Smartwatches can track COVID symptoms via heart rate

If you become ill with COVID-19, your smartwatch can track the progression of your symptoms, and it can even show how sick you are.

That’s according to a new study that examined the effects of COVID-19 with six factors drawn from heart rate data.

The same method can be used to detect other diseases such as influenza, and the researchers say this approach could be used to track illness at home or when medical resources are scarce, such as during an epidemic or in developing countries.

Following University of Michigan students and medical interns across the country, researchers discovered new cues embedded in heart rate that indicate when individuals contracted COVID and how sick they were.

The researchers found that individuals with COVID experienced an increased heart rate per step after the onset of symptoms, and that people with a cough had a significantly higher heart rate per step than those without a cough.

“We’ve found that COVID attenuates biological timekeeping signals, alters how the heart rate responds to activity, alters baseline heart rate, and causes stress signals,” says Daniel Forger, MD, professor of mathematics and professor of computational medicine and bioinformatics at the University of Michigan. “What we’ve realized is knowledge of physiology, how the body works, and mathematics that can help us get more information from these wearables.”

Researchers have found that these measures are significantly altered and can present symptomatic versus healthy periods in the wearer’s life.

“There has been some previous work to understand the disease through wearable heart rate data, but I think we’re really taking a different approach by focusing on analyzing the heart rate signal into several different components to take a multidimensional view of heart rate,” says Caleb Meyer. PhD student in mathematics.

“All of these components depend on different physiological systems. This really gives us additional information about disease progression and an understanding of how the disease affects these different physiological systems over time.”

Participants were drawn from the 2019 and 2020 cohorts of the Internal Health Study, a cohort, multi-site study that followed physicians across several institutes in the first year of their residency. The researchers also used information from the Roadmap College Data Set, a study that examined student health and well-being during the 2020-21 school year using wearable data from Fitbits, self-reported COVID-19 diagnoses, symptom information, and publicly available data.

For this analysis, researchers included individuals who reported a positive COVID test result, symptoms, and had wearable data from 50 days before symptom onset to 14 days afterward. In all, the researchers used data from 43 medical interns and 72 undergraduate and graduate students.

Specifically, the researchers found:

  • The heart rate increases with each step, a measure of cardiopulmonary dysfunction, after symptoms appear.
  • Heart rate per step was significantly higher in the participants who reported coughing.
  • The uncertainty of the circadian phase, the body’s inability to tell time to daily events, increased with the onset of COVID symptoms. As this scale relates to the strength and consistency of the circadian component of heart rate rhythm, this uncertainty may correspond to early signs of infection.
  • The daily baseline heart rate tends to increase on or before symptoms appear. The researchers hypothesized that this was due to fever or increased anxiety.
  • Heart rate tends to be more correlated when symptoms appear, which may indicate the effects of the stress-related hormone adenosine.

The researchers used an algorithm originally developed to estimate the daily circadian phase of heart rate and wearable stride data. They considered a baseline period of 8–35 days before onset of COVID symptoms and the analysis period defined as 7–14 days around onset of COVID symptoms. The researchers hope that with more testing, the same methods could enhance pre-detection of COVID with wearables.

“The global spread of SARS-CoV-2 has imposed important public health measures, affecting our daily lives,” says Song Won Choi, Associate Professor of Pediatrics. “However, during this timely and historic event, mobile technology offered tremendous potential – the ability to monitor and collect physiological data longitudinally from individuals remotely and noninvasively.”

The researchers say this work establishes algorithms that can be used to understand the impact of diseases on heart rate physiology, which could form the basis for medical professionals who may popularize the use of wearables in healthcare.

“Identifying the different patterns of different heart rate parameters derived from wearable devices across the COVID-19 infection pathway is a major advance in this area,” says Srijan Sen, MD, professor of psychiatry and director of the Francis and Kenneth Eisenberg Center for Family Depression.

“This work can help us more meaningfully follow populations in future waves of COVID-19. The study also demonstrates that following cohorts with mobile technology and robust data sharing can facilitate unexpected and valuable discoveries.”

The study’s limitations include that the work does not take into account influenza-like illnesses, according to the researchers. Future work should focus on whether the findings reflect the effects of COVID-19 or whether these effects persist in other diseases. The researchers were also unable to account for the effects of factors such as age, gender or body mass index, nor seasonal effects in the data — that is, whether the data was taken over a period of time when influenza or other illnesses were transmitted. Average.

The results appear in the journal Medicine Cell Reports.

Support for the work came from the National Institutes of Health, the Human Frontier Sciences Program, the National Science Foundation, and the Tubman Institute Innovation Project grant.

Source: University of Michigan

Leave a Reply

Your email address will not be published.