Wearable technologies like smartwatches and activity trackers have attracted a lot of interest over the past few years in terms of the potential to track our health. During the pandemic, attention has turned to whether these wearables can detect physiological changes that could indicate COVID infection. This can help isolate and test early, reducing the spread of the virus.
So what does the evidence say? Could these technologies be a powerful tool to help navigate the pandemic?
Let’s see
High respiratory rate, or respiratory rate, has been shown to be a useful biomarker for early detection COVID. The respiratory rate can be estimated using a method called optical computed tomography, which requires only a single point of contact (for example, your finger or wrist).
Radiography is often susceptible to external factors such as ambient light, pressure, or movement. So most studies looking to use this method to detect COVID have focused on tracking people while they sleep.
Electronic company Fitbit analyzed the nocturnal respiratory rates of thousands of users of their device to understand whether this measure could aid in COVID detection.
They found that over a seven-day period (from one day before the onset of symptoms, or one day before testing positive for asymptomatic participants), a portion of people with COVID showed at least one elevated respiratory rate measurement.
While this has only been detected in about a third of people with symptomatic COVID and a quarter of patients without symptoms, this study suggests that commercial wearable devices could be a way. non-invasively to detect COVID cases and get them tested.
Another study looked at the potential of US brand Whoop’s fitness tracker to predict COVID risk.
Data on respiratory rate and other indicators of heart function of a group of people with COVID were used to train an infection prediction algorithm.
The model was then tested on a separate group of people, some with COVID and others without COVID, but with similar symptoms.
Based on respiratory rates during sleep, the technology was able to identify 20% of COVID-positive cases in the two days before the onset of symptoms and 80% of cases on the third day of symptoms.
A recent study found that a fertility monitoring device called Ava, also worn around the wrist, was able to identify physiological changes in the two days before COVID symptoms appeared.
The device measures signals including breathing rate, heart rate, skin temperature and blood flow, as well as the quantity and quality of sleep. Data from COVID-positive patients is similarly used to inform a machine learning algorithm.
The test found it could pick out 68% of positive cases within two days before symptoms became apparent.
Other forms of digital detection In addition to wearables, digital technology can also be used in other ways to detect COVID. High-quality microphones have been embedded in smartphones and other devices, paving the way for audio analysis.
COVID usually affects the upper respiratory tract and vocal cords, leading to changes in a person’s voice. A mobile 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%.
My colleagues and I have developed an app that aims to detect if you have COVID by emitting your cough.
Technology is currently being researched
Disease tracking Research has also explored the potential of smart technologies and wearables to track 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 who were managing COVID at home.
The data is monitored by a trained team and used to help identify which patients may need additional medical care. Early in the pandemic, smartphones were suggested as a potential solution to detect hypoxia through the user’s fingertips.
Hypoxia is associated with low oxygen levels in body tissues and is insidious in some COVID patients with more serious illnesses.
Wearable technologies have also been used to map the impacts of COVID on a broader scale. For example, data from thousands of Fitbits has highlighted changes in sleep during a pandemic (for example, during the early part of a pandemic, people generally slept longer).
An additional line of defense Most wearables and other technologies being tested for COVID detection potential rely on artificial intelligence (AI) methods, especially machine learning and deep learning. .
AI can efficiently scan large amounts of highly detailed data to identify relevant patterns in body signals to recognize the health condition you’re interested in.
However, biosignal patterns can vary widely within and between patients, so there may be limits to these AI models in the real world. It is also important to note that wearable devices are not specifically designed to monitor infectious disease symptoms continuously.
Therefore, there may be necessary improvements to the technology and algorithms
We will need ongoing research to address these challenges, along with closely monitoring any possible privacy concerns regarding the collection of biological data for this purpose. .
But wearables and other digital technologies can provide an extra line of defense to help us stop COVID and other infectious diseases.
