Watch: Smart speakers could detect abnormal heart rhythms
While most rely on Alexa for to-do lists, alarms and news alerts, research suggests smart speakers may one day be used to detect an irregular heart rhythm.
Scientists from the University of Washington have previously demonstrated the devices could identify a person having a cardiac arrest, a medical emergency that occurs when the heart suddenly stops pumping and the brain becomes starved of oxygen.
The same team has now revealed smart speakers like Alexa, Amazon Echo and Google Dot may be able to monitor the heart rhythm of someone sitting in front of the device.
By sending out inaudible waves, a smart speaker prototype identified irregular heart beats based on how the sound was reflected back, according to the scientists.
Read more: Keep iPhone 12 15cm from pacemakers
When tested on 26 healthy volunteers and 24 people hospitalised with cardiac issues, the prototype detected heart beats at an accuracy closely matching that of a standard medical monitor, the results show.
Heart rhythm problems are not always serious, however, an irregular beat that is faster than normal is a common cause of strokes.
"Heart rhythm disorders are actually more common than some other well-known heart conditions," said study author Dr 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."
More than 2 million people in the UK alone experience heart rhythm problems, or arrhythmias, every year.
The most common form of the condition is atrial fibrillation, when the heart beats irregularly and abnormally fast.
Most arrhythmia patients lead normal lives, however, atrial fibrillation raises the risk of a stroke by five times.
Certain arrhythmias can cause sudden death, killing around 100,000 people in the UK every year. Some of these fatalities may be avoidable if the arrhythmias were diagnosed earlier, according to the NHS.
A family history of unexplained death or arrhythmia symptoms – like palpitations, dizziness and fainting – should prompt medics to carry out an electrocardiogram (ECG), which records the heart's rhythm.
Once diagnosed, a patient may be offered medication, surgery or a pacemaker.
"Regular heartbeats are easy enough to detect even if the signal is small, because you can look for a periodic pattern in the data," said co-author Dr Shyam Gollakota.
"Irregular heartbeats are really challenging because there is no such pattern.
"I wasn't sure it would be possible to detect them, so I was pleasantly surprised our algorithms could identify irregular heartbeats during tests with cardiac patients."
The scientists had the participants sit 30cm (1ft) to 60cm (2ft) in front of a prototype based on an "off-the-shelf, seven-microphone array, which had an identical microphone layout and sensitivity to the Amazon Echo Dot".
The prototype played an inaudible continuous sound that bounced off the individual, before returning to the device.
Based on how the returned sound changed, the device isolated the rise and fall chest movements of the person as they breathed.
"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 lead author Anran Wang. "The breathing signal is not regular so it's hard to simply filter it out.
"Using the fact smart speakers have multiple microphones, we designed a new beam-forming algorithm to help the speakers find heartbeats."
Read more: Skin patch tracks wearer's heart rate
This algorithm combined the signals from the smart speaker's multiple microphones to identify a 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 Dr 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."
A person's heart rate describes the number of beats over a period of time, while the rhythm refers to the pattern of these beats.
For example, a heart rate of 60 beats per minute may not have a consistent rhythm of one beat a second.
The scientists therefore created a second algorithm that segments the signal sent by a person's heartbeat into individual palpitations, allowing the system to extract the inter-beat interval; the time between two beats.
"With this method, we are not getting the electric signal of the heart contracting," said Wang. "Instead we're seeing the vibrations on the skin when the heart beats."
Watch: How atrial fibrillation leads to strokes
The scientists tested the prototype on healthy volunteers and people hospitalised with an array of cardiac conditions, including atrial fibrillation and heart failure; when the organ is unable to pump blood around the body sufficiently.
The smart speaker's inter-beat interval was compared to that of a standard monitor.
Of the nearly 12,300 heartbeats measured for the healthy participants, the prototype's median inter-beat interval was within 28 milliseconds of the standard monitor.
The prototype performed comparably well among the cardiac patients. Of the more than 5,600 heartbeats measured, the median inter-beat interval was within 30 milliseconds of the standard monitor.
Carrying out ECGs often involves an individual wearing a portable device for more than 24 hours.
Cleaning these devices can be "time consuming and burdensome", while patients with skin allergies cannot always tolerate these appliances, the Washington scientists wrote in the journal Communications Biology.
The benefits of at-home self-administered tests are "numerous", particularly if a patient lives in a rural location.
Read more: Walnuts boost heart health
The scientists hope smart speakers may one day monitor a person's heart rhythm while they sleep, helping to diagnose conditions like apnoea; when breathing stops and starts during the night, affecting the heartbeat.
"If you have a device like this, you can monitor a patient on an extended basis and define patterns that are individualised for the patient," said Dr Sridhar.
"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.
"This is the future of cardiology and the beauty of using these kinds of devices is they are already in people's homes."