SleepStageML
Beacon Biosignals, Inc.SleepStageML is a software-only medical device that uses AI to automatically analyze EEG signals from sleep studies (PSG recordings) to identify different sleep stages. It assists qualified clinicians in diagnosing sleep quality and sleep disorders in adult patients by providing automated, software-generated sleep stage annotations that clinicians can review and verify.
Intended Use
SleepStageML is intended for assisting the diagnostic evaluation by a qualified clinician to assess sleep quality from level 1 polysomnography (PSG) recordings in a clinical environment in patients aged 18 and older. It is a software-only medical device used to analyze physiological signals and automatically score sleep stages. All outputs are subject to review by a qualified clinician.
Technology
SleepStageML uses a deep learning convolutional neural network trained on a large diverse set of PSG recordings with sleep staging labels. It performs signal preprocessing on EEG channels and classifies each 30-second epoch into sleep stages (Wake, N1, N2, N3, REM). The device only processes EEG signals and outputs annotated EDF+ files returned to clinicians for review. It operates via a secure file transfer system and includes cybersecurity protections.
Performance
Performance was evaluated with retrospective validation on 100 clinical PSG recordings across diverse patient populations. SleepStageML's staging outputs were compared against consensus sleep scoring by three expert technologists using standard metrics (overall, positive, negative agreement). Results demonstrated non-inferiority and substantial equivalence to predicate device Sleep Profiler (K153412) with multi-stage agreement of 84.02%. Software verification and validation testing confirmed all requirements.
Predicate Devices
No predicate devices specified
Ready to Sharpen Your Edge?
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.