Key result
Support vector machines using wavelet-based features of ECG correctly recognized obstructive sleep apnea syndrome with 92.85% accuracy (Cohen's kappa 0.85) in an independent test set.
Why the study?
Does a support vector machine model using ECG-derived features accurately recognize obstructive sleep apnea syndrome?
Does a support vector machine model using ECG-derived features accurately recognize obstructive sleep apnea syndrome?
Effect estimate: Cohen's kappa 0.85
Support vector machines using wavelet-based features from nocturnal ECG recordings can accurately identify obstructive sleep apnea syndrome, demonstrating potential as an automated screening tool.
May aid ECG-based OSA screening; leaves open prospective validation before clinical adoption.
Obstructive sleep apnea syndrome (OSAS) is associated with cardiovascular morbidity as well as excessive daytime sleepiness and poor quality of life. In this study, we apply a machine learning technique [support vector machines (SVMs)] for automated recognition of OSAS types from their nocturnal ECG recordings. A total of 125 sets of nocturnal ECG recordings acquired from normal subjects (OSAS - ) and subjects with OSAS (OSAS +), each of approximately 8 h in duration, were analyzed. Features extracted from successive wavelet coefficient levels after wavelet decomposition of signals due to heart rate variability (HRV) from RR intervals and ECG-derived respiration (EDR) from R waves of QRS amplitudes were used as inputs to the SVMs to recognize OSAS +/- subjects. Using leave-one-out technique, the maximum accuracy of classification for 83 training sets was found to be 100% for SVMs using a subset of selected combination of HRV and EDR features. Independent test results on 42 subjects showed that it correctly recognized 24 out of 26 OSAS + subjects and 15 out of 16 OSAS - subjects (accuracy = 92.85%; Cohen's kappa value of 0.85). For estimating the relative severity of OSAS, the posterior probabilities of SVM outputs were calculated and compared with respective apnea/hypopnea index. These results suggest superior performance of SVMs in OSAS recognition supported by wavelet-based features of ECG. The results demonstrate considerable potential in applying SVMs in an ECG-based screening device that can aid a sleep specialist in the initial assessment of patients with suspected OSAS.
No takes yet. Share an insight, caveat, or question.
Khandoker et al. (2008) studied Obstructive sleep apnea syndrome (OSAS) (n=125). Support vector machines (SVMs) using wavelet-based features of ECG (HRV and EDR) vs. Clinical diagnosis (OSAS +/-) was evaluated on Automated recognition of OSAS types (accuracy) (Cohen's kappa 0.85). Support vector machines using wavelet-based features of ECG correctly recognized obstructive sleep apnea syndrome with 92.85% accuracy (Cohen's kappa 0.85) in an independent test set.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: