Background: The goal of this work was to create a sharable dataset of heart-driven signals, including ballistocardiograms (BCGs) and time-aligned electrocardiograms (ECGs), photoplethysmograms (PPGs), and blood pressure waveforms. Methods: A custom, bed-based ballistocardiographic system is described in detail. Affiliated cardiopulmonary signals are acquired using a GE Datex CardioCap 5 patient monitor (which collects ECG and PPG data) and a Finapres Medical Systems Finometer PRO (which provides continuous reconstructed brachial artery pressure waveforms and derived cardiovascular parameters). Results: Data were collected from 40 participants, 4 of whom had been or were currently diagnosed with a heart condition at the time they enrolled in the study. An investigation revealed that features extracted from a BCG could be used to track changes in systolic blood pressure (Pearson correlation coefficient of 0.54 +/− 0.15), dP/dtmax (Pearson correlation coefficient of 0.51 +/− 0.18), and stroke volume (Pearson correlation coefficient of 0.54 +/− 0.17). Conclusion: A collection of synchronized, heart-driven signals, including BCGs, ECGs, PPGs, and blood pressure waveforms, was acquired and made publicly available. An initial study indicated that bed-based ballistocardiography can be used to track beat-to-beat changes in systolic blood pressure and stroke volume. Significance: To the best of the authors’ knowledge, no other database that includes time-aligned ECG, PPG, BCG, and continuous blood pressure data is available to the public. This dataset could be used by other researchers for algorithm testing and development in this fast-growing field of health assessment, without requiring these individuals to invest considerable time and resources into hardware development and data collection.
A number of research groups have proposed methods for ballistocardiogram (BCG) peak detection toward the identification of individual cardiac cycles. However, objective comparisons of these proposed methods are lacking. This paper therefore conducts a systematic and objective performance evaluation and comparison of several of these approaches. Five peak-detection methods (three replicated from the literature and two adapted from code provided by the methods’ authors) are compared using data from 30 volunteers. A basic cross-correlation approach was also included as a sixth method. Two high-performing methods were identified: the method proposed by Sadek et al. and the method proposed by Brüser et al. The first achieved the highest average peak-detection rate of 94%, the lowest average false alarm rate of 0.0552 false alarms per second, and a relatively small mean absolute error between the real and detected peaks: 0.0175 seconds. The second method achieved the lowest mean absolute error of 0.0088 seconds between the real and detected peaks, an average peak-detection success rate of 89%, and 0.0766 false alarms per second. All metrics are averaged across participants.
Non-intrusive sleep monitoring is critical for certain populations such as severely disabled autistic children. Nocturnal disturbance analysis is an important diagnostic tool for assessing sleep issues. The objective of this paper is to detect and minimize the effects of motion artifacts in signals recorded via an unobtrusive electromechanical film-based BCG sensor integrated into a smart bed system. The goal is to have a reliable estimation of beat-to-beat (B-B) interval. The proposed algorithm includes two main stages: a motion detection algorithm followed by a motion artifact removal system. Motion detection involves a sequential detection algorithm in which successive data frames are compared to two thresholds; upper and lower thresholds. Each motion corrupted frame can then be reconstructed by an approach that relies on a parametric model of the BCG signal. Exploiting the fact that the underlying BCG parameters (J-peak to J-peak interval, J-peak to K-peak amplitude, and the most significant frequency component) change slowly and are correlated across time, an autoregressive (AR) model based tracking and Wiener smoother based parameter estimation strategies are proposed. Experimental results are presented to demonstrate effectiveness of the proposed motion artifact detection and removal algorithms. Probability of detection of 96% and high average coverage of 84% with over 90% precision for estimated B-B intervals are achieved on recordings for nineteen hours of sleep from three subjects. Our novel motion detection and removal methods demonstrate the feasibility of using bed-based BCG signals for providing a reliable unobtrusive way to estimate B-B interval in the presence of motion.
Monitoring the sleep patterns of children with autism spectrum disorders (ASD) and understanding how sleep quality influences their daytime behavior is an important issue that has received very limited attention. Polysomnography (PSG) is commonly used as a gold standard for evaluating sleep quality in children and adults. However, the intrusive nature of sensors used as part of PSG can themselves affect sleep and is, therefore, not suitable for children with ASD. In this study, we evaluate an unobtrusive and inexpensive bed system for in-home, long-term sleep quality monitoring using ballistocardiogram (BCG) signals. Using the BCG signals from this smart bed system, we define "restlessness" as a surrogate sleep quality estimator. Using this sleep feature, we build predictive models for daytime behavior based on 1-8 previous nights of sleep. Specifically, we use two supervised machine learning algorithms namely support vector machine (SVM) and artificial neural network (ANN). For all daytime behaviors, we achieve more than 78% and 79% accuracy of correctly predicting behavioral issues with both SVM and ANN classifiers, respectively. Our findings indicate the usefulness of our designed bed system and how the restlessness feature can improve the prediction performance.
Daily assessment of sleep patterns with traditional sensor systems such as polysomnography (PSG) and electrocardiograms (ECG) is not feasible for certain populations such as severely disabled autistic children. Nocturnal movement/disturbance analysis is an important diagnostic tool for assessing sleep issues. The objective of this paper is to describe a motion detection algorithm to quantify restlessness during sleep via an unobtrusive contactless electromechanical film based ballistocardiogram (BCG) sensor integrated into a smart bed system. Two methods are proposed for motion artifact detection. One involves formulating Neyman-Pearson detection test based on signal variance in time domain and the second approach is based on a sequential detection algorithm. Test results demonstrate that Neyman- Pearson and sequential detection algorithms are very effective in identifying movements with 95% and 96% probability of detection and 94% and 95.2% accuracy in sleep and restlessness state identification, respectively.
The relationship between sleep quality and daytime wellness and performance in severely disabled, autistic children is not well understood. While polysomnography and, more recently, actigraphy serve as means to obtain sleep assessment data from neurotypical children and adults, these techniques are not well-suited to severely autistic children. This paper presents recent progress on a bed sensor suite that can unobtrusively track physiological and behavioral parameters used to assess sleep quality. Electromechanical films and load cells provide data that yield heart rate, respiration rate, center of position, in-and-out-of-bed activity, and general movement, while thermocouples are used to detect bed-wetting events.