LINCOLN — Putting a smart thermometer to the ear could mean putting an ear to the ground for future COVID-19 outbreaks and the consequences of relaxing social distancing, according to a University of Nebraska-Lincoln engineer.
Working with colleagues Basheer Qolomany, who researches machine learning and big data at the University of Nebraska at Kearney, and Alison Freifeld, professor of contagious diseases at the University of Nebraska Medical Center, Fadi Alsaleem is exploring how data from Bluetooth-connected Kinsa thermometers may help forecast COVID-19 hotspots in Nebraska up to weeks before new outbreaks are officially reported.
“It’s a big thing if we can know that we have this virus almost a month before it is reported from testing,” said Alsaleem, UNL assistant professor of architectural engineering and construction. “One quick way we could potentially use this is to forecast a new outbreak.”
The three researchers are using Kinsa data and machine learning to construct a model that could better predict how the spread of the novel coronavirus will respond to relaxing social distancing guidelines.
Since late 2014, Kinsa has sold or donated more than 1 million thermometers that, with a user’s approval, can anonymously and wirelessly transmit temperature data to the cloud.
Because its thermometers transmit ZIP codes associated with high-temperature readings, Kinsa officials have spent several years tracking to the county level the prevalence, timing and geography of U.S. fevers. Because fevers often emerge as a response to influenza viruses, research has shown that Kinsa data may help reasonably predict the number and seasonality of flu cases in a typical year.
That predictability and an atypical 2020 provide an opportunity to track and even predict COVID-19 outbreaks.
While most people infected with COVID-19 don’t exhibit symptoms, the World Health Organization says 90 percent of those who do will get a fever.
The coronavirus’ relatively long incubation period, combined with still-sparse levels of testing in some areas, has created a notable lag between outbreaks and confirmations of COVID-19 cases.
Kinsa researchers compare the five-year average number of fevers at a given place and time with the corresponding incidence in 2020 to identify areas with substantial spikes in fevers. That work has shown promise in earlier forecasting of coronavirus outbreaks.
When Alsaleem compared the historical fever data for Nebraska with the emergence of fevers in mid-March, he saw a substantial spike. It predated the outbreak of officially reported coronavirus cases by about a month.
The disparity in fevers between 2020 and prior years closely aligned with the number of coronavirus cases reported in Nebraska from mid-April to mid-May, further suggesting that the coronavirus was responsible for most of the spike.
With assistance from Kinsa and the Office of Research and Economic Development’s COVID-19 Rapid Response Grant Program, Alsaleem hopes to factor in the number of Kinsa thermometers sold in each state and the respective demographics of users.
He believes integrating such information better could help bolster the fever data’s predictive power and determine the benefits of using more thermometers.
Alsaleem also is examining state-specific lags between fever spikes and coronavirus confirmations — longer in Nebraska than New York, for example. He thinks that’s mostly related to test availability and type in each state.
His review of Nebraska’s fever data has revealed something else.
Data was streaming into the Kinsa system before social distancing, when COVID-19 barely registered in Nebraskans’ minds but already may have been infecting them. It was compared to data collected when social distancing rules expanded and quarantines became routine.
As Alsaleem expected, the incidence of fevers in Nebraska began sharply declining when state officials announced social distancing guidelines, schools shifted to remote instruction and some employers began allowing or requiring employees to work from home.
He said the decline’s trajectory gives a much-needed empirical perspective on the effectiveness of social distancing. It also could help preview outcomes of relaxing such guidelines.
In tandem with UNK’s Qolomany and UNMC’s Freifeld, Alsaleem is incorporating that data into a model aimed at projecting how infection rates will respond in Nebraska and elsewhere.
“There are a lot of models out there now trying to predict the impact of removing social distancing,” said Alsaleem, who is seeking grant support from the National Institutes of Health. “Many of them are not based in much data. But this one will be because we have data on (fever) cases with social distancing and without.”
He said the model can be used as a guideline for when and how much to relax social distancing, and when there is a need to go back.
Alsaleem and Qolomany also are looking into whether Twitter mentions of the word “fever,” which appeared to spike with roughly the same magnitude and advance warning as the fever data itself, could further refine the model.
Integrating the data on bike-riding frequency and out-of-state riders collected during two recent Nebraska Department of Transportation studies that also seems responsive to social distancing guidelines might prove useful, too.
‘“Thermometer data will never give you 100 percent accuracy,” Alsaleem said. “Twitter, by itself, will never give you 100 percent accuracy. But the more you bring these leading indicators together, the stronger your signal.”