Multimodal Classification of Obstructive Sleep Apnea Using Feature Level Fusion

Memis, Gokhan; Sert, Mustafa

doi:10.1109/icsc.2017.87

Cited by 20 publications

(11 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fusing multiple vital signs is also advantageous in detecting apneic events. Furthermore, models exist that combine oxygen saturation with other modalities, such as ECG [23], [24], electroencephalography [25], respiratory effort and ECG [26], nasal airflow [27] or tracheal sounds [28].…”

Section: A Multisensory Fusionmentioning

confidence: 99%

Multispectral Video Fusion for Non-Contact Monitoring of Respiratory Rate and Apnea

Scebba

Poian

Karlen

2021

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Continuous monitoring of respiratory activity is desirable in many clinical applications to detect respiratory events. Non-contact monitoring of respiration can be achieved with near-and far-infrared spectrum cameras. However, current technologies are not sufficiently robust to be used in clinical applications. For example, they fail to estimate an accurate respiratory rate (RR) during apnea. We present a novel algorithm based on multispectral data fusion that aims at estimating RR also during apnea. The algorithm independently addresses the RR estimation and apnea detection tasks. Respiratory information is extracted from multiple sources and fed into an RR estimator and an apnea detector whose results are fused into a final respiratory activity estimation. We evaluated the system retrospectively using data from 30 healthy adults who performed diverse controlled breathing tasks while lying supine in a dark room and reproduced central and obstructive apneic events. Combining multiple respiratory information from multispectral cameras improved the root mean square error (RMSE) accuracy of the RR estimation from up to 4.64 monospectral data down to 1.60 breaths/min. The median F1 scores for classifying obstructive (0.75 to 0.86) and central apnea (0.75 to 0.93) also improved. Furthermore, the independent consideration of apnea detection led to a more robust system (RMSE of 4.44 vs. 7.96 breaths/min). Our findings may represent a step towards the use of cameras for vital sign monitoring in medical applications.

show abstract

Section: A Multisensory Fusionmentioning

confidence: 99%

Multispectral Video Fusion for Non-Contact Monitoring of Respiratory Rate and Apnea

Scebba

Poian

Karlen

2021

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…The table is categorised into four sections, related to different approaches analysed. By analysing algorithms, the highest accuracy was reported by [14] based on oximetry, [18] and [21] using respiration analysis, [35] based on ECG and [40] with combined approaches. Maximum sensitivity was reported by [12] and [14] using oximetry analysis and by [29] using analysis of ECG signals.…”

Section: Resultsmentioning

confidence: 99%

Developmental Strategies in Diagnosing Obstructive Sleep Apnea

Santhiya,

Ravichandran,

Yamuna

et al. 2020

IJEAT

View full text Add to dashboard Cite

A key mission in medical science is diagnosing a disease due to its criticality and accuracy in examining whether a patient is suffering from particular disease or not. Then, the most appropriate side of treatment can be decided. Obstructive Sleep Apnea (OSA) syndrome is the most widespread sleep disorder characterized by chronic episodes of reduction in the airflow or stoppage in airflow during sleep, being caused by blockage of upper airway. The intention of this review is to analyze already existing algorithms for detecting apnea all the way through usage of different sensors that have not been implemented on hardware. This study offers an exhaustive literature research value from 2003 to 2019 and setting a roadmap for bio-engineers and medical doctors thereby reducing research period and improving medical service efficiency concerning obstructive sleep apnea diagnosis.

show abstract

“…We name this situation as severity-dependent tests. We use three test scenarios [49] to evaluate the effectiveness of our method:…”

Section: Results and Evaluationsmentioning

confidence: 99%

“…We name this situation as severity-dependent tests. We use three test scenarios [49] to evaluate the effectiveness of our method:  Within Subject with Same Severity (WSwSS)  Between Subjects with Same Severity (BSwSS)  Between Subjects with Different Severity (BSwDS) For the WSwSS scenario, we use a subset of the dataset including the same subject's same severity records. We use this subset for both in training and testing phases.…”

Section: Results and Evaluationsmentioning

confidence: 99%

Obstrüktif Uyku Apnesi Tanıma için Öznitelik Seçimi

Sert

2019

Bilişim Teknolojileri Dergisi

Self Cite

View full text Add to dashboard Cite

Obstructive sleep apnea (OSA) is a kind of sleep disorder and it is described by breathing irregularity during sleep. This disorder may lead to long-term consequences, such as sleep related irregularities and/or cardiovascular diseases. This paper proposes a multimodal and feature selection-based processing pipeline to detect OSA as a computerbased alternative way to clinical polysomnography (PSG) method. In the proposed method, the oxygen saturation (SpO2) and the electrocardiogram (ECG) signals are fused at the feature-level for the classification. Five feature selection methods, namely Relieff, Chi-Square, Information Gain (IG), Principal Component Analysis (PCA), and Gain Ratio (GR) were applied to the problem to obtain robust features from both signal sources and to reduce the feature dimensionality. The effectiveness of utilized feature selection methods was analyzed using the Support Vector Machine (SVM), k-nearest neighbor (k-NN), and Naive Bayes (NB) classifiers. The experimental results on the real clinical samples from the PhysioNet dataset show that the proposed multimodal and feature selection-based method improves the classification accuracy, significantly.

show abstract

Multimodal Classification of Obstructive Sleep Apnea Using Feature Level Fusion

Cited by 20 publications

References 12 publications

Multispectral Video Fusion for Non-Contact Monitoring of Respiratory Rate and Apnea

Multispectral Video Fusion for Non-Contact Monitoring of Respiratory Rate and Apnea

Developmental Strategies in Diagnosing Obstructive Sleep Apnea

Obstrüktif Uyku Apnesi Tanıma için Öznitelik Seçimi

Contact Info

Product

Resources

About