USC researchers develop new sleep analysis tool based on heart data

We know that a good night’s sleep is as essential to survival as food and water. But despite spending a third of our lives asleep, it remains largely a scientific mystery.

Not that experts haven’t tried.

Sleep analysis, also known as polysomnography, is used to diagnose sleep disorders by recording multiple types of data, including the brain (electroencephalogram or EEG) and the heart (electrocardiogram or ECG). Normally, patients in a clinic are connected to dozens of sensors and wires, which monitor brain, eye, muscle, breathing and heart activity while they sleep. Not exactly Zzz-inducing.

But what if you could perform the same test at home, just as accurately and in real time?

For the first time, computer scientists at the University of Southern California have developed an approach that rivals the performance of expert-scored polysomnography using just a single-lead echocardiogram. The software, which is open-source, allows anyone with basic coding experience to create their own low-cost DIY sleep tracking device.

“Researchers have been trying for decades to find simpler and cheaper methods to monitor sleep, especially without the troublesome limit,” said lead author Adam Jones, who recently received his PhD from USC. “But so far, poor performance, even under ideal conditions, has led to the conclusion that it will not be possible and that measuring brain activity is necessary. Our research shows that this assumption is no longer true.”

The model, which assesses sleep stages at the highest level, also performed significantly better than other EEG-less models, the researchers said, including commercial sleep tracking devices. “We wanted to develop a system that addresses the limitations of current methods and the need for greater accessibility and affordability in sleep analysis,” said Jones.

The study, published in June 2024 in the journal Computers in biology and medicinewas co-authored by Laurent Itti, professor of computer science and Jones’ advisor, and Jones’ longtime collaborator, Bhavin R. Sheth, a USC alumnus and electrical engineer at the University of Houston.

Could the heart lead the bond?

Sleep, an important predictor of cognitive decline, becomes shorter and more fragmented with age; a finding that is confirmed by both previous studies and the researchers’ neural network. But this decline is happening sooner than you might expect. A recent study in Neurology found that people who experience more interrupted sleep between the ages of 30 and 40 are more than twice as likely to have memory problems ten years later.

Chronic poor sleep can also contribute to the buildup of beta-amyloid plaques, a hallmark of Alzheimer’s disease.

“It’s a bit scary,” says Jones, who admits he used to be in the “sleep as I die” camp before taking up this research as a hobby project in 2010. ‘That is why I want these interventions to come quickly and make them accessible to as many people as possible. This software can help tease apart what happens every night as we sleep.”

The researchers trained their model on a large, diverse dataset of 4,000 recordings from subjects aged 5 to 90 years old, using only heart data and a deep learning neural network. Through trial and error spanning hundreds of iterations, they discovered that the automated ECG-only network could score sleep as well as the “gold standard” polysomnography. It successfully categorized sleep into all five stages, including rapid eye movement (REM), which is essential for memory consolidation and emotional stability, and non-REM sleep, including deep sleep, which is crucial for physical and mental recovery.

This insight not only simplifies a typically expensive and cumbersome process, but also highlights a deeper connection between the heart and brain than previously thought. It also underlines the role of the autonomic nervous system, which connects the brain and heart.

The heart and brain are connected in ways that are not yet well understood, and this research aims to bridge that gap. There is a lot of evidence in my article that the heart actually leads the bond, so to speak.”

Adam Jones, lead author

The work could also help improve sleep studies in remote populations, shedding light on the origins and functions of sleep.

In a follow-up article currently in preparation, Jones plans to further explore what the network focuses on in the ECG data. “I think there’s a lot of information hidden in the heart that we don’t know about yet,” he said.