This milestone marks a significant expansion of Beacon's analysis platform, extending its application from at-home sleep monitoring to comprehensive coverage of traditional in-lab polysomnography (PSG).
The software, developed by Beacon Biosignals, automatically stages sleep from electroencephalogram (EEG) signals of clinical PSG recordings. This advancement promises to aid in the diagnosis and evaluation of sleep and sleep-related disorders, offering a more consistent, efficient, and precise method for sleep staging in therapeutic areas such as neurological, psychiatric, and sleep disorders.
“With FDA clearances for both SleepStageML and Dreem 3S headband, Beacon now provides an unparalleled capability to measure sleep physiology whether studies are conducted in-home or in-clinic," said Jacob Donoghue, CEO of Beacon Biosignals.
"Beacon’s powerful analytics platform allows for rich analysis of clinical datasets across multiple environments to spur innovation in therapies for sleep disorders as well as neurological and psychiatric conditions with sleep comorbidities."
Therapies for sleep disorders
The software uses advanced deep-learning models trained on extensive datasets containing hundreds of thousands of hours of PSG recordings. These datasets encompass a diverse range of individuals, including healthy subjects and patients with various sleep disorders, neurological diseases, and psychiatric conditions. Clinical validation testing has demonstrated that SleepStageML performs comparably to or even outperforms individual human experts, as reported in literature.
Key benefits include automating the labor-intensive manual sleep staging process, reducing subjective variability in scoring between human experts, and supporting faster PSG analysis turnaround time.
Brandon Westover is Landau Professor of Neurology at Harvard Medical School and co-founder of Beacon Biosignals.
Development for sleep-related disorders
He said: “The advanced machine learning algorithms powering SleepStageML reduce human scoring variability and increase precision of sleep measurements.
“This automated approach unlocks new clinical insights to drive forward therapy development for sleep and sleep-related disorders.”
An additional notable aspect is its designation as the first medical device within the sleep space to be FDA-cleared with a Predetermined Change Control Plan (PCCP). This regulatory pathway allows Beacon to continuously improve the sleep staging machine learning algorithm while operating under the initial 510(k) clearance. The Predetermined Change Control Plan outlines strict validation testing criteria for any updates to the AI/ML model, ensuring improved performance compared to the originally cleared version.
Robust sleep staging capabilities
“SleepStageML’s approved PCCP is a game-changing development for the sleep field,” said Alexander Chan, VP of analytics and machine learning at Beacon Biosignals.
“With this regulatory pathway, we can provide even more accurate and robust sleep staging capabilities over time. This ability to iteratively enhance SleepStageML will be invaluable for generating insights to accelerate sleep therapy research and development.”
The company says FDA clearance for SleepStageML represents a significant milestone for the company, bolstering its powerful machine-learning platform for rapidly analyzing large neurophysiology datasets.
Beacon's array of analytical solutions positions the company as a premier technology partner for pharmaceutical companies, research institutions, and clinical trial organizations seeking to incorporate high-fidelity brain monitoring and sleep measurement into their neuroscience, psychiatry, sleep, and neurodegenerative disease research programs.
