Sundar Pichai, the CEO of Google, has laid lots of emphasis on deep learning. Recently, Google issued a research paper on how it aims to predict cardiovascular (CV) risks, such as heart disease, by the use of retinal images. According to the paper published in Nature Biomedical Engineering, it stated clearly that images of the eye can help in reducing cardiovascular risks apart from detecting heart diseases.
According to a Google statement on a blog post as quoted below:
Using deep learning algorithms trained on data from 284,335 patients, we were able to predict CV risk factors from retinal images with surprisingly high accuracy for patients from two independent datasets of 12,026 and 999 patients.
The post explained that by using deep learning algorithm, one can easily detect from the retinal image of a person if he or she is a smoker or a non-smoker, and also firgure out his or her systolic blood pressure as well.
Google team also stated that the algorithm gave blood vessels more importance in the process of prediction. The algorithm identified the person who had cardiovascular risk with 70% accuracy.
The Google team said, and I quote:
Our approach uses deep learning to draw connections between changes in the human anatomy and disease, akin to how doctors learn to associate signs and symptoms with the diagnosis of a new disease. This could help scientists generate more targeted hypotheses and drive a wide range of future research,
To ensure a better and accurate predictability, Google is tweaking the algorithm and testing it on a bigger dataset. Earlier, the company also used the deep learning to detect diabetic eye disease.
It is interesting to let you know that Google’s parent company, Alphabet, has a company under its portfolio called Calico, which stresses upon healthcare and research.