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

Abstract

Rationale: The increased prevalence of obstructive sleep apnea (OSA) coincides with a severe shortage of sleep physicians. There is a need for widescale home-sleep-testing devices with accurate automated scoring to accelerate access to treatment.Objectives: To examine the accuracy of an automated apnea-index (AHI) derived from spectral analysis of cardiopulmonary coupling (CPC) extracted from electrocardiograms, combined with oximetry signals, in relation to polysomnograms (PSGs).Methods: Electrocardiograms and pulse-oximeter tracings on PSGs from APPLES (Apnea Positive Pressure Long-term Efficacy Study) were analyzed. Distinct CPC spectral bands were combined with the oxygen desaturation index to create a derived AHI (DAHI). Correlation statistics between the DAHI and the conventionally scored AHI, in which hypopneas required ≥50% airflow reduction alone or a lesser airflow reduction associated with ≥3% desaturation or arousal, using PSGs from APPLES were calculated.Results: A total of 833 adult subjects were included. The DAHI has excellent and strong correlation with the conventionally scored AHI on PSGs, with Pearson coefficients of 0.972 and receiver operating characteristic curves demonstrating strong agreement in all OSA categories: 98.5% in mild OSA (95% confidence interval [CI], 97.6-99.3%), 96.4% in moderate OSA (95% CI, 95.3-97.5%), and 98.5% in severe OSA (95% CI, 97.8-99.2%).Conclusions: An accurate automated AHI can be derived from oximetry and CPC.

Keywords: diagnostic equipment; medical informatics applications; obstructive sleep apnea; pattern recognition.

Figure 1.

Sample of APPLES (Apnea Positive Pressure Long-term Efficacy Study) polysomnogram analysis using cardiopulmonary coupling and the oxygen desaturation index. BPM = beats per minute; CVHR = cyclic variation of heart rate; Desats = desaturations; REM = rapid eye movement; Sp_O2 = oxygen saturation as measured by pulse oximetry; WK = wake.

Figure 2.

Scatterplot diagram showing the correlation between the DAHI obtained by SleepImage and the AHI3% in APPLES (Apnea Positive Pressure Long-term Efficacy Study). AHI3% = apnea–hypopnea index in which hypopneas required ≥50% airflow reduction alone or a lesser airflow reduction associated with ≥3% desaturation or arousal; DAHI = derived apnea–hypopnea index.

Figure 3.

ROC curve of diagnostic accuracy of the DAHI obtained by SleepImage compared with the AHI3% in APPLES (Apnea Positive Pressure Long-term Efficacy Study). AHI = apnea–hypopnea index; AHI3% = an AHI in which hypopneas required ≥50% airflow reduction alone or a lesser airflow reduction associated with ≥3% desaturation or arousal; AUC = area under the curve; DAHI = derived AHI; ROC = receiver operating characteristic.

Figure 4.

ROC curve of diagnostic accuracy of the ODI3% compared with the AHI3% in APPLES (Apnea Positive Pressure Long-term Efficacy Study). AHI = apnea–hypopnea index; AHI3% = an apnea–hypopnea index in which hypopneas required ≥50% airflow reduction alone or a lesser airflow reduction associated with ≥3% desaturation or arousal; AUC = area under the curve; CPC = cardiopulmonary coupling; ODI3% = events lasting 10 seconds or longer of ≥3% desaturation within each CPC period; ROC = receiver operating characteristic.

Figure 5.

Bland-Altman plot for level of agreement between the DAHI and AHI3%. AHI3% = an apnea–hypopnea index in which hypopneas required ≥50% airflow reduction alone or a lesser airflow reduction associated with ≥3% desaturation or arousal; APPLES = Apnea Positive Pressure Long-term Efficacy Study; DAHI = derived apnea–hypopnea index.

Figure 6.

Bland-Altman plot for level of agreement between the ODI3% and AHI3%. AHI3% = an apnea–hypopnea index in which hypopneas required ≥50% airflow reduction alone or a lesser airflow reduction associated with ≥3% desaturation or arousal; APPLES = Apnea Positive Pressure Long-term Efficacy Study; CPC = cardiopulmonary coupling; ODI3% = events lasting 10 seconds or longer of ≥3% desaturation within each CPC period.

Figure 7.

Bland-Altman plot for level of agreement between TST generated by CPC and TST on PSGs. CPC = cardiopulmonary coupling; PSG = polysomnogram; TST = total sleep time; TSTCPC = total sleep time generated by CPC; TSTPSG = total sleep time on PSGs.