ECG-derived Respiration Signals Research Articles

Sleep apnea detection from ECG using variational mode decomposition

Sleep apnea is a pervasive breathing problem during night sleep, and its repetitive occurrence causes various health problems. Polysomnography is commonly used for apnea screening which is an expensive, time-consuming, and complex process. In this paper, a simple but efficient technique based on the variational mode decomposition (VMD) for automated detection of sleep apnea from single-lead ECG is proposed. The heart rate variability and ECG-derived respiration signals obtained from ECG are decomposed into different modes using the VMD, and these modes are used for extracting different features including spectral entropies, interquartile range, and energy. The principal component analysis is employed to reduce the dimension of the feature vector. The experiments are conducted using the Apnea-ECG dataset, and the classification performance of various classifiers is investigated. In per-segment classification, an accuracy of about 87.5% (Sens: 84.9%, Spec: 88.2%) is achieved using the K-nearest neighbor classifier. In per-recording classification, the proposed technique using the linear discriminant analysis model outperformed the existing apnea detection approaches by achieving the accuracy of 100%. The algorithm also provided the best agreement between the estimated and reference apnea-hypopnea index (AHI) values. These results show that the algorithm has the potential to be used for home-based apnea screening systems.

A novel approach towards non-obstructive detection and classification of COPD using ECG derived respiration.

The alarming rate of mortality and disability due to Chronic Obstructive Pulmonary Disease (COPD) has become a serious health concern worldwide. The progressive nature of this disease makes it inevitable to detect this disease in its early stages, leads to a greater demand for developing non-obstructive and reliable technology for COPD detection. The use of highly patient-effort dependent, time-consuming, and expensive methods are some major inherent limitations of previous techniques. Lack of knowledge about the disease and inadequacy of proper diagnostic tool for early detection of COPD is another reason behind the 3rd leading cause of death worldwide. For this reason, this study aims to explore the utility of ECG Derived Respiration (EDR) for classification between COPD patients and normal healthy subjects as EDR can be easily extracted from ECG. ECG and respiration signals collected from 30 normal and 30 COPD subjects were analysed. Error calculation and statistical analysis were performed to observe the similarity between original respiration and EDR signal. The morphological pattern changes of respiration and EDR signals were analysed and three different features were extracted from those. Classification was performed by different classifiers employing Decision Tree, Linear Discriminant Analysis (LDA), Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). Apart from obtaining comparable classification performance it was seen that EDR has better potential than the original respiration signal for classification of COPD from normal population.

Single-channel ECG suitable for ECG-derived respiration

Electrocardiogram (ECG)-derived respiration (EDR) is a tool used for estimating respiration using ECG. EDR signals are often used to avoid the use of devices such as air flow sensors, pressure transducers. Several EDR algorithms have been proposed; however, an effective ECG channel for estimating respiration has not been studied. The aim of this study was to determine an effective ECG channel for accurately estimating respiration. Twelve novel ECG channels were placed around the lower chest, and six channels: NASA, CC5, CM1, CM2, CM4, and CM5 were used for comparison. To identify the effective ECG channels, we recorded the ECG and actual respirations in 47 subjects. The actual respiratory signals were measured using an air flow sensor and a pressure transducer. To estimate the respiration waveform, 11 EDR algorithms, including the principal component analysis, were employed. The evaluation indices used to determine the effective ECG channels were the root-mean-square percentage error (RMSPE), the correlation coefficient between the actual respiratory rates and those obtained from the estimated respiratory waveforms, and limit of agreement (LOA). A conclusive evaluation was performed based on two RMSPEs of the respiratory signals measured using the air flow sensor and pressure transducer, based on the two correlation coefficients obtained from them, and based on the LOA. The estimations were most accurate when the positive and negative electrodes were attached in a way that they could measure both the bucket-handle and pump-handle movements of the ribs and when one of the two electrodes was attached near the heart. (The channel called ALPHA in a body text yielded most accurate results: RMSPEs < 0.5, correlation coefficients > 0.8, and almost all ∣LOAs∣ 8.0.) The respiration estimated with one of the proposed ECG channels was more accurate than those with conventional ECG channels.

A RR interval based automated apnea detection approach using residual network

Background and ObjectiveApnea is one of the most common conditions that causes sleep-disorder breathing. With growing number of patients worldwide, more and more patients suffer from complications of apnea. But most of them stay untreated due to the complex and time-consuming polysomnography (PSG) diagnosis method. Effective and precise diagnosis support system using electrocardiograph (ECG) is required. In this paper, we propose an approach using residual network to detect apnea based on RR intervals (intervals between R-peaks of ECG signal). MethodsIn our model, we apply residual network to represent information carried by RR intervals. Moreover, we proposed a novel perspective, called dynamic autoregressive representation, to provide interpretation of representing the RR intervals by convolutional layers. ResultsThis approach is tested for per-segment apnea detection using publicly available dataset on Physionet. 30 overnight recordings are used for training and 5 for testing. We achieve a good result of 94.4% accuracy, 93.0% sensitivity and 94.9% specificity. This result outperform other prevalent methods based on RR intervals. This model also shows its good adaptivity while using ECG-derived respiration signal (EDR) in experiments. Its extensiveness is evaluated and compared in experiments. The proposed model is also compared with deep neural networks using original ECG signals for apnea detection, and it achieves better result using fewer input samples. ConclusionsWe develop a deep residual network to detect apnea on low-sample-rate RR intervals. The result suggests a possibility of representing RR intervals by neural network. The model showed strong adaptivity when using EDR input.

Automated detection of sleep apnea using sparse residual entropy features with various dictionaries extracted from heart rate and EDR signals

Sleep is a prominent physiological activity in our daily life. Sleep apnea is the category of sleep disorder during which the breathing of the person diminishes causing the alternation in the upper airway resistance. The electrocardiogram derived respiration (EDR) and heart rate (RR-time-series) signals are normally used for the detection of sleep apnea as these two signals capture cardio-pulmonary activity information. Hence, the analysis of these two signals provides vital information about sleep apnea. In this paper, we propose the novel sparse residual entropy (SRE) features for the automated detection of sleep apnea using EDR and heart rate signals. The features required for the automated detection of sleep apnea are extracted in three steps: (i) atomic decomposition based residual estimation from both EDR and heart rate signals using orthogonal matching pursuit (OMP) with different dictionaries, (ii) estimation of probabilities from each sparse residual, and (iii) calculation of the entropy features. The proposed SRE features are fed to the combination of fuzzy K-means clustering and support vector machine (SVM) to pick the best performing classifier. The experimental results demonstrate that the proposed SRE features with radial basis function (RBF) kernel-based SVM classifier yielded higher performance with accuracy, sensitivity and specificity values of 78.07%, 78.01%, and 78.13%, respectively with Fourier dictionary and 10-fold cross-validation. For subject-specific or leave-one-out validation case, the SVM classifier has sensitivity and specificity of 85.43% and 92.60%, respectively using SRE features with Fourier dictionary (FD).

Deep learning in the cross-time frequency domain for sleep staging from a single-lead electrocardiogram

Objective: This study classifies sleep stages from a single lead electrocardiogram (ECG) using beat detection, cardiorespiratory coupling in the time-frequency domain and a deep convolutional neural network (CNN). Approach: An ECG-derived respiration (EDR) signal and synchronous beat-to-beat heart rate variability (HRV) time series were derived from the ECG using previously described robust algorithms. A measure of cardiorespiratory coupling (CRC) was extracted by calculating the coherence and cross-spectrogram of the EDR and HRV signal in 5 min windows. A CNN was then trained to classify the sleep stages (wake, rapid-eye-movement (REM) sleep, non-REM (NREM) light sleep and NREM deep sleep) from the corresponding CRC spectrograms. A support vector machine was then used to combine the output of CNN with the other features derived from the ECG, including phase-rectified signal averaging (PRSA), sample entropy, as well as standard spectral and temporal HRV measures. The MIT-BIH Polysomnographic Database (SLPDB), the PhysioNet/Computing in Cardiology Challenge 2018 database (CinC2018) and the Sleep Heart Health Study (SHHS) database, all expert-annotated for sleep stages, were used to train and validate the algorithm. Main results: Ten-fold cross validation results showed that the proposed algorithm achieved an accuracy (Acc) of 75.4% and a Cohen’s kappa coefficient of = 0.54 on the out of sample validation data in the classification of Wake, REM, NREM light and deep sleep in SLPDB. This rose to Acc = 81.6% and = 0.63 for the classification of Wake, REM sleep and NREM sleep and Acc = 85.1% and = 0.68 for the classification of NREM sleep versus REM/wakefulness in SLPDB. Significance: The proposed ECG-based sleep stage classification approach that represents the highest reported results on non-electroencephalographic data and uses datasets over ten times larger than those in previous studies. By using a state-of-the-art QRS detector and deep learning model, the system does not require human annotation and can therefore be scaled for mass analysis.

Electrocardiogram Derived Respiratory Signal through the Segmented-Beat Modulation Method.

Respiration rate and variability are indicators of health-condition changes. In chronic disease management, it is becoming increasingly desirable to use wearable devices in order to minimize invasiveness and maximize comfort. However, not all wearable devices integrate sensors for direct acquisition of respiratory (DAR) signal. In these cases, the breathing extraction can be done through indirect methods, typically from the electrocardiogram (ECG). The aim of the present study is to propose a single-ECG-lead procedure based on the Segmented-Beat Modulation Method (SBMM) as a suitable tool for ECG-derived respiratory (EDR) signal estimation and respiration frequency (RF) identification. Clinical data consisted of combined measurements of two-lead (I and II) ECG and DAR signals from 20 healthy subjects ('CEBS' database by Physionet). Each respiration-affected ECG lead was submitted to a specifically designed SBMMbased procedure for EDR estimation by ECG subtraction. RF from EDR and DAR were identified as the frequency at which the Fourier spectrum has a maximum in the 0.07-1.00 Hz frequency range. Results indicated that mean RF values over the population from EDR signals ($0.27 \pm 0.09$ Hz and $0.27 \pm 0.09$ Hz from leads I and II, respectively) were not significantly different from that from DAR ($0.28 \pm 0.09$ Hz). Moreover, differences in RF identification ($0.01 \pm 0.03$ Hz and $0.00 \pm 0.02$ Hz from leads I and II, respectively) were, on average not significantly different from 0. Thus, SBMM-based procedure is robust and accurate for EDR estimation and RF identification.

ECG-derived respiration estimation from single-lead ECG using gaussian process and phase space reconstruction methods

Abstract Respiratory activity influences electrocardiographic measurements (ECG) in various ways. Therefore, extraction of respiratory information from ECG, namely ECG-derived respiratory (EDR), can be used as a promising noninvasive method to monitor respiration activity. In this paper, an automatic EDR extraction system using single-lead ECG is proposed. Respiration effects on ECG are categorized into two different models: additive and multiplicative based models. After selection of a proper model for each subject using a proposed criterion, gaussian process (GP) and phase space reconstruction area (PSRArea) are introduced as new methods of EDR extraction for additive and multiplicative models, respectively. We applied our algorithms on Fantasia database from Physionet, and the performance of our algorithms is assessed by comparing the EDR signals to the reference respiratory signal, using the normalized cross-correlation coefficient. The proposed method is also compared with other EDR techniques in the literature. The extracted EDRs using GP and PSRArea methods, considering their selected appropriate models, show mean correlations of 0.706 and 0.727 with reference respiration which is significantly better than most of the state-of-the-art methods. It can be seen that after selecting the model of each subject and using either PSRArea or GP (combined method), the correlation result, 0.717, is improved. Statistical significant differences (p

ECG-derived respiration based on iterated Hilbert transform and Hilbert vibration decomposition.

Monitoring of the respiration using the electrocardiogram (ECG) is desirable for the simultaneous study of cardiac activities and the respiration in the aspects of comfort, mobility, and cost of the healthcare system. This paper proposes a new approach for deriving the respiration from single-lead ECG based on the iterated Hilbert transform (IHT) and the Hilbert vibration decomposition (HVD). The ECG signal is first decomposed into the multicomponent sinusoidal signals using the IHT technique. Afterward, the lower order amplitude components obtained from the IHT are filtered using the HVD to extract the respiration information. Experiments are performed on the Fantasia and Apnea-ECG datasets. The performance of the proposed ECG-derived respiration (EDR) approach is compared with the existing techniques including the principal component analysis (PCA), R-peak amplitudes (RPA), respiratory sinus arrhythmia (RSA), slopes of the QRS complex, and R-wave angle. The proposed technique showed the higher median values of correlation (first and third quartile) for both the Fantasia and Apnea-ECG datasets as 0.699 (0.55, 0.82) and 0.57 (0.40, 0.73), respectively. Also, the proposed algorithm provided the lowest values of the mean absolute error and the average percentage error computed from the EDR and reference (recorded) respiration signals for both the Fantasia and Apnea-ECG datasets as 1.27 and 9.3%, and 1.35 and 10.2%, respectively. In the experiments performed over different age group subjects of the Fantasia dataset, the proposed algorithm provided effective results in the younger population but outperformed the existing techniques in the case of elderly subjects. The proposed EDR technique has the advantages over existing techniques in terms of the better agreement in the respiratory rates and specifically, it reduces the need for an extra step required for the detection of fiducial points in the ECG for the estimation of respiration which makes the process effective and less-complex. The above performance results obtained from two different datasets validate that the proposed approach can be used for monitoring of the respiration using single-lead ECG.

New algorithm for the estimation of the electrocardiogram derived respiration signal

Recently, ECG-derived respiration methods (EDR) have become a widely used tool in respiratory monitoring. In this paper, four new methods are presented for EDR signal estimation. The first two methods we have developed are based on ECG interval and QRS energy measurement. A wavelet transform method, based on the Mexican-Hat wavelet is also used in the present study. The final EDR signal method we have proposed is obtained by summing the first three estimated ECG-derived respiration signals. Correlation and magnitude squared coherence coefficients are used to evaluate the performance of the proposed EDR techniques. Compared to other recent works cited in the literature, the proposed algorithms allow us to achieve high estimation performances.

New algorithm for the estimation of the electrocardiogram derived respiration signal

Recently, ECG-derived respiration methods (EDR) have become a widely used tool in respiratory monitoring. In this paper, four new methods are presented for EDR signal estimation. The first two methods we have developed are based on ECG interval and QRS energy measurement. A wavelet transform method, based on the Mexican-Hat wavelet is also used in the present study. The final EDR signal method we have proposed is obtained by summing the first three estimated ECG-derived respiration signals. Correlation and magnitude squared coherence coefficients are used to evaluate the performance of the proposed EDR techniques. Compared to other recent works cited in the literature, the proposed algorithms allow us to achieve high estimation performances.

Application of intrinsic band function technique for automated detection of sleep apnea using HRV and EDR signals

Sleep apnea is the most common sleep disorder that causes respiratory, cardiac and brain diseases. The heart rate variability (HRV) and the electrocardiogram-derived respiration (EDR) signals to capture the cardio-respiratory information and the features extracted from these two signals have been used for the detection of sleep apnea. Detection of sleep apnea using the combination of HRV and EDR signals may provide more information. This paper proposes a novel method for the automated detection of sleep apnea based on the features extracted from HRV and EDR signals. The method involves the extraction of features from the intrinsic band functions (IBFs) of both EDR and HRV signals, and the classification using kernel extreme learning machine (KELM). The IBFs of HRV and EDR signals are evaluated using the Fourier decomposition method (FDM). The energy and the fuzzy entropy (FE) features are extracted from these IBFs. The kernel extreme learning machine (KELM) classifier with four kernel functions such as ‘linear’, ‘polynomial’, ‘radial basis function (RBF)’ and ‘cosine wavelet kernel’ is used for the automated detection of sleep apnea. The proposed technique yielded a sensitivity and a specificity of 78.02% and 74.64%, respectively using the public database. The method outperformed some of the reported works using HRV and EDR signals.

A principal component analysis based data fusion method for ECG-derived respiration from single-lead ECG.

An ECG-derived respiration (EDR) algorithm based on principal component analysis (PCA) is presented and applied to derive the respiratory signals from single-lead ECG. The respiratory-induced variabilities of ECG features, P-peak amplitude, Q-peak amplitude, R-peak amplitude, S-peak amplitude, T-peak amplitude and RR-interval, are fused by PCA to yield a better surrogate respiratory signal than other methods. The method is evaluated on data from the MIT-BIH polysomnographic database and validated against a "gold standard" respiratory obtained from simultaneously recorded respiration data. The performance of fusion algorithm is assessed by comparing the EDR signals to a reference respiratory signal, using the quantitative evaluation indexes that include true positive (TP), false positive (FP), false negative (FN), sensitivity (SE) and positive predictivity (PP). The statistically difference is significant among the PCA data fusion method and the EDR methods based on the RR intervals and the RS amplitudes, showing that PCA data fusion algorithm outperforms the others in the extraction of respiratory signals from single-lead ECGs.

MR-based respiratory and cardiac motion correction for PET imaging.

To develop a motion correction for Positron-Emission-Tomography (PET) using simultaneously acquired magnetic-resonance (MR) images within 90 s. A 90 s MR acquisition allows the generation of a cardiac and respiratory motion model of the body trunk. Thereafter, further diagnostic MR sequences can be recorded during the PET examination without any limitation. To provide full PET scan time coverage, a sensor fusion approach maps external motion signals (respiratory belt, ECG-derived respiration signal) to a complete surrogate signal on which the retrospective data binning is performed. A joint Compressed Sensing reconstruction and motion estimation of the subsampled data provides motion-resolved MR images (respiratory + cardiac). A 1-POINT DIXON method is applied to these MR images to derive a motion-resolved attenuation map. The motion model and the attenuation map are fed to the Customizable and Advanced Software for Tomographic Reconstruction (CASToR) PET reconstruction system in which the motion correction is incorporated. All reconstruction steps are performed online on the scanner via Gadgetron to provide a clinically feasible setup for improved general applicability. The method was evaluated on 36 patients with suspected liver or lung metastasis in terms of lesion quantification (SUVmax, SNR, contrast), delineation (FWHM, slope steepness) and diagnostic confidence level (3-point Likert-scale). A motion correction could be conducted for all patients, however, only in 30 patients moving lesions could be observed. For the examined 134 malignant lesions, an average improvement in lesion quantification of 22%, delineation of 64% and diagnostic confidence level of 23% was achieved. The proposed method provides a clinically feasible setup for respiratory and cardiac motion correction of PET data by simultaneous short-term MRI. The acquisition sequence and all reconstruction steps are publicly available to foster multi-center studies and various motion correction scenarios.

Variational Mode Extraction: A New Efficient Method to Derive Respiratory Signals from ECG.

ECG-derived respiratory (EDR) signal is an effective and inexpensive method to monitor the respiration. Previous studies have shown that the empirical mode decomposition (EMD) techniques can satisfactorily extract the EDR signal, however, their performances are degraded at the presence of noise. On the other hand, variational mode decomposition (VMD) performs good robustness against noise. In applications such as EDR extraction, where a specific mode is in interest, VMD imposes unnecessary computational cost. In this paper, we consider the extraction of EDR as a problem of obtaining a specific mode of a signal and suggest a new method named as variational mode extraction (VME). The method is established on the similar basis as VMD, with a new criterion: The residual signal after extracting the specific mode should have no or less energy at the center frequency of the mode. In this regard, VME is capable of solving the EDR problem by considering the EDR signal as a mode with approximate center frequency of zero. For verification, the respiratory rate signal is detected from EDR signal extracted by VME and compared it with those obtained by VMD, EMD-based methods, and bandpass filtering. The results confirm that the new method can extract the EDR signal with a better accuracy, while performing much lower computational cost and higher convergence rate.

A body position influence on ECG derived respiration.

An influence of a human body position on ECG derived respiration (EDR) signal is presented in the paper. Examinations were performed during deep, suspended and normal breathing for eight people in four different body positions. EDR and thoracic impedance signals were compared using correlation and standard deviation coefficients. Obtained results have shown that it is possible to monitor breath activity of people being in different position, however a precise interpretation of the obtained signal is limited.

Heart Rate and Respiratory Rate Influence on Heart Rate Variability Repeatability: Effects of the Correction for the Prevailing Heart Rate.

Background: Since heart rate variability (HRV) is associated with average heart rate (HR) and respiratory rate (RespRate), alterations in these parameters may impose changes in HRV. Hence the repeatability of HRV measurements may be affected by differences in HR and RespRate. The study aimed to evaluate HRV repeatability and its association with changes in HR and RespRate.Methods: Forty healthy volunteers underwent two ECG examinations 7 days apart. Standard HRV indices were calculated from 5-min ECG recordings. The ECG-derived respiration signal was estimated to assess RespRate. To investigate HR impact on HRV, HRV parameters were corrected for prevailing HR.Results: Differences in HRV parameters between the measurements were associated with the changes in HR and RespRate. However, in multiple regression analysis only HR alteration proved to be independent determinant of the HRV differences—every change in HR by 1 bpm changed HRV values by 16.5% on average. After overall removal of HR impact on HRV, coefficients of variation of the HRV parameters significantly dropped on average by 26.8% (p < 0.001), i.e., by the same extent HRV reproducibility improved. Additionally, the HRV correction for HR decreased association between RespRate and HRV.Conclusions: In stable conditions, HR but not RespRate is the most powerful factor determining HRV reproducibility and even a minimal change of HR may considerably alter HRV. However, the removal of HR impact may significantly improve HRV repeatability. The association between HRV and RespRate seems to be, at least in part, HR dependent.

Physiological noise correction using ECG-derived respiratory signals for enhanced mapping of spontaneous neuronal activity with simultaneous EEG-fMRI

The study of spontaneous brain activity based on BOLD-fMRI may be seriously compromised by the presence of signal fluctuations of non-neuronal origin, most prominently due to cardiac and respiratory mechanisms. Methods used for modeling and correction of the so-called physiological noise usually rely on the concurrent measurement of cardiac and respiratory signals. In simultaneous EEG-fMRI recordings, which are primarily aimed at the study of spontaneous brain activity, the electrocardiogram (ECG) is typically measured as part of the EEG setup but respiratory data are not generally available. Here, we propose to use the ECG-derived respiratory (EDR) signal estimated by Empirical Mode Decomposition (EMD) as a surrogate of the respiratory signal, for retrospective physiological noise correction of typical simultaneous EEG-fMRI data. A physiological noise model based on these physiological signals (P-PNM) complemented with fMRI-derived noise regressors was generated, and evaluated, for 17 simultaneous EEG-fMRI datasets acquired from a group of seven epilepsy patients imaged at 3T. The respiratory components of P-PNM were found to explain BOLD variance significantly in addition to the cardiac components, suggesting that the EDR signal was successfully extracted from the ECG, and P-PNM outperformed an image-based model (I-PNM) in terms of total BOLD variance explained. Further, the impact of the correction using P-PNM on fMRI mapping of patient-specific epileptic networks and the resting-state default mode network (DMN) was assessed in terms of sensitivity and specificity and, when compared with an ICA-based procedure and a standard pre-processing pipeline, P-PNM achieved the best performance. Overall, our results support the feasibility and utility of extracting physiological noise models of the BOLD signal resorting to ECG data exclusively, with substantial impact on the simultaneous EEG-fMRI mapping of resting-state networks, and, most importantly, epileptic networks where sensitivity and specificity are still limited.

A fast approximation method for principal component analysis applied to ECG derived respiration for OSA detection.

In this paper, we present an approximation method for principal component analysis (PCA) and apply it to estimating the respiration from the overnight ECG signal. The approximation method is computationally fast with low memory requirements. We compare it to a full PCA method which is applied to segments of the ECG. Features were calculated from the two ECG derived respiration signals (EDR) and classifiers trained to detect obstructive sleep apnoea (OSA). The Extreme Learning Machine and Linear Discriminant classifier were used to classify the recordings. The data from 35 overnight ECG recordings from MIT PhysioNet Apnea-ECG training database was utilized in the paper. Apnoea detection was evaluated with leave-one-record-out cross validation. The approximated PCA method obtained the highest accuracy of 76.4% by ELM classifier at fan-out 10 and accuracy of 78.4% by LDA. While, the segmented PCA achieved lower accuracies for both classifiers, 75.9% by ELM classifier and 76.6% by LDA. We conclude that the approximation method for PCA is well suited to deriving the respiration signal from overnight ECGs.

A robust approach for ECG-based analysis of cardiopulmonary coupling

Deriving respiratory signal from a surface electrocardiogram (ECG) measurement has advantage of simultaneously monitoring of cardiac and respiratory activities. ECG-based cardiopulmonary coupling (CPC) analysis estimated by heart period variability and ECG-derived respiration (EDR) shows promising applications in medical field. The aim of this paper is to provide a quantitative analysis of the ECG-based CPC, and further improve its performance. Two conventional strategies were tested to obtain EDR signal: R-S wave amplitude and area of the QRS complex. An adaptive filter was utilized to extract the common component of inter-beat interval (RRI) and EDR, generating enhanced versions of EDR signal. CPC is assessed through probing the nonlinear phase interactions between RRI series and respiratory signal. Respiratory oscillations presented in both RRI series and respiratory signals were extracted by ensemble empirical mode decomposition for coupling analysis via phase synchronization index. The results demonstrated that CPC estimated from conventional EDR series exhibits constant and proportional biases, while that estimated from enhanced EDR series is more reliable. Adaptive filtering can improve the accuracy of the ECG-based CPC estimation significantly and achieve robust CPC analysis. The improved ECG-based CPC estimation may provide additional prognostic information for both sleep medicine and autonomic function analysis.