Mobile Menu

Wearables in COVID-19 detection

The use of wearables is becoming increasingly popular to monitor individuals’ health. These devices allow physiological signals to be continuously monitored, providing valuable longitudinal and real-time data. Researchers have now been exploring the use of these devices in the early detection of asymptomatic and pre-symptomatic cases of COVID-19 to help monitor and control the spread of the virus. We summarise a recent article, published in Nature Electronics, that explored ongoing developments within this area.

Wearables

Wearable devices, such as smartwatches, can provide unique insights into our health and well-being. Unlike conventional testing in a clinical setting, wearables offer continuous access to real-time physiological data. This allows for deviations from a person’s baselines to be detected. During the COVID-19 pandemic, the potential of wearable health devices has become increasingly apparent.

Examples of the use of wearables in COVID-19

Late last year, Synder et al, released a paper that showed how smartwatch data can detect pre-symptomatic cases of COVID-19. The team analysed the data of 32 infected individuals (identified from a cohort of nearly 5,300 participants) and found that 26 (81%) of them had alterations in their heart rate, number of daily steps or time asleep. These aberrant physiological signals appeared 4 to 7 days in advance of the onset of symptoms or diagnosis.

Elsewhere, Quer et al, examined how similar smartwatch data in addition to self-reported symptoms can be used to detect COVID-19. The team enrolled over 30,000 participants, of which 3,811 reported at least one symptom. Although resting heart rate data alone was not a significant discriminator between positive and negative cases, when combined with sleep and activity metrics, as well as self-reported symptoms, the model’s performance was significantly improved.

Limitations

Currently, these devices are unable to differentiate between COVID-19 and other viral infections. They are also predisposed to sample bias as older individuals and low-income populations would not typically own or have access to these devices. Additionally, the detection methods also require large datasets to train the algorithms used. Therefore, for every new pathogen that causes different physiological and activity signatures, the studies would need to be repeated prior to deployment. 

These approaches could potentially be improved and extended with the use of emerging low-cost wearable sensors. In particular, electronic sensors in the form of face masks, contact lenses and patches can help collect previously inaccessible physical and biochemical signals. Next-generation wearable devices must also provide sufficient levels of reliability and robustness to be successfully integrated into daily life. The devices must be biocompatible, energy efficient, compliant and compact, all without compromising performance.

Conclusion

As wearable devices become more ubiquitous, datasets will continue to increase. Therefore, our reliance on data mining and machine-learning-based computational approaches will also increase. The COVID-19 has emphasised the value of wearables. With continued innovation, the next generation of wearables sensors could play an essential role in combating any future pandemics.

Hear Eric Topol (Director & Founder, Scripps Research Translational Institute) share his thoughts on the US’ response to COVID-19 and how genomics and digital technologies are vital to combat the virus. Registration for on-demand access to watch this talk and all our other talks from the Festival of Genomics and Biodata will end on February 12th. Register now.

Image credit: By elwynn – canva.com


More on these topics

Covid-19 / Digital Health / Wearables

Share this article