Google Health-tech division creates algorithm to assess cardiovascular risk 

 

Orange County, CA - February 23rd, 2018 -  Scientists at Verily, Google’s health-tech division, have created an algorithm allows doctors to scan the back of a patient’s eye and assess their risk of health disease. Using machine learning, the software accurately gathers data, such as the patient’s age, blood pressure, and smoking history. This information can then be used to predict cardiac irregularities, like a heart attack, with comparable accuracy to current procedures.

A leading advantage for healthcare providers and patients, the algorithm allows for a non-invasive approach. Nullifying the need for blood testing the information is quickly obtained for doctors to analyze a cardiovascular risk. Though further tests are required before implementing this method in a clinical setting, Luke Oakden-Rayner, a medical researcher at the University of Adelaide who specializes in machine learning analysis, believes the algorithm is sound and will assist in the improvement of existing diagnostic tools. “They’re taking data that’s been captured for one clinical reason and getting more out of it than we currently do,” he said. “Rather than replacing doctors, it’s trying to extend [our ability.]

To train the algorithm Verily’s scientists used machine deep learning to analyze a medical dataset of nearly 300,000 patients. Cross-referencing two sets of data, eye scans, and general medical data, the algorithm learned to recognize telltale signs correspondent with cardiovascular risk indicators- like age and blood pressure.

Google Health-tech division creates algorithm to assess cardiovascular risk

The eye’s rear interior wall provides numerous blood vessels reflective of the body’s overall health. Alun Hughes, professor of Cardiovascular Physiology and Pharmacology at London’s UCL, applauded Verily’s approach due to the “long history of looking at the retina to predict cardiovascular risk,” while acknowledging artificial intelligence will help speed up the process of existing forms of medical analysis.

In the first round of testing, the algorithm was presented with retinal images of two patients: one who had suffered a cardiovascular attack in the five years following the scan and one patient who did not. Overall algorithm prediction accuracy of at-risk patients was 70 percent. The current SCORE method (Systematic Coronary Risk Evaluation) for predicting cardiovascular risk, also requiring a blood test, reaches a conclusion with 72 percent accuracy.

For parent company Google, this work represents more than just a new method of predicting cardiovascular irregularities - it paves the way for new AI-powered scientific discoveries. While most medical algorithms are designed to replicate existing diagnostic tools, this algorithm finds new ways to interpret existing data. As aforementioned, further clinical testing is essential prior to mass consumption of the algorithm - but Google and Verily are exceedingly optimistic for their technology’s future.

 

Contact Ampronix:

Increasing Breastfeeding Rates

Email: info@ampronix.com 

International Sales: +1 949-273-8000

Domestic Sales: 1800-400-7972 for US and Canada

Follow Us:

FacebookTwitterLinkedIn

Share This Article:

TwitterFacebookLinkedIn

View our Product Catalog Online Here

 

About Ampronix

Ampronix is a renowned authorized master distributor of the medical industry's top brands as well as a world-class manufacturer of innovative technology. Since 1982, Ampronix has been dedicated to meeting the growing needs of the medical community with its extensive product knowledge, outstanding service, and state-of-the-art repair facility. Ampronix prides itself on its ability to offer tailored, one-stop solutions at a faster and more cost-effective rate than other manufacturers. Ampronix is an ISO & ANSI/ESD certified facility. To learn more go here.

Google Health-tech division creates algorithm to assess cardiovascular risk    Orange County, CA – February 23rd, 2018 –  Scientists at Verily, Google’s health-tech division, have created an algorithm allows doctors to scan the back of a patient’s eye and assess their risk of health disease. Using machine learning, the software accurately gathers data, such as the patient’s age, […]