Title :
Power spectral analysis of ECG signals during obstructive sleep apnoea hypopnoea epochs
Author :
Karmakar, Chandan K. ; Khandoker, Ahsan H. ; Palaniswami, Marimuthu
Author_Institution :
Univ. of Melbourne, Melbourne
Abstract :
Based on the evidence that sympathovagal balance around apnoeas/hypopnoeas are altered in sleep apnoea patients, we utilize power spectral density (PSD) analysis to better understand the impact of obstructive sleep apnoea (OSA) and hypopnoea on RR intervals and QRS amplitudes of ECG signals. In addition, receiver operating characteristics (ROC) analysis was performed in order to test the performance the PSD features of ECG signals to recognize OSA, hypopneas and normal breathing events. Maximum area under ROC curve was found to be 0.83 for OSA-normal group in the frequency range of 0.000-0.094 cycles/interval. For OSA- hypopnoea epochs classification, PSD of QRS amplitudes was performed better than that of RR intervals. The results of the study will be useful in designing an automated classifier to recognize apnoeas/hypopnoeas/normal epochs using PSD features of ECG signals.
Keywords :
diseases; electrocardiography; medical signal processing; neurophysiology; pneumodynamics; sensitivity analysis; signal classification; sleep; spectral analysis; ECG signals; QRS amplitude value; ROC analysis; RR interval value; automated classifier; hypopnoea epochs classification; normal breathing events; obstructive sleep apnoea patients; power spectral density analysis; receiver operating characteristics analysis; sympathovagal balance; Character recognition; Electrocardiography; Frequency; Performance analysis; Performance evaluation; Signal analysis; Signal design; Sleep apnea; Spectral analysis; Testing;
Conference_Titel :
Intelligent Sensors, Sensor Networks and Information, 2007. ISSNIP 2007. 3rd International Conference on
Conference_Location :
Melbourne, Qld.
Print_ISBN :
978-1-4244-1501-4
Electronic_ISBN :
978-1-4244-1502-1
DOI :
10.1109/ISSNIP.2007.4496906
