Almost 500,000 Americans die each year from cardiac arrest, when the heart suddenly stops beating.
People experiencing cardiac arrest will suddenly become unresponsive and either stop breathing or gasp for air, a sign known as agonal breathing.
Immediate CPR can double or triple someone’s chance of survival, but that requires a bystander to be present.
Cardiac arrests often occur outside of the hospital and in the privacy of someone’s home.
Recent research suggests that one of the most common locations for an out-of-hospital cardiac arrest is in a patient’s bedroom, where no one is likely around or awake to respond and provide care.
Researchers at the University of Washington have developed a new tool to monitor people for cardiac arrest while they’re asleep without touching them.
A new skill for a smart speaker – like Google Home and Amazon Alexa – or smartphone lets the device detect the gasping sound of agonal breathing and call for help.
On average, the proof-of-concept tool, which was developed using real agonal breathing instances captured from 911 calls, detected agonal breathing events 97% of the time from up to 20 feet (or 6 meters) away.
The findings are published June 19 in npj Digital Medicine.
“A lot of people have smart speakers in their homes, and these devices have amazing capabilities that we can take advantage of,” said co-corresponding author Shyam Gollakota, an associate professor in the UW’s Paul G. Allen School of Computer Science & Engineering.
“We envision a contactless system that works by continuously and passively monitoring the bedroom for an agonal breathing event, and alerts anyone nearby to come provide CPR. And then if there’s no response, the device can automatically call 911.”
Agonal breathing is present for about 50% of people who experience cardiac arrests, according to 911 call data, and patients who take agonal breaths often have a better chance of surviving.
“This kind of breathing happens when a patient experiences really low oxygen levels,” said co-corresponding author Dr. Jacob Sunshine, an assistant professor of anesthesiology and pain medicine at the UW School of Medicine.
“It’s sort of a guttural gasping noise, and its uniqueness makes it a good audio biomarker to use to identify if someone is experiencing a cardiac arrest.”
The researchers gathered sounds of agonal breathing from real 911 calls to Seattle’s Emergency Medical Services.
Because cardiac arrest patients are often unconscious, bystanders recorded the agonal breathing sounds by putting their phones up to the patient’s mouth so that the dispatcher could determine whether the patient needed immediate CPR.
The team collected 162 calls between 2009 and 2017 and extracted 2.5 seconds of audio at the start of each agonal breath to come up with a total of 236 clips.
The team captured the recordings on different smart devices – an Amazon Alexa, an iPhone 5s and a Samsung Galaxy S4 – and used various machine learning techniques to boost the dataset to 7,316 positive clips.
“We played these examples at different distances to simulate what it would sound like if it the patient was at different places in the bedroom,” said first author Justin Chan, a doctoral student in the Allen School.
“We also added different interfering sounds such as sounds of cats and dogs, cars honking, air conditioning, things that you might normally hear in a home.”
For the negative dataset, the team used 83 hours of audio data collected during sleep studies, yielding 7,305 sound samples.
These clips contained typical sounds that people make in their sleep, such as snoring or obstructive sleep apnea.
From these datasets, the team used machine learning to create a tool that could detect agonal breathing 97% of the time when the smart device was placed up to 6 meters away from a speaker generating the sounds.
Next the team tested the algorithm to make sure that it wouldn’t accidentally classify a different type of breathing, like snoring, as agonal breathing.
“We don’t want to alert either emergency services or loved ones unnecessarily, so it’s important that we reduce our false positive rate,” Chan said.
For the sleep lab data, the algorithm incorrectly categorized a breathing sound as agonal breathing 0.14% of the time.
The false positive rate was about 0.22% for separate audio clips, in which volunteers had recorded themselves while sleeping in their own homes.
But when the team had the tool classify something as agonal breathing only when it detected two distinct events at least 10 seconds apart, the false positive rate fell to 0% for both tests.
The team envisions this algorithm could function like an app, or a skill for Alexa that runs passively on a smart speaker or smartphone while people sleep.
“This could run locally on the processors contained in the Alexa. It’s running in real time, so you don’t need to store anything or send anything to the cloud,” Gollakota said.
“Right now, this is a good proof of concept using the 911 calls in the Seattle metropolitan area,” he said. “But we need to get access to more 911 calls related to cardiac arrest so that we can improve the accuracy of the algorithm further and ensure that it generalizes across a larger population.”
The researchers plan to commercialize this technology through a UW spinout, Sound Life Sciences, Inc.
Almost 500,000 Americans die each year from cardiac arrest, when the heart suddenly stops beating.
People experiencing cardiac arrest will suddenly become unresponsive and either stop breathing or gasp for air, a sign known as agonal breathing.
Immediate CPR can double or triple someone’s chance of survival, but that requires a bystander to be present.
Cardiac arrests often occur outside of the hospital and in the privacy of someone’s home. Recent research suggests that one of the most common locations for an out-of-hospital cardiac arrest is in a patient’s bedroom, where no one is likely around or awake to respond and provide care.
Researchers at the University of Washington have developed a new tool to monitor people for cardiac arrest while they’re asleep without touching them.
A new skill for a smart speaker – like Google Home and Amazon Alexa – or smartphone lets the device detect the gasping sound of agonal breathing and call for help.
On average, the proof-of-concept tool, which was developed using real agonal breathing instances captured from 911 calls, detected agonal breathing events 97% of the time from up to 20 feet (or 6 meters) away. The findings are published June 19 in npj Digital Medicine.
“A lot of people have smart speakers in their homes, and these devices have amazing capabilities that we can take advantage of,” said co-corresponding author Shyam Gollakota, an associate professor in the UW’s Paul G. Allen School of Computer Science & Engineering.
“We envision a contactless system that works by continuously and passively monitoring the bedroom for an agonal breathing event, and alerts anyone nearby to come provide CPR. And then if there’s no response, the device can automatically call 911.”
Agonal breathing is present for about 50% of people who experience cardiac arrests, according to 911 call data, and patients who take agonal breaths often have a better chance of surviving.
“This kind of breathing happens when a patient experiences really low oxygen levels,” said co-corresponding author Dr. Jacob Sunshine, an assistant professor of anesthesiology and pain medicine at the UW School of Medicine.
“It’s sort of a guttural gasping noise, and its uniqueness makes it a good audio biomarker to use to identify if someone is experiencing a cardiac arrest.”
The researchers gathered sounds of agonal breathing from real 911 calls to Seattle’s Emergency Medical Services.
Because cardiac arrest patients are often unconscious, bystanders recorded the agonal breathing sounds by putting their phones up to the patient’s mouth so that the dispatcher could determine whether the patient needed immediate CPR.
The team collected 162 calls between 2009 and 2017 and extracted 2.5 seconds of audio at the start of each agonal breath to come up with a total of 236 clips.
The team captured the recordings on different smart devices – an Amazon Alexa, an iPhone 5s and a Samsung Galaxy S4 – and used various machine learning techniques to boost the dataset to 7,316 positive clips.
“We played these examples at different distances to simulate what it would sound like if it the patient was at different places in the bedroom,” said first author Justin Chan, a doctoral student in the Allen School.
“We also added different interfering sounds such as sounds of cats and dogs, cars honking, air conditioning, things that you might normally hear in a home.”
For the negative dataset, the team used 83 hours of audio data collected during sleep studies, yielding 7,305 sound samples.
These clips contained typical sounds that people make in their sleep, such as snoring or obstructive sleep apnea.
From these datasets, the team used machine learning to create a tool that could detect agonal breathing 97% of the time when the smart device was placed up to 6 meters away from a speaker generating the sounds.
Next the team tested the algorithm to make sure that it wouldn’t accidentally classify a different type of breathing, like snoring, as agonal breathing.
“We don’t want to alert either emergency services or loved ones unnecessarily, so it’s important that we reduce our false positive rate,” Chan said.
For the sleep lab data, the algorithm incorrectly categorized a breathing sound as agonal breathing 0.14% of the time.
The false positive rate was about 0.22% for separate audio clips, in which volunteers had recorded themselves while sleeping in their own homes.
But when the team had the tool classify something as agonal breathing only when it detected two distinct events at least 10 seconds apart, the false positive rate fell to 0% for both tests.
The team envisions this algorithm could function like an app, or a skill for Alexa that runs passively on a smart speaker or smartphone while people sleep.
“This could run locally on the processors contained in the Alexa. It’s running in real time, so you don’t need to store anything or send anything to the cloud,” Gollakota said.
“Right now, this is a good proof of concept using the 911 calls in the Seattle metropolitan area,” he said.
“But we need to get access to more 911 calls related to cardiac arrest so that we can improve the accuracy of the algorithm further and ensure that it generalizes across a larger population.”
The researchers plan to commercialize this technology through a UW spinout, Sound Life Sciences, Inc.
“Cardiac arrests are a very common way for people to die, and right now many of them can go unwitnessed,” Sunshine said. “Part of what makes this technology so compelling is that it could help us catch more patients in time for them to be treated.”
“Cardiac arrests are a very common way for people to die, and right now many of them can go unwitnessed,” Sunshine said. “Part of what makes this technology so compelling is that it could help us catch more patients in time for them to be treated.”
When Death Comes in the Night
We spend one-third of our lives asleep, so it should be no surprise that a lot of people die in their sleep.
There is an important difference between dying overnight (especially when healthy) and dying when unconscious in the latter stages of a fatal disease.
Older people and those who are sick draw less scrutiny than the young.
Depending on the setting of the death (home versus hospital versus assisted care facility), the death may be commented on by a physician.
Rarely would an autopsy be performed (or indicated) unless there are unusual circumstances. This evaluation may be more likely in younger adults or children who die suddenly in the community without known illness.
Even an autopsy may be unrevealing.
The cause of death may not be clear. The death certificate may note non-specific reasons: “cardiorespiratory failure,” “died of natural causes,” or even “old age.”
Family and friends may be left wondering what happened, and it can be helpful to understand some of the causes of death that occur in sleep.
Setting Aside Trauma, the Environment, and Substances
In some cases, death occurs due to some sort of external factor, either directly from the environment or another outside agent.
For example, an earthquake that collapses a building may lead to a traumatic death in sleep.
Carbon monoxide poisoning from faulty ventilation and a poor heating source may contribute.
Homicide can also occur during sleep, and murders may occur more often at night.
Medications that are taken to treat medical disorders, including pain and insomnia, may increase the risk of death.
This may be more likely if these drugs are taken to excess, such as in an overdose, or with alcohol. Sedatives and opioids may alter or suppress breathing. Painful conditions like cancer, for example, may require levels of morphine that accelerate the process of dying by slowing respiration.
Let us assume natural, internal causes are the cause of death and focus on the most likely culprits.
Focusing on Failure of the Heart and Lungs
It may be helpful to think of causes of death in terms of a “Code Blue” that may be called in the hospital setting.
When someone is dying—or at imminent risk of dying—there are a few codependent systems that are usually failing. Most often, the failure of the function of the heart and lungs are to blame.
Evolving respiratory failure may gradually impact the function of the heart and other systems. Acute decline of cardiac function, such as with a massive heart attack, quickly impacts blood flow to the brain and may, in turn, lead to rapid respiratory failure. The lungs may also quickly fill up with fluid as part of pulmonary edema in heart failure.
When evaluating the causes of death in one’s sleep, it can be helpful to explore the causes that impact these two interrelated systems.
Cardiac Arrest
There is considerable evidence that cardiac function may be stressed during sleep.
Rapid eye movement (REM) sleep, in particular, may redline the system with increasing risk towards morning.
There also seems to be a circadian pattern of cardiac dysfunction, with problems often occurring late in the night and near the time of waking.
Heart attacks occur when a blood vessel (or coronary artery) supplying the muscle tissue becomes obstructed and the tissue supplied is damaged or dies.
These myocardial infarctions may range from minor events that slightly compromise function to catastrophic blockages that lead to the heart’s complete failure as a pump.
If blood cannot be circulated, the other systems of the body quickly fail and death ensues.
The heart can also experience irregularities that impact its electrical system
The charge that is required to fire off the muscle in a synchronized fashion may become disrupted. The contractions may become irregular, too fast or too slow, and the heart’s pumping effectiveness may be compromised.
Arrhythmias may be a frequent cause of death during sleep. Asystole is a cardiac arrest rhythm when the electrical activity of the heart cannot be detected.
Atrial fibrillation or flutter may undermine cardiac function. Similar ventricular rhythms, including ventricular tachycardia, may become fatal.
Cardiac blocks affecting the electrical pattern may also lead to heart dysfunction and death.
Chronic, congestive heart failure (CHF) may also gradually lead to the failure of the heart. Left-sided heart failure quickly impacts the right side of the heart, leading to fluid accumulation in the lungs (with shortness of breath, especially when lying down) and swelling in the feet and legs called peripheral edema.
If the heart experiences volume overload, its ability to circulate blood may cease.
Importantly, the heart may affect other systems that rely on its ability to circulate blood. Most notably, an irregular heart rhythm may lead to a clot that travels to the brain and causes a stroke. High blood pressure, or hypertension, may increase the risk.
If a stroke impacts the brainstem, breathing, eye-opening, muscle control, and consciousness may be compromised. These strokes may be fatal and can occur in sleep.
Respiratory Arrest
Lungs complement the function of the heart and, like a team, if one system acutely fails, the other is likely to follow in short order.
Pulmonary disease is often chronic, and the impacts may develop more slowly. When a critical threshold is reached, however, death may occur.
At the most basic level, the lungs are responsible for the exchange of oxygen and carbon dioxide with the environment.
When they do not function properly, oxygen levels fall, carbon dioxide levels rise, and dangerous changes in the acid-base balance of the body can occur.
Acute obstruction, such as choking on vomit, may lead to asphyxiation. Though unlikely, it is also possible for an obstructive sleep apnea event to prove fatal.
Respiratory failure may occur due to chronic, degenerative disease. This can be the failure of the lungs themselves, such as in:
- Chronic obstructive pulmonary disease (COPD)
- Emphysema
- Cystic fibrosis
- Lung cancer
- Pulmonary fibrosis
- Pneumonia
- Status asthmaticus
- Pulmonary embolus (clot to the lungs)
It is also possible for the lungs to fail due to changes in the muscles or nervous systems, such as with amyotrophic lateral sclerosis (ALS or Lou Gehrig’s disease) or myasthenia gravis.
There are even congenital disorders that affect the ability to breathe like congenital central hypoventilation syndrome. Sudden infant death syndrome (SIDS) represents a failure to breathe normally during sleep.
When death approaches slowly, a characteristic pattern of breathing—called Cheyne-Stokes respiration—occurs. Often noted in heart failure, narcotic medication use, and injury to the brainstem, it may indicate imminent breathing cessation and death. Consciousness may become depressed as the affected person slips away.
Considering Other Causes and the Role of Sleep Disorders
It is possible for death in sleep to occur due to a few other disorders, including some sleep conditions. In particular, seizures may be fatal. There is a condition known as sudden death in epilepsy (SUDEP) that is not fully understood.
Obstructive sleep apnea may exacerbate other medical conditions that may ultimately be fatal. These include strokes, heart attacks, heart failure, and arrhythmias that can all result in sudden death.
It is possible to die from sleep behaviors called parasomnias.
Sleepwalking can lead someone into dangerous situations, including falling out of windows from upper floors, off a cruise ship, or wandering onto the street into traffic. “Pseudo-suicide” describes fatalities among people with sleepwalking injuries who die without known depression or suicidal ideation.
REM sleep behavior disorder may lead to a fall out of bed and head trauma in sleep.
This could cause an internal hemorrhage; an epidural hematoma can quickly prove deadly.
Even if the sleep disorder is not immediately fatal, there is evidence that insomnia increases the risk of suicide.
Chronic sleep deprivation may increase overall mortality after years of poor sleep.
More information:npj Digital Medicine, DOI: 10.1038/s41746-019-0128-7
Provided by University of Washington
