Author:

Keywords:

Science & Technology, Technology, Life Sciences & Biomedicine, Computer Science, Information Systems, Computer Science, Interdisciplinary Applications, Mathematical & Computational Biology, Medical Informatics, Computer Science, Brain modeling, Sleep, Electroencephalography, Adaptation models, Recording, Data models, Training, Automatic sleep scoring, ear-EEG, personalization, SeqSleepNet, transfer learning, wearable EEG, INTERRATER RELIABILITY, EAR, Humans, Wearable Electronic Devices, Signal Processing, Computer-Assisted, Polysomnography, Male, Adult, Female, Algorithms, STADIUS-24-149

Abstract:

Wearable EEG enables us to capture large amounts of high-quality sleep data for diagnostic purposes. To make full use of this capacity we need high-performance automatic sleep scoring models. To this end, it has been noted that domain mismatch between recording equipment can be considerable, e.g. PSG to wearable EEG, but a previously observed benefit from personalizing models to individual subjects further indicates a personal domain in sleep EEG. In this work, we have investigated the extent of such a personal domain in wearable EEG, and review supervised and unsupervised approaches to personalization as found in the literature. We investigated the personalization effect of the unsupervised Adversarial Domain Adaptation and implemented an unsupervised method based on statistics alignment. No beneficial personalization effect was observed using these unsupervised methods. We find that supervised personalization leads to a substantial performance improvement on the target subject ranging from 15% Cohen's Kappa for subjects with poor performance ( ) to roughly 2% on subjects with high performance ( ). This improvement was present for models trained on both small and large data sets, indicating that even high-performance models benefit from supervised personalization. We found that this personalization can be beneficially regularized using Kullback-Leibler regularization, leading to lower variance with negligible cost to improvement. Based on the experiments, we recommend model personalization using Kullback-Leibler regularization.