After analyzing data from over a quarter million patients, the neural network can predict the patient's age (within a 4-year range), gender, smoking status, blood pressure, body mass index, and risk of cardiovascular disease.
"Given the retinal image of one patient who (up to 5 years) later experienced a major CV event (such as a heart attack) and the image of another patient who did not, our algorithm could pick out the patient who had the CV event 70% of the time".
Published study reveals that this novel technique is much accurate for predicting the various cardiovascular diseases with the help of more invasive methods, which include attaching needle in the arms of patient.
For doctors, assessing a patient's risk for cardiovascular disease is a critical first step toward reducing the likelihood that the patient suffers a cardiovascular event in the future, Lily Peng, Google Brain Team's product manager, wrote in the post.
Traditionally, medical discoveries are often made through a sophisticated form of guess and test making hypotheses from observations and then designing and running experiments to test the hypotheses. "However, with medical images, observing and quantifying associations can be hard because of the wide variety of features, patterns, colors, values and shapes that are present in real images", researchers noted in a paper (PDF) published in the Nature journal Biomedical Engineering on Tuesday. With its system, Google's deep learning tech is able to predict cardiovascular risk in any given individual simply using images of their retina.
"They're taking data that's been captured for one clinical reason and getting more out of it than we now do", he said. "Our work also suggests avenues of future research into the source of these associations, and whether they can be used to better understand and prevent cardiovascular disease", conclude the authors of the study. "But we need to validate". Peng said that they expanded their exercise and asked the deep learning model to predict whether a person was a smoker or what their blood pressure was based on retinal images. All of these factors are important predictors of cardiovascular health. For instance, the algorithm focuses on blood vessels when predicting blood pressure.
"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", Peng said. "We hope researchers in other places will take what we have and build on it".
The scientists trained deep-learning models on data gathered from over 250,000 patients.