By creating an extensive digital network to collect coronavirus outbreaks, the researchers hope to build an early warning system that uses data from activity tracking devices. worn on everyone’s body.
Currently, initial data from a study by the Scripps Research Institute for Translation Studies suggests that devices like smartwatches and Fitbits may be able to detect COVID-19 cases and possibly support Public health efforts to slow the spread of disease.
Launched in March, the DETECT study and its smartphone app gathered daily activity data from participants and matched that data against their self-reported symptoms, as well as their symptoms. what diagnostic tests they can do.
Results from the first six weeks of the study, which lasted more than 30,000 participants, showed that significant changes in a person̵7;s normal heart rate, sleep quality and daily activity could help identify New infections.
The study’s first author, Giorgio Quer, director of artificial intelligence at Scripps, said: “One of the biggest challenges in preventing COVID-19 from spreading is its ability to quickly identify and track. and isolate infected individuals.
“Early identification of people with pre-symptom or even asymptomatic is especially valuable, since people are more likely to be infectious at this stage. That is the ultimate goal,” Quer said. The results of the study were published in the journal Nature Medicine.
RELATED: Fitbit posts early findings suggesting its trackers could identify COVID-19 cases before symptoms settle.
These methods can be combined with the more common, but less effective, COVID-19 screening methods, such as measuring a person’s temperature and asking about a person’s travel history – methods that are likely to omit the asymptomatic cases. Additionally, fever alone was reported in less than a third of COVID-19 patients during hospitalization, the researchers said.
In addition, “infrequent virus tests, with often delayed results, don’t provide the real-time details we need to control the spread of the virus,” said Jennifer Radin, epidemiologist. said Scripps.
In the study, the data model can predict which people are COVID-19 positive with an accuracy of about 80% – usually when they start sleeping more and moving less. But this also includes specific deviations from everyday patterns toward coronavirus infections rather than other diseases, they say.
“The interesting thing here is that we have an authenticated digital signal for the COVID-19,” said Eric Topol, Scripps founder and director. The next step is to use this signal to prevent outbreaks from spreading. “About 100 million Americans already have trackers or wearable smartwatches that can help us; all we need is a small fraction of that – just 1% or 2% – for application use. “
RELATED: NIH Funds 7 Digital Health Projects Targeting COVID-19
Earlier this year, Fitbit – in collaboration with Scripps’ DETECT study – provided preliminary results from a similar study of its own algorithms that attracted more than 100,000 participants.
At that time, the system offered a specificity of 70%, or a false positive rate of 30%, but it could prove valuable in motivating people to seek earlier testing and isolate the plate. to avoid transmission of the virus earlier.
The company also found that its devices could detect nearly half of COVID-19 cases at least a day before participants reported any symptoms, such as fever, cough, or muscle aches. .
And this week, Fitbit received an award of nearly $ 2.5 million from the U.S. Army’s medical research division, to continue developing the algorithm and potentially use it to screen for military illness. multiply.
“Our research shows that our bodies begin to fight the disease before more obvious symptoms appear, and we believe Fitbit can reliably detect these signals. , gives us incredible opportunities to get past this virus and helps warn people that they might get sick before accidentally Amy McDonough, general manager of Fitbit Health Solutions, said.
The award will help launch a potential study with Northwell Health’s Feinstein Institute of Medical Research to help validate the early detection program. Fitbit also said it will work with FDA and other regulators to determine the best pathway for bringing these features to the public.