Automatic Detection of Target Regions of Respiratory Effort-Related Arousals Using Recurrent Neural Networks

Prainsson, Heidar Mar; Ragnarsdóttir, Hanna; Kristjansson, Gudni Fannar; Marinosson, Bragi; Finnsson, Eysteinn; Gunnlaugsson, Eysteinn; Jonsson, Sigurdur Egir; Agustsson, J. S.; Helgadóttir, Halla

doi:10.22489/cinc.2018.126

Cited by 10 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work is compared with several of them in terms of the achieved AUPRC in Table 8. Table 8 shows that our proposed DRCNN outperforms the other models submitted to the 2018 Phsyionet challenge, excluding the one in [19] which utilized a hyperparameter search to achieve the best model, but not during the official stage of the [16] Neural network with auxillary loss 0.460 Mar Priansson et al [17] Bidirectional recurrent neural network 0.452 He at al. [15] Deep neural networks with LSTM 0.430 Warrick & Homsi [29] Scattering transform and recurrent neural network 0.375 Li at al.…”

Section: Discussionmentioning

confidence: 99%

SleepNet: automated sleep analysis via dense convolutional neural network using physiological time series

Pourbabaee¹,

Patterson²,

Patterson³

et al. 2019

Physiol. Meas.

View full text Add to dashboard Cite

In this work, a dense recurrent convolutional neural network (DRCNN) was constructed to detect sleep disorders including arousal, apnea and hypopnea using Polysomnography (PSG) measurement channels provided in the 2018 Physionet challenge database. Our model structure is composed of multiple dense convolutional units (DCU) followed by a bidirectional long-short term memory (LSTM) layer followed by a softmax output layer. The sleep events including sleep stages, arousal regions and multiple types of apnea and hypopnea are manually annotated by experts which enables us to train our proposed network using a multi-task learning mechanism. Three binary cross-entropy loss functions corresponding to sleep/wake, target arousal and apneahypopnea/normal detection tasks are summed up to generate our overall network loss function that is optimized using the Adam method. Our model performance was evaluated using two metrics: the area under the precision-recall curve (AUPRC) and the area under the receiver operating characteristic curve (AUROC). To measure our model generalization, 4-fold cross-validation was also performed. For training, our model was applied to full night recording data. Finally, the average AUPRC and AUROC values associated with the arousal detection task were 0.505 and 0.922, respectively on our testing dataset. An ensemble of four models trained on different data folds improved the AUPRC and AUROC to 0.543 and 0.931, respectively. Our proposed algorithm achieved first place in the official stage of the 2018 Physionet challenge for detecting sleep arousals with AUPRC of 0.54 on the blind testing dataset.

show abstract

Section: Discussionmentioning

confidence: 99%

SleepNet: automated sleep analysis via dense convolutional neural network using physiological time series

Pourbabaee¹,

Patterson²,

Patterson³

et al. 2019

Physiol. Meas.

View full text Add to dashboard Cite

show abstract

“…Deep learning methods possess the strong capability to learn complex features by directly applying them to raw data without extracting any hand-crafted features. Only recently have researchers begun to show a preference for deep learning methods, such as CNN [68][69][70][71], ResNet [48], the Siamese architecture network [70], RNN, and LSTM [59,72,73], over traditional machine learning methods in arousal detection.…”

Section: Microarousal Detection With Deep Learning Methodsmentioning

confidence: 99%

“…The [59] QRS [61] Heart rate variability (HRV) signals [62] The general workflow in this field is shown in Figure 5. Data scientists first extract the domain-specific features of PSG signals.…”

Section: Channel Namementioning

confidence: 99%

“…Bi-LSTM depends on the output layer not only at the current time but also at the next moment. Some recent studies used RNN and LSTM networks to analyze PSG time series [59,72,73].…”

Section: Microarousal Detection With Rnn and Long Short-term Memory (Lstm)mentioning

confidence: 99%

“…Using all signals provided a significantly improved performance. Már Þráinsson et al [59] proposed a method with LSTM. The first hidden layer was LSTM and the second hidden layer was a dense neural network.…”

Section: Microarousal Detection With Rnn and Long Short-term Memory (Lstm)mentioning

confidence: 99%

See 2 more Smart Citations

A Review of Methods for Sleep Arousal Detection Using Polysomnographic Signals

Qian

Qiu

et al. 2021

Brain Sciences

View full text Add to dashboard Cite

Multiple types of sleep arousal account for a large proportion of the causes of sleep disorders. The detection of sleep arousals is very important for diagnosing sleep disorders and reducing the risk of further complications including heart disease and cognitive impairment. Sleep arousal scoring is manually completed by sleep experts by checking the recordings of several periods of sleep polysomnography (PSG), which is a time-consuming and tedious work. Therefore, the development of efficient, fast, and reliable automatic sleep arousal detection system from PSG may provide powerful help for clinicians. This paper reviews the automatic arousal detection methods in recent years, which are based on statistical rules and deep learning methods. For statistical detection methods, three important processes are typically involved, including preprocessing, feature extraction and classifier selection. For deep learning methods, different models are discussed by now, including convolution neural network (CNN), recurrent neural network (RNN), long-term and short-term memory neural network (LSTM), residual neural network (ResNet), and the combinations of these neural networks. The prediction results of these neural network models are close to the judgments of human experts, and these methods have shown robust generalization capabilities on different data sets. Therefore, we conclude that the deep neural network will be the main research method of automatic arousal detection in the future.

show abstract

Bidirectional LSTM with MFCC Feature Extraction for Sleep Arousal Detection in Multi-channel Signal Data

Kim

Jun

Nguyen

et al. 2019

Neural Information Processing

View full text Add to dashboard Cite

Automatic Detection of Target Regions of Respiratory Effort-Related Arousals Using Recurrent Neural Networks

Cited by 10 publications

References 14 publications

SleepNet: automated sleep analysis via dense convolutional neural network using physiological time series

SleepNet: automated sleep analysis via dense convolutional neural network using physiological time series

A Review of Methods for Sleep Arousal Detection Using Polysomnographic Signals

Bidirectional LSTM with MFCC Feature Extraction for Sleep Arousal Detection in Multi-channel Signal Data

Contact Info

Product

Resources

About