Based on inputs by Dr Archana Anand
In a major breakthrough Google AI has developed capability of predicting cardiovascular problems ( heart attacks and strokes) just by observing images of the retina. This in other word implies knowing about cardiovascular issues without blood or any other tests ( (such as MRI, CT scan etc.) .
This success has come after Google and its health-tech arm Verily found that Artificial Intelligence (AI) and Machine Learning (ML) could help identify signals of heart diseases through retinal images.
Google CEO Sundar Pichai has said “AI offers us the potential for new, less invasive tests for heart health — predicting cardiovascular results from retinal images with computer vision — encouraging early results!,“
Lily Peng, MD, and Project Manager in Google AI wrote in official blog of G AI “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 data sets of 12,026 and 999 patients. For example, our algorithm could distinguish the retinal images of a smoker from that of a non-smoker 71 percent of the time, compared to a ~50 percent (i.e. random) accuracy by human experts,” she said.
Doctors can only identify patients with severe high blood pressure using the retinal images, Google AI’s algorithm is a step ahead and predict the systolic blood pressure within 11 mmHg on average for patients overall, including those with and without high blood pressure.
In addition to predicting the various risk factors – age, gender, smoking, blood pressure, etc. – from retinal images, Google AI’s algorithm was fairly accurate at predicting the risk of a CV event directly. The algorithm used the entire image to quantify the association between the image and the risk of heart attack or stroke, Peng wrote.
In the blog she added “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 percent of the time. This performance approaches the accuracy of other CV risk calculators that require a blood draw to measure cholesterol.”