Summary: Researchers at the University of Houston have developed a single-lead electrocardiography (ECG) approach for sleep stage classification that matches the accuracy of polysomnography, the current gold standard. This method uses a deep learning neural network and can be performed at home, potentially making sleep studies more accessible and cost-effective. The research, published in Computers in Biology and Medicine, demonstrates that the single-lead ECG test achieves expert-level agreement with polysomnography.
Key Takeaways:
- Innovative Method: A single-lead ECG-based approach for sleep stage classification matches the accuracy of traditional polysomnography.
- Accessibility: Researchers say this new method allows for at-home sleep studies, reducing the need for expensive, cumbersome equipment and clinical visits.
- Research Impact: The complete source code is available for researchers and clinicians, promoting broader adoption and advancements in sleep medicine.
Researchers have introduced an approach to sleep stage classification that could replace polysomnography, the gold standard in sleep testing.
The new procedure, which can be performed at home by the user, uses a single-lead electrocardiography-based deep learning neural network.
Polysomnography is performed in the clinic and requires multiple sensors and wires. But what if the number of those electrodes, attached from your scalp to your heart, was reduced to simply two?
Method Matches Gold-Standard Accuracy
“We have successfully demonstrated that our method achieves expert-level agreement with the gold-standard polysomnography without the need for expensive and cumbersome equipment and a clinician to score the test,” says University of Houston associate professor of electrical and computer engineering Bhavin R. Sheth, PhD, in a release. “This advancement challenges the traditional reliance on electroencephalography (or EEG) for reliable sleep staging and paves the way for more accessible, cost-effective sleep studies.”
The research is published in Computers in Biology and Medicine.
The researchers are now proposing “cardiosomnography” —or a sleep study conducted with ECG only— for expert-level sleep staging that can be conducted in the home.
Broad Implications for Sleep Medicine
Even more, by enabling access to high-quality sleep analysis outside clinical settings, the research holds the potential to expand the reach of sleep medicine, according to the researchers.
Reliable classification of sleep stages is crucial in sleep medicine and neuroscience research for providing valuable insights, diagnoses and understanding of brain states. Although commercial devices like the Apple Watch, Fitbit, and Oura Ring track sleep, their performance is below that of polysomnography, according to the researchers.
The electrocardiography-based model was trained on 4,000 recordings from subjects 5–90 years old. They showed that the model is robust and performs just as well as a clinician scoring polysomnography.
“Our method significantly outperforms current research and commercial devices that do not use EEG and achieves gold-standard levels of agreement using only a single lead of electrocardiography data,” said Sheth, who is also a member of the UH Center for NeuroEngineering and Cognitive Systems, in a release. “It makes less-expensive, higher-quality studies accessible to a broader community, enabling improved sleep research and more personalized, accessible sleep-related healthcare interventions.”
Open Access for Wider Adoption
To that end, the complete source code has been made freely available for researchers, clinicians, and anyone else interested at cardiosomnography.com.
Photo caption: Mockup of future sleep study devices developed at University of Houston.
Photo credit: University of Houston
Leave a Reply