Comparison of Baseline Wander Removal Techniques considering the Preservation of ST Changes in the Ischemic ECG: A Simulation Study

Advancing Fairness in Cardiac Care: Strategies for Mitigating Bias in Artificial Intelligence Models Within Cardiology

In the dynamic field of medical artificial intelligence (AI), cardiology stands out as a key area for its technological advancements and clinical application. In this review we explore the complex issue of data bias, specifically addressing those encountered during the development and implementation of AI tools in cardiology. We dissect the origins and effects of these biases, which challenge their reliability and widespread applicability in health care. Using a case study, we highlight the complexities involved in addressing these biases from a clinical viewpoint. The goal of this review is to equip researchers and clinicians with the practical knowledge needed to identify, understand, and mitigate these biases, advocating for the creation of AI solutions that are not just technologically sound, but also fair and effective for all patients.

BRAVEHEART: Open-source software for automated electrocardiographic and vectorcardiographic analysis

BACKGROUND AND OBJECTIVES

Electrocardiographic (ECG) and vectorcardiographic (VCG) analyses are used to diagnose current cardiovascular disease and for risk stratification for future adverse cardiovascular events. With increasing use of digital ECGs, research into novel ECG/VCG parameters has increased, but widespread computer-based ECG/VCG analysis is limited because there are no currently available, open-source, and easily customizable software packages designed for automated and reproducible analysis.

METHODS AND RESULTS

We present BRAVEHEART, an open-source, modular, customizable, and easy to use software package implemented in the MATLAB programming language, for scientific analysis of standard 12-lead ECGs acquired in a digital format. BRAVEHEART accepts a wide variety of digital ECG formats and provides complete and automatic ECG/VCG processing with signal denoising to remove high- and low-frequency artifact, non-dominant beat identification and removal, accurate fiducial point annotation, VCG construction, median beat construction, customizable measurements on median beats, and output of measurements and results in numeric and graphical formats.

CONCLUSIONS

The BRAVEHEART software package provides easily customizable scientific analysis of ECGs and VCGs. We hope that making BRAVEHART available will allow other researchers to further the field of ECG/VCG analysis without having to spend significant time and resources developing their own ECG/VCG analysis software and will improve the reproducibility of future studies. Source code, compiled executables, and a detailed user guide can be found at http://github.com/BIVectors/BRAVEHEART. The source code is distributed under the GNU General Public License version 3.

Adaptive Signal-to-Noise Ratio Indicator for Wearable Bioimpedance Monitoring

Bioimpedance monitoring is an increasingly important non-invasive technique for assessing physiological parameters such as body composition, hydration levels, heart rate, and breathing. However, sensor signals obtained from real-world experimental conditions invariably contain noise, which can significantly degrade the reliability of the derived quantities. Therefore, it is crucial to evaluate the quality of measured signals to ensure accurate physiological parameter values. In this study, we present a novel wrist-worn wearable device for bioimpedance monitoring, and propose a method for estimating signal quality for sensor signals obtained on the device. The method is based on the continuous wavelet transform of the measured signal, identification of wavelet ridges, and assessment of their energy weighted by the ridge duration. We validate the algorithm using a small-scale experimental study with the wearable device, and explore the effects of variables such as window size and different skin/electrode coupling agents on signal quality and repeatability. In comparison with traditional wavelet-based signal denoising, the proposed method is more adaptive and achieves a comparable signal-to-noise ratio.

SE-ResNet-ViT Hybrid Model for Noise Classification in Adhesive Patch-type Wearable Electrocardiographs

In purpose of screening arrhythmia, wearable adhesive patch-type electrocardiographs that can measure electrocardiogram continuously for 14 days have been replacing the 24-hour Holter monitor. The reason for that is the patch-type electrocardiograph being smaller and lighter than the Holter monitor, making it more convenient for patients to coexist with in their daily lives. However, this type of electrocardiograph generates a lot of noise signals due to movements during various physical activities and extended wear time.While analyzing electrocardiograms automatically using software, noise signals make the analysis difficult and they may be misclassified as arrhythmia signals. These misclassified signals require a lot of effort and time from clinical technicians to reclassify them as noise. To resolve this problem, this study hypothesized that a deep learning algorithm could be used to screen noise signals. We used 7,467 noise signals and 15,638 ECG signals collected from arrhythmia patients and healthy people. The signals were divided into 10 seconds segments and labeled by cardiologists. We split the data into training and test datasets, ensuring no patient overlap.A hybrid noise classification model, Squeeze and Excitation - Residual Network - Vision Transformer (SE-ResNet-ViT) was developed using the training and validation datasets with an 8:2 ratio. We evaluated the performance of the model using a test dataset. The best F1 score was 0.964. The proposed model can effectively screen for noise signals and potentially reducing the time and effort required by clinical technicians.

Planning, conducting, and analyzing a psychophysiological experiment on challenge and threat: A comprehensive tutorial

The biopsychosocial model of challenge and threat (BPS-CT) is a powerful framework linking psychological processes to reliable patterns of cardiovascular responses during motivated performance situations. Specifically, the BPS-CT poses challenge and threat as two motivational states that can emerge in response to a demanding, self-relevant task, where greater challenge arises when perceived resources are higher than demands, and greater threat arises when perceived resources are lower than demands. By identifying unique patterns of physiological responses associated with challenge and threat, respectively, the BPS-CT affords insight into subjective appraisals of resources and demands, and their determinants, during motivated performance situations. Despite its broad utility, lack of familiarity with physiological concepts and difficulty with identifying clear guidelines in the literature are barriers to wider uptake of this approach by behavioral researchers. Our goal is to remove these barriers by providing a comprehensive, step-by-step tutorial on conducting an experiment using the challenge and threat model, offering concrete recommendations for those who are new to the method, and serving as a centralized collection of resources for those looking to deepen their understanding. The tutorial spans five parts, covering theoretical introduction, lab setup, data collection, data analysis, and appendices offering additional details about data analysis and equipment. With this, we aim to make challenge and threat research, and the insights it offers, more accessible to researchers throughout the behavioral sciences.

An ECG Stitching Scheme for Driver Arrhythmia Classification Based on Deep Learning

This study proposes an electrocardiogram (ECG) signal stitching scheme to detect arrhythmias in drivers during driving. When the ECG is measured through the steering wheel during driving, the data are always exposed to noise caused by vehicle vibrations, bumpy road conditions, and the driver's steering wheel gripping force. The proposed scheme extracts stable ECG signals and transforms them into full 10 s ECG signals to classify arrhythmias using convolutional neural networks (CNN). Before the ECG stitching algorithm is applied, data preprocessing is performed. To extract the cycle from the collected ECG data, the R peaks are found and the TP interval segmentation is applied. An abnormal P peak is very difficult to find. Therefore, this study also introduces a P peak estimation method. Finally, 4 × 2.5 s ECG segments are collected. To classify arrhythmias with stitched ECG data, each time series' ECG signal is transformed via the continuous wavelet transform (CWT) and short-time Fourier transform (STFT), and transfer learning is performed for classification using CNNs. Finally, the parameters of the networks that provide the best performance are investigated. According to the classification accuracy, GoogleNet with the CWT image set shows the best results. The classification accuracy is 82.39% for the stitched ECG data, while it is 88.99% for the original ECG data.

Influence of Photoplethysmogram Signal Quality on Pulse Arrival Time during Polysomnography

Intervals of low-quality photoplethysmogram (PPG) signals might lead to significant inaccuracies in estimation of pulse arrival time (PAT) during polysomnography (PSG) studies. While PSG is considered to be a "gold standard" test for diagnosing obstructive sleep apnea (OSA), it also enables tracking apnea-related nocturnal blood pressure fluctuations correlated with PAT. Since the electrocardiogram (ECG) is recorded synchronously with the PPG during PSG, it makes sense to use the ECG signal for PPG signal-quality assessment. (1) Objective: to develop a PPG signal-quality assessment algorithm for robust PAT estimation, and investigate the influence of signal quality on PAT during various sleep stages and events such as OSA. (2) Approach: the proposed algorithm uses R and T waves from the ECG to determine approximate locations of PPG pulse onsets. The MESA database of 2055 PSG recordings was used for this study. (3) Results: the proportions of high-quality PPG were significantly lower in apnea-related oxygen desaturation (matched-pairs rc = 0.88 and rc = 0.97, compared to OSA and hypopnea, respectively, when p < 0.001) and arousal (rc = 0.93 and rc = 0.98, when p < 0.001) than in apnea events. The significantly large effect size of interquartile ranges of PAT distributions was between low- and high-quality PPG (p < 0.001, rc = 0.98), and regular and irregular pulse waves (p < 0.001, rc = 0.74), whereas a lower quality of the PPG signal was found to be associated with a higher interquartile range of PAT across all subjects. Suggested PPG signal quality-based PAT evaluation reduced deviations (e.g., rc = 0.97, rc = 0.97, rc = 0.99 in hypopnea, oxygen desaturation, and arousal stages, respectively, when p < 0.001) and allowed obtaining statistically larger differences between different sleep stages and events. (4) Significance: the implemented algorithm has the potential to increase the robustness of PAT estimation in PSG studies related to nocturnal blood pressure monitoring.

Diagnostic quality assessment for low-dimensional ECG representations

There have been several attempts to quantify the diagnostic distortion caused by algorithms that perform low-dimensional electrocardiogram (ECG) representation. However, there is no universally accepted quantitative measure that allows the diagnostic distortion arising from denoising, compression, and ECG beat representation algorithms to be determined. Hence, the main objective of this work was to develop a framework to enable biomedical engineers to efficiently and reliably assess diagnostic distortion resulting from ECG processing algorithms. We propose a semiautomatic framework for quantifying the diagnostic resemblance between original and denoised/reconstructed ECGs. Evaluation of the ECG must be done manually, but is kept simple and does not require medical training. In a case study, we quantified the agreement between raw and reconstructed (denoised) ECG recordings by means of kappa-based statistical tests. The proposed methodology takes into account that the observers may agree by chance alone. Consequently, for the case study, our statistical analysis reports the "true", beyond-chance agreement in contrast to other, less robust measures, such as simple percent agreement calculations. Our framework allows efficient assessment of clinically important diagnostic distortion, a potential side effect of ECG (pre-)processing algorithms. Accurate quantification of a possible diagnostic loss is critical to any subsequent ECG signal analysis, for instance, the detection of ischemic ST episodes in long-term ECG recordings.

Feature Selection Techniques for a Machine Learning Model to Detect Autonomic Dysreflexia

Feature selection plays a crucial role in the development of machine learning algorithms. Understanding the impact of the features on a model, and their physiological relevance can improve the performance. This is particularly helpful in the healthcare domain wherein disease states need to be identified with relatively small quantities of data. Autonomic Dysreflexia (AD) is one such example, wherein mismanagement of this neurological condition could lead to severe consequences for individuals with spinal cord injuries. We explore different methods of feature selection needed to improve the performance of a machine learning model in the detection of the onset of AD. We present different techniques used as well as the ideal metrics using a dataset of thirty-six features extracted from electrocardiograms, skin nerve activity, blood pressure and temperature. The best performing algorithm was a 5-layer neural network with five relevant features, which resulted in 93.4% accuracy in the detection of AD. The techniques in this paper can be applied to a myriad of healthcare datasets allowing forays into deeper exploration and improved machine learning model development. Through critical feature selection, it is possible to design better machine learning algorithms for detection of niche disease states using smaller datasets.

Channel-Wise Average Pooling and 1D Pixel-Shuffle Denoising Autoencoder for Electrode Motion Artifact Removal in ECG

This paper presents a channel-wise average pooling and one dimension pixel-shuffle architecture for a denoising autoencoder (CPDAE) design that can be applied to efficiently remove electrode motion (EM) artifacts in an electrocardiogram (ECG) signal. The three advantages of the proposed design are as follows: (1) In the skip connection layer, less memory is needed to transfer the features extracted by the neural network; (2) Pixel shuffle and pixel unshuffle techniques with point-wise convolution are used to effectively reserve the key features generated from each layer in both the encoder and decoder; (3) Overall, fewer parameters are required to reconstruct the ECG signal. This paper describes three deep neural network models, namely CPDAELite, CPDAERegular, and CPDAEFull, which support various computational capacity and hardware arrangements. The three proposed structures involve an encoder and decoder with six, seven, and eight layers, respectively. Furthermore, the CPDAELite, CPDAERegular, and CPDAEFull structures require fewer multiply-accumulate operations—355.01, 56.96, and 14.69 million, respectively—and less parameter usage—2.69 million, 149.7 thousand, and 55.5 thousand, respectively. To evaluate the denoising performance, the MIT–BIH noise stress test database containing six signal-to-noise ratios (SNRs) of noisy ECGs was employed. The results demonstrated that the proposed models had a higher improvement of SNR and lower percentage root-mean-square difference than other state-of-the-art methods under various conditions of SNR.

Parylene C-Based, Breathable Tattoo Electrodes for High-Quality Bio-Potential Measurements

A breathable tattoo electrode for bio-potential recording based on a Parylene C nanofilm is presented in this study. The proposed approach allows for the fabrication of micro-perforated epidermal submicrometer-thick electrodes that conjugate the unobtrusiveness of Parylene C nanofilms and the very important feature of breathability. The electrodes were fully validated for electrocardiography (ECG) measurements showing performance comparable to that of conventional disposable gelled Ag/AgCl electrodes, with no visible negative effect on the skin even many hours after their application. This result introduces interesting perspectives in the field of epidermal electronics, particularly in applications where critical on-body measurements are involved.

Weak Supervision for Affordable Modeling of Electrocardiogram Data

Analysing electrocardiograms (ECGs) is an inexpensive and non-invasive, yet powerful way to diagnose heart disease. ECG studies using Machine Learning to automatically detect abnormal heartbeats so far depend on large, manually annotated datasets. While collecting vast amounts of unlabeled data can be straightforward, the point-by-point annotation of abnormal heartbeats is tedious and expensive. We explore the use of multiple weak supervision sources to learn diagnostic models of abnormal heartbeats via human designed heuristics, without using ground truth labels on individual data points. Our work is among the first to define weak supervision sources directly on time series data. Results show that with as few as six intuitive time series heuristics, we are able to infer high quality probabilistic label estimates for over 100,000 heartbeats with little human effort, and use the estimated labels to train competitive classifiers evaluated on held out test data.

Self-supervised representation learning from 12-lead ECG data

Clinical 12-lead electrocardiography (ECG) is one of the most widely encountered kinds of biosignals. Despite the increased availability of public ECG datasets, label scarcity remains a central challenge in the field. Self-supervised learning represents a promising way to alleviate this issue. This would allow to train more powerful models given the same amount of labeled data and to incorporate or improve predictions about rare diseases, for which training datasets are inherently limited. In this work, we put forward the first comprehensive assessment of self-supervised representation learning from clinical 12-lead ECG data. To this end, we adapt state-of-the-art self-supervised methods based on instance discrimination and latent forecasting to the ECG domain. In a first step, we learn contrastive representations and evaluate their quality based on linear evaluation performance on a recently established, comprehensive, clinical ECG classification task. In a second step, we analyze the impact of self-supervised pretraining on finetuned ECG classifiers as compared to purely supervised performance. For the best-performing method, an adaptation of contrastive predictive coding, we find a linear evaluation performance only 0.5% below supervised performance. For the finetuned models, we find improvements in downstream performance of roughly 1% compared to supervised performance, label efficiency, as well as robustness against physiological noise. This work clearly establishes the feasibility of extracting discriminative representations from ECG data via self-supervised learning and the numerous advantages when finetuning such representations on downstream tasks as compared to purely supervised training. As first comprehensive assessment of its kind in the ECG domain carried out exclusively on publicly available datasets, we hope to establish a first step towards reproducible progress in the rapidly evolving field of representation learning for biosignals.

Robustness of convolutional neural networks to physiological electrocardiogram noise

The electrocardiogram (ECG) is a widespread diagnostic tool in healthcare and supports the diagnosis of cardiovascular disorders. Deep learning methods are a successful and popular technique to detect indications of disorders from an ECG signal. However, there are open questions around the robustness of these methods to various factors, including physiological ECG noise. In this study, we generate clean and noisy versions of an ECG dataset before applying symmetric projection attractor reconstruction (SPAR) and scalogram image transformations. A convolutional neural network is used to classify these image transforms. For the clean ECG dataset, F1 scores for SPAR attractor and scalogram transforms were 0.70 and 0.79, respectively. Scores decreased by less than 0.05 for the noisy ECG datasets. Notably, when the network trained on clean data was used to classify the noisy datasets, performance decreases of up to 0.18 in F1 scores were seen. However, when the network trained on the noisy data was used to classify the clean dataset, the decrease was less than 0.05. We conclude that physiological ECG noise impacts classification using deep learning methods and careful consideration should be given to the inclusion of noisy ECG signals in the training data when developing supervised networks for ECG classification. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'.

Deep Learning-Based Data-Point Precise R-Peak Detection in Single-Lead Electrocardiograms

Low-cost wearables with capability to record electrocardiograms (ECG) are becoming increasingly available. These wearables typically acquire single-lead ECGs that are mainly used for screening of cardiac arrhythmias such as atrial fibrillation. Most arrhythmias are characteruzed by changes in the RR-interval, hence automatic methods to diagnose arrythmia may utilize R-peak detection. Existing R-peak detection methods are fairly accurate but have limited precision. To enable data-point precise detection of R-peaks, we propose a method that uses a fully convolutional dilated neural network. The network is trained and evaluated with manually annotated R-peaks in a heterogeneous set of ECGs that contain a wide range of cardiac rhythms and acquisition noise. 700 randomly chosen ECGs from the PhysioNet/CinC challenge 2017 were used for training (n=500), validation (n=100) and testing (n=100). The network achieves a precision of 0.910, recall of 0.926, and an F1-score of 0.918 on the test set. Our data-point precise R-peak detector may be important step towards fully automatic cardiac arrhythmia detection.Clinical relevance- This method enables data-point precise detection of R-peaks that provides a basis for detection and characterization of arrhythmias.

Stationary wavelet transform based ECG signal denoising method

Electrocardiogram (ECG) signals are used to diagnose cardiovascular diseases. During ECG signal acquisition, various noises like power line interference, baseline wandering, motion artifacts, and electromyogram noise corrupt the ECG signal. As an ECG signal is non-stationary, removing these noises from the recorded ECG signal is quite tricky. In this paper, along with the proposed denoising technique using stationary wavelet transform, various denoising techniques like lowpass filtering, highpass filtering, empirical mode decomposition, Fourier decomposition method, discrete wavelet transform are studied to denoise an ECG signal corrupted with noise. Signal-to-noise ratio, percentage root-mean-square difference, and root mean square error are used to compare the ECG signal denoising performance. The experimental result showed that the proposed stationary wavelet transform based ECG denoising technique outperformed the other ECG denoising techniques as more ECG signal components are preserved than other denoising algorithms.

Inter-Patient Atrial Flutter Classification Using FFT-Based Features and a Low-Variance Stacking Classifier

OBJECTIVE

Atrial Flutter (AFL) is a supraventricular tachyarrhythmia typically arising from a macroreentry circuit that can have variable atrial anatomy. It is often treated by catheter ablation, the success of which depends upon the correct determination of the electroanatomic circuit, generally through invasive electrophysiological (EP) study. We hypothesized that machine learning (ML) methods applied to the diagnostic 12-lead surface electrocardiogram (ECG) could determine the specific circuit prior to any invasive EP study.

METHODS

The 12-lead ECGs were reduced to eight independent leads: I, II, V1 V6. Through an algorithm using ventricular complex cancellation methods, windows of atrial activity in the ECG were uncovered and spectra were generated. Three ML classifier approaches were applied: Support Vector Machine (SVM), Random Forest (RF) and k-Nearest Neighbors (KNN), and their outputs combined using soft voting.

RESULTS

Ten-second surface ECGs taken from 419 AFL patients prior to invasive EP study and ablation were analyzed retrospectively. Of the 419 patients, 285 had typical cavotricuspid isthmus (CTI)-dependent AFL, 41 had atypical right-atrial AFL and 93 had left-atrial AFL, as determined during the subsequent EP study. Lead V5 was found to be most useful giving a test accuracy of 98\% and f1 score of 0.97.

CONCLUSION

We conclude that ML methods have the potential to automatically determine the AFL macroreentry circuit from the surface ECG.

SIGNIFICANCE

The AFL classification method presented in this investigation achieves 95+\% accuracy on an unbalanced inter-patient dataset which has important clinical applications.

Transit Time Measurement in Indicator Dilution Curves: Overcoming the Missing Ground Truth and Quantifying the Error

The vascular function of a vessel can be qualitatively and intraoperatively checked by recording the blood dynamics inside the vessel via fluorescence angiography (FA). Although FA is the state of the art in proving the existence of blood flow during interventions such as bypass surgery, it still lacks a quantitative blood flow measurement that could decrease the recurrence rate and postsurgical mortality. Previous approaches show that the measured flow has a significant deviation compared to the gold standard reference (ultrasonic flow meter). In order to systematically address the possible sources of error, we investigated the error in transit time measurement of an indicator. Obtaining in vivo indicator dilution curves with a known ground truth is complex and often not possible. Further, the error in transit time measurement should be quantified and reduced. To tackle both issues, we first computed many diverse indicator dilution curves using an in silico simulation of the indicator's flow. Second, we post-processed these curves to mimic measured signals. Finally, we fitted mathematical models (parabola, gamma variate, local density random walk, and mono-exponential model) to re-continualize the obtained discrete indicator dilution curves and calculate the time delay of two analytical functions. This re-continualization showed an increase in the temporal accuracy up to a sub-sample accuracy. Thereby, the Local Density Random Walk (LDRW) model performed best using the cross-correlation of the first derivative of both indicator curves with a cutting of the data at 40% of the peak intensity. The error in frames depends on the noise level and is for a signal-to-noise ratio (SNR) of 20 dB and a sampling rate of f_s = 60 Hz at fs-1·0.25(±0.18), so this error is smaller than the distance between two consecutive samples. The accurate determination of the transit time and the quantification of the error allow the calculation of the error propagation onto the flow measurement. Both can assist surgeons as an intraoperative quality check and thereby reduce the recurrence rate and post-surgical mortality.

CVAR-Seg: An Automated Signal Segmentation Pipeline for Conduction Velocity and Amplitude Restitution

BACKGROUND

Rate-varying S1S2 stimulation protocols can be used for restitution studies to characterize atrial substrate, ionic remodeling, and atrial fibrillation risk. Clinical restitution studies with numerous patients create large amounts of these data. Thus, an automated pipeline to evaluate clinically acquired S1S2 stimulation protocol data necessitates consistent, robust, reproducible, and precise evaluation of local activation times, electrogram amplitude, and conduction velocity. Here, we present the CVAR-Seg pipeline, developed focusing on three challenges: (i) No previous knowledge of the stimulation parameters is available, thus, arbitrary protocols are supported. (ii) The pipeline remains robust under different noise conditions. (iii) The pipeline supports segmentation of atrial activities in close temporal proximity to the stimulation artifact, which is challenging due to larger amplitude and slope of the stimulus compared to the atrial activity.

METHODS AND RESULTS

The S1 basic cycle length was estimated by time interval detection. Stimulation time windows were segmented by detecting synchronous peaks in different channels surpassing an amplitude threshold and identifying time intervals between detected stimuli. Elimination of the stimulation artifact by a matched filter allowed detection of local activation times in temporal proximity. A non-linear signal energy operator was used to segment periods of atrial activity. Geodesic and Euclidean inter electrode distances allowed approximation of conduction velocity. The automatic segmentation performance of the CVAR-Seg pipeline was evaluated on 37 synthetic datasets with decreasing signal-to-noise ratios. Noise was modeled by reconstructing the frequency spectrum of clinical noise. The pipeline retained a median local activation time error below a single sample (1 ms) for signal-to-noise ratios as low as 0 dB representing a high clinical noise level. As a proof of concept, the pipeline was tested on a CARTO case of a paroxysmal atrial fibrillation patient and yielded plausible restitution curves for conduction speed and amplitude.

CONCLUSION

The proposed openly available CVAR-Seg pipeline promises fast, fully automated, robust, and accurate evaluations of atrial signals even with low signal-to-noise ratios. This is achieved by solving the proximity problem of stimulation and atrial activity to enable standardized evaluation without introducing human bias for large data sets.

Non-Invasive and Quantitative Estimation of Left Atrial Fibrosis Based on P Waves of the 12-Lead ECG-A Large-Scale Computational Study Covering Anatomical Variability

The arrhythmogenesis of atrial fibrillation is associated with the presence of fibrotic atrial tissue. Not only fibrosis but also physiological anatomical variability of the atria and the thorax reflect in altered morphology of the P wave in the 12-lead electrocardiogram (ECG). Distinguishing between the effects on the P wave induced by local atrial substrate changes and those caused by healthy anatomical variations is important to gauge the potential of the 12-lead ECG as a non-invasive and cost-effective tool for the early detection of fibrotic atrial cardiomyopathy to stratify atrial fibrillation propensity. In this work, we realized 54,000 combinations of different atria and thorax geometries from statistical shape models capturing anatomical variability in the general population. For each atrial model, 10 different volume fractions (0-45%) were defined as fibrotic. Electrophysiological simulations in sinus rhythm were conducted for each model combination and the respective 12-lead ECGs were computed. P wave features (duration, amplitude, dispersion, terminal force in V1) were extracted and compared between the healthy and the diseased model cohorts. All investigated feature values systematically in- or decreased with the left atrial volume fraction covered by fibrotic tissue, however value ranges overlapped between the healthy and the diseased cohort. Using all extracted P wave features as input values, the amount of the fibrotic left atrial volume fraction was estimated by a neural network with an absolute root mean square error of 8.78%. Our simulation results suggest that although all investigated P wave features highly vary for different anatomical properties, the combination of these features can contribute to non-invasively estimate the volume fraction of atrial fibrosis using ECG-based machine learning approaches.

An Automated High-Accuracy Detection Scheme for Myocardial Ischemia Based on Multi-Lead Long-Interval ECG and Choi-Williams Time-Frequency Analysis Incorporating a Multi-Class SVM Classifier

Cardiovascular Disease (CVD) is a primary cause of heart problems such as angina and myocardial ischemia. The detection of the stage of CVD is vital for the prevention of medical complications related to the heart, as they can lead to heart muscle death (known as myocardial infarction). The electrocardiogram (ECG) reflects these cardiac condition changes as electrical signals. However, an accurate interpretation of these waveforms still calls for the expertise of an experienced cardiologist. Several algorithms have been developed to overcome issues in this area. In this study, a new scheme for myocardial ischemia detection with multi-lead long-interval ECG is proposed. This scheme involves an observation of the changes in ischemic-related ECG components (ST segment and PR segment) by way of the Choi-Williams time-frequency distribution to extract ST and PR features. These extracted features are mapped to a multi-class SVM classifier for training in the detection of unknown conditions to determine if they are normal or ischemic. The use of multi-lead ECG for classification and 1 min intervals instead of beats or frames contributes to improved detection performance. The classification process uses the data of 92 normal and 266 patients from four different databases. The proposed scheme delivered an overall result with 99.09% accuracy, 99.49% sensitivity, and 98.44% specificity. The high degree of classification accuracy for the different and unknown data sources used in this study reflects the flexibility, validity, and reliability of this proposed scheme. Additionally, this scheme can assist cardiologists in detecting signal abnormality with robustness and precision, and can even be used for home screening systems to provide rapid evaluation in emergency cases.

An epoch based methodology to denoise magnetocardiogram (MCG) signals and its application to measurements on subjects with implanted devices

Magnetocardiograms (MCG) provide clinically useful diagnostic information in a variety of cardiac dysfunctions. Low frequency baseline drifts and high frequency noise are inevitably present in routine MCG even for those measured inside magnetically shielded rooms. These interferences sometimes exceed subtle cardiac features in MCG recorded on subjects with implanted devices like cardiac pacemakers; this makes interpretation of cardiac magnetic fields difficult. The present study proposes a correlation-based beat-by-beat approach and principal component analysis to eliminate drifts and high frequency noise respectively; the approach is suitable for denoising both single and multi-channel MCG data. The methodology is critically evaluated on simulated noisy measurements using a 37 channel MCG system, when objects such as implantable permanent pacemaker and stainless-steel wire are sequentially kept externally on the chests of five healthy subjects. By characterizing the noise introduced by each of these objects, the deterioration in the quality of MCG and its subsequent restoration by using the proposed method is assessed. The performance of the proposed method is also compared with other conventional denoising techniques namely, bandpass filters, wavelets and ensemble empirical mode decomposition. The proposed method not only exhibits least distortion, but also preserves the beat-by-beat dynamics of cardiac time series. The method has also been illustrated on actual MCG measurements on two subjects with implanted pacemaker which highlight the ability of the proposed method for denoising MCG in general and during extremely noisy measurement situations. Keywords: Magnetocardiography (MCG), pacemaker, baseline correction, PCA.

ECG Beat Representation and Delineation by Means of Variable Projection

OBJECTIVE

The electrocardiogram (ECG) follows a characteristic shape, which has led to the development of several mathematical models for extracting clinically important information. Our main objective is to resolve limitations of previous approaches, that means to simultaneously cope with various noise sources, perform exact beat segmentation, and to retain diagnostically important morphological information.

METHODS

We therefore propose a model that is based on Hermite and sigmoid functions combined with piecewise polynomial interpolation for exact segmentation and low-dimensional representation of individual ECG beat segments. Hermite and sigmoidal functions enable reliable extraction of important ECG waveform information while the piecewise polynomial interpolation captures noisy signal features like the baseline wander (BLW). For that we use variable projection, which allows the separation of linear and nonlinear morphological variations of the according ECG waveforms. The resulting ECG model simultaneously performs BLW cancellation, beat segmentation, and low-dimensional waveform representation.

RESULTS

We demonstrate its BLW denoising and segmentation performance in two experiments, using synthetic and real data. Compared to state-of-the-art algorithms, the experiments showed less diagnostic distortion in case of denoising and a more robust delineation for the P and T wave.

CONCLUSION

This work suggests a novel concept for ECG beat representation, easily adaptable to other biomedical signals with similar shape characteristics, such as blood pressure and evoked potentials.

SIGNIFICANCE

Our method is able to capture linear and nonlinear wave shape changes. Therefore, it provides a novel methodology to understand the origin of morphological variations caused, for instance, by respiration, medication, and abnormalities.

Fall Detection from Electrocardiogram (ECG) Signals and Classification by Deep Transfer Learning

Fall is a prominent issue due to its severe consequences both physically and mentally. Fall detection and prevention is a critical area of research because it can help elderly people to depend less on caregivers and allow them to live and move more independently. Using electrocardiograms (ECG) signals independently for fall detection and activity classification is a novel approach used in this paper. An algorithm has been proposed which uses pre-trained convolutional neural networks AlexNet and GoogLeNet as a classifier between the fall and no fall scenarios using electrocardiogram signals. The ECGs for both falling and no falling cases were obtained as part of the study using eight volunteers. The signals are pre-processed using an elliptical filter for signal noises such as baseline wander and power-line interface. As feature extractors, frequency-time representations (scalograms) were obtained by applying a continuous wavelet transform on the filtered ECG signals. These scalograms were used as inputs to the neural network and a significant validation accuracy of 98.08% was achieved in the first model. The trained model is able to distinguish ECGs with a fall activity from an ECG with a no fall activity with an accuracy of 98.02%. For the verification of the robustness of the proposed algorithm, our experimental dataset was augmented by adding two different publicly available datasets to it. The second model can classify fall, daily activities and no activities with an accuracy of 98.44%. These models were developed by transfer learning from the domain of real images to the medical images. In comparison to traditional deep learning approaches, the transfer learning not only avoids “reinventing the wheel,” but also presents a lightweight solution to otherwise computationally heavy problems.

Comparing different wavelet transforms on removing electrocardiogram baseline wanders and special trends

Background

Electrocardiogram (ECG) signal, an important indicator for heart problems, is commonly corrupted by a low-frequency baseline wander (BW) artifact, which may cause interpretation difficulty or inaccurate analysis. Unlike current state-of-the-art approach using band-pass filters, wavelet transforms can accurately capture both time and frequency information of a signal. However, extant literature is limited in applying wavelet transforms (WTs) for baseline wander removal. In this study, we aimed to evaluate 5 wavelet families with a total of 14 wavelets for removing ECG baseline wanders from a semi-synthetic dataset.

Methods

We created a semi-synthetic ECG dataset based on a public QT Database on Physionet repository with ECG data from 105 patients. The semi-synthetic ECG dataset comprised ECG excerpts from the QT database superimposed with artificial baseline wanders. We extracted one ECG excerpt from each of 105 patients, and the ECG excerpt comprised 14 s of randomly selected ECG data. Twelve baseline wanders were manually generated, including sinusoidal waves, spikes and step functions. We implemented and evaluated 14 commonly used wavelets up to 12 WT levels. The evaluation metric was mean-square-error (MSE) between the original ECG excerpt and the processed signal with artificial BW removed.

Results

Among the 14 wavelets, Daubechies-3 wavelet and Symlets-3 wavelet with 7 levels of WT had best performance, MSE = 0.0044. The average MSEs for sinusoidal waves, step, and spike functions were 0.0271, 0.0304, 0.0199 respectively. For artificial baseline wanders with spikes or step functions, wavelet transforms in general had lower performance in removing the BW; however, WTs accurately located the temporal position of an impulse edge.

Conclusions

We found wavelet transforms in general accurately removed various baseline wanders. Daubechies-3 and Symlets-3 wavelets performed best. The study could facilitate future real-time processing of streaming ECG signals for clinical decision support systems.

A comparative study of photoplethysmogram and piezoelectric plethysmogram signals

The Photoplethysmogram (PPG) signal is one of the most important vital signals in biomedical applications. The non-invasive property and the convenience in the acquisition of both PPG and Piezoelectric Plethysmogram (PZPG) signals are considered as powerful and accurate tools for biomedical diagnosing applications, such as oxygen saturation in blood, blood flow, and blood pressure measurements. In this paper, a number of features for PPG and PZPG signals (ex. first derivative, second derivative, area under the curve and the ratio of systolic area to the diastolic area) are acquired and compared. The results show that both systems are able to extract the pulse rate (PR) and pulse rate variability (PRV), accurately with an estimation error of less than 10%. The averaged standard deviation of the ratio of the systolic area to the diastolic area for the first derivative of PPG and PZPG signals was small with less than 0.49 and 0.69 for the PPG and PZPG, respectively. Statistical analysis techniques (such as cross-correlation, P-value test, and Bland Altman method) are performed to address the relation between the PPG and PZPG signals. All of these methods showed a strong relationship between the features of the two signals (i.e. PPG and PZPG). The correlation value is found to be 0.954 with a p-value of < 0.05. This opens possibilities for combining both the PPG and PZPG systems to extract more features that can be used in diagnosing cardiovascular diseases. Such a system can provide a possibility to reduce the number of devices connected to patients (especially in emergencies) by means of measuring simultaneously both signals (PZPG and PPG).

Spectral trimming technique: a new approach for suppressing motion artefacts in stress electrocardiography

Motion artefacts in electrocardiographic (ECG) signal are suppressed mainly by adaptive noise cancellation and wavelet denoising. While the former requires a motion sensor in addition to ECG electrodes, the latter removes some of the desired low-frequency components in the signal. In this paper spectral trimming technique is being introduced for suppressing the motion artefacts in stress electrocardiography. In this method, Fourier spectral coefficients up to 1.221 Hz of noisy signal are trimmed on the basis of template derived from resting ECG signal in the same subject. The proposed spectral trimming technique has yielded the lowest value of mean ± standard deviation for root mean square error (18.92 ± 8.71) and highest value of the signal to noise ratio (6.439 ± 4.266) as compared to other three methods, namely adaptive noise cancellation, wavelet decomposition and adaptive line enhancement with compatible value of correlation coefficient. Subsequently, spectral trimming technique has been implemented in real-time (deferred by 8.2 s) application for stress electrocardiography. Spectral trimming technique thus offers a method of choice for motion artefact suppression in offline as well as deferred online applications. This method takes care of the limitations of conventional methods such as adaptive noise cancellation or wavelet denoising for suppressing motion artefacts in stress electrocardiography.

Deep learning for comprehensive ECG annotation

BACKGROUND

Increasing utilization of long-term outpatient ambulatory electrocardiographic (ECG) monitoring continues to drive the need for improved ECG interpretation algorithms.

OBJECTIVE

The purpose of this study was to describe the BeatLogic® platform for ECG interpretation and to validate the platform using electrophysiologist-adjudicated real-world data and publicly available validation data.

METHODS

Deep learning models were trained to perform beat and rhythm detection/classification using ECGs collected with the Preventice BodyGuardian® Heart monitor. Training annotations were created by certified ECG technicians, and validation annotations were adjudicated by a team of board-certified electrophysiologists. Deep learning model classification results were used to generate contiguous annotation results, and performance was assessed in accordance with the EC57 standard.

RESULTS

On the real-world validation dataset, BeatLogic beat detection sensitivity and positive predictive value were 99.84% and 99.78%, respectively. Ventricular ectopic beat classification sensitivity and positive predictive value were 89.4% and 97.8%, respectively. Episode and duration F₁ scores (range 0–100) exceeded 70 for all 14 rhythms (including noise) that were evaluated. F₁ scores for 11 rhythms exceeded 80, 7 exceeded 90, and 5 including atrial fibrillation/flutter, ventricular tachycardia, ventricular bigeminy, ventricular trigeminy, and third-degree heart block exceeded 95.

CONCLUSION

The BeatLogic platform represents the next stage of advancement for algorithmic ECG interpretation. This comprehensive platform performs beat detection, beat classification, and rhythm detection/classification with greatly improved performance over the current state of the art, with comparable or improved performance over previously published algorithms that can accomplish only 1 of these 3 tasks.

A Comparative Study of ECG-derived Respiration in Ambulatory Monitoring using the Single-lead ECG

Cardiorespiratory monitoring is crucial for the diagnosis and management of multiple conditions such as stress and sleep disorders. Therefore, the development of ambulatory systems providing continuous, comfortable, and inexpensive means for monitoring represents an important research topic. Several techniques have been proposed in the literature to derive respiratory information from the ECG signal. Ten methods to compute single-lead ECG-derived respiration (EDR) were compared under multiple conditions, including different recording systems, baseline wander, normal and abnormal breathing patterns, changes in breathing rate, noise, and artifacts. Respiratory rates, wave morphology, and cardiorespiratory information were derived from the ECG and compared to those extracted from a reference respiratory signal. Three datasets were considered for analysis, involving a total 59 482 one-min, single-lead ECG segments recorded from 156 subjects. The results indicate that the methods based on QRS slopes outperform the other methods. This result is particularly interesting since simplicity is crucial for the development of ECG-based ambulatory systems.

Stylios G. Comparison of Motion Artefact Reduction Methods and the Implementation of Adaptive Motion Artefact Reduction in Wearable Electrocardiogram Monitoring

A motion artefact is a kind of noise that exists widely in wearable electrocardiogram (ECG) monitoring. Reducing motion artefact is challenging in ECG signal preprocessing because the spectrum of motion artefact usually overlaps with the very important spectral components of the ECG signal. In this paper, the performance of the finite impulse response (FIR) filter, infinite impulse response (IIR) filter, moving average filter, moving median filter, wavelet transform, empirical mode decomposition, and adaptive filter in motion artefact reduction is studied and compared. The results of this study demonstrate that the adaptive filter performs better than other denoising methods, especially in dealing with the abnormal ECG signal which is measured from a patient with heart disease. In the implementation of adaptive motion artefact reduction, the results show that the use of the impedance pneumography signal as the reference input signal for the adaptive filter can effectively reduce the motion artefact in the ECG signal.

On the Effectiveness of Deep Representation Learning: the Atrial Fibrillation Case

The automatic and unsupervised analysis of biomedical time series is of primary importance for diagnostic and preventive medicine, enabling fast and reliable data processing to reveal clinical insights without the need for human intervention. Representation learning (RL) methods perform an automatic extraction of meaningful features that can be used, e.g., for a subsequent classification of the measured data. The goal of this study is to explore and quantify the benefits of RL techniques of varying degrees of complexity, focusing on modern deep learning (DL) architectures. We focus on the automatic classification of atrial fibrillation (AF) events from noisy single-lead electrocardiographic signals (ECG) obtained from wireless sensors. This is an important task as it allows the detection of sub-clinical AF which is hard to diagnose with a short in-clinic 12-lead ECG. The effectiveness of the considered architectures is quantified and discussed in terms of classification performance, memory/data efficiency and computational complexity.

The stationary wavelet transform as an efficient reductor of powerline interference for atrial bipolar electrograms in cardiac electrophysiology

OBJECTIVE

The most relevant source of signal contamination in the cardiac electrophysiology (EP) laboratory is the ubiquitous powerline interference (PLI). To reduce this perturbation, algorithms including common fixed-bandwidth and adaptive-notch filters have been proposed. Although such methods have proven to add artificial fractionation to intra-atrial electrograms (EGMs), they are still frequently used. However, such morphological alteration can conceal the accurate interpretation of EGMs, specially to evaluate the mechanisms supporting atrial fibrillation (AF), which is the most common cardiac arrhythmia. Given the clinical relevance of AF, a novel algorithm aimed at reducing PLI on highly contaminated bipolar EGMs and, simultaneously, preserving their morphology is proposed.

APPROACH

The method is based on the wavelet shrinkage and has been validated through customized indices on a set of synthesized EGMs to accurately quantify the achieved level of PLI reduction and signal morphology alteration. Visual validation of the algorithm's performance has also been included for some real EGM excerpts.

MAIN RESULTS

The method has outperformed common filtering-based and wavelet-based strategies in the analyzed scenario. Moreover, it possesses advantages such as insensitivity to amplitude and frequency variations in the PLI, and the capability of joint removal of several interferences.

SIGNIFICANCE

The use of this algorithm in routine cardiac EP studies may enable improved and truthful evaluation of AF mechanisms.

Electrocardiogram Baseline Wander Suppression Based on the Combination of Morphological and Wavelet Transformation Based Filtering

One of the major noise components in electrocardiogram (ECG) is the baseline wander (BW). Effective methods for suppressing BW include the wavelet-based (WT) and the mathematical morphological filtering-based (MMF) algorithms. However, the T waveform distortions introduced by the WT and the rectangular/trapezoidal distortions introduced by MMF degrade the quality of the output signal. Hence, in this study, we introduce a method by combining the MMF and WT to overcome the shortcomings of both existing methods. To demonstrate the effectiveness of the proposed method, artificial ECG signals containing a clinical BW are used for numerical simulation, and we also create a realistic model of baseline wander to compare the proposed method with other state-of-the-art methods commonly used in the literature. The results show that the BW suppression effect of the proposed method is better than that of the others. Also, the new method is capable of preserving the outline of the BW and avoiding waveform distortions caused by the morphology filter, thereby obtaining an enhanced quality of ECG.

Intra-arterial pulse wave analysis during thrombectomy for the assessment of collateral status - A feasibility study

Purpose

Knowledge of the collateralization of an occluded vessel is important for the risk-benefit analysis of difficult revascularization maneuvers during mechanical thrombectomy. If the territory behind a clot is well perfused, one could desist from performing a risky thrombectomy maneuver. The arterial pulse pressure curve may serve as an indicator for the collateralization of an occluded target vessel. We investigated the feasibility of arterial pulse measurements with a standard microcatheter.

Methods

We measured the intra-arterial blood pressure proximal and distal to the clot in 40 thrombectomy maneuvers in a porcine stroke model. We used a microcatheter (Trevo Pro 18, Stryker, Kalamazoo, CA, USA), a pressure transducer (MEMSCAP SP844), an AdInstruments Powerlab 16/35 workstation, and LabChart 8 Software (AdInstruments, Dunedin, New Zealand).

Results

Median arterial blood pressure proximal and distal to the clot was 96.0 mmHg (IQR, 23.8 mmHg) and 47.5 mmHg (IQR, 43.5 mmHg), respectively (p < .001). The median difference between systolic maximum and diastolic minimum proximal and distal to the clot decreased significantly from 1.8 mmHg (IQR, 3.6 mmHg) to 0.0 mmHg (IQR, 0.5 mmHg) (p < .001). There was loss of the curve in 26 of 40 cases and loss of pressure in 23 of 40 cases (p = .008). There was no significant correlation between vessel diameter and either loss of the pulse pressure curve (p = .20) or overall pressure loss (p = .31).

Conclusion

It is possible to measure the pulse pressure proximal and distal to the clot with a standard microcatheter used during mechanical thrombectomy.

A lightweight piecewise linear synthesis method for standard 12-lead ECG signals based on adaptive region segmentation

This paper presents a lightweight synthesis algorithm, named adaptive region segmentation based piecewise linear (ARSPL) algorithm, for reconstructing standard 12-lead electrocardiogram (ECG) signals from a 3-lead subset (I, II and V2). Such a lightweight algorithm is particularly suitable for healthcare mobile devices with limited resources for computing, communication and data storage. After detection of R-peaks, the ECGs are segmented by cardiac cycles. Each cycle is further divided into four regions according to different cardiac electrical activity stages. A personalized linear regression algorithm is then applied to these regions respectively for improved ECG synthesis. The proposed ARSPL method has been tested on 39 subjects randomly selected from the PTB diagnostic ECG database and achieved accurate synthesis of remaining leads with an average correlation coefficient of 0.947, an average root-mean-square error of 55.4μV, and an average runtime performance of 114ms. Overall, these results are significantly better than those of the common linear regression method, the back propagation (BP) neural network and the BP optimized using the genetic algorithm. We have also used the reconstructed ECG signals to evaluate the denivelation of ST segment, which is a potential symptom of intrinsic myocardial disease. After ARSPL, only 10.71% of the synthesized ECG cycles are with a ST-level synthesis error larger than 0.1mV, which is also better than those of the three above-mentioned methods.

Analyzing single-lead short ECG recordings using dense convolutional neural networks and feature-based post-processing to detect atrial fibrillation

OBJECTIVE

The prevalence of atrial fibrillation (AF) in the general population is 0.5%-1%. As AF is the most common sustained cardiac arrhythmia that is associated with an increased morbidity and mortality, its timely diagnosis is clinically desirable. The main aim of this study as our contribution to the PhysioNet/CinC Challenge 2017 was to develop an automatic algorithm for classification of normal sinus rhythm (NSR), AF, other rhythm (O), and noise using a short single-channel ECG. Furthermore, the impact of changing labels/annotations on performance of the proposed algorithm was studied in this article.

APPROACH

The challenge training dataset (8528 ECG recordings) and a complementary dataset (6312 ECG recordings) from other sources were used for algorithm development. Version 3 (v3), which is an updated version of the annotations at the official phase of the challenge (v2), was used in this study. In the proposed algorithm, densely connected convolutional networks were combined with feature-based post-processing after initial signal quality analysis for the classification of ECG recordings.

MAIN RESULTS

The F1 scores for classification of NSR, AF, and O were 0.91, 0.83, and 0.72, respectively, which led to a F1 of 0.82. There was a small or no performance difference between the top entries in the official phase of the challenge and our proposed method. An increase of 2.5% in F1 score was observed when the same annotations for training and test was used (using v3 annotations) compared to using different annotations (v2 annotations for training and v3 annotations for the test).

SIGNIFICANCE

Our promising results suggest that the availability of more data with improved labeling along with improvement in signal quality analysis make our algorithm suitable for practical clinical applications.

An adaptive spatio-temporal Gaussian filter for processing cardiac optical mapping data

Optical mapping is widely used as a tool to investigate cardiac electrophysiology in ex vivo preparations. Digital filtering of fluorescence-optical data is an important requirement for robust subsequent data analysis and still a challenge when processing data acquired from thin mammalian myocardium. Therefore, we propose and investigate the use of an adaptive spatio-temporal Gaussian filter for processing optical mapping signals from these kinds of tissue usually having low signal-to-noise ratio (SNR). We demonstrate how filtering parameters can be chosen automatically without additional user input. For systematic comparison of this filter with standard filtering methods from the literature, we generated synthetic signals representing optical recordings from atrial myocardium of a rat heart with varying SNR. Furthermore, all filter methods were applied to experimental data from an ex vivo setup. Our developed filter outperformed the other filter methods regarding local activation time detection at SNRs smaller than 3 dB which are typical noise ratios expected in these signals. At higher SNRs, the proposed filter performed slightly worse than the methods from literature. In conclusion, the proposed adaptive spatio-temporal Gaussian filter is an appropriate tool for investigating fluorescence-optical data with low SNR. The spatio-temporal filter parameters were automatically adapted in contrast to the other investigated filters.

Linear Phase Sharp Transition BPF to Detect Noninvasive Maternal and Fetal Heart Rate

Fetal heart rate (FHR) detection can be monitored using either direct fetal scalp electrode recording (invasive) or by indirect noninvasive technique. Weeks before delivery, the invasive method poses a risk factor to the fetus, while the latter provides accurate fetal ECG (FECG) information which can help diagnose fetal's well-being. Our technique employs variable order linear phase sharp transition (LPST) FIR band-pass filter which shows improved stopband attenuation at higher filter orders. The fetal frequency fiduciary edges form the band edges of the filter characterized by varying amounts of overlap of maternal ECG (MECG) spectrum. The one with the minimum maternal spectrum overlap was found to be optimum with no power line interference and maximum fetal heart beats being detected. The improved filtering is reflected in the enhancement of the performance of the fetal QRS detector (FQRS). The improvement has also occurred in fetal heart rate obtained using our algorithm which is in close agreement with the true reference (i.e., invasive fetal scalp ECG). The performance parameters of the FQRS detector such as sensitivity (Se), positive predictive value (PPV), and accuracy (F₁) were found to improve even for lower filter order. The same technique was extended to evaluate maternal QRS detector (MQRS) and found to yield satisfactory maternal heart rate (MHR) results.