Meeting Banner
Abstract #2067

Sleep Deprived and Well Rested Brains are Distinguishable by Machine Learning in T1w Imaging

Andrew Hall1, Laurentius Huber2, Daniel Handwerker2, Emily Finn2, and Peter Bandettini2

1NIH, Bethesda, MD, United States, 2NIH/NIMH, Bethesda, MD, United States

We investigated 166 T1-weighted datasets to identify neural biomarkers of sleep deprivation (3h sleep). We find that a linear classification algorithm is able to distinguish between sleep deprived and well-rested brains at 65% accuracy in T1-weighted images. The underlying hypothesis is that if glymphatic function is mediated by sleep, one should be able to tell the difference between sleepy and rested brains based on subtle shifts in T1 across brains.

This abstract and the presentation materials are available to members only; a login is required.

Join Here