Deep learning approach for ECG-based automatic sleep state classification in preterm infants

Werth, Jan; Radha, Mustafa; Andriessen, Peter; Aarts, Ronald M.; Long, Xi

doi:10.1016/j.bspc.2019.101663

Cited by 28 publications

(15 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The predictive performance of the SWB algorithm (training dataset κ = 0.38 ± 0.05, validation dataset κ = 0.24 ± 0.07) is comparable to previous work focusing on cardiorespiratory parameters. Research conducted by Werth et al [ 24 ] showed that AS and QS could be distinguished based on a CNN algorithm using HRV, with a Cohen’s kappa of κ = 0.43 ± 0.08 ( Table 3 ). Notably, the SWB algorithm was able to achieve similar performance to this method, but with less complex computations and without the need for high sampling frequency measurements that are expensive and not commonly available in NICUs.…”

Section: Discussionmentioning

confidence: 99%

“…To provide a clear view of the pros and cons of the proposed sleep–wake state classification algorithm, we compared it with seven state-of-the-art methods that were previously developed for preterm sleep staging. Werth et al [ 24 ] employed a sequential CNN model to classify AS and QS using ECG and HRV features. Koolen et al [ 18 ] trained a support vector machine (SVM) classifier with a set of EEG characteristics as input to identify AS and QS.…”

Section: Methodsmentioning

confidence: 99%

“…Until now, however, a reliable automated sleep staging model based on these parameters has not been readily available for preterm infants admitted to the NICU. A recent study conducted by Werth et al [ 24 ] employed a convolutional neural network (CNN)-based algorithm combining HR variability (HRV), ECG data, and patient information to distinguish between sleep–wake states of preterm infants, with a kappa range between 0.33 and 0.44. However, using HRV and other ECG features requires data with a high sampling rate (250–500 Hz), which is not available at most NICUs [ 28 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Sleep Well Baby project: an automated real-time sleep–wake state prediction algorithm in preterm infants

Sentner

Wang

Groot

et al. 2022

Sleep

View full text Add to dashboard Cite

Study Objectives Sleep is an important driver of early brain development. However, sleep is often disturbed in preterm infants admitted to the neonatal intensive care unit (NICU). We aimed to develop an automated algorithm based on routinely measured vital parameters to classify sleep-wake states of preterm infants in real-time at the bedside. Methods In this study, sleep-wake state observations were obtained in 1-minute epochs using a behavioral scale developed in-house while vital signs were recorded simultaneously. Three types of vital parameter data, namely, heart rate, respiratory rate, and oxygen saturation, were collected at a low-frequency sampling rate of 0.4 Hz. A supervised machine learning workflow was used to train a classifier to predict sleep-wake states. Independent training (n = 37) and validation datasets were used (n = 9). Finally, a setup was designed for real-time implementation at the bedside. Results The macro-averaged area-under-the-receiver-operator-characteristic (AUROC) of the automated sleep staging algorithm ranged between 0.69 and 0.82 for the training data, and 0.61 and 0.78 for the validation data. The algorithm provided the most accurate prediction for wake states (AUROC = 0.80). These findings were well validated on an independent sample (AUROC = 0.77). Conclusions With this study, to the best of our knowledge, a reliable, non-obtrusive, and real-time sleep staging algorithm was developed for the first time for preterm infants. Deploying this algorithm in the NICU environment may assist and adapt bedside clinical work based on infants’ sleep-wake states, potentially promoting the early brain development and well-being of preterm infants.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Sleep Well Baby project: an automated real-time sleep–wake state prediction algorithm in preterm infants

Sentner

Wang

Groot

et al. 2022

Sleep

View full text Add to dashboard Cite

show abstract

“…As a result, the two signal inputs were found to be the most advantageous with an accuracy of 92.67% and Cohen's Kappa(K) of 0.84 on two channels. Werth et al [11] proposed a model that improves the accuracy of sleep stage classification in infants by using an ECG R-peak detection algorithm. This work uses Adam optimiser to improve the learning rate and remove the learning rate decay in the model.…”

Section: Extracting Features From the Input Signalmentioning

confidence: 99%

Deep learning for sleep stages classification: modified rectified linear unit activation function and modified orthogonal weight initialisation

Bhusal

Alsadoon

Prasad

et al. 2022

Multimed Tools Appl

View full text Add to dashboard Cite

Background and AimEach stage of sleep can affect human health, and not getting enough sleep at any stage may lead to sleep disorder like parasomnia, apnea, insomnia, etc. Sleeprelated diseases could be diagnosed using Convolutional Neural Network Classifier. However, this classifier has not been successfully implemented into sleep stage classification systems due to high complexity and low accuracy of classification. The aim of this research is to increase the accuracy and reduce the learning time of Convolutional Neural Network Classifier. Methodology The proposed system used a modified Orthogonal Convolutional Neural Network and a modified Adam optimisation technique to improve the sleep stage classification accuracy and reduce the gradient saturation problem that occurs due to sigmoid activation function. The proposed system uses Leaky Rectified Linear Unit (ReLU) instead of sigmoid activation function as an activation function. Results The proposed system called Enhanced Sleep Stage Classification system (ESSC) used six different databases for training and testing the proposed model on the different sleep stages. These databases are University College Dublin database (UCD), Beth Israel Deaconess Medical Center MIT database (MIT-BIH), Sleep European Data Format (EDF), Sleep EDF Extended, Montreal Archive of Sleep Studies (MASS), and Sleep Heart Health Study (SHHS). Our results show that the gradient saturation problem does not exist anymore. The modified Adam optimiser helps to reduce the noise which in turn result in faster convergence time. Conclusion The convergence speed of ESSC is increased along with better classification accuracy compared to the state of art solution.

show abstract

“…As deep learning becomes the popular tool for specific electrocardiogram (ECG) tasks [6] such as disease detection [7,8,9,10], sleep staging [11,12], biometric human identification [13,14], and denoising [15], people start considering learning general representations of ECG using pre-training models [16,17,18,19].…”

Section: Introductionmentioning

confidence: 99%

A Simple Self-Supervised ECG Representation Learning Method via Manipulated Temporal-Spatial Reverse Detection

Zhang¹,

Geng²,

Hong³

2022

Preprint

View full text Add to dashboard Cite

Learning representations from electrocardiogram (ECG) serves as a fundamental step for many downstream machine learning-based ECG analysis tasks. However, the learning process is always restricted by lack of high-quality labeled data in reality. Existing methods addressing data deficiency either cannot provide satisfied representations for downstream tasks or require too much effort to construct similar and dissimilar pairs to learn informative representations. In this paper, we propose a straightforward but effective approach to learn ECG representations. Inspired by the temporal and spatial characteristics of ECG, we flip the original signals horizontally, vertically, and both horizontally and vertically. The learning is then done by classifying the four types of signals including the original one. To verify the effectiveness of the proposed temporal-spatial (T-S) reverse detection method, we conduct a downstream task to detect atrial fibrillation (AF) which is one of the most common ECG tasks. The results show that the ECG representations learned with our method lead to remarkable performances on the downstream task. In addition, after exploring the representational feature space and investigating which parts of the ECG signal contribute to the representations, we conclude that the temporal reverse is more effective than the spatial reverse for learning ECG representations.

show abstract

Deep learning approach for ECG-based automatic sleep state classification in preterm infants

Cited by 28 publications

References 50 publications

The Sleep Well Baby project: an automated real-time sleep–wake state prediction algorithm in preterm infants

The Sleep Well Baby project: an automated real-time sleep–wake state prediction algorithm in preterm infants

Deep learning for sleep stages classification: modified rectified linear unit activation function and modified orthogonal weight initialisation

A Simple Self-Supervised ECG Representation Learning Method via Manipulated Temporal-Spatial Reverse Detection

Contact Info

Product

Resources

About