Abstract
ternal and external 10-fold cross validation. Results: We analyzed 27,434 minutes (3599 minutes had OSA events). HRV analysis: OSA events showed higher sympathetic activity reflected by significantly higher normalized power at low frequencies (0.44 vs. 0.26), lower normalized power at high frequencies (0.51 vs. 0.70), lower mean of PP intervals (0.72 vs. 0.79), higher standard deviation of PP intervals (0.093 vs. 0.055) and higher root mean square of the difference of successive PP intervals (0.09 vs. 0.06). SpO2 characterization: Among other distinguishing parameters, OSA events had significantly greater SpO2 variability seen in higher standard deviation of SpO2 (1.33 vs. 0.56) and greater number of desaturations ≥4% from baseline (0.34 vs. 0.04) relative to Non-OSA. Spectral analysis of SpO2 showed higher normalized power at low frequencies in OSA events due to SpO2 modulation (0.81 vs. 0.45). The 10 most discriminating features were related to SpO2 modulation due to sleep apnea and HRV changes due to intermittent hypoxia. These features provided an accuracy of 81%, sensitivity of 80% and specificity of 81% identifying OSA events with a linear classifier. Conclusion: Combining SpO2 andHRV analysis enhances the detectionof OSAevents andhaspotential as an enhancedOSA screening tool. At-home screening will facilitate more natural sleep patterns with fewer disturbances, and reduce the burden to both families and the health system by screening patients prior to full PSG. Acknowledgements: This work was supported in part by The Natural Sciences and Engineering Research Council of Canada (NSERC), the Canadian Institutes of Health Research (CIHR) and the Child and Family Research Institute.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.