Researchers at the University of Washington have developed an AI-powered sound system that can detect irregular heartbeats.
The system sends inaudible sounds into its close environment and then analyzes the reflected waves to identify individual heartbeats from someone sitting close to it. The technology may be useful in detecting heart rhythm disorders, such as cardiac arrhythmias.
“Heart rhythm disorders are actually more common than some other well-known heart conditions. Cardiac arrhythmias can cause major morbidities such as strokes, but can be highly unpredictable in occurrence, and thus difficult to diagnose,” said Arun Sridhar, a researcher involved in the study, in a press release. “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.”
A major challenge in developing the technology was detecting the heartbeats and distinguishing them from breathing sounds, which are much louder. “The motion from someone’s breathing is orders of magnitude larger on the chest wall than the motion from heartbeats, so that poses a pretty big challenge,” said Anran Wang, another researcher involved in the study. “And the breathing signal is not regular so it’s hard to simply filter it out. Using the fact that smart speakers have multiple microphones, we designed a new beam-forming algorithm to help the speakers find heartbeats.”
The AI powered speakers employ an algorithm that uses the signals from multiple microphones on the device to identify the heartbeat, which is similar to the way that commercial smart speakers, such as Alexa, can use multiple microphones to listen to one voice in a room filled with other noises.
So far, the researchers have tested the technology in a group of healthy volunteers and a group of patients with a variety of cardiac conditions, and compared it with a commonly used conventional heartbeat monitor. The system detected a median inter-beat interval that was within 30 milliseconds or less of that detected by the control device, suggesting that it is comparable in terms of accuracy.
Right now, the system is suitable for a quick spot check of the heart rhythm, and a user needs to intentionally position themselves close to the device before it can analyze their heart beats. However, the researchers hope that future iterations of the technology may be able to monitor heart health continuously, even during sleep.
“If you have a device like this, you can monitor a patient on an extended basis and define patterns that are individualized for the patient. For example, we can figure out when arrhythmias are happening for each specific patient and then develop corresponding care plans that are tailored for when the patients actually need them,” said Sridhar. “This is the future of cardiology. And the beauty of using these kinds of devices is that they are already in people’s homes.”