Obstructive sleep apnea classification based on spectrogram patterns in the electrocardiogram

McNames, James; Fraser, Andrew M.

doi:10.1109/cic.2000.898633

Cited by 57 publications

(45 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, detections have been developed based on questionnaires [6], snoring [7], electrocardiograph (ECG) [8]- [12], and pulse oximetry [5], [12]- [21]. Among them, ECG and saturation of oxygen measured by pulse oximeter (SpO 2 ) are the two most extensively studied signals.…”

mentioning

confidence: 99%

Real-Time Sleep Apnea Detection by Classifier Combination

Xie

Minn

2012

IEEE Trans. Inform. Technol. Biomed.

244

142

View full text Add to dashboard Cite

Abstract-To find an efficient and valid alternative of polysomnography (PSG), this paper investigates real-time sleep apnea and hypopnea syndrome (SAHS) detection based on electrocardiograph (ECG) and saturation of peripheral oxygen (SpO 2 ) signals, individually and in combination. We include ten machinelearning algorithms in our classification experiment. It is shown that our proposed SpO 2 features outperform the ECG features in terms of diagnostic ability. More importantly, we propose classifier combination to further enhance the classification performance by harnessing the complementary information provided by individual classifiers. With our selected SpO 2 and ECG features, the classifier combination using AdaBoost with Decision Stump, Bagging with REPTree, and either kNN or Decision Table achieves sensitivity, specificity, and accuracy all around 82% for a minute-based realtime SAHS detection over 25 sleep-disordered-breathing suspects' full overnight recordings.Index Terms-Classifier combination, electrocardiograph (ECG), feature selection, hypopnea, machine learning, saturation of peripheral oxygen (SpO 2 ), sleep apnea.

show abstract

mentioning

confidence: 99%

Real-Time Sleep Apnea Detection by Classifier Combination

Xie

Minn

2012

IEEE Trans. Inform. Technol. Biomed.

244

142

View full text Add to dashboard Cite

show abstract

“…Time-domain feature extraction and processing has also been considered [1], [20], [19]. The best accuracy [18] of 92.5% is nevertheless obtained by a combination of different features extracted from the frequency-domain (power spectral density and time-frequency maps) as well as from the ECG morphology (heart-rate, S-wave amplitude and pulse energy). The main drawback of this solution is that it is a manual classification and not an automatic one.…”

Section: State Of the Artmentioning

confidence: 99%

“…Feature extraction of the ECG morphology from the recordings such as the amplitude, pulse energy and duration of specific deflections present in the ECG (R, S and T waves) has also been investigated [1], [18], [19]. These characteristics are useful as complementary features to improve the classification.…”

Section: State Of the Artmentioning

confidence: 99%

“…This specific case has been considered by [18] and [1] where the reported accuracy is respectively 78.9% and 79.2% for minute-by-minute classification. Combining this with other features extracted from the ECG enabled the latter [1] to reach the score of 89.8%.…”

Section: State Of the Artmentioning

confidence: 99%

“…While the published works targeted an offline analysis using a computer/cloud system, our main contribution in this paper is to develop methods that can directly run on a mobile device. In general, latest works [1], [18], [19] analyzed the power spectrogram of heart-beat intervals series to classify patients. This is due to the presence of a notable shift on the power distribution as presented in the spectrum in shown in Fig.…”

Section: State Of the Artmentioning

confidence: 99%

See 2 more Smart Citations

Low-Power Wearable System for Real-Time Screening of Obstructive Sleep Apnea

Surrel

Rincon

Murali

et al. 2016

2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)

View full text Add to dashboard Cite

Abstract-Obstructive Sleep Apnea (OSA) is one of the main sleep disorders, but only 10% of the cases are diagnosed. Moreover, there is a lack of tools for long-term monitoring of OSA, since current systems are too bulky and intrusive to be used continuously. In this context, recent studies have shown that it is possible to detect it automatically based on singlelead ECG recordings. This approach can be used in non-invasive smart wearable sensors which measure and process bio-signals online. This work focuses on the implementation, optimization and integration of an algorithm for OSA detection for preventive health-care. It relies on a frequency-domain analysis while targeting an ultra-low power embedded wearable device. As it must share its resources usage with other computations, it must be as lightweight as possible. Our current results based on publicly available signals show a classification accuracy of up to 83.2% for both the offline analysis and the embedded online one. This system gives an even better classification accuracy than the best offline algorithm when using the same features for classification [1].

show abstract

Sleep Disorders Detection and Classification Using Random Forests Algorithm

Tareq

2024

Studies in Systems, Decision and Control

View full text Add to dashboard Cite

Obstructive sleep apnea classification based on spectrogram patterns in the electrocardiogram

Cited by 57 publications

References 2 publications

Real-Time Sleep Apnea Detection by Classifier Combination

Real-Time Sleep Apnea Detection by Classifier Combination

Low-Power Wearable System for Real-Time Screening of Obstructive Sleep Apnea

Sleep Disorders Detection and Classification Using Random Forests Algorithm

Contact Info

Product

Resources

About