Automated Apnea Hypopnea Index from Oximetry and Spectral Analysis of Cardiopulmonary Coupling

Reference:

Ashry A, Hilmisson H, Ni Y, Thomas R. Automated Apnea Hyponea Index from oximetry and Spectral Analysis of Cardiopulmonary Coupling. Annals of the American Thoracic Society 2021; [e-publiaction ahead of print]. DOI:
10.1513/AnnalsATS.202005-510OC

Objectives:

Investigate the accuracy of an automated apnea-hypopnea index (AHI) derived from spectral analysis of cardiopulmonary coupling (CPC) extracted from the electrocardiogram, combined with oximetry signals, in relation to polysomnography.

Conclusion:

Distinct CPC-spectral bands were combined with oxygen desaturation index to create a derived apnea hypopnea index (DAHI).  Correlations statistics between the DAHI and the conventionally scored AHI3% on PSGs from the Apples Study (Trial #NCT00051363) were calculated.

Practical Significance:

DAHI has excellent and strong correlation with the conventionally scored AHI on PSGs with Perason coefficients of 0.972 and receiver operating characteristic (ROC) demonstrating strong agreement in all OSA categories: 98.5% in mild OSA [Cl95%:97.6-99.3%], 96.4% in moderate OSA [CL95%:95.3-97.5%] and 98.55 [ Cl95%: 97.8-99.2] in severe OSA.

View Publication

Automated Apnea Hypopnea Index from Oximetry and Spectral Analysis of Cardiopulmonary Coupling