Trait-like individual signatures dominate sleep EEG over insomnia-specific features.

Insomnia-specific features of sleep EEG activity have remained elusive, with existing findings being inconsistent and often weak in effect. Using machine learning, we analyzed two independent electroencephalogram (EEG) datasets spanning two nights (Nsubjects/nights=198/396), comprising individuals with insomnia disorder (ID) (mild to moderate/severe) and good sleeper controls (GSCs). The findings demonstrated that sleep EEG spectral features differentiated ID from GSC only when using identical participants for training and testing, indicating that model performance was driven by individual EEG signatures instead of ID-related patterns. Analyses with unsupervised learning, similarity matrices, and periodicity assessments further confirmed that brain activity during sleep is characterized by robust, individual-specific EEG signatures with trait-like stability over two nights. We also show that the individual sleep EEG signatures are driven by high frequency cortical activity, previously associated with cortical arousal during sleep. The results then demonstrate that high frequency cortical activity is not specific to ID, but the key to characterizing individual sleep EEG signatures. While ID may be characterized by EEG features beyond spectral power, our findings underscore the importance of a precision brain health framework that prioritizes deviations from an individual’s own neural baseline rather than relying solely on group-level comparisons.