An open-source automated algorithm for removal of noisy beats for accurate impedance cardiogram analysis

Abstract

Objective: The impedance cardiogram (ICG) is a non-invasive sensing modality for assessing the mechanical aspects of cardiac function, but is sensitive to artifacts from respiration, speaking, motion, and electrode displacement. Electrocardiogram (ECG)-synchronized ensemble averaging of ICG (conventional ensemble averaging method) partially mitigates these disturbances, as artifacts from intra-subject variability (ISVar) of ICG morphology and event latency remain. This paper describes an automated algorithm for removing noisy beats for improved artifact suppression in ensemble-averaged (EA) ICG beats. Approach: Synchronized ECG and ICG signals from 144 male subjects at rest in different psychological conditions were recorded. A 'three-stage EA ICG beat' was formed by passing 60-seconds non-overlapping ECG-synchronized ICG signals through three filtering stages. The amplitude filtering stage removed spikes/noisy beats with amplitudes outside of normal physiological ranges. Cross-correlation was applied to remove noisy beats in coarse and fine filtering stages. The accuracy of the algorithm-detected artifacts was measured with expert-identified artifacts. Agreement between the expert and the algorithm was assessed using intraclass correlation coefficients (ICC) and Bland-Altman plots. The ISVar of the cardiac parameters was evaluated to quantify improvement in these estimates provided by the proposed method. Main results: The proposed algorithm yielded an accuracy of 96.3% and high inter-rater reliability (ICC > 0.997). Bland-Altman plots showed consistently accurate results across values. The ISVar of the cardiac parameters derived using the proposed method was significantly lower than those derived via conventional ensemble averaging method (p < 0.0001). Enhancement in resolution of fiducial points and smoothing of higher-order time derivatives of the EA ICG beats were observed. Significance: The proposed algorithm provides a robust framework for removal of noisy beats and accurate estimation of ICG-based parameters. Importantly, the methodology reduced the ISVar of cardiac parameters. An open-source toolbox has been provided to enable other researchers to readily reproduce and improve upon this work.

Pulse arrival time as a surrogate of blood pressure

“…Therefore, the ICG signal has been shown to depend on haemodynamic parameters related to blood flow such as PEP 66 . As is commonly done in the literature 67 , 68 to remove the influence of high frequency noise (such as mains interference) and low frequency drift (such as respiration), the ICG signal was band-pass filtered using a 4th order IIR filter with a cut-off frequencies set at 0.5 Hz and 40 Hz. The location of the R-peaks and beat-by-beat SQI of the ECG signal were computed using the steps outlined in previous sections on PAT estimation.…”

“…Therefore, SQI was set as: The third quality metric was designed to remove beats with a significant deviation in morphology from a running window template. Sheikh et al 68 proposed an SQI based on the computation of a three-stage ensemble averaged beat, . A running window of length 30 s and step 25 s was used to construct the three-stage ensemble average.…”

ReBeatICG: Real-time Low-Complexity Beat-to-beat Impedance Cardiogram Delineation Algorithm

“…Different preprocessing and filtering methods have been proposed in literature [13], [16], which vary from simple methods such as ensemble averaging of multiple cardiac cycles [15], [22] to more advanced ones such as adaptive noise cancellation [21], [23] and wavelet analysis [24], [25]. Among them, ensemble averaging is the most commonly used method since it eliminates stochastically distributed noise as well as respiratory influences and movement artifacts [4], [9], [10]. However, averaging several cardiac cycles tends to blur less distinctive events, such as the B point, making its detection more difficult.…”

“…However, to the best of our knowledge, no real-time, low-complexity, and beat-to-beat algorithm that can be implemented on an ultra-low-power MCU has been developed yet. Most of the state-of-the-art algorithms are based on the averaging of multiple cardiac cycles technique [4], [9]- [13], which needs the beat-to-beat synchronous reference from the electrocardiogram (ECG) signal. The assemble averaging method allows the removal of movement artifacts, respiratory influences, and stochastic distributed noise, which are the main sources of noise affecting the ICG signal.…”

Validation of a new impedance cardiography analysis algorithm for clinical classification of stress states

“…The second and third filtering stages, based on cross-correlation, removed artifactcorrupted beats with a significantly different morphology from the averaged beat templates. Additional details on the description/application of CEA and TEA are available in our previous publication as referenced (Sheikh, Shah, Levantsevych, et al, 2020). The inspected beats were then collectively reviewed and noisy beats were rejected with consensus.…”