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.

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.

Stress can potentially have detrimental effects on both physical and mental well-being, but monitoring it can be challenging, especially in free-living conditions. One approach to address this challenge is to use earbud accelerometers to capture the ballistocardiogram (BCG) response. These sensors allow for noninvasive stress monitoring by estimating physiological indicators linked to stress, such as heart rate variability (HRV). However, ear-worn devices are susceptible to motion artifacts and can exhibit significant BCG signal morphology variations. These challenges necessitate accurate algorithms to estimate HRV for everyday use. Therefore, we developed a method to measure interbeat intervals (IBI) from BCG signals collected from an earbud. To enhance IBI estimation accuracy, we employed a Bayesian method that incorporates robust apriori IBI prediction weighting and sensor fusion techniques. We have also conducted a study involving 97 participants to assess the earbuds' ability to estimate HRV metrics and classify stressful activities. Our findings demonstrate low IBI estimation error (4.16% ± 1.90%), along with lower errors in subsequent higher-order HRV metrics compared to the state-of-the-art algorithms.

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.

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.

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.

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.

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.