Automated system for obstructive sleep apnea detection using heart rate variability and respiratory rate variability

Prabha, Anju; Trivedi, Akta; Kumar, Aman; Kumar, C. Santhosh

doi:10.1109/icacci.2017.8126021

Cited by 25 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Detection studies generally include single or multiple physiological signals such as ECG, oxygen saturation, EEG, EMG, and airflow for diagnosis of OSA. Feature engineering is employed in many studies by analyzing time and frequency domain information and by extracting nonlinear features from PSG records [6][7][8][9][10][11]. For this purpose, research experts who have the sufficient knowledge and experience in the related field are needed however, it is hard for researchers to gain necessary field experience.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Networks based OSA Event Prediction from ECG Scalograms and Spectrograms

Nasıfoğlu

Eroğul

2021

Preprint

View full text Add to dashboard Cite

In this study, we conducted a comparative analysis of deep convolutional neural network (CNN) models in predicting Obstructive Sleep Apnea (OSA) using electrocardiograms. Unlike other studies in the literature, this study automatically extracts time-frequency features by using CNNs instead of manual feature extraction from ECG recordings. For this purpose, the proposed model generates scalogram and spectrogram representations by transforming preprocessed 30-sec ECG segments from time domain to the frequency domain using Continuous Wavelet Transform (CWT) and Short Time Fourier transform (STFT), respectively. We examined AlexNet, GoogleNet and ResNet18 models in predicting OSA events. The effect of transfer learning on success is also investigated. Based on the observed results, we proposed a new model that is found more effective in estimation. In total, 152 ECG recordings were included in the study for training and evaluation of the models. The prediction using scalograms immediately 30 seconds before potential OSA onsets gave the best performance with 82.30% accuracy, 83.22% sensitivity, 82.27% specificity and 82.95% positive predictive value. On the other hand, the prediction using spectrograms also provided up to 80.13% accuracy and 81.99% sensitivity on prediction. The results show that the proposed CNN model can be used as a good indicator to accurately predict OSA events using ECG signals.

show abstract

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Networks based OSA Event Prediction from ECG Scalograms and Spectrograms

Nasıfoğlu

Eroğul

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…At study [37], using a database collection of Department of Neurology of Amrita Institute of Medical Sciences, Kochi, and using the SVM as a classifier the best accuracy was of 80%, with a sensitivity of 60% and a specificity of 100%.…”

Section: 29%mentioning

confidence: 99%

“…At [35], the method used using Gabor filters and LS-SVM achieved an overall accuracy of 93.31%, a sensitivity of 93.05% and a specificity of 93.46%. [29] 85.07% 72.47% 83.29% [30] 87.71% 81.30% 91.70% [31] -96.00% - [32] 93.20% 94.00% 94.60% [33] 92.10% 94.30% 90.10% [34] 84.40% 90.38% 74.44% [35] 93.31% 93.50% 93.46% [36] 87.50% -- [37] 80.00% 60.00% 100.00% [38] 97.80% --This study 82.12% 88.41%…”

mentioning

confidence: 99%

Towards an accurate sleep apnea detection based on ECG signal: The quintessential of a wise feature selection

Pinho

Pombo

Silva

et al. 2019

Applied Soft Computing

View full text Add to dashboard Cite

show abstract

“…The dataset consists of the Polysomnography recordings of a total of 1,985 subjects, a part of which is shared for developing the algorithm. The dataset contains a total of 13 time-series from 6…”

Section: Datamentioning

confidence: 99%

“…These comprise asymmetry features from 5 standard frequency bands (e.g. delta, theta, alpha, beta and gamma) of the 6 EEG channels, morphological and heart rate variability features from ECG [3], visibility graph based features from ECG, EEG and Cardio-Respiratory Interaction (CRI) time-series [4,5], breathing rate variability features from Chest, Abdomen EMG and Airflow [6].…”

Section: Domain/sensor Specific Featuresmentioning

confidence: 99%

SleepTight: Identifying Sleep Arousals Using Inter and Intra-Relation of Multimodal Signals

Bhattacharjee

Das

Alam

et al. 2018

2018 Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

Sleep arousal directly affects the quality of sleep. PhysioNet Challenge 2018 aims to correctly identify designated target arousal (non-apnea arousal) and non-arousal regions from simultaneously recorded multiple biomedical signals. Our contribution lies in a feature extraction algorithm that extracts generic and domain-specific features from different biomedical signals available in the challenge provided dataset to form a composite feature vector. 50 most significant features are selected based on Minimum Redundancy Maximum Relevance scores for final classification using multiple unbiased Random Forests. The approach is designed to produce a single label for a 20-second segment containing all channels, followed by smoothing the label time-series per subject. Our algorithm yields the median Area Under Precision-Recall Curve (AUPRC) as 0.29 on 5-fold cross-validation on the training dataset. The same value of AUPRC is maintained for the test dataset as well, thereby emphasizing the stability of the proposed algorithm. This method secured the global rank of 8 during the official phase of the challenge.

show abstract

Automated system for obstructive sleep apnea detection using heart rate variability and respiratory rate variability

Cited by 25 publications

References 16 publications

Convolutional Neural Networks based OSA Event Prediction from ECG Scalograms and Spectrograms

Convolutional Neural Networks based OSA Event Prediction from ECG Scalograms and Spectrograms

Towards an accurate sleep apnea detection based on ECG signal: The quintessential of a wise feature selection

SleepTight: Identifying Sleep Arousals Using Inter and Intra-Relation of Multimodal Signals

Contact Info

Product

Resources

About