First smart speaker for contactless observing of both reguilar and unpredictable heartbeats

Overview

• Post By :


• Source: University of Washington


• Date: 09 Mar,2021

Wise speakers, such as Amazon Echo and Google Home, have proven adept at monitoring certain health care issues at home. By way of instance, researchers at the University of Washington have shown that these devices can detect cardiac arrests or track babies breathing.

But what about monitoring something even smaller: the moment motion of individual heartbeats in a individual sitting in front of a intelligent speaker?

UW scientists have developed a new ability for a intelligent speaker that for the first time monitors both regular and irregular heartbeats without physical contact. The machine sends inaudible sounds from the speaker out into an area and, based on how the sounds are reflected back to the speaker, it can identify and monitor individual heartbeats.

Because the heartbeat is such a very small motion on the torso surface, the team’s system uses machine learning how to help the wise speaker locate signals from both regular and irregular heartbeats.

When the researchers tested this system on healthy participants and hospitalized cardiac patients, the smart speaker detected heartbeats that closely matched the beats detected by standard heartbeat monitors. The team published these findings March 9 at Communications Biology.

While lots of individuals are familiar with the idea of a heartbeat, physicians are more interested in the assessment of heart rhythm. Heart rate is the average of heartbeats with time, whereas a heart rhythm describes the pattern of heartbeats.

Regular heartbeats are easy enough to detect even if the signal is small, because you can look for a periodic pattern in the data. But irregular heartbeats are really challenging because there is no such pattern. I wasn’t sure that it would be possible to detect them, so I was pleasantly surprised that our algorithms could identify irregular heartbeats during tests with cardiac patients.”

Shyam Gollakota, Study Co-Senior Author and Associate Professor, Paul G. Allen School of Computer Science & Engineering, University of Washington

For instance, if a person has a heart rate of 60 beats per minute, they could have a normal heart rhythm — one beat every second — or an irregular heart rhythm — beats are randomly scattered across that minute but they still average out to 60 beats per minute.

“Heart rhythm disorders are now more common than some other well-known heart ailments. Cardiac arrhythmias can cause major morbidities such as strokes, but may be highly unpredictable in occurrence, and thus hard to diagnose,” said co-senior writer Dr. Arun Sridhar, assistant professor of cardiology at the UW School of Medicine. “Availability of a low-cost test that can be carried out frequently and in the convenience of home can be a game-changer for certain individuals concerning early diagnosis and management.”

With this system, the search for heartbeats begins when someone sits within 1 to 2 feet in front of the wise speaker. Then the system plays an inaudible continuous sound, which pops off the person and then returns to the speaker. Based on how the returned sound has changed, the system can isolate movements on the individual — including the rise and fall of the chest as they breathe.

“The motion from someone’s breathing is orders of magnitude larger on the chest wall than the movement from heartbeats, so that introduces a fairly big challenge,” said lead author Anran Wang, a doctoral student in the Allen School. “Along with the breathing signal isn’t regular so it’s tough 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 locate heartbeats.”

The team designed what is known as a self-supervised machine learning algorithm, which learns on the fly instead of from a training set. This algorithm combines signals from each of the wise speaker multiple microphones to identify the elusive heartbeat signal.

“This is similar to the way Alexa can always find my voice even if I am playing a video or if there are multiple people talking in the area,” Gollakota said. That’s basically what is happening here with the heartbeat.”

The heartbeat signals that the smart speaker detects do not look like the normal peaks which are generally associated with traditional heartbeat monitors. The researchers used another algorithm to segment the signal into individual heartbeats so the system could extract what’s known as the inter-beat period, or the amount of time between two heartbeats.

“With this method, we are not receiving the electric signal of the heart contracting. Instead we are seeing the vibrations on the skin once the heart beats,” Wang said.

The researchers tested a prototype smart speaker running this system on two classes: 26 healthy participants and 24 hospitalized patients with a diversity of cardiac ailments, including atrial fibrillation and heart failure. The team compared the smart speaker’s inter-beat interval with one from a standard heartbeat monitor. Of the nearly 12,300 heartbeats quantified for the wholesome participants, the smart speaker’s median inter-beat interval was within 28 milliseconds of the conventional monitor.

Currently this system is set up for spot checks: When a man or woman is concerned in their heart rhythm, they can sit in front of a intelligent speaker to get a reading. However, the research team hopes that future versions could continuously monitor heartbeats while people are asleep, something which could help doctors diagnose conditions such as sleep apnea.

“If you’ve got a device like this, you can monitor a patient on a protracted basis and define patterns that are individualized for the patient. For instance, we can find out when arrhythmias are happening for each specific patient and develop corresponding care plans that are tailored for when the patients actually need them,” Sridhar said. And the beauty of using such devices is that they are already in people’s houses.”