• Corpus ID: 202231843

Automated Polysomnography Analysis for Detection of Non-Apneic and Non-Hypopneic Arousals using Feature Engineering and a Bidirectional LSTM Network

@article{BahramiRad2019AutomatedPA,
  title={Automated Polysomnography Analysis for Detection of Non-Apneic and Non-Hypopneic Arousals using Feature Engineering and a Bidirectional LSTM Network},
  author={Ali Bahrami Rad and Morteza Zabihi and Zheng Zhao and M. Gabbouj and Aggelos K. Katsaggelos and Simo S{\"a}rkk{\"a}},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.02971}
}
Objective: The aim of this study is to develop an automated classification algorithm for polysomnography (PSG) recordings to detect non-apneic and non-hypopneic arousals. Our particular focus is on detecting the respiratory effort-related arousals (RERAs) which are very subtle respiratory events that do not meet the criteria for apnea or hypopnea, and are more challenging to detect. Methods: The proposed algorithm is based on a bidirectional long short-term memory (BiLSTM) classifier and 465… 
1 Citations

Figures and Tables from this paper

Survey of Heart Disease Prediction and Identification using Machine Learning Approaches
TLDR
The DM techniques are utilizes to summarize existing researches concerning heart disease prediction, examining a combination of DM techniques to reveal the best suitable and effective technique.

References

SHOWING 1-10 OF 88 REFERENCES
Automated Detection of Sleep Arousals From Polysomnography Data Using a Dense Convolutional Neural Network
TLDR
This work constructed a dense recurrent convolutional neural network to detect sleep arousals using available Polysomnography measurement channels and achieves the first place in the official stage of the Physionet challenge with AUPRC of 0.54 on the blind testing dataset.
Automatic Sleep Arousal Detection Using State Distance Analysis in Phase Space
TLDR
A novel approach for automatic arousal detection inspired by the states' recurrences in nonlinear dynamics by using a convolutional neural network for probing the correlated structures inside the distance matrices with the arousal occurrences.
Automatic Detection of Target Regions of Respiratory Effort-Related Arousals Using Recurrent Neural Networks
TLDR
The proposed method for classifying target sleep arousal regions of polysomnographies was developed and validated on the PhysioNet Challenge dataset and resulted in an area under precision-recall curve (AUPRC) score of 0.45.
Using Auxiliary Loss to Improve Sleep Arousal Detection With Neural Network
TLDR
The proposed algorithm was trained on 994 annotated records of polysomnographic signals and used sleep stages as additional training targets, which were easier to learn than arousals despite being multi-class.
Identification of Arousals With Deep Neural Networks (DNNs) Using Different Physiological Signals
TLDR
An effective algorithm to detect non-apnea arousals was developed, which has great potentials in the clinical diagnosis and treatment of automatic sleep disturbance in the future.
Automated Recognition of Sleep Arousal Using Multimodal and Personalized Deep Ensembles of Neural Networks
TLDR
This study proposes a deep ensemble neural network architecture for automatic arousal recognition from multi-modal sensor signals and investigates the use of shared-parameter Siamese architectures for effective feature calibration.
Expert-level sleep scoring with deep neural networks
TLDR
By creating accurate deep learning models for sleep scoring, this work opens the path toward broader and more timely access to sleep diagnostics, potentially extending the reach of sleep expertise beyond specialty clinics.
You Snooze, You Win: the PhysioNet/Computing in Cardiology Challenge 2018
TLDR
The PhysioNet/Computing in Cardiology Challenge 2018 focused on the use of various physiological signals collected during polysomnographic sleep studies to detect sources of arousal (non-apnea) during sleep to develop an algorithm that could label the presence of arousals within the hidden test set.
Automatic Human Sleep Stage Scoring Using Deep Neural Networks
TLDR
This study revealed that deep neural networks (DNNs) working with raw data performed better than feature-based methods and demonstrated that taking the local temporal structure of sleep into account a priori is important.
Characterization of obstructive nonapneic respiratory events in moderate sleep apnea syndrome.
TLDR
In a population of moderate OSAHS, OH represented the dominant type of ONAREs when RERAs should be considered as specific but relatively rare respiratory events, demonstrating some limitations in the AASM Task Force recommendations for definitions of respiratory events.
...
1
2
3
4
5
...