Portable AI Device Turns Coughing Sounds Into Health Data for Flu Forecasting
March 23, 2020

Researchers have invented a portable surveillance device powered by machine learning -- called FluSense -- which can detect coughing and crowd size in real time, then analyse the data to directly monitor flu-like illnesses and influenza trends.

The FluSense creators said the new edge-computing platform, envisioned for use in hospitals, healthcare waiting rooms, and larger public spaces, may expand the arsenal of health surveillance tools used to forecast seasonal flu and other viral respiratory outbreaks, such as the current coronavirus disease 2019 (COVID-19) pandemic.

Models like these can be lifesavers by directly informing the public health response during an influenza epidemic. These data sources can help determine the timing for influenza vaccine campaigns, potential travel restrictions, the allocation of medical supplies, and more.

“This may allow us to predict flu trends in a much more accurate manner,” said Tauhidur Rahman, University of Massachusetts Amherst, Amherst, Massachusetts.

The research was published in Proceedings of the Association for Computing Machinery on Interactive, Mobile, Wearable and Ubiquitous Technologies.

The FluSense platform processes a low-cost microphone array and thermal imaging data with a Raspberry Pi and neural computing engine. It stores no personally identifiable information, such as speech data or distinguishing images. In Rahman’s Mosaic Lab, where computer scientists develop sensors to observe human health and behaviour, the researchers first developed a lab-based cough model. Then they trained the deep neural network classifier to draw bounding boxes on thermal images representing people, and then to count them.

“Our main goal was to build predictive models at the population level, not the individual level,” Rahman explained.

They placed the FluSense devices, encased in a rectangular box about the size of a large dictionary, in 4 healthcare waiting rooms at University of Massachusetts University Health Services clinic. From December 2018 to July 2019, the FluSense platform collected and analysed more than 350,000 thermal images and 21 million non-speech audio samples from the public waiting areas.

The researchers found that FluSense was able to accurately predict daily illness rates at the university clinic. Multiple and complementary sets of FluSense signals “strongly correlated” with laboratory-based testing for flu-like illnesses and influenza itself.

The researchers said that the next step is to test FluSense in other public areas and geographic locations.

“We have the initial validation that the coughing indeed has a correlation with influenza-related illness,” said Andrew Lover, University of Massachusetts Amherst School of Public Health and Health Sciences. “Now we want to validate it beyond this specific hospital setting and show that we can generalise across locations.”

Reference: https://dl.acm.org/doi/abs/10.1145/3381014

SOURCE: University of Massachusetts Amherst