Robust autoregressive hidden semi-Markov models applied to EEG sleep spindles detection
share
We propose a generative model for single-channel EEG that incorporates the constraints experts actively enforce while visually scoring recordings. In particular, the framework takes the form of a robust hidden semi-Markov model that explicitly segments sequences into local, reoccurring dynamical regimes. Unlike typical detectors, our approach takes the raw data (up to resampling) without any filtering, windowing, nor thresholding. This not only makes the model appealing to real-time applications, but it also yields interpretable hyperparameters that are analogous to known clinical criteria. We validate the model on stage 2 non-REM sleep recordings that display characteristic sleep spindles. We derive tractable algorithms for exact inference and prove that more complex models are able to surpass state of the art detectors while being completely transparent, auditable, and generalizable.
READ FULL TEXT
