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

Artificial Intelligence-Driven Prognosis of Respiratory Mechanics: Forecasting Tissue Hysteresivity Using Long Short-Term Memory and Continuous Sensor Data

Tissue hysteresivity is an important marker for determining the onset and progression of respiratory diseases, calculated from forced oscillation lung function test data. This study aims to reduce the number and duration of required measurements by combining multivariate data from various sensing devices. We propose using the Forced Oscillation Technique (FOT) lung function test in both a low-frequency prototype and the commercial RESMON device, combined with continuous monitoring from the Equivital (EQV) LifeMonitor and processed by artificial intelligence (AI) algorithms. While AI and deep learning have been employed in various aspects of respiratory system analysis, such as predicting lung tissue displacement and respiratory failure, the prediction or forecasting of tissue hysteresivity remains largely unexplored in the literature. In this work, the Long Short-Term Memory (LSTM) model is used in two ways: (1) to estimate the hysteresivity coefficient η using heart rate (HR) data collected continuously by the EQV sensor, and (2) to forecast η values by first predicting the heart rate from electrocardiogram (ECG) data. Our methodology involves a rigorous two-hour measurement protocol, with synchronized data collection from the EQV, FOT, and RESMON devices. Our results demonstrate that LSTM networks can accurately estimate the tissue hysteresivity parameter η, achieving an R2 of 0.851 and a mean squared error (MSE) of 0.296 for estimation, and forecast η with an R2 of 0.883 and an MSE of 0.528, while significantly reducing the number of required measurements by a factor of three (i.e., from ten to three) for the patient. We conclude that our novel approach minimizes patient effort by reducing the measurement time and the overall ambulatory time and costs while highlighting the potential of artificial intelligence methods in respiratory monitoring.

Cardiac Multi-Frequency Vibration Signal Sensor Module and Feature Extraction Method Based on Vibration Modeling

Cardiovascular diseases pose a long-term risk to human health. This study focuses on the rich-spectrum mechanical vibrations generated during cardiac activity. By combining Fourier series theory, we propose a multi-frequency vibration model for the heart, decomposing cardiac vibration into frequency bands and establishing a systematic interpretation for detecting multi-frequency cardiac vibrations. Based on this, we develop a small multi-frequency vibration sensor module based on flexible polyvinylidene fluoride (PVDF) films, which is capable of synchronously collecting ultra-low-frequency seismocardiography (ULF-SCG), seismocardiography (SCG), and phonocardiography (PCG) signals with high sensitivity. Comparative experiments validate the sensor's performance and we further develop an algorithm framework for feature extraction based on 1D-CNN models, achieving continuous recognition of multiple vibration features. Testing shows that the recognition coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) of the 8 features are 0.95, 2.18 ms, and 4.89 ms, respectively, with an average prediction speed of 60.18 us/point, meeting the re-quirements for online monitoring while ensuring accuracy in extracting multiple feature points. Finally, integrating the vibration model, sensor, and feature extraction algorithm, we propose a dynamic monitoring system for multi-frequency cardiac vibration, which can be applied to portable monitoring devices for daily dynamic cardiac monitoring, providing a new approach for the early diagnosis and prevention of cardiovascular diseases.

Accurate Localization of First and Second Heart Sounds via Template Matching in Forcecardiography Signals

Cardiac auscultation is an essential part of physical examination and plays a key role in the early diagnosis of many cardiovascular diseases. The analysis of phonocardiography (PCG) recordings is generally based on the recognition of the main heart sounds, i.e., S1 and S2, which is not a trivial task. This study proposes a method for an accurate recognition and localization of heart sounds in Forcecardiography (FCG) recordings. FCG is a novel technique able to measure subsonic vibrations and sounds via small force sensors placed onto a subject's thorax, allowing continuous cardio-respiratory monitoring. In this study, a template-matching technique based on normalized cross-correlation was used to automatically recognize heart sounds in FCG signals recorded from six healthy subjects at rest. Distinct templates were manually selected from each FCG recording and used to separately localize S1 and S2 sounds, as well as S1-S2 pairs. A simultaneously recorded electrocardiography (ECG) trace was used for performance evaluation. The results show that the template matching approach proved capable of separately classifying S1 and S2 sounds in more than 96% of all heartbeats. Linear regression, correlation, and Bland-Altman analyses showed that inter-beat intervals were estimated with high accuracy. Indeed, the estimation error was confined within 10 ms, with negligible impact on heart rate estimation. Heart rate variability (HRV) indices were also computed and turned out to be almost comparable with those obtained from ECG. The preliminary yet encouraging results of this study suggest that the template matching approach based on normalized cross-correlation allows very accurate heart sounds localization and inter-beat intervals estimation.

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

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

Heartbeat Detection in Gyrocardiography Signals without Concurrent ECG Tracings

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

A smart approach to EMG envelope extraction and powerful denoising for human-machine interfaces

Electromyography (EMG) is widely used in human-machine interfaces (HMIs) to measure muscle contraction by computing the EMG envelope. However, EMG is largely affected by powerline interference and motion artifacts. Boards that directly provide EMG envelope, without denoising the raw signal, are often unreliable and hinder HMIs performance. Sophisticated filtering provides high performance but is not viable when power and computational resources must be optimized. This study investigates the application of feed-forward comb (FFC) filters to remove both powerline interferences and motion artifacts from raw EMG. FFC filter and EMG envelope extractor can be implemented without computing any multiplication. This approach is particularly suitable for very low-cost, low-power platforms. The performance of the FFC filter was first demonstrated offline by corrupting clean EMG signals with powerline noise and motion artifacts. The correlation coefficients of the filtered signals envelopes and the true envelopes were greater than 0.98 and 0.94 for EMG corrupted by powerline noise and motion artifacts, respectively. Further tests on real, highly noisy EMG signals confirmed these achievements. Finally, the real-time operation of the proposed approach was successfully tested by implementation on a simple Arduino Uno board.

ECG-Free Heartbeat Detection in Seismocardiography Signals via Template Matching

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

Soft Electronics for Health Monitoring Assisted by Machine Learning

Due to the development of the novel materials, the past two decades have witnessed the rapid advances of soft electronics. The soft electronics have huge potential in the physical sign monitoring and health care. One of the important advantages of soft electronics is forming good interface with skin, which can increase the user scale and improve the signal quality. Therefore, it is easy to build the specific dataset, which is important to improve the performance of machine learning algorithm. At the same time, with the assistance of machine learning algorithm, the soft electronics have become more and more intelligent to realize real-time analysis and diagnosis. The soft electronics and machining learning algorithms complement each other very well. It is indubitable that the soft electronics will bring us to a healthier and more intelligent world in the near future. Therefore, in this review, we will give a careful introduction about the new soft material, physiological signal detected by soft devices, and the soft devices assisted by machine learning algorithm. Some soft materials will be discussed such as two-dimensional material, carbon nanotube, nanowire, nanomesh, and hydrogel. Then, soft sensors will be discussed according to the physiological signal types (pulse, respiration, human motion, intraocular pressure, phonation, etc.). After that, the soft electronics assisted by various algorithms will be reviewed, including some classical algorithms and powerful neural network algorithms. Especially, the soft device assisted by neural network will be introduced carefully. Finally, the outlook, challenge, and conclusion of soft system powered by machine learning algorithm will be discussed.

Design and Fabrication of an Integrated Hollow Concave Cilium MEMS Cardiac Sound Sensor

In light of a need for low-frequency, high sensitivity and broadband cardiac murmur signal detection, the present work puts forward an integrated MEMS-based heart sound sensor with a hollow concave ciliary micro-structure. The advantages of a hollow MEMS structure, in contrast to planar ciliated micro-structures, are that it reduces the ciliated mass and enhances the operating bandwidth. Meanwhile, the area of acoustic-wave reception is enlarged by the concave architecture, thereby enhancing the sensitivity at low frequencies. By rationally designing the acoustic encapsulation, the loss of heart acoustic distortion and weak cardiac murmurs is reduced. As demonstrated by experimentation, the proposed hollow MEMS structure cardiac sound sensor has a sensitivity of up to -206.9 dB at 200 Hz, showing 6.5 dB and 170 Hz increases in the sensitivity and operating bandwidth, respectively, in contrast to the planar ciliated MEMS sensor. The SNR of the sensor is 26.471 dB, showing good detectability for cardiac sounds.

Changes in Forcecardiography Heartbeat Morphology Induced by Cardio-Respiratory Interactions

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

Multimodal Finger Pulse Wave Sensing: Comparison of Forcecardiography and Photoplethysmography Sensors

Pulse waves (PWs) are mechanical waves that propagate from the ventricles through the whole vascular system as brisk enlargements of the blood vessels' lumens, caused by sudden increases in local blood pressure. Photoplethysmography (PPG) is one of the most widespread techniques employed for PW sensing due to its ability to measure blood oxygen saturation. Other sensors and techniques have been proposed to record PWs, and include applanation tonometers, piezoelectric sensors, force sensors of different kinds, and accelerometers. The performances of these sensors have been analyzed individually, and their results have been found not to be in good agreement (e.g., in terms of PW morphology and the physiological parameters extracted). Such a comparison has led to a deeper comprehension of their strengths and weaknesses, and ultimately, to the consideration that a multimodal approach accomplished via sensor fusion would lead to a more robust, reliable, and potentially more informative methodology for PW monitoring. However, apart from various multichannel and multi-site systems proposed in the literature, no true multimodal sensors for PW recording have been proposed yet that acquire PW signals simultaneously from the same measurement site. In this study, a true multimodal PW sensor is presented, which was obtained by integrating a piezoelectric forcecardiography (FCG) sensor and a PPG sensor, thus enabling simultaneous mechanical-optical measurements of PWs from the same site on the body. The novel sensor performance was assessed by measuring the finger PWs of five healthy subjects at rest. The preliminary results of this study showed, for the first time, that a delay exists between the PWs recorded simultaneously by the PPG and FCG sensors. Despite such a delay, the pulse waveforms acquired by the PPG and FCG sensors, along with their first and second derivatives, had very high normalized cross-correlation indices in excess of 0.98. Six well-established morphological parameters of the PWs were compared via linear regression, correlation, and Bland-Altman analyses, which showed that some of these parameters were not in good agreement for all subjects. The preliminary results of this proof-of-concept study must be confirmed in a much larger cohort of subjects. Further investigation is also necessary to shed light on the physical origin of the observed delay between optical and mechanical PW signals. This research paves the way for the development of true multimodal, wearable, integrated sensors and for potential sensor fusion approaches to improve the performance of PW monitoring at various body sites.

Respiratory-Induced Amplitude Modulation of Forcecardiography Signals

Forcecardiography (FCG) is a novel technique that records the weak forces induced on the chest wall by cardio-respiratory activity, by using specific force sensors. FCG sensors feature a wide frequency band, which allows us to capture respiration, heart wall motion, heart valves opening and closing (similar to the Seismocardiogram, SCG) and heart sounds, all simultaneously from a single contact point on the chest. As a result, the raw FCG sensors signals exhibit a large component related to the respiratory activity, referred to as a Forcerespirogram (FRG), with a much smaller, superimposed component related to the cardiac activity (the actual FCG) that contains both infrasonic vibrations, referred to as LF-FCG and HF-FCG, and heart sounds. Although respiration can be readily monitored by extracting the very low-frequency component of the raw FCG signal (FRG), it has been observed that the respiratory activity also influences other FCG components, particularly causing amplitude modulations (AM). This preliminary study aimed to assess the consistency of the amplitude modulations of the LF-FCG and HF-FCG signals within the respiratory cycle. A retrospective analysis was performed on the FCG signals acquired in a previous study on six healthy subjects at rest, during quiet breathing. To this aim, the AM of LF-FCG and HF-FCG were first extracted via a linear envelope (LE) operation, consisting of rectification followed by low-pass filtering; then, the inspiratory peaks were located both in the LE of LF-FCG and HF-FCG, and in the reference respiratory signal (FRG). Finally, the inter-breath intervals were extracted from the obtained inspiratory peaks, and further analyzed via statistical analyses. The AM of HF-FCG exhibited higher consistency within the respiratory cycle, as compared to the LF-FCG. Indeed, the inspiratory peaks were recognized with a sensitivity and positive predictive value (PPV) in excess of 99% in the LE of HF-FCG, and with a sensitivity and PPV of 96.7% and 92.6%, respectively, in the LE of LF-FCG. In addition, the inter-breath intervals estimated from the HF-FCG scored a higher R2 value (0.95 vs. 0.86) and lower limits of agreement (± 0.710 s vs. ±1.34 s) as compared to LF-FCG, by considering those extracted from the FRG as the reference. The obtained results are consistent with those observed in previous studies on SCG. A possible explanation of these results was discussed. However, the preliminary results obtained in this study must be confirmed on a larger cohort of subjects and in different experimental conditions.

Development of a Real-Time Thermoplastic Mask Compression Force Monitoring System Using Capacitive Force Sensor

Purpose: Thermoplastic masks keep patients in an appropriate position to ensure accurate radiation delivery. For a thermoplastic mask to maintain clinical efficacy, the mask should wrap the patient's surface properly and provide uniform pressure to all areas. However, to our best knowledge, no explicit method for achieving such a goal currently exists. Therefore, in this study, we intended to develop a real-time thermoplastic mask compression force (TMCF) monitoring system to measure compression force quantitatively. A prototype system was fabricated, and the feasibility of the proposed method was evaluated.

Methods: The real-time TMCF monitoring system basically consists of four force sensor units, a microcontroller board (Arduino Bluno Mega 2560), a control PC, and an in-house software program. To evaluate the reproducibility of the TMCF monitoring system, both a reproducibility test using a micrometer and a setup reproducibility test using a head phantom were performed. Additionally, the reproducibility tests of mask setup and motion detection tests were carried out with a cohort of six volunteers.

Results: The system provided stable pressure readings in all 10 trials during the sensor unit reproducibility test. The largest standard deviation (SD) among trials was about 36 gf/cm² (∼2.4% of the full-scale range). For five repeated mask setups on the phantom, the compression force variation of the mask was less than 39 gf/cm² (2.6% of the full-scale range). We were successful in making masks together with the monitoring system connected and demonstrated feasible utilization of the system. Compression force variations were observed among the volunteers and according to the location of the sensor (among forehead, both cheekbones, and chin). The TMCF monitoring system provided the information in real time on whether the mask was properly pressing the human subject as an immobilization tool.

Conclusion: With the developed system, it is possible to monitor the effectiveness of the mask in real time by continuously measuring the compression force between the mask and patient during the treatment. The graphical user interface (GUI) of the monitoring system developed provides a warning signal when the compression force of the mask is insufficient. Although the number of volunteers participated in the study was small, the obtained preliminary results suggest that the system could ostensibly improve the setup accuracy of a thermoplastic mask.

A BLE-Connected Piezoresistive and Inertial Chest Band for Remote Monitoring of the Respiratory Activity by an Android Application: Hardware Design and Software Optimization

Breathing is essential for human life. Issues related to respiration can be an indicator of problems related to the cardiorespiratory system; thus, accurate breathing monitoring is fundamental for establishing the patient’s condition. This paper presents a ready-to-use and discreet chest band for monitoring the respiratory parameters based on the piezoresistive transduction mechanism. In detail, it relies on a strain sensor realized with a pressure-sensitive fabric (EeonTex LTT-SLPA-20K) for monitoring the chest movements induced by respiration. In addition, the band includes an Inertial Measurement Unit (IMU), which is used to remove the motion artefacts from the acquired signal, thereby improving the measurement reliability. Moreover, the band comprises a low-power conditioning and acquisition section that processes the signal from sensors, providing a reliable measurement of the respiration rate (RR), in addition to other breathing parameters, such as inhalation (TI) and exhalation (TE) times, inhalation-to-exhalation ratio (IER), and flow rate (V). The device wirelessly transmits the extracted parameters to a host device, where a custom mobile application displays them. Different test campaigns were carried out to evaluate the performance of the designed chest band in measuring the RR, by comparing the measurements provided by the chest band with those obtained by breath count. In detail, six users, of different genders, ages, and physical constitutions, were involved in the tests. The obtained results demonstrated the effectiveness of the proposed approach in detecting the RR. The achieved performance was in line with that of other RR monitoring systems based on piezoresistive textiles, but which use more powerful acquisition systems or have low wearability. In particular, the inertia-assisted piezoresistive chest band obtained a Pearson correlation coefficient with respect to the measurements based on breath count of 0.96 when the user was seated. Finally, Bland–Altman analysis demonstrated that the developed system obtained 0.68 Breaths Per Minute (BrPM) mean difference (MD), and Limits of Agreement (LoAs) of +3.20 and −1.75 BrPM when the user was seated.

Development of an Electronic Stethoscope and a Classification Algorithm for Cardiopulmonary Sounds

With conventional stethoscopes, the auscultation results may vary from one doctor to another due to a decline in his/her hearing ability with age or his/her different professional training, and the problematic cardiopulmonary sound cannot be recorded for analysis. In this paper, to resolve the above-mentioned issues, an electronic stethoscope was developed consisting of a traditional stethoscope with a condenser microphone embedded in the head to collect cardiopulmonary sounds and an AI-based classifier for cardiopulmonary sounds was proposed. Different deployments of the microphone in the stethoscope head with amplification and filter circuits were explored and analyzed using fast Fourier transform (FFT) to evaluate the effects of noise reduction. After testing, the microphone placed in the stethoscope head surrounded by cork is found to have better noise reduction. For classifying normal (healthy) and abnormal (pathological) cardiopulmonary sounds, each sample of cardiopulmonary sound is first segmented into several small frames and then a principal component analysis is performed on each small frame. The difference signal is obtained by subtracting PCA from the original signal. MFCC (Mel-frequency cepstral coefficients) and statistics are used for feature extraction based on the difference signal, and ensemble learning is used as the classifier. The final results are determined by voting based on the classification results of each small frame. After the testing, two distinct classifiers, one for heart sounds and one for lung sounds, are proposed. The best voting for heart sounds falls at 5-45% and the best voting for lung sounds falls at 5-65%. The best accuracy of 86.9%, sensitivity of 81.9%, specificity of 91.8%, and F1 score of 86.1% are obtained for heart sounds using 2 s frame segmentation with a 20% overlap, whereas the best accuracy of 73.3%, sensitivity of 66.7%, specificity of 80%, and F1 score of 71.5% are yielded for lung sounds using 5 s frame segmentation with a 50% overlap.

An accelerometer-derived ballistocardiogram method for detecting heartrates in free-ranging marine mammals

Physio-logging methods, which use animal-borne devices to record physiological variables, are entering a new era driven by advances in sensor development. However, existing datasets collected with traditional bio-loggers, such as accelerometers, still contain untapped eco-physiological information. Here, we present a computational method for extracting heart rate from high-resolution accelerometer data using a ballistocardiogram. We validated our method with simultaneous accelerometer–electrocardiogram tag deployments in a controlled setting on a killer whale (Orcinus orca) and demonstrate the predictions correspond with previously observed cardiovascular patterns in a blue whale (Balaenoptera musculus), including the magnitude of apneic bradycardia and increase in heart rate prior to and during ascent. Our ballistocardiogram method may be applied to mine heart rates from previously collected accelerometery data and expand our understanding of comparative cardiovascular physiology.

Highlighted Article: Validation of a computational method for extracting heart rate in free-ranging cetaceans from high-resolution accelerometer data using a ballistocardiogram.

A Comparison of Heart Pulsations Provided by Forcecardiography and Double Integration of Seismocardiogram

Seismocardiography (SCG) is largely regarded as the state-of-the-art technique for continuous, long-term monitoring of cardiac mechanical activity in wearable applications. SCG signals are acquired via small, lightweight accelerometers fixed on the chest. They provide timings of important cardiac events, such as heart valves openings and closures, thus allowing the estimation of cardiac time intervals of clinical relevance. Forcecardiography (FCG) is a novel technique that records the cardiac-induced vibrations of the chest wall by means of specific force sensors, which proved capable of monitoring respiration, heart sounds and infrasonic cardiac vibrations, simultaneously from a single contact point on the chest. A specific infrasonic component captures the heart walls displacements and looks very similar to the Apexcardiogram. This low-frequency component is not visible in SCG recordings, nor it can be extracted by simple filtering. In this study, a feasible way to extract this information from SCG signals is presented. The proposed approach is based on double integration of SCG. Numerical double integration is usually very prone to large errors, therefore a specific numerical procedure was devised. This procedure yields a new displacement signal (DSCG) that features a low-frequency component (LF-DSCG) very similar to that of the FCG (LF-FCG). Experimental tests were carried out using an FCG sensor and an off-the-shelf accelerometer firmly attached to each other and placed onto the precordial region. Simultaneous recordings were acquired from both sensors, together with an electrocardiogram lead (used as a reference). Quantitative morphological comparison confirmed the high similarity between LF-FCG and LF-DSCG (normalized cross-correlation index >0.9). Statistical analyses suggested that LF-DSCG, although achieving a fair sensitivity in heartbeat detection (about 90%), has not a very high consistency within the cardiac cycle, leading to inaccuracies in inter-beat intervals estimation. Future experiments with high-performance accelerometers and improved processing methods are envisioned to investigate the potential enhancement of the accuracy and reliability of the proposed method.

Automated Detection of Hypertension Using Continuous Wavelet Transform and a Deep Neural Network with Ballistocardiography Signals

Managing hypertension (HPT) remains a significant challenge for humanity. Despite advancements in blood pressure (BP)-measuring systems and the accessibility of effective and safe anti-hypertensive medicines, HPT is a major public health concern. Headaches, dizziness and fainting are common symptoms of HPT. In HPT patients, normalcy may be observed at one instant and abnormality may prevail during a long duration of 24 h ambulatory BP. This may cause difficulty in identifying patients with HPT, and hence there is a possibility that individuals may be untreated or administered insufficiently. Most importantly, uncontrolled HPT can lead to severe complications (stroke, heart attack, kidney disease, and heart failure), mainly ignoring the signs in nascent stages. HPT in the beginning stages may not present distinct symptoms and may be difficult to diagnose from standard physiological signals. Hence, ballistocardiography (BCG) signal was used in this study to detect HPT automatically. The processed signals from BCG were converted into scalogram images using a continuous wavelet transform (CWT) and were then fed into a 2-D convolutional neural network model (2D-CNN). The model was trained to learn and recognize BCG patterns of healthy controls (HC) and HPT classes. Our proposed model obtained a high classification accuracy of 86.14% with a ten-fold cross-validation (CV) strategy. Hence, this is the first use of a 2D-CNN model (deep-learning algorithm) to detect HPT employing BCG signals.

Detection of Aortic Valve Opening and Estimation of Pre-Ejection Period in Forcecardiography Recordings

Forcecardiography (FCG) is a novel technique that measures the local forces induced on the chest wall by the mechanical activity of the heart. Specific piezoresistive or piezoelectric force sensors are placed on subjects’ thorax to measure these very small forces. The FCG signal can be divided into three components: low-frequency FCG, high-frequency FCG (HF-FCG) and heart sound FCG. HF-FCG has been shown to share a high similarity with the Seismocardiogram (SCG), which is commonly acquired via small accelerometers and is mainly used to locate specific fiducial markers corresponding to essential events of the cardiac cycle (e.g., heart valves opening and closure, peaks of blood flow). However, HF-FCG has not yet been demonstrated to provide the timings of these markers with reasonable accuracy. This study addresses the detection of the aortic valve opening (AO) marker in FCG signals. To this aim, simultaneous recordings from FCG and SCG sensors were acquired, together with Electrocardiogram (ECG) recordings, from a few healthy subjects at rest, both during quiet breathing and apnea. The AO markers were located in both SCG and FCG signals to obtain pre-ejection periods (PEP) estimates, which were compared via statistical analyses. The PEPs estimated from FCG and SCG showed a strong linear relationship (r > 0.95) with a practically unit slope, and 95% of their differences were found to be distributed within ± 4.6 ms around small biases of approximately 1 ms, corresponding to percentage differences lower than 5% of the mean measured PEP. These preliminary results suggest that FCG can provide accurate AO timings and PEP estimates.

Non-Intrusive Contact Respiratory Sensor for Vehicles

In this work, we propose a low-cost solution capable of collecting the driver's respiratory signal in a robust and non-intrusive way by contact with the chest and abdomen. It consists of a microcontroller and two piezoelectric sensors with their respective 3D printed plastic housings attached to the seat belt. An iterative process was conducted to find the optimal shape of the sensor housing. The location of the sensors can be easily adapted by sliding them along the seat belt. A few participants took part in three test sessions in a driving simulator. They had to perform various activities: resting, deep breathing, manual driving, and a non-driving-related task during automated driving. The subjects' breathing rates were calculated from raw data collected with a reference chest belt, each sensor alone, and the fusion of the two. Results indicate that respiratory rate could be assessed from a single sensor located on the chest with an average absolute error of 0.92 min^-1 across all periods, dropping to 0.13 min^-1 during deep breathing. Sensor fusion did not improve system performance. A 4-pole filter with a cutoff frequency of 1 Hz emerged as the best option to minimize the error during the different periods. The results suggest that such a system could be used to assess the driver's breathing rate while performing various activities in a vehicle.

Design of a 3D-Printed Hand Exoskeleton Based on Force-Myography Control for Assistance and Rehabilitation

Voluntary hand movements are usually impaired after a cerebral stroke, affecting millions of people per year worldwide. Recently, the use of hand exoskeletons for assistance and motor rehabilitation has become increasingly widespread. This study presents a novel hand exoskeleton, designed to be low cost, wearable, easily adaptable and suitable for home use. Most of the components of the exoskeleton are 3D printed, allowing for easy replication, customization and maintenance at a low cost. A strongly underactuated mechanical system allows one to synergically move the four fingers by means of a single actuator through a rigid transmission, while the thumb is kept in an adduction or abduction position. The exoskeleton’s ability to extend a typical hypertonic paretic hand of stroke patients was firstly tested using the SimScape Multibody simulation environment; this helped in the choice of a proper electric actuator. Force-myography was used instead of the standard electromyography to voluntarily control the exoskeleton with more simplicity. The user can activate the flexion/extension of the exoskeleton by a weak contraction of two antagonist muscles. A symmetrical master–slave motion strategy (i.e., the paretic hand motion is activated by the healthy hand) is also available for patients with severe muscle atrophy. An inexpensive microcontroller board was used to implement the electronic control of the exoskeleton and provide feedback to the user. The entire exoskeleton including batteries can be worn on the patient’s arm. The ability to provide a fluid and safe grip, like that of a healthy hand, was verified through kinematic analyses obtained by processing high-framerate videos. The trajectories described by the phalanges of the natural and the exoskeleton finger were compared by means of cross-correlation coefficients; a similarity of about 80% was found. The time required for both closing and opening of the hand exoskeleton was about 0.9 s. A rigid cylindric handlebar containing a load cell measured an average power grasp force of 94.61 N, enough to assist the user in performing most of the activities of daily living. The exoskeleton can be used as an aid and to promote motor function recovery during patient’s neurorehabilitation therapy.