Wearables can track COVID symptoms and other symptoms

If you contract COVID-19, your smartwatch can track the progression of your symptoms and even show you how sick you’re getting.

That’s according to a University of Michigan study that looked at the impact of COVID-19 using six factors derived from heart rate data. The same method could be used to detect other diseases, such as influenza, and the researchers say the approach could be used to track illnesses at home or when medical resources are scarce like during a pandemic or in developing countries.

The researchers tracked UM students and medical interns across the country and discovered new signals embedded in heart rates that indicated when people had contracted COVID and how sick they were getting. The researchers found that people with COVID experienced an increase in heart rate per step after symptoms started, and people with a cough had a much higher heart rate per step than people without a cough.

“We found that COVID dampens biological timekeeping signals, alters your heart rate’s response to activity, alters baseline heart rate, and causes stress signals,” he said Daniel Forger, Professor of Mathematics and Research Professor of Computational Medicine and Bioinformatics. “What we realized was that knowledge of physiology, how the body works, and math can help us glean more information from these wearables.”

The researchers found that these measures were significantly altered and could reflect symptomatic vs. healthy periods in the carriers’ lives.

“There has been some previous work on understanding disease through wearable heart rate data, but I think we’re really taking a different approach by focusing on breaking down the heart rate signal into several different components to get a multidimensional view of heart rate,” he said Caleb MayerPhD student in mathematics.

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

Participants were drawn from the 2019 and 2020 cohorts of the Intern Health Study, a multi-site cohort study that follows physicians during their first year of residency at multiple institutions. Researchers also used information from the Roadmap College Student Data Set, a study examining student health and well-being during the 2020-21 academic year using Fitbits wearable data, self-reported COVID-19 diagnoses and symptom information, and publicly available data examined.

For this analysis, researchers included people who reported a COVID-positive test, symptoms, and wearable data from 50 days before symptom onset to 14 days after. Overall, the researchers used data from 43 medical interns and 72 undergraduate and graduate students.

Specifically, the researchers found:

  • Increase in heart rate per step, a measure of cardiopulmonary dysfunction, increases after onset of symptoms.
  • Heart rate per step was significantly higher in participants who reported coughing.
  • Circadian phase uncertainty, the body’s inability to time daily events, increased around the onset of COVID symptoms. Because this measure relates to the strength and consistency of the circadian component of the heart rate rhythm, this uncertainty can correspond to early signs of infection.
  • Daily basal heart rate tended to increase at or before onset of symptoms. The researchers suspect that this was due to a fever or increased anxiety.
  • Heart rate tended to correlate more strongly with onset of symptoms, which may indicate the action of the stress-related hormone adenosine.

Researchers used an algorithm originally designed to estimate daily circadian phase from wearable heart rate and step data. They considered a baseline period of 8 to 35 days before COVID symptom onset and an analysis period defined as 7 to 14 days around COVID symptom onset. The researchers hope that the same methods, with further testing, could improve the pre-detection of COVID with wearables.

“The global outbreak of the SARS-CoV-2 virus required important public health measures that impacted our daily lives,” he said Sung Won Choi, Associate Professor of Pediatrics. “However, during this historic event in time, mobile technology offered tremendous opportunity – the ability to non-invasively and remotely longitudinally monitor and collect physiological data from individuals.

“We were amazed at the willingness and desire of UM students to participate in this study, which was conducted remotely from recruitment to enrollment to onboarding. The work reported by Mayer and our team was truly made possible not only by the wearable sensors themselves, but the convergence of novel data analysis, remarkable advances in technology and computational power, and the overlap of “team science” between research teams.”

This “Team Science” approach emerged as a by-product of the 2019 UM Ideas Lab, which the team’s lead investigators attended.

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

“Identifying the distinct patterns of different heart rate parameters derived from wearables during the course of COVID-19 infection is a significant advance for the field,” he said Srijan Sen, Professor of Psychiatry and Director of the UM Eisenberg Family Depression Center. “This work may help us more meaningfully track populations in future COVID-19 waves. The study also shows that tracking cohorts with mobile technology and robust data sharing can enable unexpected and valuable discoveries.”

One of the limitations of the study is that the work doesn’t account for flu-like illnesses, the researchers said. Future work should focus on whether the results reflect the effects of COVID-19 or whether those effects persist in other diseases. The researchers also couldn’t account for the impact of factors like age, gender, or BMI, nor for seasonal effects in the data — that is, whether the data was collected during a period when transmission of influenza or other diseases is high.

The study’s co-authors also include UM researchers Jonathan Tyler, Yu Fang, Christopher Flora, Elena Frank, and Muneesh Tewari. The work was supported by the National Institutes of Health, the Human Frontier Science Program, the National Science Foundation, and a grant from the Taubman Institute Innovation Project.

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of the press releases published on EurekAlert! by contributing institutions or for the use of information about the EurekAlert system.

Leave a Comment