16 March 2020 in IEEE Access
This paper describes an integrated chest wearable apparatus for continuous blood pressure (BP) measurements exploiting the heart-rate (HR) and the pulse arrival time (PAT) in a modified Moens-Korteweg model. The device embeds a miniaturized gas pressure sensor to record the phonocardiogram (PCG) of the heart sounds, a LED-photodiode pair to detect the photoplethysmogram (PPG) of the blood flow wave, a μcontroller, a wireless communication module and the power supply. With the proposed device no active participation would be required from human subjects for BP measurements, since the HR and the PAT are continuously extracted from the PCG and PPG signals. Dedicated signal processing algorithms were developed and implemented off-line to extract both HR and PAT. A subject-specific calibration protocol of the BP model was designed and implemented. The calibration and validation of the apparatus were performed on a cohort of 20 healthy subjects. A GIMA ABPM pressure Holter was chosen as reference device, and 8 measurements points, evenly distributed over a 10-minute interval, were used for model calibration for each subject. The range of DBP and SBP measurements were 52-85 mmHg and 90-141 mmHg, respectively. The results from Bl- and-Altman analysis showed that the mean±1.96SD for the estimated diastolic, systolic, and mean BP with the proposed method against reference were 0.01±7.55, 1.47±3.76, 0.74±4.38 mmHg, respectively. The corresponding mean absolute differences (MAD) were 3.06, 1.83, and 1.80 mmHg. These results demonstrates that the acquisition apparatus is able to continuously estimate the BP with an accuracy comparable to traditional cuff-based devices.
1 November 2010 in Journal of Applied Physiology
Expulsive maneuvers (EMs) caused by simultaneous contraction of diaphragm and abdominal muscles shift substantial quantities of blood from the splanchnic circulation to the extremities. This suggests that the diaphragm assisted by abdominal muscles might accomplish ventilation and circulation simultaneously by repeated EMs. We tested this hypothesis in normal subjects by measuring changes (Δ) in body volume (Vb) by whole body plethysmography simultaneously with changes in trunk volume (Vtr) by optoelectronic plethysmography, which measures the same parameters as whole body plethysmography plus the volume of blood shifts (Vbs) between trunk and extremities: Vbs = ΔVtr − ΔVb. We also measured abdominal pressure, pleural pressure, the arterial pressure wave, and cardiac output (Q̇c). EMs with abdominal pressure ∼100 cmH2O for 1 s, followed by 2-s relaxations, repeated over 90 s, produced a “stroke volume” from the splanchnic bed of 0.35 ± 0.07 (SD) liter, an output of 6.84 ± 0.75 l/min compared with a resting Q̇c of 5.59 ± 1.14 l/min. Refilling during relaxation was complete, and the splanchnic bed did not progressively empty. Diastolic pressure increased by 25 mmHg during each EM. Between EMs, Q̇c increased to 7.09 ± 1.14 l/min due to increased stroke volume and heart rate. The circulatory function of the diaphragm assisted by simultaneous contractions of abdominal muscles with appropriate pressure and duration at 20 min−1can produce a circulatory output as great as resting Q̇c, as well as ventilation. These combined functions of the diaphragm have potential for cardiopulmonary resuscitation. The abdominal circulatory pump can act as an auxiliary heart.
14 April 2023 in IEEE Journal of Biomedical and Health Informatics
Evidence is rapidly accumulating that multifactorial nocturnal monitoring, through the coupling of wearable devices and deep learning, may be disruptive for early diagnosis and assessment of sleep disorders. In this work, optical, differential air-pressure and acceleration signals, acquired by a chest-worn sensor, are elaborated into five somnographic-like signals, which are then used to feed a deep network. This addresses a three-fold classification problem to predict the overall signal quality (normal, corrupted), three breathing-related patterns (normal, apnea, irregular) and three sleep-related patterns (normal, snoring, noise). In order to promote explainability, the developed architecture generates additional information in the form of qualitative (saliency maps) and quantitative (confidence indices) data, which helps to improve the interpretation of the predictions. Twenty healthy subjects enrolled in this study were monitored overnight for approximately ten hours during sleep. Somnographic-like signals were manually labeled according to the three class sets to build the training dataset. Both record- and subject-wise analyses were performed to evaluate the prediction performance and the coherence of the results. The network was accurate (0.96) in distinguishing normal from corrupted signals. Breathing patterns were predicted with higher accuracy (0.93) than sleep patterns (0.76). The prediction of irregular breathing was less accurate (0.88) than that of apnea (0.97). In the sleep pattern set, the distinction between snoring (0.73) and noise events (0.61) was less effective. The confidence index associated with the prediction allowed us to elucidate ambiguous predictions better. The saliency map analysis provided useful insights to relate predictions to the input signal content. While preliminary, this work supported the recent perspective on the use of deep learning to detect particular sleep events in multiple somnographic signals, thus representing a step towards bringing the use of AI-based tools for sleep disorder detection incrementally closer to clinical translation.
4 February 2022 in IEEE Transactions on Biomedical Engineering
The accurate detection of physiologically-related events in photopletismographic (PPG) and phonocardiographic (PCG) signals, recorded by wearable sensors, is mandatory to perform the estimation of relevant cardiovascular parameters like the heart rate and the blood pressure. However, the measurement performed in uncontrolled conditions without clinical supervision leaves the detection quality particularly susceptible to noise and motion artifacts. This work proposes a new fully-automatic computational framework, based on convolutional networks, to identify and localize fiducial points in time as the foot, maximum slope and peak in PPG signal and the S1 sound in the PCG signal, both acquired by a custom chest sensor, described recently in the literature by our group. The event detection problem was reframed as a single hybrid regression-classification problem entailing a custom neural architecture to process sequentially the PPG and PCG signals. Tests were performed analysing four different acquisition conditions (rest, cycling, rest recovery and walking). Cross-validation results for the three PPG fiducial points showed identification accuracy greater than 93 % and localization error (RMSE) less than 10 ms. As expected, cycling and walking conditions provided worse results than rest and recovery, however reaching an accuracy greater than 90 % and a localization error less than 15 ms. Likewise, the identification and localization error for S1 sound were greater than 90 % and less than 25 ms. Overall, this study showcased the ability of the proposed technique to detect events with high accuracy not only for steady acquisitions but also during subject movements. We also showed that the proposed network outperformed traditional Shannon-energy-envelope method in the detection of S1 sound, reaching detection performance comparable to state of the art algorithms. Therefore, we argue that coupling chest sensors and deep learning processing techniques may disclose wearable devices to unobtrusively acquire health information, being less affected by noise and motion artifacts.
7 January 2016 in Frontiers in Physiology
Apart from its role as a flow generator for ventilation the diaphragm has a circulatory role. The cyclical abdominal pressure variations from its contractions cause swings in venous return from the splanchnic venous circulation. During exercise the action of the abdominal muscles may enhance this circulatory function of the diaphragm. Eleven healthy subjects (25±7yr, 70±11kg, 1.78±0.1m, 3F) performed plantar flexion exercise at ∼4 METs. Changes in body volume (ΔVb) and trunk volume (ΔVtr) were measured simultaneously by double body plethysmography. Volume of blood shifts between trunk and extremities (Vbs) was determined non-invasively as ΔVtr-ΔVb. Three types of breathing were studied: spontaneous (SE), rib cage (RCE, voluntary emphasized inspiratory rib cage breathing) and abdominal (ABE, voluntary active abdominal expiration breathing).. During SE and RCE blood was displaced from the extremities into the trunk (on average 0.16± 0.33L and 0.48±0.55L, p<0.05 SE vs RCE), while during ABE it was displaced from the trunk to the extremities (0.22±0.20L p<0.001, p<0.05 RCE and SE vs ABE respectively). At baseline, Vbs swings (maximum to minimum amplitude) were bimodal and averaged 0.13±0.08L. During exercise, Vbs swings consistently increased (0.42±0.34L, 0.40±0.26L, 0.46±0.21L, for SE, RCE and ABE respectively, all p<0.01 vs. baseline). It follows that during leg exercise significant bi-directional blood shifting occurs between the trunk and the extremities. The dynamics and partitioning of these blood shifts strongly depend on the relative predominance of the action of the diaphragm, the rib cage and the abdominal muscles. Depending on the partitioning between respiratory muscles for the act of breathing, the distribution of blood between trunk and extremities can vary by up to 1 L. We conclude that during exercise the abdominal muscles and the diaphragm might play a role of an ‘auxiliary heart’.