Fever Screening Tech Doubles as Early Warning System for Infectious Outbreaks

Researchers from Columbia Engineering and the Columbia Mailman School of Public Health have invented a system that can automatically take temperature readings of multiple people nearby. Uniquely, no one has to stand in front of a camera to take a measurement. And no one needs to read the measurement and approve the person’s entry.

Fred Jiang, associate professor of electrical engineering, teamed up with Andrew Rundle, professor of epidemiology, to develop SIFTER, a low-cost thermal imaging system designed to serve a dual purpose: as a gatekeeping tool to flag the presence of someone with a fever and as a public health early warning system for outbreaks of COVID, influenza, and other infectious diseases that cause fever.

“By using advanced algorithms and models, we’ve developed an inexpensive way for hospitals, restaurants, subway stations, schools, hi-rise buildings with elevators, and more to perform fever screening without disrupting the normal flow of traffic, helping to restore some amount of ‘normal’ to our everyday lives,” said team leader Fred Jiang, who got the idea after seeing how his wife's hospital was overwhelmed during the pandemic by the numbers of people coming through the entrance.

“Fever is a symptom of many infectious diseases, and this system will provide a low-cost, near-real-time and continuous means of detecting spikes in the number of people experiencing fever,” says Andrew Rundle. “We see SIFTER as a complement to other more costly and slower public health surveillance systems that rely on lab tests and case reporting. We expect this system to help improve detection of emerging infectious diseases and seasonal surges in flu.”

The team tested SIFTER in the real world, for 10 months in collaboration with ColumbiaDoctors at their midtown clinic in New York City. It screened more than 4,000 people, with a measurement error within 0.4° F at two meters and around 0.6° F at 3.5 meters. In comparison, most infrared thermal scanners on the market have about a 1◦F measurement error measured within 0.5 meters.

SIFTER’s software is open-source and the hardware costs less than $500 to set up and operate. The data processing component is provided for free by Jiang’s Columbia Intelligent and Connected Systems Lab.

SIFTER is designed with strong privacy protections. While its camera and software recognize facial features to pinpoint optimal locations for thermal imaging, it does not identify faces using facial recognition or store facial images.

Jiang and Rundle are currently working to improve SIFTER in terms of range and accuracy, so that the system can be deployed in more scenarios, such as in large open spaces and transport hubs.

Meanwhile, the researchers are expanding SIFTER to create a “World Wide Flu and Emerging Disease Vision Surveillance System,” which they will jointly run. In the coming months, they will deploy their system in a public space to continuously monitor the number of people experiencing a fever. They will test whether the day-to-day variation in fever prevalence tracks with the day-to-day variation in COVID case counts. While the system cannot detect asymptomatic spreaders, the researchers believe there may be enough people circulating in public with fever that the system can detect actionable trends.

“Each day the camera will count up the number of people who crossed its field of view and the percentage of those people who had fever,” says Rundle. “When the prevalence of fever has risen above a low background normal rate, our system would alert public health authorities to help point them to direct resources, collect samples, and alert physicians.”