Acute psychological stress has a multifaceted impact on cardiovascular physiology, including increases in chronotropy, inotropy, and vascular tone. Chronic exposure to stress may greatly increase cardiovascular risk. To examine the cardiovascular impact of acute stress comprehensively, new multimodal portable monitoring solutions are needed. We examined the feasibility of using a compact multimodal wearable patch to measure laboratory-based stress-induced cardiovascular responses in a diverse sample with recent myocardial infarction (MI) and healthy participants (N = 37, 28 MI) during a protocol with a public-speaking stressor. Using the electrocardiogram, seismocardiogram, and photoplethysmogram captured from the device, we found several significant (p < 0.05) autonomic changes in the pooled sample suggesting stress activation: increases in heart rate, chest photoplethysmogram amplitude, and perfusion index and decreases in heart rate variability, left ventricular ejection time, pulse arrival time, and pulse transit time. We, thus, demonstrated that a single wearable device can capture stress-induced cardiovascular changes, enabling simultaneous examination of stress-induced inotropic, chronotropic, and vascular effects. This portable, wireless chest patch may be useful in comprehensively and unobtrusively examining stress-induced cardiovascular effects in-lab. Given the public health importance of psychological stress and cardiovascular disease, future studies should assess the device’s full clinical potential in larger groups with longer monitoring periods.

Forecasting the. near-exact moments of cardiac phases is crucial for several cardiovascular health applications. For instance, forecasts can enable the timing of specific stimuli (e.g., image or text presentation in psycholinguistic experiments) to coincide with cardiac phases like systole (cardiac ejection) and diastole (cardiac filling). This capability could be leveraged to enhance the amplitude of a subject's response, prompt them in fight-or-flight scenarios or conduct retrospective analysis for physiological predictive models. While autoregressive models have been employed for physiological signal forecasting, no prior study has explored their application to forecasting aortic opening and closing timings. This work addresses this gap by presenting a comprehensive comparative analysis of autoregressive models, including various forms of Kalman filter-based implementations, that use previously detected R-peak, aortic opening, and closing timings from electrocardiogram (ECG) and seismocardiogram (SCG) to forecast subsequent timings. We evaluate the robustness of these models to noise introduced in both SCG signals and the output of feature detectors. Our findings indicate that time-varying and multi-feature algorithms outperform others, with forecast errors below 2 ms for R-peak, below 3 ms for aortic opening timing, and below 10 ms for aortic closing timing. Importantly, we elucidate the distinct advantages of integrating multi-feature models, which improve noise robustness, and time-varying approaches, which adapt to rapid physiological changes. These models can be extended to a wide range of short-term physiological predictive systems, such as acute stress detection, neuromodulation sensor feedback, or muscle fatigue monitoring, broadening their applicability beyond cardiac feature forecasting.

Orthostatic hypotension (OH), caused by efferent baroreflex failure, can lead to syncope and is associated with high mortality rates among individuals with neurodegenerative diseases. Several studies in recent years have aimed to estimate baroreflex sensitivity (BRS) during orthostatic stressors using measures of cardiovascular coupling (CVC): the degree of synchronization between time series cardiovascular signals. However, these efforts have relied on blood pressure sensing using bulky, wired setups, and the majority have only quantified changes in CVC during or after the occurrence of OH. In this study, we characterized CVC at rest in$N=26$participants (20 with a neurodegenerative disease) using a chest-worn patch that recorded electrocardiogram (ECG) and photoplethysmogram (PPG) signals. From the ECG and PPG data recorded during a 5-minute supine rest period prior to an orthostatic challenge, we derived interbeat interval (IBI) and PPG amplitude (PPG$_{\text{amp }}$) time series features as indices of cardiac rhythm and vascular function, respectively. We then quantified the coupling between IBI and$\text{PPG}_{\text{amp }}$using time delay stability (TDS). Following an active standing test, 12 participants experienced OH. We found that mean TDS during the rest period was 22.9% lower in the OH group than in the no-OH group$(p<\text{0. 0 1})$. Furthermore, we found that resting TDS was moderately correlated with the change in systolic blood pressure from supine to standing ($\rho=0.43, p<$0.05). Thus, we demonstrated the effectiveness of a multimodal wearable in capturing a marker of impaired resting CVC prior to OH occurrence. This work enables the deployment of wearable sensing for estimating BRS to assist with early screening of autonomic dysfunction in the future.

Opioid use disorder (OUD) is a significant global health issue, leading to severe physiological and psychological impacts and substantial societal costs. Current methods for assessing opioid withdrawal, primarily relying on subjective scales, suffer from limitations such as incomplete symptom capture, recall bias, and imprecision. Wearable sensor technologies offer a promising alternative for objective assessment, with previous studies demonstrating their ability to detect opioid use and measure related physiological changes. In this study we investigated the correlation between local cardio-mechanical variability quantified using dynamic time warping (DTW) distances of seismocardiogram (SCG) signals and subjective opioid withdrawal severity (SOWS) scores. In a 7-day in-patient protocol for individuals with OUD$(N=13)$, we found a statistically significant inverse correlation: shorter median DTW distances and reduced variance in SCG signals were associated with higher subjective withdrawal scores with statistically significant differences between the highest withdrawal bin and the two lowest bins ($\mathbf{p}=0.038$and$\mathbf{p}=0.044$, respectively). Our results suggests that local cardio-mechanical variability, as captured by wearable sensors and analyzed with DTW, can serve as a valuable indicator for quantifying opioid withdrawal severity, potentially enabling more timely and effective preventive care.

Seismocardiography is a potent non-invasive cardiovascular monitoring technique whose widespread adoption is currently limited in ambulatory settings due to its susceptibility to corruption from environmental noise. In the absence of a clean concurrently collected electrocardiogram (ECG) signal as a heartbeat reference, template matching paired with windowing methods can serve as a useful method by which to assess seismocardiogram (SCG) signal quality. However, windowing methods can introduce a time-shift in the segmentation of the SCG beats as compared to a template due to persistently adapting heart rate. In this study, we assess the performance of a state-of-the-art SCG signal quality assessment algorithm, dynamic time feature matching (DTFM), in ranking SCG beats by signal-to-noise ratio when introducing an artificial timedelay. We compare this performance against that of a novel methodology based on topological data analysis (TDA) using persistence diagrams. We found no significant difference$(p>0.05)$in ranking performance between topological data analysis (TDA) and dynamic time feature matching (DTFM) when SCG beats were segmented by true R-peak locations. However, we found that TDA significantly outperformed DTFM$(p<0.001)$when SCG beats were segmented 100, 200, or 300 ms earlier than the R-peak locations. These results suggest the potential promise of TDAbased methods for robust ECG-free SCG signal quality analysis. These advancements may facilitate the analysis of longitudinal SCG data taken in out-of-clinic settings in situations where ECG monitoring is not viable.

Cold exposure activates thermoregulatory processes through the autonomic nervous system that, while maintaining homeostasis, reduce peripheral blood flow and dexterity in the extremities. Transcutaneous median nerve stimulation (tMNS) represents a promising method for autonomic regulation through activation of parasympathetic vagal nerve afferents to the brain. However, the effect of this type of non-invasive therapy has not been investigated thoroughly in the context of thermoregulation. We analyzed peripheral skin temperature data in an ancillary study from a cohort of 19 participants who underwent two study visits of a protocol, each involving a dose-response activity, a cold pressor activity, and either tMNS or sham stimulation. Data from each protocol segment was averaged and then normalized as a percent difference from a baseline rest section. Paired t-tests and Pitman-Morgan tests were run on data from the cold pressor and dose-response activities respectively to determine statistical significance. We found that tMNS had a significant$(p=0.036)$effect of blunting peripheral skin temperature drops during cold pressor recovery as compared to sham stimulation. Additionally, tMNS had a general regulatory effect on skin temperature change during the dose-response activity, with significantly less variance than sham stimulation$(p<0.05)$. These results indicate that possible regulation of peripheral skin temperature with tMNS can serve as a therapy for cold exposure. Future work should investigate this mechanism in a larger cohort with a protocol designed to assess reactivity in temperature and dexterity to both cold and heat exposure.

Juvenile idiopathic arthritis (JIA) and its enthesitis related arthritis (ERA) subtype often present diagnostic challenges due to variable symptomatology and limited accessibility of advanced imaging. Here, we explore a non-invasive approach for diagnostic decision support using active vibrational sensing and machine learning to classify locomotion tasks to characterize symptomatology. By comparing classification performance across JIA subgroups, including ERA and its active/inactive states, we observed that ERA-related physiology reduces ML classifier accuracy, with sample comparison of ERA to the No ERA group yielding p = 0.002 and Cohen's d effect size d = 2.05. Notably, the classification metrics' performance was consistently higher on the No ERA group compared to the three ERA subgroups we considered, indicating that acoustic signatures from inflamed tendons and entheses modulate predictive performance. These findings suggest that task-based classification accuracy might serve as a surrogate biomarker for inflammation severity. Beyond presenting the methodology, ranging from data acquisition with a miniature vibration motor and accelerometer, to PCA-based feature extraction and multi-class classification, our results underscore the potential of integrating vibration sensing into clinical workflows. Ultimately, this study lays the groundwork for potentially enabling more robust, cost-effective diagnostic tools that could support early detection, monitoring, and personalized management of JIA and ERA.

Accurate, continuous monitoring of cardiac output (CO) is crucial for effective resuscitation management in hemorrhagic trauma, yet current gold-standard methods are invasive and impractical in field settings. This study introduces a fully non-invasive and wearable sensing-based approach utilizing electrocardiography (ECG), seismocardiography (SCG), and photoplethysmography (PPG) signals, integrated with machine learning algorithms, to enable stroke volume (SV) and CO estimation without requiring baseline calibration or normalization. This critical feature makes the model especially suitable for casualty care scenarios where baseline measurements are often unavailable. The proposed methodology was evaluated on a porcine model$(\mathrm{n}=6)$subjected to controlled hemorrhage and resuscitation protocols. Clinically-validated cardiovascular features were used as inputs for regression models, including linear, ridge, LASSO, random forest, and XGBoost regressors. Among these, the LASSO demonstrated the best performance, achieving a high correlation$(R=0.79)$and a mean absolute percentage error (MAPE) of 14.31%, well within clinically-acceptable limits for non-invasive CO monitoring. The framework reliably tracked SV trends crucial for clinical decision-making during resuscitation scenarios. This work highlights the potential for intelligent, noninvasive CO monitoring systems to improve clinical and trauma care outcomes.

Short-term physiological forecasting holds promise for applications requiring capture of rapid changes in physiological signals. Modeling these transient dynamics may enable the quantification of subtle physiological changes that can be critical in many real-time or sensitive contexts, such as assessing acute stress or closed-loop resuscitation. In this paper, we demonstrate the effectiveness of a time-varying autoregressive Kalman filterbased framework for short-term forecasting of physiological features. To eliminate the need for manual hyperparameter tuning, we integrate an adaptive mechanism that dynamically estimates the process and measurement noise parameters of the Kalman filter. Our results demonstrate that the proposed method outperforms baseline models by approximately 1 ms in predicting the next heartbeat's pre-ejection period and by$2-3 \text{ms}$in predicting the next heartbeat's left ventricular ejection period. Moreover, we demonstrate that it can achieve this improved performance without hyperparameter tuning. This work provides a robust forecasting framework for tracking physiological features and generating new ones to capture short-term physiological variations.

Noninvasive monitoring of hemodynamic parameters is essential for assessing cardiovascular function to enable early identification of high-risk individuals and help prevent injuries. However, current wearable solutions that use the electrocardiogram or photoplethysmogram offer a limited view of cardiovascular health, particularly in capturing cardiomechanical function. The seismocardiogram (SCG), a cardiomechanical signal, has shown promise in filling this gap with features previously shown to reflect key hemodynamic parameters. However, the SCG is susceptible to motion-artifacts, limiting its effectiveness in real-world settings where monitoring during physical activities or in hot environments is crucial due to the increased injury risk. In these environments, motion artifacts are variable and high in magnitude necessitating effective motion-artifact reduction algorithms. In this work, we propose a score-based generative diffusion model framework to obtain high quality SCG signals in daily-life environments. We leverage the periodicity of clean SCG beats to learn a probability space, which can be used as a prior to generate motion-free SCG signals from corrupted observations. Furthermore, generation quality is enhanced through a multi-generation averaging approach. Performance was analyzed on a waveform level and through feature extraction accuracy using a healthy dataset of participants undergoing exercises. We achieved mean absolute errors of 3.74 ms and 7.67 ms on two extracted SCG features: aortic valve opening (AO) and closing (AC), respectively, outperforming other signal processing and deep learning approaches from prior work. Furthermore, we demonstrated effective denoising capabilities on an unseen dataset collected in daily life settings, demonstrating the model's generalizability. Denoising systems such as this have the potential to be integrated into wearable systems, enabling reliable SCG signal acquisition for more accurate hemodynamic indices and reducing injuries in high-risk individuals.

Physiological markers of stress and neuromodulation (e.g., heart rate variability) are often inconsistent when it comes to quantifying changes in autonomic nervous system function. This inconsistency is explained by the autonomic nervous system's output varying across organ systems, as well as limitations in what each marker quantifies. In this work, we present an unsupervised learning approach we term StressFADS: Stress Factor Analysis via Dynamical Systems. StressFADS overcomes single marker inconsistencies by learning underlying dynamics that are shared across physiological markers of stress. StressFADS's encoder summarizes a time window of physiological markers and initializes a recurrent neural network (RNN) with this summary. This RNN is autonomously simulated forward in time, and the output at each timestep is fed through a dimension-ality reduction stage trained to reconstruct the original window of physiological markers. This forces the model to learn latent representations that capture shared dynamics across the markers. We apply StressFADS to the analysis of approximately 50 hours of 1-Hz cardiovascular and respiratory marker time series from a double-blind, randomized controlled trial (N = 26) involving trauma recall and active or sham cervical transcutaneous vagus nerve stimulation (tVNS). We find that StressFADS learned latent factors that successfully quantify differences between stress induced by trauma recall, a neutral condition, and active or sham tVNS. This is promising and motivates future work in learning latent autonomic states that more faithfully track changes in stress and intervention effects for just-in-time stress mitigation.

Pleural effusion (PE) affects millions of people and is caused by a wide variety of underlying diseases. The excess of fluid in the pleural cavity leads to shortness of breath and increased risk for infections that require timely interventions. Yet, existing clinical assessments lack the temporal resolution for continuous monitoring of PE and associated respiratory symptoms. Novel wearable technologies capable of measuring multi-frequency transthoracic bioimpedance (BioZ) continuously hold promise for PE monitoring. In this study, we evaluated the feasibility of monitoring a bilateral PE in a pig model using continuous multi-frequency transthoracic BioZ obtained with a previously-validated wearable device. A novel multi-resolution approach yielded strong and significant correlations to the infused PE at the DClbaseline, respiratory windows, and breath-by-breath resolutions. A total of 1.65 L of saline was infused bilaterally, first left then right, in steps of 275 mL. The low-frequency DC resistance yielded the strongest correlation to the PE size (R2=O.99, −14%/L, p

BACKGROUND: Posttraumatic stress disorder (PTSD) causes heightened fight-or-flight responses to traumatic memories (i.e., hyperarousal). Although hyperarousal is hypothesized to cause irregular breathing (i.e., respiratory variability), no quantitative markers of respiratory variability have been shown to correspond with PTSD symptoms in humans. OBJECTIVE: In this study, we define interpretable markers of respiration pattern variability (RPV) and investigate whether these markers respond during traumatic memories, correlate with PTSD symptoms, and differ in patients with PTSD. METHODS: We recruited 156 veterans from the Vietnam-Era Twin Registry to participate in a trauma recall protocol. From respiratory effort and electrocardiogram measurements, we extracted respiratory timings and rate using a robust quality assessment and fusion approach. We then quantified RPV using the interquartile range and compared RPV between baseline and trauma recall conditions, correlated PTSD symptoms to the difference between trauma recall and baseline RPV (i.e., ∆RPV), and compared ∆RPV between patients with PTSD and trauma-exposed controls. Leveraging a subset of 116 paired twins, we then uniquely controlled for factors shared by co-twins via within-pair analysis for further validation. RESULTS: We found RPV was increased during traumatic memories (p .001), ∆ RPV was positively correlated with PTSD symptoms (p .05), and patients with PTSD exhibited higher ∆ RPV than trauma-exposed controls (p . 05). CONCLUSIONS: This paper is the first to elucidate RPV markers that respond during traumatic memories, especially in patients with PTSD, and correlate with PTSD symptoms. SIGNIFICANCE: These findings encourage future studies outside the clinic, where interpretable markers of respiratory variability are used to track hyperarousal.

Seismocardiogram (SCG) signals are noninvasively obtained cardiomechanical signals containing important features for cardiovascular health monitoring. However, these signals are prone to contamination by motion noise, which can significantly impact accuracy and robustness of the measurements. A deep learning model based on the U-Net architecture is proposed to recover SCG signals contaminated by motion noise induced by walking. The model performance was evaluated through qualitative visualization, as well as quantitative analyses. Quantitative analyses included distance-based comparisons before and after applying our model. Analyses also included assessments of the model's efficacy in improving the performance of downstream tasks related to health parameter estimation during walking. Experimental findings revealed that the denoising model improved similarity to clean signals by approximately 90%. The performance of the model in enhancing heart rate estimation demonstrated a mean absolute error of 1.21 BPM and a root-mean-squared error (RMSE) of 1.97 BPM during walking after denoising with 9.16 BPM and 10.38 BPM improvements, respectively, compared to without denoising. Furthermore, the RMSEs of aortic opening and aortic closing time estimation after denoising for one dataset with catheter ground truth were 7.29 ms and 19.71 ms during walking, respectively, with 50.33 ms and 51.91 ms RMSE improvements compared to without denoising. And for another dataset with ICG-derived PEP ground truth, the RMSE of aortic opening time estimation after denoising was 10.21 ms during walking, with 38.74 ms RMSE improvement compared to without denoising. The proposed model attenuates motion noise from corrupted SCG signals while preserving cardiac information. This development paves the way for improved ambulatory cardiac health monitoring using wearable accelerometers during daily activities.

Recent advances in wearable sensing platforms and robust, dry electrode materials have enabled adhesive-free, continuous bioimpedance sensing [1]. However, long-term continuous monitoring of bioimpedance requires high-impedance dry-electrodes which can exacerbate input-impedance mismatch errors. We present a modified mathematical model and design methodology for designing a high-input impedance buffer to improve voltage sensing in four-electrode bioimpedance applications. The bootstrapped buffer design presented confers nearly 75% less common-mode to differential-mode conversion at low-frequencies, and 50% less error at high-frequencies based on the worst-case model.The voltage buffer was directly used and alternated with the baseline inputs inputs of a commercially available off the shelf integrated circuit (AD5940) to determine the extent of transient bioimpedance errors emerging from input impedance mismatch. In a small pilot study of two young male adults, we show the system reduces the time for the 5% convergence time of the final bioimpedance by 100.7s seconds on average. The voltage buffer typically reduces bioimpedance errors by 20% compared to the baseline inputs based on exponential decay curves of best-fit in dry-electrode applications.

Studies of stress often assume that baseline periods, stressors, and neutral conditions elicit their intended responses. This assumption may not always hold. In this study, we use a comprehensive set of cardiovascular and respiratory markers to demonstrate that factors including habituation and apprehension can lead to unintended physiological responses. Re-analyzing the data from a previous investigation of traumatic stress, we studied N = 26 participants with history of prior trauma. These participants took part in a three-hour protocol involving repeated exposure to traumatic stressors and neutral conditions. Electrocardiogram, photoplethysmogram, seismocardiogram, and respiratory effort signals were collected. Unlike previous studies, we investigated the physiological responses to each neutral condition and traumatic stressor separately, rather than aggregating over repetitions. We find that habituation reduces the physiological responses to repeated traumatic stressors. We also observe transient stress responses during the first neutral conditions of the protocol. We attribute this stress to apprehension. Notably, the stress exhibited during the first neutral condition was on par with that of the second traumatic stressor. To our knowledge, the data herein are the first to quantitatively show that apprehension during a neutral condition can produce stress responses on par with trauma recall. These results advocate against classifying periods of data as "stress" or "no stress" based solely on the protocol. Instead, studies of stress should incorporate physiological sensing to assess whether the protocol’s intended effects are consistent with observed changes in physiological markers.

Uncontrolled hemorrhaging is a time-sensitive condition that affects military and civilian populations, necessitating the need for timely blood loss evaluations during prehospital care. These evaluations have been shown to be correlated with hemodynamic parameters accessible using the seismocardiogram (SCG), a noninvasively measured cardiac signal. However, SCG usage for hemorrhage control during transport in prehospital care vehicles is difficult due to the environmental vibrations affecting signal quality which is not easily verifiable. In this work, we test if pertinent SCG features could be detected in the presence of military vehicle artifacts. Using a novel simulated and realistic data collection approach with multiple vehicles, we applied robust denoising and feature extraction algorithms to improve SCG feature detection accuracy. We determined that this data collection approach is effective for testing vibrational artifacts and that detection accuracy is drastically improved across all tested vehicles after applying our processing pipeline, This suggests that SCG processing algorithms can be tested in this manner, and such processing pipeline would enable the SCG to be used in uncontrolled settings.

Acute decompensated heart failure (ADHF) is one of the leading causes for hospitalization in the US. Patient’s weight and limb girth are monitored to assess medication efficacy and readiness for hospital discharge. Such metrics are assessed manually by a trained professional at discrete time intervals, thereby missing potentially critical information about treatment responsiveness. Full, upper, and lower-body bioimpedance analysis have shown promise in tracking changes in patient weight, but requires bulky systems to place electrodes across different limbs. In this work, we evaluate the use of convenient ankle limb bioimpedance for tracking fluid status changes in a proof-of-concept dataset obtained in 9 hospitalized patients with ADHF. Continuous bioimpedance measurements were recorded while the patients received diuretic treatment for more than 2 days. Biomarkers derived from the low-frequency bioimpedance measurements, ratio of low-to-high bioimpedance measurements and limb girth were significantly different from hospital admission to discharge. Bioimpedance measures correlated to changes in weight (Pearson’s r = − 0.63, subject-specific), and limb girth (Pearson’s r = − 0.83 and r = − 0.87, subject-specific and global, respectively). Such bioimpedance measures captured from the ankle in a wearable form-factor and in a continuous manner provide better insight to the patient’s acute response to medication. Such a tool can be further used to better schedule medications and alter dosage in the clinic and be sent home with patients to detect fluid accumulation early.

Current methods for quantifying osteoarthritis severity have limited resolution and accessibility. Patient-recorded outcome measures such as the Knee Injury and Osteoarthritis Outcome Score (KOOS) capture symptom severity, but are subjectively reported and have little correlation with quantifiable metrics of disease such as Kellgren-Lawrence x-ray grade or MRI findings. Knee acoustic emissions (KAEs) offer a convenient, noninvasive option for quantifying joint health. Here, we use machine learning and wearable design to create an interpretable two-stage algorithm for combining KAEs and KOOS scores into an objective, more accessible method of quantifying disease severity. Our algorithm successfully discriminated between early and late-stage osteoarthritis (balanced accuracy = 85%, ROC-AUC = 0.88). The addition of KAEs improved classification of osteoarthritis severity over the use of KAEs (balanced accuracy = 53%, ROC-AUC = 0.786) or KOOS scores alone (balanced accuracy = 63%, ROC-AUC = 0.593). The findings suggest that KAEs combined with patient-recorded metrics can be used to make a more objective and accessible metric for digitally monitoring knee joint health.

Continuous remote monitoring of key health parameters can be facilitated by noninvasive cardiovascular signals such as the seismocardiogram (SCG) and electrocardiogram (ECG). However, the accuracy of health parameter estimation is dependent on the quality of the signals collected and the algorithms used, which can be particularly challenging in the presence of environmental noise and motion artifacts. In this work, SeismoNet, a highly-sensitive, low-power, multi-node wireless wearable platform is introduced that enables recording of small amplitude acceleration signals (especially SCG signals) and ECG from multiple points on the human body. Using the SeismoNet, we performed a study involving 20 human participants with five nodes placed around the trunk, and showed that combining multiple nodes can improve the estimation performance of heart rate (HR) and respiration rate (RR) by approximately 30% and 23%, respectively. This suggests that combining acceleration data from multiple points on the body can enhance the cardiac and respiratory content of the acquired data, resulting in more accurate predictions. Furthermore, the SeismoNet platform and the dataset collected can be utilized to explore research questions related to multi-point physiological sensing.

Knee health assessment is crucial in reducing the risk of knee injuries, which can have a significant impact on individuals of all ages and activity levels. Knee acoustic emissions (KAEs) have emerged as a promising bio-signal for assessing knee health, which can be recorded using a wide-band microphone. However, the monitoring of KAE has been dependent on expensive and bulky systems, limiting the accessibility and scalability of the technology for a large population. In this work, we introduce a low-cost small form-factor wireless wearable knee monitoring system (KneeMS), capable of recording KAEs. The frequency response of KneeMS was evaluated through spectral density (PSD) comparison against a previously validated benchtop system. A Pearson’s r = 0.99 was achieved for PSD comparison between the sine sweep response of KneeMS and the benchtop system. A human participant study was conducted to validate the system’s performance in the context of KAEs, showing that KneeMS performs comparably to the benchtop system in joint loading experiments. The study achieved a Pearson’s r = 0.96 for root mean square (RMS) amplitude comparison between KneeMS and benchtop system. Moreover, the study showed that KneeMS exhibits an RMS ratio behavior similar to the benchtop for different joint loading conditions. Thus, KneeMS offers a more efficient, scalable, and accessible solution for measuring KAEs. The system’s portability and wireless connectivity enables continuous monitoring of KAEs, offering a solution for remote and longitunal monitoring for future studies on the use of KAEs for knee health monitoring.

Non-invasive vibration measurements from the knee offer a convenient and affordable alternative to benchtop or biomechanics lab joint health monitoring systems. Recently, joint acoustic emissions (JAEs) measured from the knee were shown to be an indicator of knee health. However, the origin of JAEs is still not fully understood, which limits its acceptance and use by clinical experts. In this proof-of-concept study, rather than relying on the movements of the knee and corresponding frictional rubbing of internal surfaces to produce vibrations, we propose using an active vibration sensing approach with a known vibration source interrogating the knee. We aim to elucidate the linkage between knee vibration characteristics and structural changes in the joint following injuries. We measured tibial vibration responses of two participants using a laser vibrometer system to quantify the frequency band where the most repeatable tibial vibration measurement can be taken. Subsequently, a custom-designed wearable system measured mid-activity tibial vibration characteristics from four participants (five healthy knees and three knees with prior acute injury) during unloaded knee flexion-extensions. An active sensing knee health score was defined as the ratio of the changes in low- to high-frequency response during flexion-extension. Since changes in the boundary of tibia would alter low-frequency response more than high frequency response, we found that increased knee laxity with acute injuries resulted in an increased active sensing knee health score. Our findings demonstrate the potential of active vibration sensing as an interpretable, computationally inexpensive alternative to JAEs for wearable knee health assessment.

Stress leads to widespread peripheral effects, including manifestations of respiratory distress. The combination of respiratory monitoring and non-invasive Peripheral Nerve Stimulation (PNS) represents a promising technological approach to quantify and reduce the physiological manifestations of stress. Such technologies require non-invasive, reliable respiratory information with adequate signal quality during various conditions. In this work, we computed an established respiratory quality index (RQI) on four respiratory signals derived from three common respiratory sensing modalities (respiratory effort (RSP), electrocardiogram-derived respiration (EDR), and Impedance Pneumography (IP)) in a complex stress protocol wherein 15 subjects underwent three stressors while receiving 1 of 3 active PNS modalities or sham. Our results indicate that the RQI of all signals changed substantially throughout the protocol with a maximal reduction from baseline of 21.28% (p< 0.001) during stressors involving speech. Further, RSP and IP resulted in the highest average quality and both were significantly higher in quality than the two EDR signals (p < 0.001). These results provide unique information that may inform the design of new technologies and studies leveraging respiratory markers for continuous stress detection and mitigation.

OBJECTIVE: To design and validate a novel deep generative model for seismocardiogram (SCG) dataset augmentation. SCG is a noninvasively acquired cardiomechanical signal used in a wide range of cardivascular monitoring tasks; however, these approaches are limited due to the scarcity of SCG data. METHODS: A deep generative model based on transformer neural networks is proposed to enable SCG dataset augmentation with control over features such as aortic opening (AO), aortic closing (AC), and participant-specific morphology. We compared the generated SCG beats to real human beats using various distribution distance metrics, notably Sliced-Wasserstein Distance (SWD). The benefits of dataset augmentation using the proposed model for other machine learning tasks were also explored. RESULTS: Experimental results showed smaller distribution distances for all metrics between the synthetically generated set of SCG and a test set of human SCG, compared to distances from an animal dataset (1.14× SWD), Gaussian noise (2.5× SWD), or other comparison sets of data. The input and output features also showed minimal error (95% limits of agreement for pre-ejection period [PEP] and left ventricular ejection time [LVET] timings are 0.03 ± 3.81 ms and -0.28 ± 6.08 ms, respectively). Experimental results for data augmentation for a PEP estimation task showed 3.3% accuracy improvement on an average for every 10% augmentation (ratio of synthetic data to real data). CONCLUSION: The model is thus able to generate physiologically diverse, realistic SCG signals with precise control over AO and AC features. This will uniquely enable dataset augmentation for SCG processing and machine learning to overcome data scarcity.

Wearable systems can provide accurate cardiovascular evaluations by estimating hemodynamic indices in real-time. Key hemodynamic parameters can be non-invasively estimated using the seismocardiogram (SCG), a cardiomechanical signal whose features link to cardiac events like aortic valve opening (AO) and closing (AC). However, tracking a single SCG feature is unreliable due to physiological changes, motion artifacts, and external vibrations. This work proposes an adaptable Gaussian Mixture Model (GMM) to track multiple AO/AC correlated features in quasi-real-time from the SCG. The GMM calculates the likelihood of an extremum being an AO/AC feature for each SCG beat. The Dijkstra algorithm selects heartbeat-related extrema, and a Kalman filter updates the GMM parameters while filtering features. Tracking accuracy is tested on a porcine hypovolemia dataset with varying noise levels. Blood volume loss estimation accuracy is also evaluated using the tracked features on a previously developed model. Experimental results show a 4.5 ms tracking latency and average root mean square errors (RMSE) of 1.47 ms for AO and 7.67 ms for AC at 10 dB noise, and 6.18 ms for AO and 15.3 ms for AC at -10 dB noise. When considering all AO/AC correlated features, the combined RMSE remains in similar ranges, specifically 2.70 ms for AO and 11.91 ms for AC at 10 dB noise, and 7.50 ms for AO and 16.35 ms for AC at -10 dB noise. The proposed algorithm offers low latency and RMSE for all tracked features, making it suitable for real-time processing. These systems enable accurate, timely extraction of hemodynamic indices for many cardiovascular monitoring applications, including trauma care in field settings.

Chronic respiratory diseases affect millions and are leading causes of death in the US and worldwide. Pulmonary auscultation provides clinicians with critical respiratory health information through the study of Lung Sounds (LS) and the context of the breathing-phase and chest location in which they are measured. Existing auscultation technologies, however, do not enable the simultaneous measurement of this context, thereby potentially limiting computerized LS analysis. In this work, LS and Impedance Pneumography (IP) measurements were obtained from 10 healthy volunteers while performing normal and forced-expiratory (FE) breathing maneuvers using our wearable IP and respiratory sounds (WIRS) system. Simultaneous auscultation was performed with the Eko CORE stethoscope (EKO). The breathing-phase context was extracted from the IP signals and used to compute phase-by-phase (Inspiratory (I), expiratory (E), and their ratio (I:E)) and breath-by-breath acoustic features. Their individual and added value was then elucidated through machine learning analysis. We found that the phase-contextualized features effectively captured the underlying acoustic differences between deep and FE breaths, yielding a maximum F1 Score of 84.1 ±11.4% with the phase-by-phase features as the strongest contributors to this performance. Further, the individual phase-contextualized models outperformed the traditional breath-by-breath models in all cases. The validity of the results was demonstrated for the LS obtained with WIRS, EKO, and their combination. These results suggest that incorporating breathing-phase context may enhance computerized LS analysis. Hence, multimodal sensing systems that enable this, such as WIRS, have the potential to advance LS clinical utility beyond traditional manual auscultation and improve patient care.

We employed wearable multimodal sensing (heart rate and triaxial accelerometry) with machine learning to enable early prediction of impending exertional heat stroke (EHS). US Army Rangers and Combat Engineers (N = 2,102) were instrumented while participating in rigorous 7-mile and 12-mile loaded rucksack timed marches. There were three EHS cases, and data from 478 Rangers were analyzed for model building and controls. The data-driven machine learning approach incorporated estimates of physiological strain (heart rate) and physical stress (estimated metabolic rate) trajectories, followed by reconstruction to obtain compressed representations which then fed into anomaly detection for EHS prediction. Impending EHS was predicted from 33 to 69 min before collapse. These findings demonstrate that low dimensional physiological stress to strain patterns with machine learning anomaly detection enables early prediction of impending EHS which will allow interventions that minimize or avoid pathophysiological sequelae. We describe how our approach can be expanded to other physical activities and enhanced with novel sensors.

Inertial measurement units (IMUs) are extensively used for body motion tracking applications. Despite their ubiquity, they often suffer from sensor drift over time, and environmental disturbances. Additionally, their use cases are mostly limited to applications with slowly varying accelerations and low-dynamic motions. Sensor fusion algorithms are used for scenarios where more dynamic, faster motions are encountered. However, such algorithms often come with high computational costs. In this work, we present a low-drift, computationally-efficient motion tracking system that suppresses ambient magnetic noise and is applicable to various motion dynamics. We augmented inertial sensors with localized magnets, and implemented a localization algorithm that takes in the magnetic measurements and outputs the sensor positions as the sensors move in the vicinity of the magnets. For applications with movements around a central joint, we extended our position tracking to a joint angle measurement platform. We conducted two preliminary studies to evaluate our system performance, and validated our system against a computer vision system. Our first study uses a goniometric setup to evaluate drift-reductions in angle estimates. Our method is compared against a commonly-used IMU-based method. We collected 60 minutes of data from 4 study sessions, with both static conditions and various dynamic motions. The motions had angular velocities ranging from 0 to 47 (°/sec). Results show the average root mean square error (RMSE) of 1° for static and 2.7° for dynamic motions. In the second study, an on-body setup monitors the knee flexions and extensions performed by a pilot user. We collected 30 minutes of data from 4 study sessions. Our system reports the average RMSE of 3.7° for dynamic motions with an average angular velocity of 17 (°/sec). Based on these promising results, in future work we will extend our user studies to a greater number of users to evaluate the generalizability.

OBJECTIVE: At-home monitoring of respiration is of critical urgency especially in the era of the global pandemic due to COVID-19. Electrocardiogram (ECG) and seismocardiogram (SCG) signals-measured in less cumbersome contact form factors than the conventional sealed mask that measures respiratory air flow-are promising solutions for respiratory monitoring. In particular, respiratory rates (RR) can be estimated from ECG-derived respiratory (EDR) and SCG-derived respiratory (SDR) signals. Yet, non-respiratory artifacts might still be present in these surrogates of respiratory signals, hindering the accuracy of the RRs estimated. METHODS: In this paper, we propose a novel U-Net-based cascaded framework to address this problem. The EDR and SDR signals were transformed to the spectro-temporal domain and subsequently denoised by a 2D U-Net to reduce the non-respiratory artifacts. MAJOR RESULTS: ) of 0.89 using data collected from our chest-worn wearable patch. We also qualitatively provided insights on the complementariness between EDR and SDR signals and demonstrated the generalizability of the proposed framework. CONCLUSION: ECG and SCG collected from a chest-worn wearable patch can complement each other and yield reliable RR estimation using the proposed cascaded framework. SIGNIFICANCE: We anticipate that convenient and comfortable ECG and SCG measurement systems can be augmented with this framework to facilitate pervasive and accurate RR measurement.

Although respiratory failure is one of the primary causes of admission to intensive care, the importance placed on measurement of respiratory parameters is commonly overshadowed compared to cardiac parameters. With the increased demand for unobtrusive yet quantifiable respiratory monitoring, many technologies have been proposed recently. However, there are challenges to be addressed for such technologies to enable widespread use. In this work, we explore the feasibility of using load cell sensors embedded on a hospital bed for monitoring respiratory rate (RR) and tidal volume (TV). We propose a globalized machine learning (ML)-based algorithm for estimating TV without the requirement of subject-specific calibration or training. In a study of 15 healthy subjects performing respiratory tasks in four different postures, the outputs from four load cell channels and the reference spirometer were recorded simultaneously. A signal processing pipeline was implemented to extract features that capture respiratory movement and the respiratory effects on the cardiac (i.e., ballistocardiogram, BCG) signals. The proposed RR estimation algorithm achieved a root mean square error (RMSE) of 0.6 breaths per minute (brpm) against the ground truth RR from the spirometer. The TV estimation results demonstrated that combining all three axes of the low-frequency force signals and the BCG heartbeat features best quantifies the respiratory effects of TV. The model resulted in a correlation and RMSE between the estimated and true TV values of 0.85 and 0.23 L, respectively, in the posture independent model without electrocardiogram (ECG) signals. This study suggests that load cell sensors already existing in certain hospital beds can be used for convenient and continuous respiratory monitoring in general care settings.

Current methods of evaluating essential tremor (ET) either rely on subjective ratings or use limited tremor metrics (i.e., severity/amplitude and frequency). In this study, we explored performance metrics from Fitts’ law tasks that replicate and expand existing tremor metrics, to enable low-cost, home-based tremor quantification and analyze the cursor movements of individuals using a 3D mouse while performing a collection of drawing tasks. We analyzed the 3D mouse cursor movements of 11 patients with ET and three controls, on three computer-based tasks—a spiral navigation (SPN) task, a rectangular track navigation (RTN) task, and multi-directional tapping/clicking (MDT)—with several performance metrics (i.e., outside area (OA), throughput (TP in Fitts’ law), path efficiency (PE), and completion time (CT). Using an accelerometer and scores from the Essential Tremor Rating Assessment Scale (TETRAS), we correlated the proposed performance metrics with the baseline tremor metrics and found that the OA of the SPN and RTN tasks were strongly correlated with baseline tremor severity (R2= 0.57, and R2= 0.83). We also found that the TP in the MDT tasks were strongly correlated with tremor frequency (R2= 0.70). In addition, as the OA of the SPN and RTN tasks was correlated with tremor severity and frequency, it may represent an independent metric that increases the dimensionality of the characterization of an individual's tremor. Thus, this pilot study of the analysis of those with ET-associated tremor performing Fitts’ law tasks demonstrates the feasibility of introducing a new tremor metric that can be expanded for repeatable multi-dimensional data analyses.

Joint acoustic emission (JAE) sensing is emerging as a potential modality for quantitative at-home joint health assessment. We designed and validated a low-profile, easy-to-use wearable system for JAE sensing at the wrist. An embedded microcontroller on a wrist-worn printed circuit board is used to record multi-microphone (mic) joint acoustics sampled at 46.875 kHz using an on-board analog-to-digital converter. A flex sensor and a force sensitive resistor (FSR) are sampled at 300 Hz to capture kinematics and mic backing force. Custom sensor casing solutions and real-time user feedback systems enhance audio sensing capabilities at locations both proximal and distal to the wrist. An experiment extracting wrist JAEs from healthy adults (n=6) allowed for comparison to a previously established benchtop JAE sensing system. The acoustic data were bandpass filtered (150 Hz-5.5 kHz). Qualitative observations reveal the wearable system mics successfully capture JAEs. Signal-to-noise ratio (SNR), intraclass correlation coefficient (model 3, k), and coefficients of variability were calculated to evaluate acoustic signal strength and repeatability in both systems' recordings. SNR reveals that JAE acoustic signal strength is higher when recorded using the wearable system than with the benchtop system (p<0.01). Reliability measures show that the wearable system records JAEs with similar levels of reliability to the benchtop system. Initial recordings in clinical wrist JAE research studies demonstrate high quality JAE measurements from children with Juvenile Idiopathic Arthritis (JIA) and healthy controls (HCs) (4 JIA, 3 HC). Eventually, this system may be developed into a tool for at-home wrist joint health monitoring.

Impedance pneumography (IP), a measure of the changes in the lung and thoracic bioimpedance, holds promise for non-invasive monitoring of pulmonary health. A key limitation of IP is the need for complex and frequent calibrations that require the subject to perform various maneuvers. In this work, we explore different calibration approaches to reduce the effects of inter-subject variability and postural changes on IP by utilizing a dual-frequency calibration approach. Dual-frequency IP was deployed for the first time in this work and its performance in estimating tidal volume (TV) was evaluated and compared to the conventional single frequency approaches. TV values obtained from a spirometer estimated with the subject- and posture-specific IP calibration approach are shown to correlate highly with the ground truth TV$(r > 0.9)$in all postures, including supine, left/right lateral, and seated postures for both 5 kHz and 100 kHz IP signals. Eliminating posture specificity results in a correlation of$r > 0.8$• With the globalized calibration approach that does not require any subject or posture-specific calibration, a correlation of$r=0.75$was achieved with the dual-frequency approach, and this was higher than the corresponding correlation of around$r=0.68$using any single frequency. This result has implications for the feasibility of dual-frequency IP for mitigating inter-subject variability and posture-specific calibrations.

OBJECTIVE: We developed a wearable watch-based device to provide noninvasive, cuff-less blood pressure (BP) estimation in an at-home setting. METHODS: The watch measures single-lead electrocardiogram (ECG), tri-axial seismocardiogram (SCG), and multi-wavelength photoplethysmogram (PPG) signals to compute the pulse transit time (PTT), allowing for BP estimation. We sent our custom watch device and an oscillometric BP cuff home with 21 healthy subjects, and captured the natural variability in BP over the course of a 24-hour period. RESULTS: After calibration, our Pearson correlation coefficient (PCC) of 0.69 and root-mean-square-error (RMSE) of 2.72 mmHg suggest that noninvasive PTT measurements correlate with around-the-clock BP. Using a novel two-point calibration method, we achieved a RMSE of 3.86 mmHg. We further demonstrated the potential of a semi-globalized adaptive model to reduce calibration requirements. CONCLUSION: This is, to the best of our knowledge, the first time that BP has been comprehensively estimated noninvasively using PTT in an at-home setting. We showed a more convenient method for obtaining ambulatory BP than through the use of the standard oscillometric cuff. We presented new calibration methods for BP estimation using fewer calibration points that are more practical for a real-world scenario. SIGNIFICANCE: A custom watch (SeismoWatch) capable of taking multiple BP measurements enables reliable remote monitoring of daily BP and paves the way towards convenient hypertension screening and management, which can potentially reduce hospitalizations and improve quality of life.

OBJECTIVE: We studied and compared joint acoustical emissions (JAEs) in loaded and unloaded knees as digital biomarkers for evaluating knee health status during the course of treatment in patients with juvenile idiopathic arthritis (JIA). METHODS: JAEs were recorded from 38 participants, performing 10 repetitions of unloaded flexion/extension (FE) and loaded squat exercises. A novel algorithm was developed to detect and exclude rubbing noise and loose microphone artifacts from the signals, and then 72 features were extracted. These features were down-selected based on different criteria to train three logistic regression classifiers. The classifiers were trained with healthy and pre-treatment data and were used to predict the knee health scores of post-treatment data for the same patients with JIA who had a follow-up recording. This knee health score represents the probability of having JIA in a subject (0 for healthy and 1 for arthritis). RESULTS: Post-treatment knee health scores were lower than pre-treatment scores, agreeing with the clinical records of successful treatment. Regarding loaded versus unloaded knee scores, the squats achieved a higher score on average compared to FEs. CONCLUSION: In healthy subjects with smooth cartilage, the knee scores of squats and FEs were similar indicating that vibrations from the friction of articulating surfaces do not significantly change by the joint load. However, in subjects with JIA, the scores of squats were higher than the scores of FEs, revealing that these two exercises contain different, possibly clinically relevant, information that could be used to further improve this novel assessment modality in JIA.

The ballistocardiogram (BCG), a cardiac vibration signal, has been widely investigated for continuous monitoring of heart rate (HR). Among BCG sensing modalities, a hospital bed with multi-channel load-cells could provide robust HR estimation in hospital setups. In this work, we present a novel array processing technique to improve the existing HR estimation algorithm by optimizing the fusion of information from multiple channels. The array processing includes a Gaussian curve to weight the joint probability according to the reference value obtained from the previous inter-beat-interval (IBI) estimations. Additionally, the probability density functions were selected and combined according to their reliability measured by q-values. We demonstrate that this array processing significantly reduces the HR estimation error compared to state-of-the-art multi-channel heartbeat detection algorithms in the existing literature. In the best case, the average mean absolute error (MAE) of 1.76 bpm in the supine position was achieved compared to 2.68 bpm and 1.91 bpm for two state-of-the-art methods from the existing literature. Moreover, the lowest error was found in the supine posture (1.76 bpm) and the highest in the lateral posture (3.03 bpm), thus elucidating the postural effects on HR estimation. The IBI estimation capability was also evaluated, with a MAE of 16.66 ms and confidence interval (95%) of 38.98 ms. The results demonstrate that improved HR estimation can be obtained for a bed-based BCG system with the multi-channel data acquisition and processing approach described in this work.

Hypovolemia remains the leading cause of preventable death in trauma cases. Recent research has demonstrated that using noninvasive continuous waveforms rather than traditional vital signs improves accuracy in early detection of hypovolemia to assist in triage and resuscitation. This work evaluates random forest models trained on different subsets of data from a pig model (n = 6) of absolute (bleeding) and relative (nitroglycerin-induced vasodilation) progressive hypovolemia (to 20% decrease in mean arterial pressure) and resuscitation. Features for the models were derived from a multi-modal set of wearable sensors, comprised of the electrocardiogram (ECG), seismocardiogram (SCG) and reflective photoplethysmogram (RPPG) and were normalized to each subject.s baseline. The median RMSE between predicted and actual percent progression towards cardiovascular decompensation for the best model was 30.5% during the relative period, 16.8% during absolute and 22.1% during resuscitation. The least squares best fit line over the mean aggregated predictions had a slope of 0.65 and intercept of 12.3, with an R2value of 0.93. When transitioned to a binary classification problem to identify decompensation, this model achieved an AUROC of 0.80. This study: a) developed a global model incorporating ECG, SCG and RPPG features for estimating individual-specific decompensation from progressive relative and absolute hypovolemia and resuscitation; b) demonstrated SCG as the most important modality to predict decompensation; c) demonstrated efficacy of random forest models trained on different data subsets; and d) demonstrated adding training data from two discrete forms of hypovolemia increases prediction accuracy for the other form of hypovolemia and resuscitation.

OBJECTIVE: Optimizing peri-operative fluid management has been shown to improve patient outcomes and the use of stroke volume (SV) measurement has become an accepted tool to guide fluid therapy. The Transesophageal Doppler (TED) is a validated, minimally invasive device that allows clinical assessment of SV. Unfortunately, the use of the TED is restricted to the intra-operative setting in anesthetized patients and requires constant supervision and periodic adjustment for accurate signal quality. However, post-operative fluid management is also vital for improved outcomes. Currently, there is no device regularly used in clinics that can track patient's SV continuously and non-invasively both during and after surgery. METHODS: In this paper, we propose the use of a wearable patch mounted on the mid-sternum, which captures the seismocardiogram (SCG) and electrocardiogram (ECG) signals continuously to predict SV in patients undergoing major surgery. In a study of 12 patients, hemodynamic data was recorded simultaneously using the TED and wearable patch. Signal processing and regression techniques were used to derive SV from the signals (SCG and ECG) captured by the wearable patch and compare it to values obtained by the TED. RESULTS: The results showed that the combination of SCG and ECG contains substantial information regarding SV, resulting in a correlation and median absolute error between the predicted and reference SV values of 0.81 and 7.56 mL, respectively. SIGNIFICANCE: This work shows promise for the proposed wearable-based methodology to be used as an alternative to TED for continuous patient monitoring and guiding peri-operative fluid management.

Objective: To estimate instantaneous oxygen uptake VO2with a small, low-cost wearable sensor during exercise and daily activities in order to enable monitoring of energy expenditure (EE) in uncontrolled settings. We aim to do so using a combination of seismocardiogram (SCG), electrocardiogram (ECG) and atmospheric pressure (AP) signals obtained from a minimally obtrusive wearable device. Methods: In this study, subjects performed a treadmill protocol in a controlled environment and an outside walking protocol in an uncontrolled environment. During testing, the COSMED K5 metabolic system collected gold standard breath-by-breath (B×B) data and a custombuilt wearable patch placed on the mid-sternum collected SCG, ECG and AP signals. We extracted features from these signals to estimate the B×B VO2data obtained from the COSMED system. Results: In estimating instantaneous VO2, we achieved our best results on the treadmill protocol using a combination of SCG (frequency) and AP features (RMSE of 3.68 ± 0.98 ml/kg/min and R2of 0.77). For the outside protocol, we achieved our best results using a combination of SCG (frequency), ECG and AP features (RMSE of 4.3 ± 1.47 ml/kg/min and R2of 0.64). In estimating VO2consumed over one minute intervals during the protocols, our median percentage error was 15.8% for the treadmill protocol and 20.5% for the outside protocol. Conclusion: SCG, ECG and AP signals from a small wearable patch can enable accurate estimation of instantaneous VO2in both controlled and uncontrolled settings. SCG signals capturing variation in cardio-mechanical processes, AP signals, and state of the art machine learning models contribute significantly to the accurate estimation of instantaneous VO2. Significance: Accurate estimation of VO2with a low cost, minimally obtrusive wearable patch can enable the monitoring of VO2and EE in everyday settings and make the many applications of these measurements more accessible to the general public.

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 (AORDH) shows the average detection ratio can reach 90%, indicating a high ratio of the AORDHthat are exactly the same as AO detected using the ECG R-wave (AOECG). Additionally, the left ventricular ejection time (LVET) values estimated from the ensemble averaged radar waveform through AORDHsegmentation are within 2 ms of those through AOECGsegmentation, for all the detected subjects. Further analysis demonstrates that the beat-to-beat intervals calculated from AORDHhave 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.

Transcutaneous cervical vagal nerve stimulation (tcVNS) devices are attractive alternatives to surgical implants, and can be applied for a number of conditions in ambulatory settings, including stress-related neuropsychiatric disorders. Transferring tcVNS technologies to at-home settings brings challenges associated with the assessment of therapy response. The ability to accurately detect whether tcVNS has been effectively delivered in a remote setting such as the home has never been investigated. We designed and conducted a study in which 12 human subjects received active tcVNS and 14 received sham stimulation in tandem with traumatic stress, and measured continuous cardiopulmonary signals including the electrocardiogram (ECG), photoplethysmogram (PPG), seismocardiogram (SCG), and respiratory effort (RSP). We extracted physiological parameters related to autonomic nervous system activity, and created a feature set from these parameters to: 1) detect active (vs. sham) tcVNS stimulation presence with machine learning methods, and 2) determine which sensing modalities and features provide the most salient markers of tcVNS-based changes in physiological signals. Heart rate (ECG), vasomotor activity (PPG), and pulse arrival time (ECG+PPG) provided sufficient information to determine target engagement (compared to sham) in addition to other combinations of sensors. resulting in 96% accuracy, precision, and recall with a receiver operator characteristics area of 0.96. Two commonly utilized sensing modalities (ECG and PPG) that are suitable for home use can provide useful information on therapy response for tcVNS. The methods presented herein could be deployed in wearable devices to quantify adherence for at-home use of tcVNS technologies.

The ballistocardiography (BCG) signal is a measurement of the vibrations of the center of mass of the body due to the cardiac cycle and can be used for noninvasive hemodynamic monitoring. The seismocardiography (SCG) signals measure the local vibrations of the chest wall due to the cardiac cycle. While BCG is a more well-known modality, it requires the use of a modified bathroom scale or a force plate and cannot be measured in a wearable setting, whereas SCG signals can be measured using wearable accelerometers placed on the sternum. In this paper, we explore the idea of finding a mapping between zero mean and unit 12-norm SCG and BCG signal segments such that, the BCG signal can be acquired using wearable accelerometers (without retaining amplitude information). We use neural networks to find such a mapping and make use of the recently introduced UNet architecture. We trained our models on 26 healthy subjects and tested them on ten subjects. Our results show that we can estimate the aforementioned segments of the BCG signal with a median Pearson correlation coefficient of 0.71 and a median absolute deviation (MAD) of 0.17. Furthermore, our model can estimate the R-I, R-J and R-K timing intervals with median absolute errors (and MAD) of 10.00 (8.90), 6.00 (5.93), and 8.00 (5.93), respectively. We show that using all three axis of the SCG accelerometer produces the best results, whereas the headto-foot SCG signal produces the best results when a single SCG axis is used.

OBJECTIVE: Left ventricular assist devices (LVADs) fail in up to 10% of patients due to the development of pump thrombosis. Remote monitoring of patients with LVADs can enable early detection and, subsequently, treatment and prevention of pump thrombosis. We assessed whether acoustical signals measured on the chest of patients with LVADs, combined with machine learning algorithms, can be used for detecting pump thrombosis. METHODS: 13 centrifugal pump (HVAD) recipients were enrolled in the study. When hospitalized for suspected pump thrombosis, clinical data and acoustical recordings were obtained at admission, prior to and after administration of thrombolytic therapy, and every 24 hours until laboratory and pump parameters normalized. First, we selected the most important features among our feature set using LDH-based correlation analysis. Then using these features, we trained a logistic regression model and determined our decision threshold to differentiate between thrombosis and non-thrombosis episodes. RESULTS: Accuracy, sensitivity and precision were calculated to be 88.9%, 90.9% and 83.3%, respectively. When tested on the post-thrombolysis data, our algorithm suggested possible pump abnormalities that were not identified by the reference pump power or biomarker abnormalities. SIGNIFICANCE: We showed that the acoustical signatures of LVADs can be an index of mechanical deterioration and, when combined with machine learning algorithms, provide clinical decision support regarding the presence of pump thrombosis.

The objective of this study was to investigate the measurement instrument-dependent variability in the morphology of the ballistocardiogram (BCG) waveform in human subjects and computational methods to mitigate the variability. The BCG was measured in 22 young healthy subjects using a high-performance force plate and a customized commercial weighing scale under upright standing posture. The timing and amplitude features associated with the major I, J, K waves in the BCG waveforms were extracted and quantitatively analyzed. The results indicated that 1) the I, J, K waves associated with the weighing scale BCG exhibited delay in the timings within the cardiac cycle relative to the ECG R wave as well as attenuation in the absolute amplitudes than the respective force plate counterparts, whereas 2) the time intervals between the I, J, K waves were comparable. Then, two alternative computational methods were conceived in an attempt to mitigate the discrepancy between force plate versus weighing-scale BCG: a transfer function and an amplitude-phase correction. The results suggested that both methods effectively mitigated the discrepancy in the timings and amplitudes associated with the I, J, K waves between the force plate and weighing-scale BCG. Hence, signal processing may serve as a viable solution to the mitigation of the instrument-induced morphological variability in the BCG, thereby facilitating the standardized analysis and interpretation of the timing and amplitude features in the BCG across wide-ranging measurement platforms.

The seismocardiogram (SCG) measures the movement of the chest wall in response to underlying cardiovascular events. Though this signal contains clinically-relevant information, its morphology is both patient-specific and highly transient. In light of recent work suggesting the existence of population-level patterns in SCG signals, the objective of this study is to develop a method which harnesses these patterns to enable robust signal processing despite morphological variability. Specifically, we introduce seismocardiogram generative factor encoding (SGFE), which models the SCG waveform as a stochastic sample from a low-dimensional subspace defined by a unified set of generative factors. We then demonstrate that during dynamic processes such as exercise-recovery, learned factors correlate strongly with known generative factors including aortic opening (AO) and closing (AC), following consistent trajectories in subspace despite morphological differences. Furthermore, we found that changes in sensor location affect the perceived underlying dynamic process in predictable ways, thereby enabling algorithmic compensation for sensor misplacement during generative factor inference. Mapping these trajectories to AO and AC yielded $R^2$ values from 0.81-0.90 for AO and 0.72-0.83 for AC respectively across five sensor positions. Identification of consistent behavior of SCG signals in low dimensions corroborates the existence of population-level patterns in these signals; SGFE may also serve as a harbinger for processing methods that are abstracted from the time domain, which may ultimately improve the feasibility of SCG utilization in ambulatory and outpatient settings.

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.

OBJECTIVE: Ballistocardiogram (BCG) can be recorded using inexpensive and non-invasive hardware to estimate physiological changes in the heart. In this paper, a methodology is developed to evaluate the impact of additive noise on the BCG signal. METHODS: A statistical model is built that incorporates subject-specific BCG morphology. BCG signals segmented by electrocardiogram RR intervals (BCG heartbeats) are averaged to estimate a parent template and subtemplates leveraging the quasi-periodic nature of the heart. Noise statistics are obtained for subtemplates with respect to the parent template. Then, a synthesis algorithm with adjustable additive noise is devised to generate subtemplates based on the individual's parent template and statistics. For the example use of the synthesis algorithm, the average correlation coefficient between subtemplates and the parent template (subtemplate versus parent template approach) is tested as a signal quality index. RESULTS: A BCG heartbeat synthesis framework that incorporates an individual's BCG morphology and physiological variability was developed to quantify variations in the BCG signal against additive noise. The signal quality assessment of a person's BCG recording can be performed without requiring any a priori knowledge of the person's BCG morphology. A data-driven constraint on the required minimum number of heartbeats for a reliable template estimation was provided. CONCLUSION: The impact of additive noise on BCG morphology and estimated physiological parameters can be analyzed using the developed methodology without requiring prior statistics. SIGNIFICANCE: This paper can facilitate the performance evaluation of BCG analysis algorithms against additive noise.

The seven papers included in this special section focus on machine learning applications for the mental health industry. Mental health is one of the major global health issues affecting substantially more people than other noncommunicable diseases. Much research has been focused on developing novel technologies for tackling this global health challenge, including the development of advanced analytical techniques based on extensive datasets and multimodal acquisition for early detection and treatment of mental illnesses. The papers in this issue are dedicated to cover the related topics on technological advancements for mental health care and diagnosis with a focus on pervasive sensing and machine learning.

OBJECTIVE: Systolic time intervals, such as the pre-ejection period (PEP), are important parameters for assessing cardiac contractility that can be measured non-invasively using seismocardiography (SCG). Recent studies have shown that specific points on accelerometer- and gyroscope-based SCG signals can be used for PEP estimation. However, the complex morphology and inter-subject variation of the SCG signal can make this assumption very challenging and increase the root mean squared error (RMSE) when these techniques are used to develop a global model. METHODS: In this study, we compared gyroscope- and accelerometer-based SCG signals, individually and in combination, for estimating PEP to show the efficacy of these sensors in capturing valuable information regarding cardiovascular health. We extracted general time-domain features from all the axes of these sensors and developed global models using various regression techniques. RESULTS: In single-axis comparison of gyroscope and accelerometer, angular velocity signal around head to foot axis from the gyroscope provided the lowest RMSE of 12.63 ± 0.49 ms across all subjects. The best estimate of PEP, with a RMSE of 11.46 ± 0.32 ms across all subjects, was achieved by combining features from the gyroscope and accelerometer. Our global model showed 30% lower RMSE when compared to algorithms used in recent literature. CONCLUSION: Gyroscopes can provide better PEP estimation compared to accelerometers located on the mid-sternum. Global PEP estimation models can be improved by combining general time domain features from both sensors. SIGNIFICANCE: This work can be used to develop a low-cost wearable heart-monitoring device and to generate a universal estimation model for systolic time intervals using a single- or multiple-sensor fusion.

Transcutaneous vagus nerve stimulation (t-VNS) is a promising technology for modulating brain function and possibly treating disorders of the central nervous system. While handheld devices are available for t-VNS, stimulation efficacy can only be quantified using expensive imaging or blood biomarker analyses. Additionally, the parameters and "dosage" recommendations for t-VNS are typically fixed, as there are limited biomarkers that can assess downstream effects of the stimulation outside of clinical settings. In this proof-of-concept study, we evaluated non-invasive peripheral cardiovascular measurements as physiological biomarkers of t-VNS efficacy. Specifically, we hypothesized two physiological biomarkers: (1) the pre-ejection period (PEP) of the heart - a parameter closely linked to sympathetic tone - and (2) the amplitude of peripheral photoplethysmogram (PPG) waveforms - representing changes in vasomotor tone and thus parasympathetic / sympathetic activation. A total of six healthy human subjects participated in the multi-day study, half each undergoing active or sham t-VNS stimulus. The three subjects receiving t-VNS had no decrease in PEP and an increase in PPG amplitude following t-VNS, while the subjects receiving sham stimulus had a decrease in PEP and no change in PPG amplitude. When combined with mental stress (a traumatic script being read back to the subjects), the group with t-VNS had no decrease in PEP and only a slight decrease in PPG amplitude following stimulus, while the group receiving sham stimulus had a decrease in PEP and also a slight decrease in PPG amplitude. These studies suggest that PEP and PPG amplitude measures may provide non-invasive physiological biomarkers of t-VNS efficacy, including in the presence of mental stress.

FingerPing is a novel sensing technique that can recognize various fine-grained hand poses by analyzing acoustic resonance features. A surface-transducer mounted on a thumb ring injects acoustic chirps (20Hz to 6,000Hz) to the body. Four receivers distributed on the wrist and thumb collect the chirps. Different hand poses of the hand create distinct paths for the acoustic chirps to travel, creating unique frequency responses at the four receivers. We demonstrate how FingerPing can differentiate up to 22 hand poses, including the thumb touching each of the 12 phalanges on the hand as well as 10 American sign language poses. A user study with 16 participants showed that our system can recognize these two sets of poses with an accuracy of 93.77% and 95.64%, respectively. We discuss the opportunities and remaining challenges for the widespread use of this input technique.

The touchscreen has been the dominant input surface for smartphones and smartwatches. However, its small size compared to a phone limits the richness of the input gestures that can be supported. We present TapSkin, an interaction technique that recognizes up to 11 distinct tap gestures on the skin around the watch using only the inertial sensors and microphone on a commodity smartwatch. An evaluation with 12 participants shows our system can provide classification accuracies from 90.69% to 97.32% in three gesture families -- number pad, d-pad, and corner taps. We discuss the opportunities and remaining challenges for widespread use of this technique to increase input richness on a smartwatch without requiring further on-body instrumentation.

Knee-joint sounds could potentially be used to noninvasively probe the physical and/or physiological changes in the knee associated with rehabilitation following acute injury. In this paper, a system and methods for investigating the consistency of knee-joint sounds during complex motions in silent and loud background settings are presented. The wearable hardware component of the system consists of a microelectromechanical systems microphone and inertial rate sensors interfaced with a field programmable gate array-based real-time processor to capture knee-joint sound and angle information during three types of motion: flexion-extension (FE), sit-to-stand (SS), and walking (W) tasks. The data were post-processed to extract high-frequency and short-duration joint sounds (clicks) with particular waveform signatures. Such clicks were extracted in the presence of three different sources of interference: background, stepping, and rubbing noise. A histogram-vector Vn(→) was generated from the clicks in a motion-cycle n, where the bin range was 10°. The Euclidean distance between a vector and the arithmetic mean Vav(→) of all vectors in a recording normalized by the Vav(→) is used as a consistency metric dn. Measurements from eight healthy subjects performing FE, SS, and W show that the mean (of mean) consistency metric for all subjects during SS (μ [ μ (dn)] = 0.72 in silent, 0.85 in loud) is smaller compared with the FE (μ [ μ (dn)] = 1.02 in silent, 0.95 in loud) and W ( μ [ μ (dn)] = 0.94 in silent, 0.97 in loud) exercises, thereby implying more consistent click-generation during SS compared with the FE and W. Knee-joint sounds from one subject performing FE during five consecutive work-days (μ [ μ (dn) = 0.72) and five different times of a day (μ [ μ (dn) = 0.73) suggests high consistency of the clicks on different days and throughout a day. This work represents the first time, to the best of our knowledge, that joint sound consistency has been quantified in ambulatory subjects performing every-day activities (e.g., SS, walking). Moreover, it is demonstrated that noise inherent with joint-sound recordings during complex motions in uncontrolled settings does not prevent joint-sound-features from being detected successfully.

Continuous measurement of cardiac time intervals throughout normal activities of daily living is of interest for both chronic disease management and preventive wellness monitoring. Systolic time intervals in particular — i.e., pre-ejection period (PEP) and left ventricular ejection time (LVET) — have been shown to be relevant to assessing myocardial health and performance, but are challenging to measure with wearable sensors. In this paper, we present novel methods for estimating PEP and LVET from a single three-axis accelerometer placed at the sternum, based on the measurement of cardiogenic vibrations: seismocardiography (SCG) and ballistocardiography (BCG). Although such signals have been examined in the existing literature, the analysis and interpretation has focused mainly on the dorso-ventral components only in the context of systolic time interval estimation. In this paper, we find that features extracted from the head-to-foot accelerations yield better correlations to PEP measured from impedance cardiogram (ICG) than standard approaches based on dorso-ventral components. Additionally, we examine the effects of postural variations on the correlation between PEP estimated from accelerometer and ICG signals and also on correlation between LVET estimated from both sensors. We determine that such correlations are robust to postural changes. Based on these findings, we anticipate that wearable, accelerometer based vibration measurements from standing subjects can be used for robust systolic time interval estimation in a variety of ubiquitous cardiovascular health and fitness sensing applications.

The ultimate objective of this research is to quantify changes in joint sounds during recovery from musculoskeletal injury, and to then use the characteristics of such sounds as a biomarker for quantifying joint rehabilitation progress. This paper focuses on the robust measurement of joint acoustic emissions using miniature microphones placed on the knee and interfaced to custom hardware. Two types of microphones were investigated: (1) miniature microphones with a sound port for detecting airborne sounds; and (2) piezoelectric film based contact microphones for detecting skin vibrations associated with internal sounds. Additionally, inertial measurements were taken simultaneously with joint sounds to observe the consistency in the acoustic emissions in the context of particular activities: knee flexion / extension (without load) and multi-joint weighted movement involving knee and hip flexion / extension (i.e. sit-to-stand). The preliminary data demonstrated that high quality joint sound measurements can be obtained with unique and repeatable acoustic signatures in healthy and injured joints. Additionally, the results suggest that combining piezoelectric contact microphones (which detect high quality acoustic emission signals directly from the skin vibrations but can be compromised with loss of skin contact) and electret microphones (which measure lower signal-to-noise ratio airborne sounds from the joint but can even measure such sounds at 5 cm distance from the skin) can provide robust measurements for a future wearable system to assess joint health in patients during rehabilitation at home.

In the past decade, there has been a resurgence in the field of unobtrusive cardiomechanical assessment, through advancing methods for measuring and interpreting ballistocardiogram (BCG) and seismocardiogram (SCG) signals. Novel instrumentation solutions have enabled BCG and SCG measurement outside of clinical settings, in the home, in the field, and even in microgravity. Customized signal processing algorithms have led to reduced measurement noise, clinically relevant feature extraction, and signal modeling. Finally, human subjects physiology studies have been conducted using these novel instruments and signal processing tools with promising results. This paper reviews the recent advances in these areas of modern BCG and SCG research.

Ballistocardiography is a noninvasive measurement of the mechanical movement of the body caused by cardiac ejection of blood. Recent studies have demonstrated that ballistocardiogram (BCG) signals can be measured using a modified home weighing scale and used to track changes in myocardial contractility and cardiac output. With this approach, the BCG can potentially be used both for preventive screening and for chronic disease management applications. However, for achieving high signal quality, subjects are required to stand still on the scale in an upright position for the measurement; the effects of intentional (for user comfort) or unintentional (due to user error) modifications in the position or posture of the subject during the measurement have not been investigated in the existing literature. In this study, we quantified the effects of different standing and seated postures on the measured BCG signals, and on the most salient BCG-derived features compared to reference standard measurements (e.g., impedance cardiography). We determined that the standing upright posture led to the least distorted signals as hypothesized, and that the correlation between BCG-derived timing interval features (R-J interval) and the preejection period, PEP (measured using ICG), decreased significantly with impaired posture or sitting position. We further implemented two novel approaches to improve the PEP estimates from other standing and sitting postures, using system identification and improved J-wave detection methods. These approaches can improve the usability of standing BCG measurements in unsupervised settings (i.e., the home), by improving the robustness to nonideal posture, as well as enabling high-quality seated BCG measurements.

The papers in this special section aim to present advances in the technologies for assessing the mechanical cardiovascular function outside of clinical settings. There is a compelling need for unobtrusive cardiovascular monitoring in extra-clinical settings that remains unfulfilled by current technologies. As the population of patients burdened with chronic cardiovascular dysfunction, such as heart failure, continues to grow, we should find solutions 1) to obtain an efficient surveillance of the patient’s health status in daily life, 2) to enable physicians to tailor therapy and rehabilitation programs on the basis of the real patient reaction to the everyday challenges, and 3) to expand our understanding of cardiovascular pathophysiology during spontaneous behavior. In clinics some of the most important parameters of cardiovascular performance that physicians consider are related to the mechanical aspects of cardiovascular function.However, current technology, often by ultrasound measures, does not facilitate the unobtrusive assessment of cardiovascular mechanics at home or during outdoor activities.

Ballistocardiography, the measurement of the reaction forces of the body to cardiac ejection of blood, is one of the few techniques available for unobtrusively assessing the mechanical aspects of cardiovascular health outside clinical settings. Recently, multiple experimental studies involving healthy subjects and subjects with various cardiovascular diseases have demonstrated that the ballistocardiogram (BCG) signal can be used to trend cardiac output, contractility, and beat-by-beat ventricular function for arrhythmias. The majority of these studies has been performed with "fixed" BCG instrumentation-such as weighing scales or chairs-rather than wearable measurements. Enabling wearable, and thus continuous, recording of BCG signals would greatly expand the capabilities of the technique; however, BCG signals measured using wearable devices are morphologically dissimilar to measurements from "fixed" instruments, precluding the analysis and interpretation techniques from one domain to be applied to the other. In particular, the time intervals between the electrocardiogram (ECG) and BCG-namely, the R-J interval, a surrogate for measuring contractility changes-are significantly different for the accelerometer compared to a "fixed" BCG measurement. This paper addresses this need for quantitatively normalizing wearable BCG measurement to "fixed" measurements with a systematic experimental approach. With these methods, the same analysis and interpretation techniques developed over the past decade for "fixed" BCG measurement can be successfully translated to wearable measurements.

Analyzing systolic time intervals-specifically the preejection-period (PEP)-is widely accepted as one of the few methods for the noninvasive assessment of cardiac contractility. In this paper, we investigated the ballistocardiogram (BCG) as a way to noninvasively measure myocardial contractility when combined with the ECG. Specifically, we derived a parameter from the BCG and ECG that we hypothesized would be highly correlated to PEP. This is the time delay between the J-wave peak of the BCG and the R-wave of the ECG, which we refer to as the RJ interval. The RJ interval was correlated to PEP (r(2) = 0.86) for 2126 heartbeats across ten subjects, with a y-intercept of 138 ms and slope of 1.05. This suggests that the RJ interval can be reliably used as a noninvasive assessment of cardiac contractility.

The ballistocardiogram (BCG) is a measure of the reaction force of the body to cardiac ejection of blood. A variety of systems can be used for BCG detection, including beds, tables, chairs, and weighing scales. Weighing scales, in particular, have several practical advantages over the alternatives: low cost, small size, unobtrusiveness, and familiarity to the user; one disadvantage is that the subject must stand during the recording, rather than sit or lay supine, resulting in a higher susceptibility to motion artifacts in the measured signal. This paper evaluates the electromyogram (EMG) signal acquired from the feet of the subject during BCG recording as a noise reference for standing BCG measurements. As a subject moves while standing on the scale, muscle contractions in the feet are detected by the EMG signal, and used to flag segments of the BCG signal that are corrupted by elevated noise. For the purposes of evaluating this method, estimates of the BCG noise-to-signal ratio (NSR) were independently calculated with an ensemble average method, using the R-wave of a simultaneously-acquired chest ECG as a timing reference. The linear correlation between EMG power alone and BCG NSR from 14 subjects was found to be moderate ( r = 0.58, F-statistic p -value 0.05); combined with body-mass index (BMI), multiple linear regression yielded a stronger correlation ( r = 0.73, F -statistic p-value = 0.01). Additionally, an example usage of the lower-leg EMG for improving BCG measurement robustness is provided.

A bathroom scale ballistocardiogram (BCG) recorder has been developed in our group as a potential home monitor for heart failure outpatients. While the signal quality obtained by this device is as high as elaborate table- and bed-based BCG systems discussed previously in the literature, the standing posture required by this system may lead to undesired motion induced noise in the signal, particularly for elderly patients. Electromyogram (EMG) signals from the feet are proposed as a noise reference for the standing BCG measurement. The correlation between these signals and the BCG noise is quantified for a case with low (eyes open) and higher (eyes closed) involuntary movement on the scale. For the six subjects considered in this trial, the foot EMG appears to be a valuable reference for BCG movement noise estimation. Additionally, the fact that many bathroom scales have electrodes on the feet for various body fat percentage estimates makes the measurement highly practical for future implementations.