0
0
In a revolutionary stride towards transforming sleep medicine, Bhavin R. Sheth, an associate professor of electrical and computer engineering at the University of Houston, along with former student Adam Jones, has introduced a novel method for sleep stage classification. This innovative approach, poised to replace the current gold standard polysomnography, leverages a single-lead electrocardiography-based deep learning neural network and can be performed by users in the comfort of their homes.
Polysomnography, the traditional sleep test, is often an ordeal. Patients are hooked up to a plethora of sensors and wires, making the task of falling asleep arduous. The new procedure, which reduces the number of electrodes from numerous to just two, promises a far more user-friendly experience.
“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,” reports Sheth in the journal Computers in Biology and Medicine. “This advancement challenges the traditional reliance on electroencephalography (EEG) for reliable sleep staging and paves the way for more accessible, cost-effective sleep studies.”
The potential impact of this breakthrough is substantial. By enabling high-quality sleep analysis outside clinical settings, Sheth and Jones’s research could significantly expand the reach of sleep medicine, making it more accessible and affordable.
Accurate sleep stage classification is essential in sleep medicine and neuroscience research, providing crucial insights for diagnoses and a deeper understanding of brain states. While commercial devices like the Apple Watch, Fitbit, and Oura Ring offer sleep tracking, their accuracy pales in comparison to polysomnography.
The researchers trained their electrocardiography-based model on 4,000 recordings from subjects aged 5 to 90 years. The results are impressive: the model performs on par with clinicians 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. “It makes less-expensive, higher-quality studies accessible to a broader community, enabling improved sleep research and more personalized, accessible sleep-related healthcare interventions.”
To further the reach and impact of their work, Jones has made the complete source code freely available at cardiosomnography.com, encouraging researchers, clinicians, and interested parties to explore and utilize their method. This collaboration also includes Laurent Itti from the University of Southern California, highlighting the interdisciplinary nature of this groundbreaking research.
This new approach marks a significant leap forward in sleep medicine, promising a future where high-quality sleep analysis is accessible to all, leading to better sleep health and well-being for countless individuals.
