The team of researchers reportedly predicted cardiovascular risk factors that were "not previously thought to be present or quantifiable in retinal images" using the deep learning models that they trained on data from 284,335 patients. Given the fact that heart diseases is one of the leading causes of deaths in the world, this algorithm could be a big breakthrough. The role of AI and machine learning in making human lives easier is conventional, but using the advanced technology tools to have a lasting impact on human health is certainly a breakthrough.
Veirly's software can also look at data such as individual's age, blood pressure, and whether or not they smoke before it can predict outcomes.
However, deep learning techniques can also be used to increase the accuracy of diagnoses for these conditions, Peng wrote.
If the eyes are the window to the soul, Google thinks it's proven that the retina can offer a window to the state of the heart. The discovery may point to more ways to diagnose health issues from retinal images, researchers said.
Google AI's method reportedly uses deep learning algorithms to create a so-called "heat map or graphical representation of data which revealed which pixels in an image".
"In summary, we have provided evidence that deep learning may uncover additional signals in retinal images that will allow for better cardiovascular risk stratification". Just by analyzing the images, the algorithm could distinguish the retinal images of a smoker from a non-smoker 71 percent of the time, according to the study.
This new algorithm is fairly accurate at predicting the risk of a cardiovascular event directly by scanning the eyes. When presented images of the eyes of two different people - one who suffered a major adverse cardiac event such as a heart attack or stroke within five years of the photo and the other who did not - the algorithms could correctly pick the patient who fell ill 70 percent of the time. "This performance approaches the accuracy of other CV risk calculators that require a blood draw to measure cholesterol", Peng said. Maulik Majmudar, associate director of the Healthcare Transformation Lab at Massachusetts General Hospital, called the model "impressive" but noted that the results show how tough it is to make significant improvements in cardiovascular risk prediction. Explaining how the algorithm is making its prediction gives doctor more confidence in the algorithm itself. "This could help scientists generate more targeted hypotheses and drive a wide range of future research", researchers added.