Unobtrusive Estimation of Cardiovascular Parameters with Limb Ballistocardiography

Sensor-Location-Specific Joint Acquisition of Peripheral Artery Bioimpedance and Photoplethysmogram for Wearable Applications

BACKGROUND

Cardiovascular diseases (CVDs), being the culprit for one-third of deaths globally, constitute a challenge for biomedical instrumentation development, especially for early disease detection. Pulsating arterial blood flow, providing access to cardiac-related parameters, involves the whole body. Unobtrusive and continuous acquisition of electrical bioimpedance (EBI) and photoplethysmography (PPG) constitute important techniques for monitoring the peripheral arteries, requiring novel approaches and clever means.

METHODS

In this work, five peripheral arteries were selected for EBI and PPG signal acquisition. The acquisition sites were evaluated based on the signal morphological parameters. A small-data-based deep learning model, which increases the data by dividing them into cardiac periods, was proposed to evaluate the continuity of the signals.

RESULTS

The highest sensitivity of EBI was gained for the carotid artery (0.86%), three times higher than that for the next best, the posterior tibial artery (0.27%). The excitation signal parameters affect the measured EBI, confirming the suitability of classical 100 kHz frequency (average probability of 52.35%). The continuity evaluation of the EBI signals confirmed the advantage of the carotid artery (59.4%), while the posterior tibial artery (49.26%) surpasses the radial artery (48.17%). The PPG signal, conversely, commends the location of the posterior tibial artery (97.87%).

CONCLUSIONS

The peripheral arteries are highly suitable for non-invasive EBI and PPG signal acquisition. The posterior tibial artery constitutes a candidate for the joint acquisition of EBI and PPG signals in sensor-fusion-based wearable devices-an important finding of this research.

Wearable Seismocardiography‐Based Assessment of Stroke Volume in Congenital Heart Disease

Background

Patients with congenital heart disease (CHD) are at risk for the development of low cardiac output and other physiologic derangements, which could be detected early through continuous stroke volume (SV) measurement. Unfortunately, existing SV measurement methods are limited in the clinic because of their invasiveness (eg, thermodilution), location (eg, cardiac magnetic resonance imaging), or unreliability (eg, bioimpedance). Multimodal wearable sensing, leveraging the seismocardiogram, a sternal vibration signal associated with cardiomechanical activity, offers a means to monitoring SV conveniently, affordably, and continuously. However, it has not been evaluated in a population with significant anatomical and physiological differences (ie, children with CHD) or compared against a true gold standard (ie, cardiac magnetic resonance). Here, we present the feasibility of wearable estimation of SV in a diverse CHD population (N=45 patients).

Methods and Results

We used our chest‐worn wearable biosensor to measure baseline ECG and seismocardiogram signals from patients with CHD before and after their routine cardiovascular magnetic resonance imaging, and derived features from the measured signals, predominantly systolic time intervals, to estimate SV using ridge regression. Wearable signal features achieved acceptable SV estimation (28% error with respect to cardiovascular magnetic resonance imaging) in a held‐out test set, per cardiac output measurement guidelines, with a root‐mean‐square error of 11.48 mL and R 2 of 0.76. Additionally, we observed that using a combination of electrical and cardiomechanical features surpassed the performance of either modality alone.

Conclusions

A convenient wearable biosensor that estimates SV enables remote monitoring of cardiac function and may potentially help identify decompensation in patients with CHD.

Digital Optical Ballistocardiographic System for Activity, Heart Rate, and Breath Rate Determination during Sleep

In this work, we present a ballistocardiographic (BCG) system for the determination of heart and breath rates and activity of a user lying in bed. Our primary goal was to simplify the analog and digital processing usually required in these kinds of systems while retaining high performance. A novel sensing approach is proposed consisting of a white LED facing a digital light detector. This detector provides precise measurements of the variations of the light intensity of the incident light due to the vibrations of the bed produced by the subject's breathing, heartbeat, or activity. Four small springs, acting as a bandpass filter, connect the boards where the LED and the detector are mounted. Owing to the mechanical bandpass filtering caused by the compressed springs, the proposed system generates a BCG signal that reflects the main frequencies of the heartbeat, breathing, and movement of the lying subject. Without requiring any analog signal processing, this device continuously transmits the measurements to a microcontroller through a two-wire communication protocol, where they are processed to provide an estimation of the parameters of interest in configurable time intervals. The final information of interest is wirelessly sent to the user's smartphone by means of a Bluetooth connection. For evaluation purposes, the proposed system has been compared with typical BCG systems showing excellent performance for different subject positions. Moreover, applied postprocessing methods have shown good behavior for information separation from a single-channel signal. Therefore, the determination of the heart rate, breathing rate, and activity of the patient is achieved through a highly simplified signal processing without any need for analog signal conditioning.

Flexible Pressure Sensor Array with Multi-Channel Wireless Readout Chip

Flexible sensor arrays are widely used for wearable physiological signal recording applications. A high density sensor array requires the signal readout to be compatible with multiple channels. This paper presents a highly-integrated remote health monitoring system integrating a flexible pressure sensor array with a multi-channel wireless readout chip. The custom-designed chip features 64 voltage readout channels, a power management unit, and a wireless transceiver. The whole chip fabricated in a 65 nm complementary metal-oxide-semiconductor (CMOS) process occupies 3.7 × 3.7 mm², and the core blocks consume 2.3 mW from a 1 V supply in the wireless recording mode. The proposed multi-channel system is validated by measuring the ballistocardiogram (BCG) and pulse wave, which paves the way for future portable remote human physiological signals monitoring devices.

Classification of Blood Volume Decompensation State via Machine Learning Analysis of Multi-Modal Wearable-Compatible Physiological Signals

This paper presents a novel computational algorithm to estimate blood volume decompensation state based on machine learning (ML) analysis of multi-modal wearable-compatible physiological signals. To the best of our knowledge, our algorithm may be the first of its kind which can not only discriminate normovolemia from hypovolemia but also classify hypovolemia into absolute hypovolemia and relative hypovolemia. We realized our blood volume classification algorithm by (i) extracting a multitude of features from multi-modal physiological signals including the electrocardiogram (ECG), the seismocardiogram (SCG), the ballistocardiogram (BCG), and the photoplethysmogram (PPG), (ii) constructing two ML classifiers using the features, one to classify normovolemia vs. hypovolemia and the other to classify hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) sequentially integrating the two to enable multi-class classification (normovolemia, absolute hypovolemia, and relative hypovolemia). We developed the blood volume decompensation state classification algorithm using the experimental data collected from six animals undergoing normovolemia, relative hypovolemia, and absolute hypovolemia challenges. Leave-one-subject-out analysis showed that our classification algorithm achieved an F1 score and accuracy of (i) 0.93 and 0.89 in classifying normovolemia vs. hypovolemia, (ii) 0.88 and 0.89 in classifying hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) 0.77 and 0.81 in classifying the overall blood volume decompensation state. The analysis of the features embedded in the ML classifiers indicated that many features are physiologically plausible, and that multi-modal SCG-BCG fusion may play an important role in achieving good blood volume classification efficacy. Our work may complement existing computational algorithms to estimate blood volume compensatory reserve as a potential decision-support tool to provide guidance on context-sensitive hypovolemia therapeutic strategy.

The Latest Progress and Development Trend in the Research of Ballistocardiography (BCG) and Seismocardiogram (SCG) in the Field of Health Care

The current status of the research of Ballistocardiography (BCG) and Seismocardiogram (SCG) in the field of medical treatment, health care and nursing was analyzed systematically, and the important direction in the research was explored, to provide reference for the relevant researches. This study, based on two large databases, CNKI and PubMed, used the bibliometric analysis method to review the existing documents in the past 20 years, and made analyses on the literature of BCG and SCG for their annual changes, main countries/regions, types of research, frequently-used subject words, and important research subjects. The results show that the developed countries have taken a leading position in the researches in this field, and have made breakthroughs in some subjects, but their research results have been mainly gained in the area of research and development of the technologies, and very few have been actually industrialized into commodities. This means that in the future the researchers should focus on the transformation of BCG and SCG technologies into commercialized products, and set up quantitative health assessment models, so as to become the daily tools for people to monitor their health status and manage their own health, and as the main approaches of improving the quality of life and preventing diseases for individuals.

Reconstruction of Pulse Wave and Respiration from Wrist Accelerometer During Sleep

OBJECTIVE

Nocturnal recordings of heart rate and respiratory rate usually require several separate sensors or electrodes attached to different body parts -- a disadvantage for at-home screening tests and for large cohort studies. In this paper, we demonstrate that a state-of-the-art accelerometer placed at subjects' wrists can be used to derive reliable signal reconstructions of heartbeat (pulse wave intervals) and respiration during sleep.

METHODS

Based on 226 full-night recordings, we evaluate the performance of our signal reconstruction methodology with respect to polysomnography. We use a phase synchronization analysis metrics that considers individual heartbeats or breaths.

RESULTS

The quantitative comparison reveals that pulse-wave signal reconstructions are generally better than respiratory signal reconstructions. The best quality is achieved during deep sleep, followed by light sleep N2 and REM sleep. In addition, a suggested internal evaluation of multiple derived reconstructions can be used to identify time periods with highly reliable signals, particularly for pulse waves. Furthermore, we find that pulse-wave reconstructions are hardly affected by apnea and hypopnea events.

CONCLUSION

During sleep, pulse wave and respiration signals can simultaneously be reconstructed from the same accelerometer recording at the wrist without the need for additional sensors. Reliability can be increased by internal evaluation if the reconstructed signals are not needed for the whole sleep duration.

SIGNIFICANCE

The presented methodology can help to determine sleep characteristics and improve diagnostics and treatment of sleep disorders in the subjects' normal sleep environment.

Heart rate estimation from ballistocardiographic signals using deep learning

Objective.Ballistocardiography (BCG) is an unobtrusive approach for cost-effective and patient-friendly health monitoring. In this work, deep learning methods are used for heart rate estimation from BCG signals and are compared against five digital signal processing methods found in literature.Approach.The models are evaluated on a dataset featuring BCG recordings from 42 patients, acquired with a pneumatic system. Several different deep learning architectures, including convolutional, recurrent and a combination of both are investigated. Besides model performance, we are also concerned about model size and specifically investigate less complex and smaller networks.Main results.Deep learning models outperform traditional methods by a large margin. Across 14 patients in a held-out testing set, an architecture with stacked convolutional and recurrent layers achieves an average mean absolute error (MAE) of 2.07 beat min^-1, whereas the best-performing traditional method reaches 4.24 beat min^-1. Besides smaller errors, deep learning models show more consistent performance across different patients, indicating the ability to better deal with inter-patient variability, a prevalent issue in BCG analysis. In addition, we develop a smaller version of the best-performing architecture, that only features 8283 parameters, yet still achieves an average MAE of 2.32 beat min^-1on the testing set.Significance.This is the first study that applies and compares different deep learning architectures to heart rate estimation from bed-based BCG signals. Compared to signal processing algorithms, deep learning models show dramatically smaller errors and more consistent results across different individuals. The results show that using smaller models instead of excessively large ones can lead to sufficient performance for specific biosignal processing applications. Additionally, we investigate the use of fully convolutional networks for 1D signal processing, which is rarely applied in literature.

Wearable and Nearable Biosensors and Systems for Healthcare

Biosensors and systems in the form of wearables and "nearables" (i [...].

Bed-Based Ballistocardiography: Dataset and Ability to Track Cardiovascular Parameters

BACKGROUND

The goal of this work was to create a sharable dataset of heart-driven signals, including ballistocardiograms (BCGs) and time-aligned electrocardiograms (ECGs), photoplethysmograms (PPGs), and blood pressure waveforms.

METHODS

A custom, bed-based ballistocardiographic system is described in detail. Affiliated cardiopulmonary signals are acquired using a GE Datex CardioCap 5 patient monitor (which collects ECG and PPG data) and a Finapres Medical Systems Finometer PRO (which provides continuous reconstructed brachial artery pressure waveforms and derived cardiovascular parameters).

RESULTS

Data were collected from 40 participants, 4 of whom had been or were currently diagnosed with a heart condition at the time they enrolled in the study. An investigation revealed that features extracted from a BCG could be used to track changes in systolic blood pressure (Pearson correlation coefficient of 0.54 +/- 0.15), dP/dtmax (Pearson correlation coefficient of 0.51 +/- 0.18), and stroke volume (Pearson correlation coefficient of 0.54 +/- 0.17).

CONCLUSION

A collection of synchronized, heart-driven signals, including BCGs, ECGs, PPGs, and blood pressure waveforms, was acquired and made publicly available. An initial study indicated that bed-based ballistocardiography can be used to track beat-to-beat changes in systolic blood pressure and stroke volume.

SIGNIFICANCE

To the best of the authors' knowledge, no other database that includes time-aligned ECG, PPG, BCG, and continuous blood pressure data is available to the public. This dataset could be used by other researchers for algorithm testing and development in this fast-growing field of health assessment, without requiring these individuals to invest considerable time and resources into hardware development and data collection.

A Unified Approach to Wearable Ballistocardiogram Gating and Wave Localization

OBJECTIVE

Toward the ultimate goal of cuff-less blood pressure (BP) trend tracking via pulse transit time (PTT) using wearable ballistocardiogram (BCG) signals, we present a unified approach to the gating of wearable BCG and the localization of wearable BCG waves.

METHODS

We present a unified approach to localize wearable BCG waves suited to various gating and localization reference signals. Our approach gates individual wearable BCG beats and identifies candidate waves in each wearable BCG beat using a fiducial point in a reference signal, and exploits a pre-specified probability distribution of the time interval between the BCG wave and the fiducial point in the reference signal to accurately localize the wave in each wearable BCG beat. We tested the validity of our approach using experimental data collected from 17 healthy volunteers.

RESULTS

We showed that our approach could localize the J wave in the wearable wrist BCG accurately with both the electrocardiogram (ECG) and the wearable wrist photoplethysmogram (PPG) signals as reference, and that the wrist BCG-PPG PTT thus derived exhibited high correlation to BP.

CONCLUSION

We demonstrated the proof-of-concept of a unified approach to localize wearable BCG waves suited to various gating and localization reference signals compatible with wearable measurement.

SIGNIFICANCE

Prior work using the BCG itself or the ECG to gate the BCG beats and localize the waves to compute PTT are not ideally suited to the wearable BCG. Our approach may foster the development of cuff-less BP monitoring technologies based on the wearable BCG.

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 Personalized Beat-to-Beat Heart Rate Detection System From Ballistocardiogram for Smart Home Applications

This paper presents a ballistocardiogram (BCG) based beat-to-beat heart rate (HR) measurement system for healthcare applications in smart home. The BCG signal is picked up by two parallel connected piezoelectric elements, and processed by a robust HR detection algorithm. To deal with the diversity in BCG signal, a personalized heartbeat template is extracted to handle the diversity in BCG signal. The Pearson correlation coefficient is used to correlate between personalized template and the BCG signal. Heartbeats are detected by using the Hilbert Transform. The system is verified on 32 subjects with simultaneously recorded BCG and ECG signals. With the reference to ECG signal, we have achieved mean absolute relative error of the beat-to-beat intervals of 4.56%, and average absolute error ±standard deviation of absolute error for HR estimation in a 30-seconds window of 0.59 ±0.56 beats per minute. Meanwhile, 99.67% of the beat-to-beat intervals are detected on average.