Google Artificial Intelligence to Predict Heart Disease

Researchers from Google and its health-tech subsidiary Verily announced on Monday that they have successfully created algorithms to predict whether someone has high blood pressure or is at risk of a heart attack or stroke simply by scanning a person's eyes, the Washington Post reports. Those scans helped train the networks on which telltale signs tended to indicate long-term health dangers.

Scientists have developed an algorithm that predicts the risk of a heart attack from images of people's retinas with similar accuracy to blood tests.

Essentially Google has taken a diagnosis method with an established history, found new ways to analyze the data and sped it up significantly.

The study was published in Nature Biomedical Engineering, and Google Brain Team Product Manager Lily Peng, one of the researchers behind the study, also wrote up a blog entry on the study for Google Research.

With this information, the AI is then able to draw patterns between someone being both older and having high blood pressure, and their eye appearing in a particular way. The latest applies machine learning to retinal images to identify the risk factors of cardiovascular disease.

Krumholz cautioned that an eye scan isn't ready to replace more conventional approaches. Using attention techniques, the researchers generated a heatmap that showed which pixels were the most important for predicting a specific cardiovascular risk factor.

More news: Trump signs budget deal, government to reopen

In the era of AI and machine learning, doctors are using patterns, generated by algorithms, to recognise diseases.

Google's algorithms approached the accuracy of current methods but were far from ideal.

As part of the research, retinal images of two patients were presented, one of whom suffered a cardiovascular event and one of whom did not.

Google and Verily's scientists used machine learning to analyze a medical dataset of almost 300,000 patients, as per the report. "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. Explaining how the algorithm is making its prediction gives the doctor more confidence in the algorithm itself.

The idea that the hallmarks of disease could be detected through computational analysis has been alluring to engineers. The algorithm was able to accurately identify the scan belonging to the person susceptible to heart disease 70 percent of the time, which is on par with a method used today called SCORE.

  • Myrtle Hill