Deep transfer learning for improving single-EEG arousal detection
Preprint
Abstract
Datasets in sleep science present challenges for machine learning algorithms due to differences in recording setups across clinics. We investigate two deep transfer learning strategies for overcoming the channel mismatch problem for cases where two datasets do not contain exactly the same setup leading to degraded performance in single-EEG models. Specifically, we train a baseline model on multivariate polysomnography data and subsequently replace the first two layers to prepare the architecture for single-channel electroencephalography data. Using a fine-tuning strategy, our model yields similar performance to the baseline model (F1=0.682 and F1=0.694, respectively), and was significantly better than a comparable single-channel model. Our results are promising for researchers working with small databases who wish to use deep learning models pre-trained on larger databases.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Design of a deep learning model for automatic scoring of periodic and non-periodic leg movements during sleep validated against multiple human expertsSleep Medicine, 2020
- Automatic detection of cortical arousals in sleep and their contribution to daytime sleepinessClinical Neurophysiology, 2020
- DOSED: A deep learning approach to detect multiple sleep micro-events in EEG signalJournal of Neuroscience Methods, 2019
- Neural network analysis of sleep stages enables efficient diagnosis of narcolepsyNature Communications, 2018
- Expert-level sleep scoring with deep neural networksJournal of the American Medical Informatics Association, 2018
- Deep residual networks for automatic sleep stage classification of raw polysomnographic waveforms2018
- The National Sleep Research Resource: towards a sleep data commonsJournal of the American Medical Informatics Association, 2018
- Design and baseline characteristics of the osteoporotic fractures in men (MrOS) study — A large observational study of the determinants of fracture in older menContemporary Clinical Trials, 2005
- Overview of recruitment for the osteoporotic fractures in men study (MrOS)Contemporary Clinical Trials, 2005
- Interobserver Agreement Among Sleep Scorers From Different Centers in a Large DatasetSLEEP, 2000