A new University of South Australia study reveals that wearable activity trackers show promise in detecting early signals of disease – particularly atrial fibrillation associated with stroke, and COVID-19.

Assessing the reliability and accuracy of consumer-grade wearable activity trackers to detect and monitor a wide range of medical conditions and events, University of South Australia (UniSA) researchers conducted a systematic review and meta-analysis of 28 studies with 1.2 million participants.

The study found that wearable technology could correctly identify:

• COVID-19 status (positive or negative) in 88 out of 100 people, similar to rapid screening tests.
• Atrial fibrillation in 87 out of 100 people, akin to tests undertaken by doctors.
• Falls in 82 of 100 people.

The research was published in a paper entitled Real-World Accuracy of Wearable Activity Trackers for Detecting Medical Conditions: Systematic Review and Meta-Analysis in the journal JMIR mhealth and uhealth.

Lead researcher, UniSA’s Dr Ben Singh, says that wearable activity trackers could revolutionise the detection of medical conditions and disease.

“As healthcare budgets continue to soar, the need for cost-effective interventions that reduce healthcare costs and improve patient outcomes has never been more urgent,” Dr Singh says.

“Our systematic review shows that wearable activity trackers like Fitbits and Apple Watches have significant promise in detecting COVID-19 and heart conditions in real-world settings, which has the potential to improve personal health monitoring.

While wearable activity trackers present opportunities for improved personal heath monitoring, co-researcher UniSA’s Professor Carol Maher says there is scope for expansion and improvement.

“The beauty of wearable activity trackers is that they provide an easy and convenient way for people to monitor real-time aspects of their health and wellbeing; but their full potential is yet to be realised,” Prof Maher says.

“Wearable trackers are providing some excellent health data, but their application must encompass a greater number of health conditions and demonstrate greater results across diverse populations before they can be considered for clinical practice.”

Image: Image © Tahir AI - Adobe Stock.