MetaSleepLearner: Fast Adaptation of Bio-signals-Based Sleep Stage Classifier to New Individual Subject Using Meta-Learning
Authors:
- Nannapas BanluesombatkulNBNannapas Banluesombatkul
- Pichayoot OuppaphanPOPichayoot Ouppaphan
- Pitshaporn LeelaarpornPLPitshaporn Leelaarporn
- Payongkit LakhanPLPayongkit Lakhan
- Busarakum ChaitusaneyBCBusarakum Chaitusaney
- Nattapong JaimchariyatamNJNattapong Jaimchariyatam
- Ekapol ChuangsuwanichECEkapol Chuangsuwanich
- Nat DilokthanakulNDNat Dilokthanakul
- Theerawit WilaiprasitpornTWTheerawit Wilaiprasitporn
Preprint
Abstract
Objective: Identifying bio-signals based-sleep stages requires time-consuming and tedious labor of skilled clinicians. Deep learning approaches have been introduced in order to challenge the automatic sleep stage classification conundrum. However, disadvantages can be posed in replacing the clinicians with the automatic system. Thus, we aim to develop a framework, capable of assisting the clinicians and lessening the workload. Methods: We proposed the transfer learning framework entitled MetaSleepLearner, using a Model Agnostic Meta-Learning (MAML), in order to transfer the acquired sleep staging knowledge from a large dataset to new individual subject. The capability of MAML was elicited for this task by allowing clinicians to label for a few samples and let the rest be handled by the system. Layer-wise Relevance Propagation (LRP) was also applied to understand the learning course of our approach. Results: In all acquired datasets, in comparison to the conventional approach, MetaSleepLearner achieved a range of 6.15 % to 12.12 % improvement with statistical difference in the mean of both approaches. The illustration of the model interpretation after the adaptation to each subject also confirmed that the performance was directed towards reasonable learning. Conclusion: MetaSleepLearner outperformed the conventional approach as a result from the fine-tuning using the recordings of both healthy subjects and patients. Significance: This is the first paper that investigated a non-conventional pre-training method, MAML, in this task, resulting in a framework for human-machine collaboration in sleep stage classification, easing the burden of the clinicians in labelling the sleep stages through only several epochs rather than an entire recording.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- A review of automated sleep stage scoring based on physiological signals for the new millenniaComputer Methods and Programs in Biomedicine, 2019
- Deep learning for healthcare applications based on physiological signals: A reviewComputer Methods and Programs in Biomedicine, 2018
- Investigating the contribution of distance-based features to automatic sleep stage classificationComputers in Biology and Medicine, 2018
- A convolutional neural network for sleep stage scoring from raw single-channel EEGBiomedical Signal Processing and Control, 2018
- A comparative review on sleep stage classification methods in patients and healthy individualsComputer Methods and Programs in Biomedicine, 2017
- Interpretable deep neural networks for single-trial EEG classificationJournal of Neuroscience Methods, 2016
- ISRUC-Sleep: A comprehensive public dataset for sleep researchersComputer Methods and Programs in Biomedicine, 2016
- Sleep scoring using artificial neural networksSleep Medicine Reviews, 2012
- Trait-like individual differences in the human sleep electroencephalogramNeuroscience, 2006
- Atlas, rules, and recording techniques for the scoring of cyclic alternating pattern (CAP) in human sleepSleep Medicine, 2002