Automated Quality Assessment for Accelerometer-Based Heart Sounds Recorded with a Novel Subcutaneous Medical Implant.

In the context of monitoring patients with heart failure conditions, the automated assessment of heart sound quality is of major importance to insure the relevance of the medical analysis of the heart sound data. We propose in this study a technique of quality classification based on the selection of a small set of representative features. The first features are chosen to characterize whether the periodicity, complexity or statistical nature of the heart sound recordings. After segmentation process, the latter features are probing the detectability of the heart sounds in cardiac cycles. Our method is applied on a novel subcutaneous medical implant that combines ECG and accelerometric-based heart sound measurements. The actual prototype is in pre-clinical phase and has been implanted on 4 pigs, which anatomy and activity constitute a challenging environment for obtaining clean heart sounds. As reference quality labeling, we have performed a three-class manual annotation of each recording, qualified as "good", "unsure" and "bad". Our method allows to retrieve good quality heart sounds with a sensitivity and an accuracy of 82% ± 2% and 88% ± 6% respectively. Clinical Relevance- By accurately recovering high quality heart sound sequences, our method will enable to monitor reliable physiological indicators of heart failure complications such as decompensation.

Accelerometry-derived respiratory index estimating apnea-hypopnea index for sleep apnea screening.

BACKGROUND AND OBJECTIVE: Sleep Apnea Syndrome (SAS) is a multimorbid chronic disease with individual and societal deleterious consequences. Polysomnography (PSG) is the multi-parametric reference diagnostic tool that allows a manual quantification of the apnea-hypopnea index (AHI) to assess SAS severity. The burden of SAS is affecting nearly one billion people worldwide explaining that SAS remains largely under-diagnosed and undertreated. The development of an easy to use and automatic solution for early detection and screening of SAS is highly desirable. METHODS: We proposed an Accelerometry-Derived Respiratory index (ADR) solution based on a dual accelerometry system for airflow estimation included in a machine learning process. It calculated the AHI thanks to a RUSBoosted Tree model and used physiological and explanatory specifically developed features. The performances of this method were evaluated against a configuration using gold-standard PSG signals on a database of 28 subjects. RESULTS: The AHI estimation accuracy, specificity and sensitivity of the ADR index were 89%, 100% and 80% respectively. The added value of the specifically developed features was also demonstrated. CONCLUSION: Overnight physiological monitoring with the proposed ADR solution using a machine learning approach provided a clinically relevant estimate of AHI for SAS screening. The physiological component of the solution has a real interest for improving performance and facilitating physician's adhesion to an automatic AHI estimation.

A novel bimodal stethoscope for gastric collection of heart sounds: preliminary results.

Heart sound analysis is commonly used by physicians during auscultations to evaluate cardiac activity as a first line. These sounds originate from heartbeats and the resulting blood flow, and can provide important information about heart function and hemodynamics. The monitoring of heart sounds in patients suffering from chronic cardiac pathologies can be useful to detect or prevent cardiac events. For this purpose, a bimodal implanted gastric stethoscope was developed allowing home monitoring of electrophysiological and mechanical parameters.An in-vivo experiment in pigs was carried out to validate the feasibility of heart sound detection from an accelerometer embedded in a stethoscope prototype implanted in the submucosal layer of the gastric wall. Data recorded over several weeks validate the tolerance and the sensitivity of the device. These promising preliminary results confirm the interest of considering the stomach as a strategic implantation site for heart sound monitoring.

Fetal heart rate estimation from a single phonocardiogram signal using non-negative matrix factorization.

Fetal heart rate (FHR) is an important characteristic in fetal well-being follow-up. It is classically estimated using the cardiotocogram (CTG) non-invasive reference technique. However, this latter presents some significant drawbacks. An alternative non-invasive solution based on the fetal phonocardiogram (fetal PCG) can be used. But most of proposed methods based on the PCG signal need to detect and to label the fetal cardiac S1 and S2 sounds, which may be a difficult task in certain conditions. Therefore, in this paper, we propose a new methodology for FHR estimation from fetal PCG with one single cardio-microphone and without the distinction constraint of heart sounds. The method is based on the non-negative matrix factorization (NMF) applied on the spectrogram of fetal PCG considered as a source-filter model. The proposed method provides satisfactory results on a preliminary dataset of abdominal PCG signals. When compared to the reference CTG, correlation on FHR estimations between PCG and CTG is around 90%.

Adaptive Accelerometry Derived Respiration: Comparison with Respiratory Inductance Plethysmography during Sleep.

Polysomnography (PSG) is a multi-parametric test used in the study of sleep and as a diagnostic tool in sleep medicine. PSG is the gold standard that manually quantifies the apnea-hypopnea index (AHI) to assess the severity of sleep apnea syndrome (SAS). This work presents a novel method based on a dual tri-axis accelerometer system (Adaptive Accelerometry Derived Respiration, ADR) which was patched on the subject's chest that adaptively reconstructed thoracic and abdominal respiratory efforts. Performance evaluation was performed on a 60s-epoch basis using signal and physiological indicators: the evaluation consisted in the comparison of airflow estimations from ADR and RIP to the nasal airflow, considered as reference. Results showed that 74% of the 60s-epoch ADR airflow estimation present a correlation coefficient with nasal airflow ≥ 70% compared to 64% for RIP. Relative errors for one-minute respiration rate and tidal volume estimation appeared to be relatively low which reflected the good feasibility of the adaptive ADR method for respiration monitoring during sleep.

Non-invasive cardiac output monitoring in pharmacology: A plethysmographie solution in rats.

Cardiovascular monitoring is of great importance in pharmacology but there is a lack of convenient non-invasive alternatives. Hence, we aim to evaluate the relevance of inductive plethysmography (IP) in preclinical cardiac studies. An IP system was specifically designed for rat. Its evaluation carried out using a mechanical test bench has shown appropriate instrumental performances for cardiac monitoring in rats. Measurements were also performed during a volume overload hemodynamic challenge in vivo in rats. The cardiac output variation has similar kinetic and amplitude when compared to results of previous studies. This suggests that our system is suitable for cardiac output monitoring in rat.

An application of Gaussian processes on ocular artifact removal from EEG.

Consequences of eye movements are one of the main interferences that distort the brain EEG recordings. In this paper, a multi-modal approach is used to estimate the ocular artifacts in the EEG: both vertical and horizontal eye movement signals recorded by an eye tracker are used as a reference to denoise the EEG. A Gaussian process, i.e. a second order statistics method, is assumed to model the link between the eye tracker signals and the EEG signals. The proposed method is thus a non-linear extension of the well-known adaptive filtering and can be applied with a single EEG signal contrary to independent component analysis (ICA) which is extensively used. The results show the applicability and the efficiency of this model on the ocular artifact removal.

Modeling quasi-periodic signals by a non-parametric model: application on fetal ECG extraction.

Quasi-periodic signals can be modeled by their second order statistics as Gaussian process. This work presents a non-parametric method to model such signals. ECG, as a quasi-periodic signal, can also be modeled by such method which can help to extract the fetal ECG from the maternal ECG signal, using a single source abdominal channel. The prior information on the signal shape, and on the maternal and fetal RR interval, helps to better estimate the parameters while applying the Bayesian principles. The values of the parameters of the method, among which the R-peak instants, are accurately estimated using the Metropolis-Hastings algorithm. This estimation provides very precise values for the R-peaks, so that they can be located even between the existing time samples.

Empirical mode decomposition of respiratory inductive plethysmographic signals for stroke volume variations monitoring: respiratory protocol and comparison with impedance cardiography.

We investigate Respiratory Inductive Plethysmography (RIP) to estimate cardiac activity from thoracic volume variations and study cardio-respiratory interactions. The objective of the present study is to evaluate the ability of RIP to monitor stroke volume (SV) variations, with reference to impedance cardiography (IMP). Five healthy volunteers in seated and supine positions were asked to blow into a manometer in order to induce significant SV decreases. Time-scale analysis was applied on calibrated RIP signals to extract cardiac volume signals. Averaged SV values, in quasi-stationary states at rest and during the respiratory maneuvers, were then estimated from these cardiac signals and from IMP signals simultaneously acquired. SV variations between rest and maneuvers were finally evaluated for both techniques. We show that SV values as well as SV variations are correlated between RIP and IMP estimations, suggesting that RIP could be used for SV variations monitoring.

Rectus abdominis electromyography and MechanoMyoGraphy comparison for the detection of cough.

We recently developed a novel active implant for the treatment of severe stress urinary incontinence. This innovative medical device has been developed with the main purpose of reducing the mean urethral occlusive pressure of the current prosthesis. This goal is achieved by detecting circumstances implying either high or low intra-abdominal pressures by a single 3-axis accelerometer. In fact, posture and activity of the patient are monitored in real time. We investigated in this study the possibility of detecting cough events (one of the main causes of urine loss in incontinent patient) by MechanoMyoGraphy (MMG) of the Rectus Abdominis (RA) using the same accelerometer. We compared MMG signal detection characteristics (burst onset times and RMS values) to the method of reference, the ElectroMyoGraphy (EMG). It is shown that detection of cough effort by MMG presents lower performances, mostly in terms of cough anticipation, than EMG detection. However, MMG still remains a good option for an implantable system comparing to implantable EMG disadvantages.

A simple dynamic model of respiratory pump.

To study the interaction of forces that produce chest wall motion, we propose a model based on the lever system of Hillman and Finucane (J Appl Physiol 63(3):951-961, 1987) and introduce some dynamic properties of the respiratory system. The passive elements (rib cage and abdomen) are considered as elastic compartments linked to the open air via a resistive tube, an image of airways. The respiratory muscles (active) force is applied to both compartments. Parameters of the model are identified in using experimental data of airflow signal measured by pneumotachography and rib cage and abdomen signals measured by respiratory inductive plethysmography on eleven healthy volunteers in five conditions: at rest and with four level of added loads. A breath by breath analysis showed, whatever the individual and the condition are, that there are several breaths on which the airflow simulated by our model is well fitted to the airflow measured by pneumotachography as estimated by a determination coefficient R(2) > or = 0.70. This very simple model may well represent the behaviour of the chest wall and thus may be useful to interpret the relative motion of rib cage and abdomen during quiet breathing.

Cardiogenic oscillations extraction in inductive plethysmography: Ensemble empirical mode decomposition.

The purpose of this study is to investigate the potential of the ensemble empirical mode decomposition (EEMD) to extract cardiogenic oscillations from inductive plethysmography signals in order to measure cardiac stroke volume. First, a simple cardio-respiratory model is used to simulate cardiac, respiratory, and cardio-respiratory signals. Second, application of empirical mode decomposition (EMD) to simulated cardio-respiratory signals demonstrates that the mode mixing phenomenon affects the extraction performance and hence also the cardiac stroke volume measurement. Stroke volume is measured as the amplitude of extracted cardiogenic oscillations, and it is compared to the stroke volume of simulated cardiac activity. Finally, we show that the EEMD leads to mode mixing removal.

A model of mechanical interactions between heart and lungs.

To study the mechanical interactions between heart, lungs and thorax, we propose a mathematical model combining a ventilatory neuromuscular model and a model of the cardiovascular system, as described by Smith et al. (Smith, Chase, Nokes, Shaw & Wake 2004 Med. Eng. Phys.26, 131-139. (doi:10.1016/j.medengphy.2003.10.001)). The respiratory model has been adapted from Thibault et al. (Thibault, Heyer, Benchetrit & Baconnier 2002 Acta Biotheor. 50, 269-279. (doi:10.1023/A:1022616701863)); using a Liénard oscillator, it allows the activity of the respiratory centres, the respiratory muscles and rib cage internal mechanics to be simulated. The minimal haemodynamic system model of Smith includes the heart, as well as the pulmonary and systemic circulation systems. These two modules interact mechanically by means of the pleural pressure, calculated in the mechanical respiratory system, and the intrathoracic blood volume, calculated in the cardiovascular model. The simulation by the proposed model provides results, first, close to experimental data, second, in agreement with the literature results and, finally, highlighting the presence of mechanical cardiorespiratory interactions.

Contribution to structural intensity tool: application to the cancellation of ECG interference in diaphragmatic EMG.

This paper is concerned with the problem of localizing the typical features of a signal when it is observed with noise in order to align a set of curves. Structural intensity (SI) is a recent tool that computes the "density" of the location of the modulus maxima of a wavelet representation along various scales in order to identify singularities of an unknown signal. As a contribution to this novel approach we establish a modified SI using the Berkner transform which allows maxima linkage to insure accurate localization of singularities. An application to cancellation of ECG interference in diaphragmatic EMG is also proposed.

An adaptive detector of genioglossus EMG reflex using Berkner transform for time latency measurement in OSA pathophysiological studies.

To investigate obstructive sleep apnea syndrome mechanisms, we developed a device to measure the surface electromyogram (EMG) time latency reflex of the genioglossus muscle stimulated by time and amplitude calibrated negative pharyngeal pressure drops. The reflex signals were found to be disturbed by transient signals that generate false alarms. Thus, to reduce false alarm occurrences we designed an adaptive multiscale method. Continuous wavelet transform (CWT) is widely used in biomedical signal event detection processes. The Berkner transform is an approximation of a CWT that is based on a hierarchical scheme similar to discrete wavelet transform. We used the Berkner transform to build a multiscale detector because it offers the possibility of maxima coefficients linkage that leads to good accuracy in reflex onset localization. As a contribution to this novel approach we used a reconstruction formula to develop an adaptive method for scale range determination in our surface EMG reflex detector. Finally, we characterized our detector in terms of accuracy and robustness, first on synthesized signals and second, on signals acquired on apneic patients and healthy subjects. Preliminary results showed a significant difference (p < 0.01) between the two populations regarding the genioglossus muscle mean latency time. These physiological findings may partly explain why the upper airway protective reflex occurring when a negative pressure is applied to the upper airway is ineffective in OSA patients, leading to pharyngeal collapse.

Analysis of the collapsibility of the upper airway in a spectrum of sleep-disordered breathing: a modelling approach.

Using a simplified model of the upper airways with two independent collapsible elements (nostrils and hypo-pharynx), we calculated the cross-sectional area of these two elements, taking into account pressure drops. We experimentally measured flow and pressure in the fossa and hypo-pharynx in various syndromes. This allowed us to compare the behaviour of the area supplied by our model with the aerodynamic resistance that is often used to analyse upper airway flow limitation events. We showed that nostril and hypo-pharyngeal areas are better correlated than the resistance values and thus concluded that the pressure divided by the square of the flow is a better parameter for analysing flow limitation in upper airways than resistance. Owing to its simplicity, our model is able to supply the area of the collapsible element in real time, which is impossible with more sophisticated models.