Automatic sleep scoring using patient-specific ensemble models and knowledge distillation for ear-EEG data

Human sleep can be described as a series of transitions between distinct states. This makes automatic sleep analysis (scoring) suitable for an automatic implementation using machine learning. However, the task becomes harder when data is sampled using more light-weight or mobile equipment, often chosen due to greater comfort for the patient. In this study we investigate the improvement in sleep scoring when multiple state-of-the-art neural networks are joined into an ensemble, and subsequently distilled into a single model of identical network architecture, but with improved predictive performance. In this study we investigate ensembles of up to 10 networks, and show that, on the same data, ensembles of neural networks perform better than each single subject model (improvement: 2.4%) and that this improvement can be transferred back into a single network using a combination of patient specific data and knowledge distillation. The study demonstrates both a way to further improve automatic sleep scoring from mobile devices, which in itself is interesting, but also highlights the great potential of the vast amounts of unlabeled personal data which will become available from personal recording devices.

Automated summary

In this study, the improvement in sleep scoring is investigated by using an ensemble of multiple state-of-the-art neural networks and distilling them into a single model. The results show that ensembles of neural networks outperform individual models (improvement: 2.4%), and this improvement can be transferred to a single network through a combination of patient specific data and knowledge distillation. The study not only provides a method to enhance automatic sleep scoring from mobile devices but also highlights the potential of unlabeled personal data from personal recording devices.