Can an automated deep learning scoring system simplify sleep staging classification ?

Takeaway

  • The deep learning model predicts sleep stage with moderate to strong agreement compared with expert human scorers across multiple datasets.

Why this matters ?

    Sleep staging is a key part of evaluating overnight polysomnography (PSG), but the process is labor intensive and suffers from variability in inter- and intra-rater reliability. Successful development of a reliable and accurate automated scoring system using machine learning will reduce the variability and burden of PSG scoring that affects Sleep Medicine research and clinical practice.