# Performance and utility trade-off in interpretable sleep staging

arXiv: https://arxiv.org/abs/2211.03282 · HTML: https://mlsanity.com/paper/2211.03282/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 60 references that are in the map.
- First posted on arXiv 7 Nov 2022.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [CatBoost: gradient boosting with categorical features support](https://mlsanity.com/paper/1810.11363/) (2018)
- [DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG](https://mlsanity.com/paper/1703.04046/) (2017)
- [SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging](https://mlsanity.com/paper/1809.10932/) (2018)
- [U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging](https://mlsanity.com/paper/1910.11162/) (2019)
- [SleepTransformer: Automatic Sleep Staging with Interpretability and Uncertainty Quantification](https://mlsanity.com/paper/2105.11043/) (2021)
- [Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence](https://mlsanity.com/paper/2002.04803/) (2020)
- [Interpretability of machine learning based prediction models in healthcare](https://mlsanity.com/paper/2002.08596/) (2020)
- [A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series](https://mlsanity.com/paper/1707.03321/) (2017)
- [Neural network an1alysis of sleep stages enables efficient diagnosis of narcolepsy](https://mlsanity.com/paper/1710.02094/) (2017)
- [Dreem Open Datasets: Multi-Scored Sleep Datasets to compare Human and Automated sleep staging](https://mlsanity.com/paper/1911.03221/) (2019)
- [CatBoost: unbiased boosting with categorical features](https://mlsanity.com/paper/1706.09516/) (2017)
- [Mixed Neural Network Approach for Temporal Sleep Stage Classification](https://mlsanity.com/paper/1610.06421/) (2016)
- [SLEEPNET: Automated Sleep Staging System via Deep Learning](https://mlsanity.com/paper/1707.08262/) (2017)
- [tsflex: flexible time series processing & feature extraction](https://mlsanity.com/paper/2111.12429/) (2021)
- [SLEEPER: interpretable Sleep staging via Prototypes from Expert Rules](https://mlsanity.com/paper/1910.06100/) (2019)
- [SERF: Interpretable Sleep Staging using Embeddings, Rules, and Features](https://mlsanity.com/paper/2209.11174/) (2022)

## Abstract (arXiv)

Recent advances in deep learning have led to the development of models approaching the human level of accuracy. However, healthcare remains an area lacking in widespread adoption. The safety-critical nature of healthcare results in a natural reticence to put these black-box deep learning models into practice. This paper explores interpretable methods for a clinical decision support system called sleep staging, an essential step in diagnosing sleep disorders. Clinical sleep staging is an arduous process requiring manual annotation for each 30s of sleep using physiological signals such as electroencephalogram (EEG). Recent work has shown that sleep staging using simple models and an exhaustive set of features can perform nearly as well as deep learning approaches but only for some specific datasets. Moreover, the utility of those features from a clinical standpoint is ambiguous. On the other hand, the proposed framework, NormIntSleep demonstrates exceptional performance across different datasets by representing deep learning embeddings using normalized features. NormIntSleep performs 4.5% better than the exhaustive feature-based approach and 1.5% better than other representation learning approaches. An empirical comparison between the utility of the interpretations of these models highlights the improved alignment with clinical expectations when performance is traded-off slightly. NormIntSleep paired with a clinically meaningful set of features can best balance this trade-off by providing reliable, clinically relevant interpretation with robust performance.