
Smart thermometer readings are especially useful for people who have only mild symptoms and can avoid a trip to the doctor, and those who don’t have access to or can’t afford medical care, Singh said. That means thermometers can catch people missed by health departments and provide a more accurate picture of how flu waves are developing.
University researchers working with Kinsa employees compared the company’s data with those from the health department to see how well they matched and to determine the extent to which users’ temperature readings and symptom reports could help model and predict outbreaks. At the national and state levels, researchers found that the Kinsa data correlated closely with official surveillance measures, but detected ILI cases up to three weeks before health officials reported them — possibly between the time someone developed a fever and the illness. There is a lag in official reporting.
Of course, smart thermometers aren’t the only form of digital monitoring. Analyzing Google search data could also provide a head start on predicting disease outbreaks — people often Google their symptoms before going to the doctor. But their searches are often based only on perceived symptoms, which can be subjective. “Kinsa’s strength is that it relies on objective temperature readings rather than just self-reported symptoms,” said Sarah Ackley, a UCSF postdoctoral fellow in epidemiology and biostatistics who examined Kinsa’s regional forecasts.
Kinsa thermometers are available at major pharmacies, and the company distributes them free of charge to families and U.S. public school staff who request them. To date, the New York City Department of Health and Mental Hygiene is the only government agency to partner with the company citywide, distributing more than 100,000 thermometers to 500 public schools for free since September 2021.
New York City is currently reporting very high rates of influenza-like illness. In the week ended Dec. 3, 13% of patients presenting to healthcare facilities were due to respiratory illness, including fever with cough or sore throat. This is above the national baseline of 2.5% this winter. According to Kinsa’s projections, New York City’s current case peak will be slightly later than the nation’s — meaning the risk of infection is expected to remain high into the new year. “We believe this will be the toughest season, and we’ve been predicting it for some time,” Singh said.
However, the extent to which the New York City health department is using Kinsa’s real-time data this flu season is unclear: “The partnership with Kinsa is a pilot, and we are still exploring how best to use the data,” a department spokesperson wrote via email. connection.
Health agencies tend to be relatively conservative when it comes to new data systems, said Jay Varma, a professor of population health sciences at Cornell University who worked on the New York pilot project. “When new systems emerge, it may take time to understand how best to use them for decision-making,” he said. In addition, he said, new systems require additional staff and resources, and there is always the question of how those resources will be maintained in the future.