“Hey Alexa, Are My Heart Rhythms Normal?”

River D'Almeida, Ph.D
2 min readMar 18, 2021

Scientists train smart speakers to pick up the faint sounds of heartbeats.

Image via Pexels

Smart speakers-devices such as Amazon’s Echo and the Google Home-lend a helping hand around the house, telling us the weather, turning on lights, and giving us the latest news headlines. Now, scientists say they could also keep track of our heart rhythms, alerting us to the presence of possibly life-threatening irregularities.

Heart rhythms describe the pattern of heartbeats over time and are an important measure of heart health.

Heart rhythm disorders are actually more common than some other well-known heart conditions,” explained professor of cardiology, Arun Sridhar. “Cardiac arrhythmias can cause major morbidities such as strokes, but can be highly unpredictable in occurrence, and thus difficult to diagnose.”

“Availability of a low-cost test that can be performed frequently and at the convenience of home can be a game-changer for certain patients in terms of early diagnosis and management.”

The new smart speaker system can pick up individual heartbeats by sending out a series of sounds from the speaker that can not be detected by the human ear. These bounce off people in the room and are reflected back to the speaker where heart rhythms are assessed for signs of irregularities.

Sridhar and colleagues tested the new system on a cohort of healthy participants and hospitalized cardiac patients. They found that the smart speaker performed as well as standard heartbeat monitoring technology. They reported their findings in Communications Biology.

The secret behind the smart speaker’s success is a so-called “self-supervised” machine learning algorithm. Instead of traditional algorithms that rely on training datasets, this system learns in real time, combining input signals from the smart speaker’s network of microphones to identify the faint heartbeat signals.

The team designed what’s called a self-supervised machine learning algorithm, which learns on the fly instead of from a training set. This algorithm combines signals from all of the smart speaker’s multiple microphones to identify the elusive heartbeat signal.

“This is similar to how Alexa can always find my voice even if I’m playing a video or if there are multiple people talking in the room,” said co-senior author Shyam Gollakota.

“When I say, ‘Hey, Alexa,’ the microphones are working together to find me in the room and listen to what I say next. That’s basically what’s happening here but with the heartbeat.”

Sources: Communications Biology, University of Washington.

Originally published at https://www.labroots.com on March 24, 2021.

River D'Almeida, Ph.D

Follow me for bite-sized stories on the latest discoveries and innovations in biomedical research.