Bispectral Analysis of Heart Rate Variability to Characterize and Help Diagnose Pediatric Sleep Apnea

Abstract

Pediatric obstructive sleep apnea (OSA) is a breathing disorder that alters heart rate variability (HRV) dynamics during sleep. HRV in children is commonly assessed through conventional spectral analysis. However, bispectral analysis provides both linearity and stationarity information and has not been applied to the assessment of HRV in pediatric OSA. Here, this work aimed to assess HRV using bispectral analysis in children with OSA for signal characterization and diagnostic purposes in two large pediatric databases (0–13 years). The first database (training set) was composed of 981 overnight ECG recordings obtained during polysomnography. The second database (test set) was a subset of the Childhood Adenotonsillectomy Trial database (757 children). We characterized three bispectral regions based on the classic HRV frequency ranges (very low frequency: 0–0.04 Hz; low frequency: 0.04–0.15 Hz; and high frequency: 0.15–0.40 Hz), as well as three OSA-specific frequency ranges obtained in recent studies (BW1: 0.001–0.005 Hz; BW2: 0.028–0.074 Hz; BWRes: a subject-adaptive respiratory region). In each region, up to 14 bispectral features were computed. The fast correlation-based filter was applied to the features obtained from the classic and OSA-specific regions, showing complementary information regarding OSA alterations in HRV. This information was then used to train multi-layer perceptron (MLP) neural networks aimed at automatically detecting pediatric OSA using three clinically defined severity classifiers. Both classic and OSA-specific MLP models showed high and similar accuracy (Acc) and areas under the receiver operating characteristic curve (AUCs) for moderate (classic regions: Acc = 81.0%, AUC = 0.774; OSA-specific regions: Acc = 81.0%, AUC = 0.791) and severe (classic regions: Acc = 91.7%, AUC = 0.847; OSA-specific regions: Acc = 89.3%, AUC = 0.841) OSA levels. Thus, the current findings highlight the usefulness of bispectral analysis on HRV to characterize and diagnose pediatric OSA.

Erratum: Martín-Montero et al. Bispectral Analysis of Heart Rate Variability to Characterize and Help Diagnose Pediatric Sleep Apnea. Entropy 2021, 23, 1016

“…The author wishes to make the following correction to this paper [1]. Due to missing data, five rows were added to Table 4 The Entropy Editorial Office would like to apologize for any inconvenience caused to readers by these changes.…”

Automatic analysis of overnight airflow to help in the diagnosis of pediatric obstructive sleep apnea

“…Martín-Montero et al (2020) used a spectral analysis approach to characterize the classic frequency bands of the HRV signal, as well as to define and characterize novel specific OSA-related bands in children. In a later study (Martín-Montero et al, 2021), the authors analyzed these bands using bispectral techniques, which allowed them to obtain additional information about the particularities that pediatric OSA causes in HRV.…”

“…Bispectrum is a frequency analysis method that provides information about the non-gaussianity, non-linearity, and non-stationarity of a time series (Chua et al, 2010;Zhang et al, 2000). Although these are intrinsic properties of cardiorespiratory signals such as AF (Martín-González et al, 2018), the classical spectral analysis methods ignore them since they are not capable of detecting behavioral changes or trends associated to these properties (Martín-Montero et al, 2021;Vaquerizo-Villar et al, 2018b). In contrast, bispectrum can reveal this type of alterations and is less sensitive to noise, making it a suitable analysis method for physiological signals (Atri and Mohebbi, 2015;Martín-Montero et al, 2021).…”

“…Although these are intrinsic properties of cardiorespiratory signals such as AF (Martín-González et al, 2018), the classical spectral analysis methods ignore them since they are not capable of detecting behavioral changes or trends associated to these properties (Martín-Montero et al, 2021;Vaquerizo-Villar et al, 2018b). In contrast, bispectrum can reveal this type of alterations and is less sensitive to noise, making it a suitable analysis method for physiological signals (Atri and Mohebbi, 2015;Martín-Montero et al, 2021). In addition, the signal amplitude and phase information is kept by means of this technique, which also allows us to discover interactions and phase couplings between the different signal patterns (Chua et al, 2010;Emin Tagluk and Sezgin, 2011).…”

“…Computationally, bispectrum represents the third-order cumulant of the spectral probability distribution of a signal and it can be estimated by means of the following equation (Chua et al, 2010;Martín-Montero et al, 2021):…”