Computer-aided obstructive sleep apnea identification using statistical features in the EMD domain and extreme learning machine. (27th April 2016)

• Record Type: Journal Article
• Authors: Hassan, Ahnaf Rashik; Haque, Mohammad Aynal
• Is Part Of: Biomedical physics & engineering express. Volume 2:Number 3(2016)
• Publication Date: 2016-04-27
• Subjects: obstructive sleep apnea -- classification -- extreme learning machine -- EMD; Medical physics -- Periodicals; Biophysics -- Periodicals; Biomedical engineering -- Periodicals; Medical sciences -- Periodicals; 610.153
• DOI: 10.1088/2057-1976/2/3/035003
• Languages: English
• ISSNs: 2057-1976

Abstract

Abstract: Automated sleep apnea identification is important in order to eradicate the clinicians duty of analyzing a large volume of data and to speed-up diagnosis. Again, the feasibility of a wearable and portable sleep quality evaluation device necessitates the use of a minimum number of leads. As a result, there is a dire need for a single-lead based apnea detection algorithm. In this work, a single-lead electrocardiogram (ECG) based computerized sleep apnea detection scheme is propounded. ECG signal segments are first decomposed using Empirical Mode Decomposition. Various statistical moment based features are then extracted. After performing statistical analysis for feature selection, sleep apnea classification is performed using a newly proposed classification model, namely- extreme learning machine. The efficacy and the discrimination capability of statistical features are evaluated. The performance of the proposed feature extraction scheme is also analyzed for various classification models. Experimental outcomes backed by statistical and graphical analyses suggest that the proposed sleep apnea detection scheme outperforms the state-of-the-art ones in terms of accuracy.