Passive detection of heart conditions via a smart watch could prevent strokes and death
Published: 11 APR 2018 09:23AM
Words by AC Speed | Senior Editor
Cardiovascular Disease (CVD)
is still one of the biggest killers worldwide with over 400 people a day losing their lives to CVD
, and over 500 people suffering a heart attack in the UK alone on a daily basis. CVD accounts for over 150000 deaths every single year in our country and it can have multiple causes.
One of the biggest battles is trying to detect these conditions and diseases early enough in order to be able to treat it to prevent serious health problems or death.
“Atrial fibrillation (AF) affects 34 million people worldwide and is a leading cause of stroke” - Geoffrey H. Tison, MD, MPH
A recent study has shown that a simple smartwatch can passively detect Atrial Fibrillation and alert the user to the problem, the findings were published in a paper titled ‘Passive Detection of Atrial Fibrillation Using a Commercially Available Smartwatch’
The team included Geoffrey H. Tison, Division of Cardiology, Department of Medicine, University of California, Jose M. Sanchez, Cardiogram Incorporated, San Francisco and Brandon Ballinger, 3Department of Epidemiology and Biostatistics, University of California.
A total of 9750 participants enrolled in the Health eHeart Study and 51 patients undergoing cardioversion at the University of California where smartwatches were used to obtain heart rate and step count data for algorithm development.
Of the 9750 participants enrolled in the remote cohort, including 347 participants with AF, 6143 (63.0%) were male, and the mean (SD) age was 42 (12) years.
There were more than 139 million heart rate measurements on which the deep neural network was trained.
The idea behind the concept was to develop an algorithm that would be able to detect whether the user was experiencing a specific heart rhythm/rate in correlation to similar steps detected in patients suffering from AF.
“These data support the proof of concept that a commercially available smartwatch coupled with a deep neural network classifier can passively detect atrial fibrillation.”
“Among 1617 ambulatory individuals who wore a smartwatch, those with self-reported atrial fibrillation were correctly classified with moderate accuracy.”
This could lead to the development of smartwatches that can easily detect early signs of not just AF, but other heart conditions and prevent serious long term health problems from a cardiovascular event or even death.
If you like this article, please help us grow and support independent journalism by sharing it with friends and family. Thank You!