UK: Wearable technologies such as smartwatches and activity trackers have attracted a lot of interest over the past few years because of their ability to monitor our health.
During the pandemic, attention turned to whether these wearable devices could detect physiological changes that could indicate COVID infection. This in turn could help with early isolation and testing, reducing the spread of the virus.
So what does the evidence say? Could these technologies be an effective tool to help navigate the pandemic? We’ll take a look.
An elevated respiratory rate, or respiratory rate, has been shown to be a useful biomarker for early detection of COVID. Respiratory rates can be estimated using a method called photoplethysmography which requires only one point of contact (for example, your finger or wrist).
Photoplethysmography is often sensitive to external factors such as ambient light, pressure or movement. Thus, most studies seeking to use this method to detect COVID have focused on monitoring people while they sleep.
Electronics company Fitbit analyzed the nocturnal respiratory rates of thousands of users of their devices to understand if this measurement could help in the detection of COVID.
They found that over a seven-day period (from one day before symptom onset or one day before testing positive for participants without symptoms), a portion of people with COVID showed at least one measure high respiratory rate.
Although this was only detected in about a third of people with symptomatic COVID and a quarter of asymptomatic patients, this study suggests that commercial clothing could potentially be a non-invasive means of detecting possible COVID infections and of have them tested.
Another study looked at the potential of a fitness tracker from the American brand WHOOP to predict COVID risk.
Respiratory rate data and other indicators of heart function from a group of people with COVID were used to train an algorithm to predict infection.
The model was then tested on a separate group of people, some with COVID and some without COVID, but with similar symptoms.
Based on respiratory rate during sleep, the technology was able to identify 20% of COVID-positive cases within two days of symptom onset and 80% of cases by the third day of symptoms.
A recent study found that a fertility tracker called Ava, also worn around the wrist, could identify physiological changes up to two days before the onset of COVID symptoms.
The device measures signals such as respiratory rate, heart rate, skin temperature and blood flow, as well as sleep quantity and quality. Data from COVID-positive patients was similarly used to inform a machine learning algorithm.
Tests found it was able to detect 68% of positive cases up to two days before symptoms became evident.
Other forms of digital sensing
In addition to wearables, digital technologies could also be used in other ways to detect COVID. High-quality microphones are already built into smartphones and other gadgets, paving the way for audio analysis.
COVID typically affects the upper respiratory tract and vocal cords, causing changes in a person’s voice. A mobile phone app trained on hundreds of audio samples from people with and without COVID has been shown to accurately detect whether a person has the virus 89% of the time.
My colleagues and I have developed an app that aims to detect if you might have COVID by the sound of your cough.
The technology is currently under study.
Research has also explored the potential of smart technologies and wearable devices to monitor people during COVID infection.
For example, one team used an in-ear device to measure oxygen saturation, respiratory rate, heart rate, and temperature every 15 minutes in high-risk patients managing COVID at home.
The data was monitored by a trained team and used to help identify patients who may need additional medical attention. At the start of the pandemic, smartphones were offered as a potential solution to detect hypoxia via the user’s fingertip.
Hypoxia refers to low levels of oxygen in body tissues and occurs silently in some COVID patients with more severe disease.
Wearables have also been used to map the impacts of COVID on a larger scale. For example, data from several thousand Fitbits showed changes in sleep during the pandemic (at the start of the pandemic, people generally slept longer, for example).
An extra line of defense
Most of the wearable and other technologies being tested for their COVID detection potential rely on artificial intelligence (AI) methods, particularly machine learning and deep learning.
AI can efficiently analyze large amounts of data in great detail to identify relevant patterns in body signals to recognize the health condition of interest.
However, biological signal patterns can be highly variable within and between patients, so there may be limitations to these real-world AI models. It should also be noted that off-the-shelf portable devices were not specifically designed to continuously monitor symptoms of infectious diseases.
So there may be necessary improvements to technology and algorithms.
We will need continued research to address these challenges, alongside careful consideration of any potential privacy issues associated with the collection of biological data for this purpose.
But wearables and other digital technologies could provide an additional line of defense to help us keep COVID and other infectious diseases at bay.