Multitaper Spectral Estimation HDP-HMMs for EEG Sleep Inference

TL;DR

This paper introduces a Bayesian nonparametric model combining multitaper spectral estimation and HDP-HMMs to automatically identify and characterize sleep states and microstates from EEG data, improving objectivity and detail.

Contribution

It presents a novel, automated, data-driven approach using HDP-HMMs with multitaper spectral estimation for personalized sleep state analysis from EEG.

Findings

Recovered general sleep dynamics

Identified subject-specific microstates

Discovered stage-dependent sub-oscillations

Abstract

Electroencephalographic (EEG) monitoring of neural activity is widely used for sleep disorder diagnostics and research. The standard of care is to manually classify 30-second epochs of EEG time-domain traces into 5 discrete sleep stages. Unfortunately, this scoring process is subjective and time-consuming, and the defined stages do not capture the heterogeneous landscape of healthy and clinical neural dynamics. This motivates the search for a data-driven and principled way to identify the number and composition of salient, reoccurring brain states present during sleep. To this end, we propose a Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM), combined with wide-sense stationary (WSS) time series spectral estimation to construct a generative model for personalized subject sleep states. In addition, we employ multitaper spectral estimation to further reduce the large variance of the spectral estimates inherent to finite-length EEG measurements. By applying our method to both simulated and human sleep data, we arrive at three main results: 1) a Bayesian nonparametric automated algorithm that recovers general temporal dynamics of sleep, 2) identification of subject-specific "microstates" within canonical sleep stages, and 3) discovery of stage-dependent sub-oscillations with shared spectral signatures across subjects.