You Snooze, You Win: The PhysioNet/Computing in Cardiology Challenge 2018

Ghassemi, Mohammad M.; Moody, Benjamin; Lehman, Li-wei H.; Song, Christopher; Li, Qiao; Sun, Haoqi; Mark, Roger G.; Westover, M. Brandon; Clifford, Gari D.

doi:10.22489/cinc.2018.049

Cited by 112 publications

(107 citation statements)

References 8 publications

Supporting

Mentioning

107

Contrasting

Order By: Relevance

“…Neural networks with a memory capability such as long short‐term memory (LSTM) and residual neural networks are very well suited to this type of data. LSTM networks have been successfully applied to PSG processing and were the enabling technology solutions to the top performing systems in the 2018 Computing in Cardiology Physionet competition of identifying non‐apnea arousals from the PSG . They have also been successfully applied to ECG and airflow signals …”

Section: Key Enablers For the Development Of Novel Analysis Methodsmentioning

confidence: 99%

“…The PTT can provide a surrogate measure of blood pressure and help identify patients with systolic pressure surges during sleep. 59,60 Combining information from the EEG, EOG, EMG, ECG and oximetry sensors was used to develop automated systems for identifying non-apnea arousals (such as respiratory event-related arousals) from the PSG 61 with the best systems achieving an area under the receiver operator curve (ROC) exceeding 0.9. This potentially broadens the use of PSG to automatically detect sleep disturbance in patients who do not have hypopneas/apneas but still have respiratory-related sleep disturbance.…”

Section: Multi-sensor Methodsmentioning

confidence: 99%

“…LSTM networks have been successfully applied to PSG processing and were the enabling technology solutions to the top performing systems in the 2018 Computing in Cardiology Physionet competition of identifying non-apnea arousals from the PSG. 61 They have also been successfully applied to ECG and airflow signals. [79][80][81]…”

Section: Machine Learningmentioning

confidence: 99%

See 2 more Smart Citations

Advanced polysomnographic analysis for OSA: A pathway to personalized management?

2019

View full text Add to dashboard Cite

Obstructive sleep apnea (OSA) is a highly heterogeneous disorder, with diverse pathways to disease, expression of disease, susceptibility to co‐morbidities and response to therapy, and is ideally suited to precision medicine approaches. Clinically, the content of the information‐rich polysomnogram (PSG) is not currently fully utilized in determining patient management. Novel PSG parameters such as hypoxic burden, pulse transit time, cardiopulmonary coupling and the frequency representations of PSG sensor signals could predict a variety of cardiovascular disease, cancer and neurodegeneration co‐morbidities. The PSG can also be used to identify key pathophysiological parameters such as loop gain, arousal threshold and muscle compensation which can enhance understanding of the causes of OSA in an individual, and thereby guide choices on therapy. Machine learning methods performing their own parameter extraction coupled with large PSG data sets offer an exciting opportunity for discovering new links between the PSG variables and disease outcomes. By exploiting existing and emerging analytical methods, the PSG may offer a pathway to personalized management for OSA.

show abstract

Section: Key Enablers For the Development Of Novel Analysis Methodsmentioning

confidence: 99%

Section: Multi-sensor Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Advanced polysomnographic analysis for OSA: A pathway to personalized management?

2019

View full text Add to dashboard Cite

show abstract

“…The PhysioNet/CinC Challenge 2018 dataset [4] was first partitioned such that 10% of the data was set aside as a Held-Out Test (HOT) set, with the other 90% was used for ten-fold cross-validation, each fold being partitioned as training (90%), validation (10%) and testing (10%).…”

Section: Dataset Preparation Phasementioning

confidence: 99%

“…In this paper, we explore the use of the Scattering Transform (ST) for feature extraction along with deep Recurrent Neural Network (RNN), especially Long Shortterm Memory (LSTM) networks to predict arousal regions in 13 PSG recordings of the Physionet/CinC Challenge2018 dataset [4]. To best of our knowledge, this is the first study that investigates how the combination of these techniques is efficient on sleep arousal recognition using multimodal time series data.…”

Section: Introductionmentioning

confidence: 99%

Sleep Arousal Detection From Polysomnography Using the Scattering Transform and Recurrent Neural Networks

Warrick¹,

Homsi²

2018

2018 Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

Sleep disorders are implicated in a growing number of health problems. In this paper, we present a signal-processing/machine learning approach to detecting arousals in the multi-channel polysomnographic recordings of the Physionet/CinC Challenge2018 dataset.Methods: Our network architecture consists of two components. Inputs were presented to a Scattering Transform (ST) representation layer which fed a recurrent neural network for sequence learning using three layers of Long Short-Term Memory (LSTM). The STs were calculated for each signal with downsampling parameters chosen to give approximately 1 s time resolution, resulting in an eighteen-fold data reduction. The LSTM layers then operated at this downsampled rate.Results: The proposed approach detected arousal regions on the 10% random sample of the hidden test set with an AUROC of 88.0% and an AUPRC of 42.1%.

show abstract

Deep convolutional architecture‐based hybrid learning for sleep arousal events detection through single‐lead EEG signals

et al. 2023

View full text Add to dashboard Cite

Introduction: Detecting arousal events during sleep is a challenging, time-consuming, and costly process that requires neurology knowledge. Even though similar automated systems detect sleep stages exclusively, early detection of sleep events can assist in identifying neuropathology progression.Methods: An efficient hybrid deep learning method to identify and evaluate arousal events is presented in this paper using only single-lead electroencephalography (EEG) signals for the first time. Using the proposed architecture, which incorporates Inception-ResNet-v2 learning transfer models and optimized support vector machine (SVM) with the radial basis function (RBF) kernel, it is possible to classify with a minimum error level of less than 8%. In addition to maintaining accuracy, the Inception module and ResNet have led to significant reductions in computational complexity for the detection of arousal events in EEG signals. Moreover, in order to improve the classification performance of the SVM, the grey wolf algorithm (GWO) has optimized its kernel parameters.Results: This method has been validated using pre-processed samples from the 2018 Challenge Physiobank sleep dataset. In addition to reducing computational complexity, the results of this method show that different parts of feature extraction and classification are effective at identifying sleep disorders. The proposed model detects sleep arousal events with an average accuracy of 93.82%. With the lead present in the identification, the method becomes less aggressive in recording people's EEG signals. Conclusion:According to this study, the suggested strategy is effective in detecting arousals in sleep disorder clinical trials and may be used in sleep disorder detection clinics.

show abstract

You Snooze, You Win: The PhysioNet/Computing in Cardiology Challenge 2018

Cited by 112 publications

References 8 publications

Advanced polysomnographic analysis for OSA: A pathway to personalized management?

Advanced polysomnographic analysis for OSA: A pathway to personalized management?

Sleep Arousal Detection From Polysomnography Using the Scattering Transform and Recurrent Neural Networks

Deep convolutional architecture‐based hybrid learning for sleep arousal events detection through single‐lead EEG signals

Contact Info

Product

Resources

About