SERF: Interpretable Sleep Staging using Embeddings, Rules, and Features

Al-Hussaini, Irfan; Mitchell, Cassie S.

doi:10.1145/3511808.3557700

Cited by 4 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. A CNN-LSTM network [42] is trained end-to-end on sleep staging using the multi-channel EEG, EOG, and EMG signals as input. The CNN is composed of 3 convolutional layers where each layer is followed by batch normalization, ReLU activation, and max pooling.…”

Section: Methodsmentioning

confidence: 99%

“…10% of the most significant features are retained for the next steps using ANOVA, resulting in 249 features for the ISRUC dataset and 105 for the Physionet dataset. • FeatShort: a smaller set of clinically interpretable features inspired by the recent work of Al-Hussaini et al [42]. The features are designed according to the AASM manual [17].…”

Section: Methodsmentioning

confidence: 99%

“…1. Beta waves [42] have frequencies between 8 Hz and 20 Hz. This frequency range is present in Wake [52], REM [52], and N2 (through the overlapping sigma band in Spindles [53]).…”

Section: Interpretation and Clinical Relevancementioning

confidence: 99%

See 2 more Smart Citations

Performance and utility trade-off in interpretable sleep staging

Al-Hussaini¹,

Mitchell²

2022

Preprint

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Performance and utility trade-off in interpretable sleep staging

Al-Hussaini¹,

Mitchell²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep learning is a subset of machine learning that employs artificial neural networks with many hidden layers. Such artificial neural networks learn hierarchical representations of input data, which makes them particularly suitable for analyzing complex, high-dimensional EEG signals [ 30 , 31 , 32 , 33 , 34 ]. Some deep learning models have obtained remarkable accuracy for detecting seizures, such as Convolutional Neural Network (CNN) [ 28 ], Recurrent-CNN (RCNN) [ 26 ], and auto-encoders [ 27 ].…”

Section: Introductionmentioning

confidence: 99%

“…Some deep learning models have obtained remarkable accuracy for detecting seizures, such as Convolutional Neural Network (CNN) [ 28 ], Recurrent-CNN (RCNN) [ 26 ], and auto-encoders [ 27 ]. However, deep learning models often lack interpretability, which is crucial for fostering trust and accountability in clinical settings [ 35 , 36 , 37 , 38 , 39 ].…”

Section: Introductionmentioning

confidence: 99%

SeizFt: Interpretable Machine Learning for Seizure Detection Using Wearables

Al-Hussaini

Mitchell

2023

Bioengineering

Self Cite

View full text Add to dashboard Cite

This work presents SeizFt—a novel seizure detection framework that utilizes machine learning to automatically detect seizures using wearable SensorDot EEG data. Inspired by interpretable sleep staging, our novel approach employs a unique combination of data augmentation, meaningful feature extraction, and an ensemble of decision trees to improve resilience to variations in EEG and to increase the capacity to generalize to unseen data. Fourier Transform (FT) Surrogates were utilized to increase sample size and improve the class balance between labeled non-seizure and seizure epochs. To enhance model stability and accuracy, SeizFt utilizes an ensemble of decision trees through the CatBoost classifier to classify each second of EEG recording as seizure or non-seizure. The SeizIt1 dataset was used for training, and the SeizIt2 dataset for validation and testing. Model performance for seizure detection was evaluated using two primary metrics: sensitivity using the any-overlap method (OVLP) and False Alarm (FA) rate using epoch-based scoring (EPOCH). Notably, SeizFt placed first among an array of state-of-the-art seizure detection algorithms as part of the Seizure Detection Grand Challenge at the 2023 International Conference on Acoustics, Speech, and Signal Processing (ICASSP). SeizFt outperformed state-of-the-art black-box models in accurate seizure detection and minimized false alarms, obtaining a total score of 40.15, combining OVLP and EPOCH across two tasks and representing an improvement of ~30% from the next best approach. The interpretability of SeizFt is a key advantage, as it fosters trust and accountability among healthcare professionals. The most predictive seizure detection features extracted from SeizFt were: delta wave, interquartile range, standard deviation, total absolute power, theta wave, the ratio of delta to theta, binned entropy, Hjorth complexity, delta + theta, and Higuchi fractal dimension. In conclusion, the successful application of SeizFt to wearable SensorDot data suggests its potential for real-time, continuous monitoring to improve personalized medicine for epilepsy.

show abstract

Towards Interpretable Seizure Detection Using Wearables

Al-Hussaini

Mitchell

2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

SERF: Interpretable Sleep Staging using Embeddings, Rules, and Features

Cited by 4 publications

References 26 publications

Performance and utility trade-off in interpretable sleep staging

Performance and utility trade-off in interpretable sleep staging

SeizFt: Interpretable Machine Learning for Seizure Detection Using Wearables

Towards Interpretable Seizure Detection Using Wearables

Contact Info

Product

Resources

About