deployment.
Although initial indications show that it has the potential to revolutionize how cardiac ailments are diagnosed, there are a still a few things that must be taken care of before the algorithm can be used in a real clinical setting.
Reaching this stage was not easy at all. In order to train the algorithm, Google’s scientists at its healthcare subsidiary analyzed medical data sets from more than 300,000 patients using machine learning technology. This included general medical data as well as eye scans from various people. Google then tried to match the telltale signs of the eye scans with the metrics often used to diagnose the risk of cardiovascular diseases. This is how the new algorithm was born.
It looks simple but it’s actually very complicated. However, the idea of using eye scans as a way to assess health conditions is not new. There is a lot of basis in existing literature for the use of eye scans in diagnosing various diseases.
There are a number of reasons for this. To start with, the interior wall of the eye also known as the fundus is filled with blood vessels. These vessels can be used to reflect the patient’s overall health. By looking at these vessels, it is actually possible for doctors to check things like blood pressure, the age of the patient, and whether the patient is a smoker or not. These are all very important metrics that can be used to predict the risk of heart attacks.
There is no doubt that this is a big advancement. At the moment, AI is primarily used to measure the risk of a heart attack. But Google sees this as an important breakthrough that could lead to other applications of AI in the healthcare industry. Most medical AIs are designed to mimic existing diagnostic tools. There is still a level of human input needed for them to work. The aim moving forward is to create AI systems that can do the job without human intervention.