Automatic and Robust Delineation of the Fiducial Points of the Seismocardiogram Signal for Non-invasive Estimation of Cardiac Time Intervals

ECGVEDNET: A Variational Encoder-Decoder Network for ECG Delineation in Morphology Variant ECGs

Electrocardiogram (ECG) delineation to identify the fiducial points of ECG segments, plays an important role in cardiovascular diagnosis and care. Whilst deep delineation frameworks have been deployed within the literature, several factors still hinder their development: (a) data availability: the capacity of deep learning models to generalise is limited by the amount of available data; (b) morphology variations: ECG complexes vary, even within the same person, which degrades the performance of conventional deep learning models. To address these concerns, we present a large-scale 12-leads ECG dataset, ICDIRS, to train and evaluate a novel deep delineation model-ECGVEDNET. ICDIRS is a large-scale ECG dataset with 156,145 QRS onset annotations and 156,145 T peak annotations. ECGVEDNET is a novel variational encoder-decoder network designed to address morphology variations. In ECGVEDNET, we construct a well-regularized latent space, in which the latent features of ECG follow a regular distribution and present smaller morphology variations than in the raw data space. Finally, a transfer learning framework is proposed to transfer the knowledge learned on ICDIRS to smaller datasets. On ICDIRS, ECGVEDNET achieves accuracy of 86.28%/88.31% within 5/10 ms tolerance for QRS onset and accuracy of 89.94%/91.16% within 5/10 ms tolerance for T peak. On QTDB, the average time errors computed for QRS onset and T peak are -1.86 ± 8.02 ms and -0.50 ± 12.96 ms, respectively, achieving state-of-the-art performances on both large and small-scale datasets. We will release the source code and the pre-trained model on ICDIRS once accepted.

Maximum a posteriori detection of heartbeats from a chest-worn accelerometer

Objective. Unobtrusive long-term monitoring of cardiac parameters is important in a wide variety of clinical applications, such as the assesment of acute illness severity and unobtrusive sleep monitoring. Here we determined the accuracy and robustness of heartbeat detection by an accelerometer worn on the chest.Approach. We performed overnight recordings in 147 individuals (69 female, 78 male) referred to two sleep centers. Two methods for heartbeat detection in the acceleration signal were compared: one previously described approach, based on local periodicity, and a novel extended method incorporating maximumaposterioriestimation and a Markov decision process to approach an optimal solution.Main results. The maximumaposterioriestimation significantly improved performance, with a mean absolute error for the estimation of inter-beat intervals of only 3.5 ms, and 95% limits of agreement of -1.7 to +1.0 beats per minute for heartrate measurement. Performance held during posture changes and was only weakly affected by the presence of sleep disorders and demographic factors.Significance. The new method may enable the use of a chest-worn accelerometer in a variety of applications such as ambulatory sleep staging and in-patient monitoring.

ECG-Free Heartbeat Detection in Seismocardiography and Gyrocardiography Signals Provides Acceptable Heart Rate Variability Indices in Healthy and Pathological Subjects

Cardio-mechanical monitoring techniques, such as Seismocardiography (SCG) and Gyrocardiography (GCG), have received an ever-growing interest in recent years as potential alternatives to Electrocardiography (ECG) for heart rate monitoring. Wearable SCG and GCG devices based on lightweight accelerometers and gyroscopes are particularly appealing for continuous, long-term monitoring of heart rate and its variability (HRV). Heartbeat detection in cardio-mechanical signals is usually performed with the support of a concurrent ECG lead, which, however, limits their applicability in standalone cardio-mechanical monitoring applications. The complex and variable morphology of SCG and GCG signals makes the ECG-free heartbeat detection task quite challenging; therefore, only a few methods have been proposed. Very recently, a template matching method based on normalized cross-correlation (NCC) has been demonstrated to provide very accurate detection of heartbeats and estimation of inter-beat intervals in SCG and GCG signals of pathological subjects. In this study, the accuracy of HRV indices obtained with this template matching method is evaluated by comparison with ECG. Tests were performed on two public datasets of SCG and GCG signals from healthy and pathological subjects. Linear regression, correlation, and Bland-Altman analyses were carried out to evaluate the agreement of 24 HRV indices obtained from SCG and GCG signals with those obtained from ECG signals, simultaneously acquired from the same subjects. The results of this study show that the NCC-based template matching method allowed estimating HRV indices from SCG and GCG signals of healthy subjects with acceptable accuracy. On healthy subjects, the relative errors on time-domain indices ranged from 0.25% to 15%, on frequency-domain indices ranged from 10% to 20%, and on non-linear indices were within 8%. The estimates obtained on signals from pathological subjects were affected by larger errors. Overall, GCG provided slightly better performances as compared to SCG, both on healthy and pathological subjects. These findings provide, for the first time, clear evidence that monitoring HRV via SCG and GCG sensors without concurrent ECG is feasible with the NCC-based template matching method for heartbeat detection.

Heartbeat Detection in Gyrocardiography Signals without Concurrent ECG Tracings

A heartbeat generates tiny mechanical vibrations, mainly due to the opening and closing of heart valves. These vibrations can be recorded by accelerometers and gyroscopes applied on a subject's chest. In particular, the local 3D linear accelerations and 3D angular velocities of the chest wall are referred to as seismocardiograms (SCG) and gyrocardiograms (GCG), respectively. These signals usually exhibit a low signal-to-noise ratio, as well as non-negligible amplitude and morphological changes due to changes in posture and the sensors' location, respiratory activity, as well as other sources of intra-subject and inter-subject variability. These factors make heartbeat detection a complex task; therefore, a reference electrocardiogram (ECG) lead is usually acquired in SCG and GCG studies to ensure correct localization of heartbeats. Recently, a template matching technique based on cross correlation has proven to be particularly effective in recognizing individual heartbeats in SCG signals. This study aims to verify the performance of this technique when applied on GCG signals. Tests were conducted on a public database consisting of SCG, GCG, and ECG signals recorded synchronously on 100 patients with valvular heart diseases. The results show that the template matching technique identified heartbeats in GCG signals with a sensitivity and positive predictive value (PPV) of 87% and 92%, respectively. Regression, correlation, and Bland-Altman analyses carried out on inter-beat intervals obtained from GCG and ECG (assumed as reference) reported a slope of 0.995, an intercept of 4.06 ms (R² > 0.99), a Pearson's correlation coefficient of 0.9993, and limits of agreement of about ±13 ms with a negligible bias. A comparison with the results of a previous study obtained on SCG signals from the same database revealed that GCG enabled effective cardiac monitoring in significantly more patients than SCG (95 vs. 77). This result suggests that GCG could ensure more robust and reliable cardiac monitoring in patients with heart diseases with respect to SCG.

ECG-Free Heartbeat Detection in Seismocardiography Signals via Template Matching

Cardiac monitoring can be performed by means of an accelerometer attached to a subject's chest, which produces the Seismocardiography (SCG) signal. Detection of SCG heartbeats is commonly carried out by taking advantage of a simultaneous electrocardiogram (ECG). SCG-based long-term monitoring would certainly be less obtrusive and easier to implement without an ECG. Few studies have addressed this issue using a variety of complex approaches. This study proposes a novel approach to ECG-free heartbeat detection in SCG signals via template matching, based on normalized cross-correlation as heartbeats similarity measure. The algorithm was tested on the SCG signals acquired from 77 patients with valvular heart diseases, available from a public database. The performance of the proposed approach was assessed in terms of sensitivity and positive predictive value (PPV) of the heartbeat detection and accuracy of inter-beat intervals measurement. Sensitivity and PPV of 96% and 97%, respectively, were obtained by considering templates that included both systolic and diastolic complexes. Regression, correlation, and Bland-Altman analyses carried out on inter-beat intervals reported slope and intercept of 0.997 and 2.8 ms (R² > 0.999), as well as non-significant bias and limits of agreement of ±7.8 ms. The results are comparable or superior to those achieved by far more complex algorithms, also based on artificial intelligence. The low computational burden of the proposed approach makes it suitable for direct implementation in wearable devices.

Changes in Forcecardiography Heartbeat Morphology Induced by Cardio-Respiratory Interactions

The cardiac function is influenced by respiration. In particular, various parameters such as cardiac time intervals and the stroke volume are modulated by respiratory activity. It has long been recognized that cardio-respiratory interactions modify the morphology of cardio-mechanical signals, e.g., phonocardiogram, seismocardiogram (SCG), and ballistocardiogram. Forcecardiography (FCG) records the weak forces induced on the chest wall by the mechanical activity of the heart and lungs and relies on specific force sensors that are capable of monitoring respiration, infrasonic cardiac vibrations, and heart sounds, all simultaneously from a single site on the chest. This study addressed the changes in FCG heartbeat morphology caused by respiration. Two respiratory-modulated parameters were considered, namely the left ventricular ejection time (LVET) and a morphological similarity index (MSi) between heartbeats. The time trends of these parameters were extracted from FCG signals and further analyzed to evaluate their consistency within the respiratory cycle in order to assess their relationship with the breathing activity. The respiratory acts were localized in the time trends of the LVET and MSi and compared with a reference respiratory signal by computing the sensitivity and positive predictive value (PPV). In addition, the agreement between the inter-breath intervals estimated from the LVET and MSi and those estimated from the reference respiratory signal was assessed via linear regression and Bland-Altman analyses. The results of this study clearly showed a tight relationship between the respiratory activity and the considered respiratory-modulated parameters. Both the LVET and MSi exhibited cyclic time trends that remarkably matched the reference respiratory signal. In addition, they achieved a very high sensitivity and PPV (LVET: 94.7% and 95.7%, respectively; MSi: 99.3% and 95.3%, respectively). The linear regression analysis reported almost unit slopes for both the LVET (R² = 0.86) and MSi (R² = 0.97); the Bland-Altman analysis reported a non-significant bias for both the LVET and MSi as well as limits of agreement of ±1.68 s and ±0.771 s, respectively. In summary, the results obtained were substantially in line with previous findings on SCG signals, adding to the evidence that FCG and SCG signals share a similar information content.

Precordial Vibrations: A Review of Wearable Systems, Signal Processing Techniques, and Main Applications

Recently, the ever-growing interest in the continuous monitoring of heart function in out-of-laboratory settings for an early diagnosis of cardiovascular diseases has led to the investigation of innovative methods for cardiac monitoring. Among others, wearables recording seismic waves induced on the chest surface by the mechanical activity of the heart are becoming popular. For what concerns wearable-based methods, cardiac vibrations can be recorded from the thorax in the form of acceleration, angular velocity, and/or displacement by means of accelerometers, gyroscopes, and fiber optic sensors, respectively. The present paper reviews the currently available wearables for measuring precordial vibrations. The focus is on sensor technology and signal processing techniques for the extraction of the parameters of interest. Lastly, the explored application scenarios and experimental protocols with the relative influencing factors are discussed for each technique. The goal is to delve into these three fundamental aspects (i.e., wearable system, signal processing, and application scenario), which are mutually interrelated, to give a holistic view of the whole process, beyond the sensor aspect alone. The reader can gain a more complete picture of this context without disregarding any of these 3 aspects.

Mechanical deconditioning of the heart due to long-term bed rest as observed on seismocardiogram morphology

During head-down tilt bed rest (HDT) the cardiovascular system is subject to headward fluid shifts. The fluid shift phenomenon is analogous to weightlessness experienced during spaceflight microgravity. The purpose of this study was to investigate the effect of prolonged 60-day bed rest on the mechanical performance of the heart using the morphology of seismocardiography (SCG). Three-lead electrocardiogram (ECG), SCG and blood pressure recordings were collected simultaneously from 20 males in a 60-day HDT study (MEDES, Toulouse, France). The study was divided into two campaigns of ten participants. The first commenced in January, and the second in September. Signals were recorded in the supine position during the baseline data collection (BDC) before bed rest, during 6° HDT bed rest and during recovery (R), post-bed rest. Using SCG and blood pressure at the finger, the following were determined: Pulse Transit Time (PTT); and left-ventricular ejection time (LVET). SCG morphology was analyzed using functional data analysis (FDA). The coefficients of the model were estimated over 20 cycles of SCG recordings of BDC12 and HDT52. SCG fiducial morphology AO (aortic valve opening) and AC (aortic valve closing) amplitudes showed significant decrease between BDC12 and HDT52 (p < 0.03). PTT and LVET were also found to decrease through HDT bed rest (p < 0.01). Furthermore, PTT and LVET magnitude of response to bed rest was found to be different between campaigns (p < 0.001) possibly due to seasonal effects on of the cardiovascular system. Correlations between FDA and cardiac timing intervals PTT and LVET using SCG suggests decreases in mechanical strength of the heart and increased arterial stiffness due to fluid shifts associated with the prolonged bed rest.

Automatic Detection of Aortic Valve Events Using Deep Neural Networks on Cardiac Signals From Epicardially Placed Accelerometer

BACKGROUND

Miniaturized accelerometers incorporated in pacing leads attached to the myocardium, are used to monitor cardiac function. For this purpose functional indices must be extracted from the acceleration signal. A method that automatically detects time of aortic valve opening (AVO) and aortic valve closure (AVC) will be helpful for such extraction. We tested if deep learning can be used to detect these valve events from epicardially attached accelerometers, using high fidelity pressure measurements to establish ground truth for these valve events.

METHOD

A deep neural network consisting of a CNN, an RNN, and a multi-head attention module was trained and tested on 130 recordings from 19 canines and 159 recordings from 27 porcines covering different interventions. Due to limited data, nested cross-validation was used to assess the accuracy of the method.

RESULT

The correct detection rates were 98.9% and 97.1% for AVO and AVC in canines and 98.2% and 96.7% in porcines when defining a correct detection as a prediction closer than 40 ms to the ground truth. The incorrect detection rates were 0.7% and 2.3% for AVO and AVC in canines and 1.1% and 2.3% in porcines. The mean absolute error between correct detections and their ground truth was 8.4 ms and 7.2 ms for AVO and AVC in canines, and 8.9 ms and 10.1 ms in porcines.

CONCLUSION

Deep neural networks can be used on signals from epicardially attached accelerometers for robust and accurate detection of the opening and closing of the aortic valve.

An Innovative Machine Learning Approach for Classifying ECG Signals in Healthcare Devices

An ECG is a diagnostic technique that examines and records the heart's electrical impulses. It is easy to categorise and prevent computational abstractions in the ECG signal using the conventional method for obtaining ECG features. It is a significant issue, but it is also a difficult and time-consuming chore for cardiologists and medical professionals. The proposed classifier eliminates all of the following limitations. Machine learning in healthcare equipment reduces moral transgressions. This study's primary purpose is to calculate the R-R interval and analyze the blockage utilising simple algorithms and approaches that give high accuracy. The MIT-BIH dataset may be used to rebuild the data. The acquired data may include both normal and abnormal ECGs. A Gabor filter is employed to generate a noiseless signal, and DCT-DOST is used to calculate the signal's amplitude. The amplitude is computed to detect any cardiac anomalies. A genetic algorithm derives the main highlights from the R peak and cycle segment length underlying the ECG signal. So, combining data with specific qualities maximises identification. The genetic algorithm aids in hereditary computations, which aids in multitarget improvement. Finally, Radial Basis Function Neural Network (RBFNN) is presented as an example. An efficient feedforward neural network lowers the number of local minima in the signal. It shows progress in identifying both normal and abnormal ECG signals.

Can Seismocardiogram Fiducial Points Be Used for the Routine Estimation of Cardiac Time Intervals in Cardiac Patients?

The indexes of cardiac mechanics can be derived from the cardiac time intervals, CTIs, i.e., the timings among the opening and closure of the aortic and mitral valves and the Q wave in the ECG. Traditionally, CTIs are estimated by ultrasound (US) techniques, but they may also be more easily assessed by the identification of specific fiducial points (FPs) inside the waveform of the seismocardiogram (SCG), i.e., the measure of the thorax micro-accelerations produced by the heart motion. While the correspondence of the FPs with the valve movements has been verified in healthy subjects, less information is available on whether this methodology may be routinely employed in the clinical practice for the monitoring of cardiac patients, in which an SCG waveform distortion is expected because of the heart dysfunction. In this study we checked the SCG shape in 90 patients with myocardial infarction (MI), heart failure (HF), or transplanted heart (TX), referred to our hospital for rehabilitation after an acute event or after surgery. The SCG shapes were classified as traditional (T) or non-traditional (NT) on whether the FPs were visible or not on the basis of nomenclature previously proposed in literature. The T shape was present in 62% of the patients, with a higher ∓ prevalence in MI (79%). No relationship was found between T prevalence and ejection fraction (EF). In 20 patients with T shape, we checked the FPs correspondence with the real valve movements by concomitant SCG and US measures. When compared with reference values in healthy subjects available in the literature, we observed that the Echo vs. FP differences are significantly more dispersed in the patients than in the healthy population with higher differences for the estimation of the mitral valve closure (−17 vs. 4 ms on average). Our results indicate that not every cardiac patient has an SCG waveform suitable for the CTI estimation, thus before starting an SCG-based CTI monitoring a preliminary check by a simultaneous SCG-US measure is advisable to verify the applicability of the methodology.

Efficient detection of aortic stenosis using morphological characteristics of cardiomechanical signals and heart rate variability parameters

Recent research has shown promising results for the detection of aortic stenosis (AS) using cardio-mechanical signals. However, they are limited by two main factors: lacking physical explanations for decision-making on the existence of AS, and the need for auxiliary signals. The main goal of this paper is to address these shortcomings through a wearable inertial measurement unit (IMU), where the physical causes of AS are determined from IMU readings. To this end, we develop a framework based on seismo-cardiogram (SCG) and gyro-cardiogram (GCG) morphologies, where highly-optimized algorithms are designed to extract features deemed potentially relevant to AS. Extracted features are then analyzed through machine learning techniques for AS diagnosis. It is demonstrated that AS could be detected with 95.49-100.00% confidence. Based on the ablation study on the feature space, the GCG time-domain feature space holds higher consistency, i.e., 95.19-100.00%, with the presence of AS than HRV parameters with a low contribution of 66.00-80.00%. Furthermore, the robustness of the proposed method is evaluated by conducting analyses on the classification of the AS severity level. These analyses are resulted in a high confidence of 92.29%, demonstrating the reliability of the proposed framework. Additionally, game theory-based approaches are employed to rank the top features, among which GCG time-domain features are found to be highly consistent with both the occurrence and severity level of AS. The proposed framework contributes to reliable, low-cost wearable cardiac monitoring due to accurate performance and usage of solitary inertial sensors.

A Novel Broadband Forcecardiography Sensor for Simultaneous Monitoring of Respiration, Infrasonic Cardiac Vibrations and Heart Sounds

The precordial mechanical vibrations generated by cardiac contractions have a rich frequency spectrum. While the lowest frequencies can be palpated, the higher infrasonic frequencies are usually captured by the seismocardiogram (SCG) signal and the audible ones correspond to heart sounds. Forcecardiography (FCG) is a non-invasive technique that measures these vibrations via force sensing resistors (FSR). This study presents a new piezoelectric sensor able to record all heart vibrations simultaneously, as well as a respiration signal. The new sensor was compared to the FSR-based one to assess its suitability for FCG. An electrocardiogram (ECG) lead and a signal from an electro-resistive respiration band (ERB) were synchronously acquired as references on six healthy volunteers (4 males, 2 females) at rest. The raw signals from the piezoelectric and the FSR-based sensors turned out to be very similar. The raw signals were divided into four components: Forcerespirogram (FRG), Low-Frequency FCG (LF-FCG), High-Frequency FCG (HF-FCG) and heart sounds (HS-FCG). A beat-by-beat comparison of FCG and ECG signals was carried out by means of regression, correlation and Bland–Altman analyses, and similarly for respiration signals (FRG and ERB). The results showed that the infrasonic FCG components are strongly related to the cardiac cycle (R² > 0.999, null bias and Limits of Agreement (LoA) of ± 4.9 ms for HF-FCG; R² > 0.99, null bias and LoA of ± 26.9 ms for LF-FCG) and the FRG inter-breath intervals are consistent with ERB ones (R² > 0.99, non-significant bias and LoA of ± 0.46 s). Furthermore, the piezoelectric sensor was tested against an accelerometer and an electronic stethoscope: synchronous acquisitions were performed to quantify the similarity between the signals. ECG-triggered ensemble averages (synchronized with R-peaks) of HF-FCG and SCG showed a correlation greater than 0.81, while those of HS-FCG and PCG scored a correlation greater than 0.85. The piezoelectric sensor demonstrated superior performances as compared to the FSR, providing more accurate, beat-by-beat measurements. This is the first time that a single piezoelectric sensor demonstrated the ability to simultaneously capture respiration, heart sounds, an SCG-like signal (i.e., HF-FCG) and the LF-FCG signal, which may provide information on ventricular emptying and filling events. According to these preliminary results the novel piezoelectric FCG sensor stands as a promising device for accurate, unobtrusive, long-term monitoring of cardiorespiratory functions and paves the way for a wide range of potential applications, both in the research and clinical fields. However, these results should be confirmed by further analyses on a larger cohort of subjects, possibly including also pathological patients.

A Comprehensive Review on Seismocardiogram: Current Advancements on Acquisition, Annotation, and Applications

In recent years, cardiovascular diseases are on the rise, and they entail enormous health burdens on global economies. Cardiac vibrations yield a wide and rich spectrum of essential information regarding the functioning of the heart, and thus it is necessary to take advantage of this data to better monitor cardiac health by way of prevention in early stages. Specifically, seismocardiography (SCG) is a noninvasive technique that can record cardiac vibrations by using new cutting-edge devices as accelerometers. Therefore, providing new and reliable data regarding advancements in the field of SCG, i.e., new devices and tools, is necessary to outperform the current understanding of the State-of-the-Art (SoTA). This paper reviews the SoTA on SCG and concentrates on three critical aspects of the SCG approach, i.e., on the acquisition, annotation, and its current applications. Moreover, this comprehensive overview also presents a detailed summary of recent advancements in SCG, such as the adoption of new techniques based on the artificial intelligence field, e.g., machine learning, deep learning, artificial neural networks, and fuzzy logic. Finally, a discussion on the open issues and future investigations regarding the topic is included.

The Delineation of Fiducial Points for Non-Contact Radar Seismocardiogram Signals Without Concurrent ECG

OBJECTIVE

Non-contact sensing of seismocardiogram (SCG) signals through a microwave Doppler radar is promising for biomedical applications. However, the delineation of fiducial points for radar SCG still relies on concurrent ECG which requires a contact sensor and limits the complete non-contact detection of SCG.

METHODS

Instead of ECG, a new reference signal, the radar displacement signal of heartbeat (RDH), was derived through the complex Fourier transform and the band pass filtering of the radar signal. The RDH signal was used to locate each cardiac cycle and mask the systolic profile, which was further used to detect an important fiducial point, aortic valve opening (AO). The beat-to-beat interval was estimated from AO-AO interval and compared with the gold standard, ECG R-to-R interval.

RESULTS

For the 22 subjects in the study, the evaluation of the AOs detected by RDH (AO_RDH) shows the average detection ratio can reach 90%, indicating a high ratio of the AO_RDH that are exactly the same as AO detected using the ECG R-wave (AO_ECG). Additionally, the left ventricular ejection time (LVET) values estimated from the ensemble averaged radar waveform through AO_RDH segmentation are within 2 ms of those through AO_ECG segmentation, for all the detected subjects. Further analysis demonstrates that the beat-to-beat intervals calculated from AO_RDH have an average root-mean-square-deviation (RMSD) of 53.73 ms when compared with ECG R-to-R intervals, and have an average RMSD of 23.47 ms after removing the beats in which AO cannot be identified.

CONCLUSIONS

Radar signal RDH can be used as a reference signal to delineate fiducial points for non-contact radar SCG signals.

SIGNIFICANCE

This study can be applied to develop complete non-contact sensing of SCG and monitoring of vital signs, where contact-based SCG is not feasible.

A Unified Methodology for Heartbeats Detection in Seismocardiogram and Ballistocardiogram Signals

This work presents a methodology to analyze and segment both seismocardiogram (SCG) and ballistocardiogram (BCG) signals in a unified fashion. An unsupervised approach is followed to extract a template of SCG/BCG heartbeats, which is then used to fine-tune temporal waveform annotation. Rigorous performance assessment is conducted in terms of sensitivity, precision, Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of annotation. The methodology is tested on four independent datasets, covering different measurement setups and time resolutions. A wide application range is therefore explored, which better characterizes the robustness and generality of the method with respect to a single dataset. Overall, sensitivity and precision scores are uniform across all datasets ( p > 0.05 from the Kruskal–Wallis test): the average sensitivity among datasets is 98.7%, with 98.2% precision. On the other hand, a slight yet significant difference in RMSE and MAE scores was found ( p < 0.01 ) in favor of datasets with higher sampling frequency. The best RMSE scores for SCG and BCG are 4.5 and 4.8 ms, respectively; similarly, the best MAE scores are 3.3 and 3.6 ms. The results were compared to relevant recent literature and are found to improve both detection performance and temporal annotation errors.

A Unified Framework for Quality Indexing and Classification of Seismocardiogram Signals

The seismocardiogram (SCG) is a noninvasively-obtained cardiovascular bio-signal that has gained traction in recent years, however is limited by its susceptibility to noise and motion artifacts. Because of this, signal quality must be assured before data are used to inform clinical care. Common methods of signal quality assurance include signal classification or assignment of a numerical quality index. Such tasks are difficult with SCG because there is no accepted standard for signal morphology. In this paper, we propose a unified method of quality indexing and classification that uses multi-subject-based methods to overcome this challenge. Dynamic-time feature matching is introduced as a novel method of obtaining the distance between a signal and reference template, with this metric, the signal quality index (SQI) is defined as a function of the inverse distance between the SCG and a large set of template signals. We demonstrate that this method is able to stratify SCG signals on held-out subjects based on their level of motion-artifact corruption. This method is extended, using the SQI as a feature for classification by ensembled quadratic discriminant analysis. Classification is validated by demonstrating, for the first time, both detection and localization of SCG sensor misplacement, achieving an F1 score of 0.83 on held-out subjects. This paper may provide a necessary step toward automating the analysis of SCG signals, addressing many of the key limitations and concerns precluding the method from being widely used in clinical and physiological sensing applications.

Identifying Patients With Coronary Artery Disease Using Rest and Exercise Seismocardiography

Coronary artery disease (CAD) is the most common cause of death globally. Patients with suspected CAD are usually assessed by exercise electrocardiography (ECG). Subsequent tests, such as coronary angiography and coronary computed tomography angiography (CCTA) are performed to localize the stenosis and to estimate the degree of blockage. The present study describes a non-invasive methodology to identify patients with CAD based on the analysis of both rest and exercise seismocardiography (SCG). SCG is a non-invasive technology for capturing the acceleration of the chest induced by myocardial motion and vibrations. SCG signals were recorded from 185 individuals at rest and immediately after exercise. Two models were developed using the characterization of the rest and exercise SCG signals to identify individuals with CAD. The models were validated against related results from angiography. For the rest model, accuracy was 74%, and sensitivity and specificity were estimated as 75 and 72%, respectively. For the exercise model accuracy, sensitivity, and specificity were 81, 82, and 84%, respectively. The rest and exercise models presented a bootstrap-corrected area under the curve of 0.77 and 0.91, respectively. The discrimination slope was estimated 0.32 for rest model and 0.47 for the exercise model. The difference between the discrimination slopes of these two models was 0.15 (95% CI: 0.10 to 0.23, p < 0.0001). Both rest and exercise models are able to detect CAD with comparable accuracy, sensitivity, and specificity. Performance of SCG is better compared to stress-ECG and it is identical to stress-echocardiography and CCTA. SCG examination is fast, inexpensive, and may even be carried out by laypersons.

Classification of Aortic Stenosis Using Time-Frequency Features From Chest Cardio-Mechanical Signals

OBJECTIVES

This paper introduces a novel method for the detection and classification of aortic stenosis (AS) using the time-frequency features of chest cardio-mechanical signals collected from wearable sensors, namely seismo-cardiogram (SCG) and gyro-cardiogram (GCG) signals. Such a method could potentially monitor high-risk patients out of the clinic.

METHODS

Experimental measurements were collected from twenty patients with AS and twenty healthy subjects. Firstly, a digital signal processing framework is proposed to extract time-frequency features. The features are then selected via the analysis of variance test. Different combinations of features are evaluated using the decision tree, random forest, and artificial neural network methods. Two classification tasks are conducted. The first task is a binary classification between normal subjects and AS patients. The second task is a multi-class classification of AS patients with co-existing valvular heart diseases.

RESULTS

In the binary classification task, the average accuracies achieved are 96.25% from decision tree, 97.43% from random forest, and 95.56% from neural network. The best performance is from combined SCG and GCG features with random forest classifier. In the multi-class classification, the best performance is 92.99% using the random forest classifier and SCG features.

CONCLUSION

The results suggest that the solution could be a feasible method for classifying aortic stenosis, both in the binary and multi-class tasks. It also indicates that most of the important time-frequency features are below 11 Hz.

SIGNIFICANCE

The proposed method shows great potential to provide continuous monitoring of valvular heart diseases to prevent patients from sudden critical cardiac situations.

Real-Time Cardiac Beat Detection and Heart Rate Monitoring from Combined Seismocardiography and Gyrocardiography

Cardiography is an indispensable element of health care. However, the accessibility of at-home cardiac monitoring is limited by device complexity, accuracy, and cost. We have developed a real-time algorithm for heart rate monitoring and beat detection implemented in a custom-built, affordable system. These measurements were processed from seismocardiography (SCG) and gyrocardiography (GCG) signals recorded at the sternum, with concurrent electrocardiography (ECG) used as a reference. Our system demonstrated the feasibility of non-invasive electro-mechanical cardiac monitoring on supine, stationary subjects at a cost of $100, and with the SCG-GCG and ECG algorithms decoupled as standalone measurements. Testing was performed on 25 subjects in the supine position when relaxed, and when recovering from physical exercise, to record 23,984 cardiac cycles at heart rates in the range of 36-140 bpm. The correlation between the two measurements had r2 coefficients of 0.9783 and 0.9982 for normal (averaged) and instantaneous (beat identification) heart rates, respectively. At a sampling frequency of 250 Hz, the average computational time required was 0.088 s per measurement cycle, indicating the maximum refresh rate. A combined SCG and GCG measurement was found to improve accuracy due to fundamentally different noise rejection criteria in the mutually orthogonal signals. The speed, accuracy, and simplicity of our system validated its potential as a real-time, non-invasive, and affordable solution for outpatient cardiac monitoring in situations with negligible motion artifact.

Recent Advances in Seismocardiography

Cardiovascular disease is a major cause of death worldwide. New diagnostic tools are needed to provide early detection and intervention to reduce mortality and increase both the duration and quality of life for patients with heart disease. Seismocardiography (SCG) is a technique for noninvasive evaluation of cardiac activity. However, the complexity of SCG signals introduced challenges in SCG studies. Renewed interest in investigating the utility of SCG accelerated in recent years and benefited from new advances in low-cost lightweight sensors, and signal processing and machine learning methods. Recent studies demonstrated the potential clinical utility of SCG signals for the detection and monitoring of certain cardiovascular conditions. While some studies focused on investigating the genesis of SCG signals and their clinical applications, others focused on developing proper signal processing algorithms for noise reduction, and SCG signal feature extraction and classification. This paper reviews the recent advances in the field of SCG.

High-Resolution Seismocardiogram Acquisition and Analysis System

Several devices and measurement approaches have recently been developed to perform ballistocardiogram (BCG) and seismocardiogram (SCG) measurements. The development of a wireless acquisition system (hardware and software), incorporating a novel high-resolution micro-electro-mechanical system (MEMS) accelerometer for SCG and BCG signals acquisition and data treatment is presented in this paper. A small accelerometer, with a sensitivity of up to 0.164 µs/µg and a noise density below 6.5 µg/Hz is presented and used in a wireless acquisition system for BCG and SCG measurement applications. The wireless acquisition system also incorporates electrocardiogram (ECG) signals acquisition, and the developed software enables the real-time acquisition and visualization of SCG and ECG signals (sensor positioned on chest). It then calculates metrics related to cardiac performance as well as the correlation of data from previously performed sessions with echocardiogram (ECHO) parameters. A preliminarily clinical study of over 22 subjects (including healthy subjects and cardiovascular patients) was performed to test the capability of the developed system. Data correlation between this measurement system and echocardiogram exams is also performed. The high resolution of the MEMS accelerometer used provides a better signal for SCG wave recognition, enabling a more consistent study of the diagnostic capability of this technique in clinical analysis.

Automatic Detection of Aortic Valve Opening Using Seismocardiography in Healthy Individuals

Accurate detection of fiducial points in a seismocardiogram (SCG) is a challenging research problem for its clinical application. In this paper, an automated method for detecting aortic valve opening (AO) instants using the dorso-ventral component of the SCG signal is proposed. This method does not require electrocardiogram (ECG) as a reference signal. After preprocessing the SCG, multiscale wavelet decomposition is carried out to get signal components in different wavelet subbands. The subbands having possible AO peaks are selected by a newly proposed dominant-multiscale-kurtosis- and dominant-multiscale-central-frequency-based criterion. The signal is reconstructed using selected subbands, and it is emphasized using the weights derived from the proposed relative squared dominant multiscale kurtosis. The Shannon energy followed by autocorrelation coefficients is computed for systole envelope construction. Finally, AO peaks are detected by a Gaussian-derivative-filtering-based scheme. The robustness of the proposed method is tested using clean and noisy SCG signals from the combined measurement of ECG, breathing, and SCG database. Evaluation results show that the method can achieve an average sensitivity of 94%, a prediction rate of 90%, and a detection accuracy of 86% approximately over 4585 analyzed beats.

On the Design of an Efficient Cardiac Health Monitoring System Through Combined Analysis of ECG and SCG Signals

Cardiovascular disease (CVD) is a major public concern and socioeconomic problem across the globe. The popular high-end cardiac health monitoring systems such as magnetic resonance imaging (MRI), computerized tomography scan (CT scan), and echocardiography (Echo) are highly expensive and do not support long-term continuous monitoring of patients without disrupting their activities of daily living (ADL). In this paper, the continuous and non-invasive cardiac health monitoring using unobtrusive sensors is explored aiming to provide a feasible and low-cost alternative to foresee possible cardiac anomalies in an early stage. It is learned that cardiac health monitoring based on sole usage of electrocardiogram (ECG) signals may not provide powerful insights as ECG provides shallow information on various cardiac activities in the form of electrical impulses only. Hence, a novel low-cost, non-invasive seismocardiogram (SCG) signal along with ECG signals are jointly investigated for the robust cardiac health monitoring. For this purpose, the in-laboratory data collection model is designed for simultaneous acquisition of ECG and SCG signals followed by mechanisms for the automatic delineation of relevant feature points in acquired ECG and SCG signals. In addition, separate feature points based novel approach is adopted to distinguish between normal and abnormal morphology in each ECG and SCG cardiac cycle. Finally, a combined analysis of ECG and SCG is carried out by designing a Naïve Bayes conditional probability model. Experiments on Institutional Review Board (IRB) approved licensed ECG/SCG signals acquired from real subjects containing 12,000 cardiac cycles show that the proposed feature point delineation mechanisms and abnormal morphology detection methods consistently perform well and give promising results. In addition, experimental results show that the combined analysis of ECG and SCG signals provide more reliable cardiac health monitoring compared to the standalone use of ECG and SCG.

An algorithm for the beat-to-beat assessment of cardiac mechanics during sleep on Earth and in microgravity from the seismocardiogram

Seismocardiogram, SCG, is the measure of precordial vibrations produced by the beating heart, from which cardiac mechanics may be explored on a beat-to-beat basis. We recently collected a large amount of SCG data (>69 recording hours) from an astronaut to investigate cardiac mechanics during sleep aboard the International Space Station and on Earth. SCG sleep recordings are characterized by a prolonged duration and wide heart rate swings, thus a specific algorithm was developed for their analysis. In this article we describe the new algorithm and its performance. The algorithm is composed of three parts: 1) artifacts removal, 2) identification in each SCG waveform of four fiducial points associated with the opening and closure of the aortic and mitral valves, 3) beat-to-beat computation of indexes of cardiac mechanics from the SCG fiducial points. The algorithm was tested on two sleep recordings and yielded the identification of the fiducial points in more than 36,000 beats with a precision, quantified by the Positive Predictive Value, ≥99.2%. These positive findings provide the first evidence that cardiac mechanics may be explored by the automatic analysis of SCG long-lasting recordings, taken out of the laboratory setting, and in presence of significant heart rate modulations.

Gyrocardiography: A New Non-invasive Monitoring Method for the Assessment of Cardiac Mechanics and the Estimation of Hemodynamic Variables

Gyrocardiography (GCG) is a new non-invasive technique for assessing heart motions by using a sensor of angular motion – gyroscope – attached to the skin of the chest. In this study, we conducted simultaneous recordings of electrocardiography (ECG), GCG, and echocardiography in a group of subjects consisting of nine healthy volunteer men. Annotation of underlying fiducial points in GCG is presented and compared to opening and closing points of heart valves measured by a pulse wave Doppler. Comparison between GCG and synchronized tissue Doppler imaging (TDI) data shows that the GCG signal is also capable of providing temporal information on the systolic and early diastolic peak velocities of the myocardium. Furthermore, time intervals from the ECG Q-wave to the maximum of the integrated GCG (angular displacement) signal and maximal myocardial strain curves obtained by 3D speckle tracking are correlated. We see GCG as a promising mechanical cardiac monitoring tool that enables quantification of beat-by-beat dynamics of systolic time intervals (STI) related to hemodynamic variables and myocardial contractility.

Automatic Detection of Seismocardiogram Sensor Misplacement for Robust Pre-Ejection Period Estimation in Unsupervised Settings

Seismocardiography (SCG), the measurement of the local chest vibrations due to the movements of blood and the heart, is a non-invasive technique for assessing myocardial contractility via the pre-ejection period (PEP). Recently, SCG-based extraction of PEP has been shown to be an effective means of classifying decompensated from compensated heart failure patients, and thus can be potentially used for monitoring such patients at home. Accurate extraction of PEP from SCG signals hinges on lab-based population data (i.e., regression curves) linking particular time-domain features of the SCG signal to corresponding features from reference standard bulky instruments such as impedance cardiography (ICG). Such regression curves, in the case of SCG, have always been estimated based on the "ideal" positioning of the SCG sensor on the chest. However, in settings such as the home where users may position the SCG measurement hardware on the chest without supervision, it is likely that the sensor will not always be placed exactly on this "ideal" location on the sternum, but rather on other positions on the chest as well. In this study, we show for the first time that the regression curve for estimating PEP from SCG signals differs significantly as the position of the sensor changes. We further devise a method to automatically detect when the sensor is placed in any position other than the desired one in order to avoid inaccurate systolic time interval estimation. Our classification algorithm for this purpose resulted in 0.83 precision and 0.82 recall when classifying whether the sensor is placed in the desired position or not. The classifier was tested with heartbeats taken both at rest, and also during exercise recovery to ensure that waveform changes due to positioning could be accurately discriminated from those due to physiological effects.