Researchers at the University of Birmingham in the UK have revealed that monitoring heart rate and physical activity using smart wearable devices – such as smart watches or smart wristbands – by consumers has clinical value when comparing patients’ response to two different treatments for atrial fibrillation and heart failure.
The study, published July 15 in Nature Medicine, examined the feasibility of continuously monitoring drug response using a commercially available fitness tracker and smartphone, providing medical information similar to hospital assessments.
The wearable devices – consisting of a wristband and a connected smartphone – collected a large amount of data on how patients responded to two different drugs prescribed as part of a patient trial funded by the National Institute for Health and Care Research.
Analysis of the results
The researchers used artificial intelligence to analyze more than 140 million heart rate data points in 53 individuals over 20 weeks and found that digoxin and beta-blockers had a similar effect on heart rate, even after accounting for differences in physical activity. This was in contrast to previous studies that only assessed the short-term effects of digoxin.
A neural network was developed that takes into account missing information to avoid an overly optimistic view of the data stream from wearables. Using this approach, the team found that wearables were equivalent to standard tests often used in hospitals and human trials that require staff time and resources. The average age of the study participants was 76, highlighting the potential future value regardless of age or experience with the technology.
“People around the world are increasingly using wearable devices in their daily lives to monitor their activity and health,” said lead researcher Professor Deepak Kotecha, from the University of Birmingham’s Institute of Cardiovascular Sciences, EurekAlert. “This study shows the potential for this new technology to be used to assess treatment response and make a positive contribution to routine patient care.”
“Heart conditions such as atrial fibrillation and heart failure are expected to double in prevalence over the next few decades, resulting in a significant burden on patients and significant cost to healthcare. This study is an exciting demonstration of how AI can support new ways to better help patients,” he added.