Dynamic Bayesian Model for Detecting Obstructive Respiratory Events by Using an Experimental Model

In this study, we propose a model-based tool for the detection of obstructive apnea episodes by using ECG features from a single lead channel. Several sequences of recurrent apnea were provoked in separate 15-min periods in anesthetized rats during an experimental model of obstructive sleep apnea (OSA). Morphology-based ECG markers and the beat-to-beat interval (RR) were assessed in each sequence. These markers were used to train dynamic Bayesian networks (DBN) with different orders and feature combinations to find a good tradeoff between network complexity and apnea-detection performance. By using a filtering approach, the resulting DBNs were used to infer the apnea probability signal for subsequent episodes in the same rat. These signals were then processed using by 15-s epochs to determine whether epochs were classified as apneic or nonapneic. Our results showed that fifth-order models provided suitable RMSE values, since higher order models become significantly more complex and present worse generalization. A global threshold of 0.2 gave the best overall performance for all combinations tested, with Acc = 81.3%, Se = 69.8% and Sp = 81.5%, using only two parameters including the RR and Ds (R-wave downslope) markers. We concluded that multivariate models using DBNs represent a powerful tool for detecting obstructive apnea episodes in short segments, which may also serve to estimate the number of total events in a given time period.

Differences in acoustic features of cough by pneumonia severity in patients with COVID-19: a cross-sectional study

Background

Acute respiratory syndrome due to coronavirus 2 (SARS-CoV-2) is characterised by heterogeneous levels of disease severity. It is not necessarily apparent whether a patient will develop a severe disease or not. This cross-sectional study explores whether acoustic properties of the cough sound of patients with coronavirus disease (COVID-19), the illness caused by SARS-CoV-2, correlate with their disease and pneumonia severity, with the aim of identifying patients with a severe disease.

Methods

Voluntary cough sounds were recorded using a smartphone in 70 COVID-19 patients within the first 24 h of their hospital arrival, between April 2020 and May 2021. Based on gas exchange abnormalities, patients were classified as mild, moderate, or severe. Time- and frequency-based variables were obtained from each cough effort and analysed using a linear mixed-effects modelling approach.

Results

Records from 62 patients (37% female) were eligible for inclusion in the analysis, with mild, moderate, and severe groups consisting of 31, 14 and 17 patients respectively. 5 of the parameters examined were found to be significantly different in the cough of patients at different disease levels of severity, with a further 2 parameters found to be affected differently by the disease severity in men and women.

Conclusions

We suggest that all these differences reflect the progressive pathophysiological alterations occurring in the respiratory system of COVID-19 patients, and potentially would provide an easy and cost-effective way to initially stratify patients, identifying those with more severe disease, and thereby most effectively allocate healthcare resources.

Predicting 6-minute walking test outcomes in patients with chronic obstructive pulmonary disease without physical performance measures

BACKGROUND AND OBJECTIVE

Chronic obstructive pulmonary disease (COPD) requires a multifactorial assessment, evaluating the airflow limitation and symptoms of the patients. The 6-min walk test (6MWT) is commonly used to evaluate the functional exercise capacity in these patients. This study aims to propose a novel predictive model of the major 6MWT outcomes for COPD assessment, without physical performance measurements.

METHODS

Cardiopulmonary and clinical parameters were obtained from fifty COPD patients. These parameters were used as inputs of a Bayesian network (BN), which integrated three multivariate models including the 6-min walking distance (6MWD), the maximum HR (HR_max) after the walking, and the HR decay 3 min after (HRR₃). The use of BN allows the assessment of the patients' status by predicting the 6MWT outcomes, but also inferring disease severity parameters based on actual patient's 6MWT outcomes.

RESULTS

Firstly, the correlation obtained between the estimated and actual 6MWT measures was strong (R = 0.84, MAPE = 8.10% for HR_max) and moderate (R = 0.58, MAPE = 15.43% for 6MWD and R = 0.58, MAPE = 32.49% for HRR₃), improving the classical methods to estimate 6MWD. Secondly, the classification of disease severity showed an accuracy of 78.3% using three severity groups, which increased up to 84.4% for two defined severity groups.

CONCLUSIONS

We propose a powerful two-way assessment tool for COPD patients, capable of predicting 6MWT outcomes without the need for an actual walking exercise. This model-based tool opens the way to implement a continuous monitoring system for COPD patients at home and to provide more personalized care.

Detection of Sleep-Disordered Breathing in Patients with Spinal Cord Injury Using a Smartphone

Patients with spinal cord injury (SCI) have an increased risk of sleep-disordered breathing (SDB), which can lead to serious comorbidities and impact patients’ recovery and quality of life. However, sleep tests are rarely performed on SCI patients, given their multiple health needs and the cost and complexity of diagnostic equipment. The objective of this study was to use a novel smartphone system as a simple non-invasive tool to monitor SDB in SCI patients. We recorded pulse oximetry, acoustic, and accelerometer data using a smartphone during overnight tests in 19 SCI patients and 19 able-bodied controls. Then, we analyzed these signals with automatic algorithms to detect desaturation, apnea, and hypopnea events and monitor sleep position. The apnea–hypopnea index (AHI) was significantly higher in SCI patients than controls (25 ± 15 vs. 9 ± 7, p < 0.001). We found that 63% of SCI patients had moderate-to-severe SDB (AHI ≥ 15) in contrast to 21% of control subjects. Most SCI patients slept predominantly in supine position, but an increased occurrence of events in supine position was only observed for eight patients. This study highlights the problem of SDB in SCI and provides simple cost-effective sleep monitoring tools to facilitate the detection, understanding, and management of SDB in SCI patients.

Quantitative evaluation of trunk function and the StartReact effect during reaching in patients with cervical and thoracic spinal cord injury

Objective.Impaired trunk stability is frequent in spinal cord injury (SCI), but there is a lack of quantitative measures for assessing trunk function. Our objectives were to: (a) evaluate trunk muscle activity and movement patterns during a reaching task in SCI patients, (b) compare the impact of cervical (cSCI) and thoracic (tSCI) injuries in trunk function, and (c) investigate the effects of a startling acoustic stimulus (SAS) in these patients.Approach.Electromyographic (EMG) and smartphone accelerometer data were recorded from 15 cSCI patients, nine tSCI patients, and 24 healthy controls, during a reaching task requiring trunk tilting. We calculated the response time (RespT) until pressing a target button, EMG onset latencies and amplitudes, and trunk tilt, lateral deviation, and other movement features from accelerometry. Statistical analysis was applied to analyze the effects of group (cSCI, tSCI, control) and condition (SAS, non-SAS) in each outcome measure.Main results.SCI patients, especially those with cSCI, presented significantly longer RespT and EMG onset latencies than controls. Moreover, in SCI patients, forward trunk tilt was accompanied by significant lateral deviation. RespT and EMG latencies were remarkably shortened by the SAS (the so-called StartReact effect) in tSCI patients and controls, but not in cSCI patients, who also showed higher variability.Significance. The combination of EMG and smartphone accelerometer data can provide quantitative measures for the assessment of trunk function in SCI. Our results show deficits in postural control and compensatory strategies employed by SCI patients, including delayed responses and higher lateral deviations, possibly to improve sitting balance. This is the first study investigating the StartReact responses in trunk muscles in SCI patients and shows that the SAS significantly accelerates RespT in tSCI, but not in cSCI, suggesting an increased cortical control exerted by these patients.

SleepPos App: An Automated Smartphone Application for Angle Based High Resolution Sleep Position Monitoring and Treatment

Poor sleep quality or disturbed sleep is associated with multiple health conditions. Sleep position affects the severity and occurrence of these complications, and positional therapy is one of the less invasive treatments to deal with them. Sleep positions can be self-reported, which is unreliable, or determined by using specific devices, such as polysomnography, polygraphy or cameras, that can be expensive and difficult to employ at home. The aim of this study is to determine how smartphones could be used to monitor and treat sleep position at home. We divided our research into three tasks: (1) develop an Android smartphone application (‘SleepPos’ app) which monitors angle-based high-resolution sleep position and allows to simultaneously apply positional treatment; (2) test the smartphone application at home coupled with a pulse oximeter; and (3) explore the potential of this tool to detect the positional occurrence of desaturation events. The results show how the ‘SleepPos’ app successfully determined the sleep position and revealed positional patterns of occurrence of desaturation events. The ‘SleepPos’ app also succeeded in applying positional therapy and preventing the subjects from sleeping in the supine sleep position. This study demonstrates how smartphones are capable of reliably monitoring high-resolution sleep position and provide useful clinical information about the positional occurrence of desaturation events.

Enhanced Monitoring of Sleep Position in Sleep Apnea Patients: Smartphone Triaxial Accelerometry Compared with Video-Validated Position from Polysomnography

Poor sleep quality is a risk factor for multiple mental, cardiovascular, and cerebrovascular diseases. Certain sleep positions or excessive position changes can be related to some diseases and poor sleep quality. Nevertheless, sleep position is usually classified into four discrete values: supine, prone, left and right. An increase in sleep position resolution is necessary to better assess sleep position dynamics and to interpret more accurately intermediate sleep positions. This research aims to study the feasibility of smartphones as sleep position monitors by (1) developing algorithms to retrieve the sleep position angle from smartphone accelerometry; (2) monitoring the sleep position angle in patients with obstructive sleep apnea (OSA); (3) comparing the discretized sleep angle versus the four classic sleep positions obtained by the video-validated polysomnography (PSG); and (4) analyzing the presence of positional OSA (pOSA) related to its sleep angle of occurrence. Results from 19 OSA patients reveal that a higher resolution sleep position would help to better diagnose and treat patients with position-dependent diseases such as pOSA. They also show that smartphones are promising mHealth tools for enhanced position monitoring at hospitals and home, as they can provide sleep position with higher resolution than the gold-standard video-validated PSG.

Health Outcomes from Home Hospitalization: Multisource Predictive Modeling

BACKGROUND

Home hospitalization is widely accepted as a cost-effective alternative to conventional hospitalization for selected patients. A recent analysis of the home hospitalization and early discharge (HH/ED) program at Hospital Clínic de Barcelona over a 10-year period demonstrated high levels of acceptance by patients and professionals, as well as health value-based generation at the provider and health-system levels. However, health risk assessment was identified as an unmet need with the potential to enhance clinical decision making.

OBJECTIVE

The objective of this study is to generate and assess predictive models of mortality and in-hospital admission at entry and at HH/ED discharge.

METHODS

Predictive modeling of mortality and in-hospital admission was done in 2 different scenarios: at entry into the HH/ED program and at discharge, from January 2009 to December 2015. Multisource predictive variables, including standard clinical data, patients' functional features, and population health risk assessment, were considered.

RESULTS

We studied 1925 HH/ED patients by applying a random forest classifier, as it showed the best performance. Average results of the area under the receiver operating characteristic curve (AUROC; sensitivity/specificity) for the prediction of mortality were 0.88 (0.81/0.76) and 0.89 (0.81/0.81) at entry and at home hospitalization discharge, respectively; the AUROC (sensitivity/specificity) values for in-hospital admission were 0.71 (0.67/0.64) and 0.70 (0.71/0.61) at entry and at home hospitalization discharge, respectively.

CONCLUSIONS

The results showed potential for feeding clinical decision support systems aimed at supporting health professionals for inclusion of candidates into the HH/ED program, and have the capacity to guide transitions toward community-based care at HH discharge.

Chest Movement and Respiratory Volume both Contribute to Thoracic Bioimpedance during Loaded Breathing

Bioimpedance has been widely studied as alternative to respiratory monitoring methods because of its linear relationship with respiratory volume during normal breathing. However, other body tissues and fluids contribute to the bioimpedance measurement. The objective of this study is to investigate the relevance of chest movement in thoracic bioimpedance contributions to evaluate the applicability of bioimpedance for respiratory monitoring. We measured airflow, bioimpedance at four electrode configurations and thoracic accelerometer data in 10 healthy subjects during inspiratory loading. This protocol permitted us to study the contributions during different levels of inspiratory muscle activity. We used chest movement and volume signals to characterize the bioimpedance signal using linear mixed-effect models and neural networks for each subject and level of muscle activity. The performance was evaluated using the Mean Average Percentage Errors for each respiratory cycle. The lowest errors corresponded to the combination of chest movement and volume for both linear models and neural networks. Particularly, neural networks presented lower errors (median below 4.29%). At high levels of muscle activity, the differences in model performance indicated an increased contribution of chest movement to the bioimpedance signal. Accordingly, chest movement contributed substantially to bioimpedance measurement and more notably at high muscle activity levels.

Engineered Macroscale Cardiac Constructs Elicit Human Myocardial Tissue-like Functionality

In vitro surrogate models of human cardiac tissue hold great promise in disease modeling, cardiotoxicity testing, and future applications in regenerative medicine. However, the generation of engineered human cardiac constructs with tissue-like functionality is currently thwarted by difficulties in achieving efficient maturation at the cellular and/or tissular level. Here, we report on the design and implementation of a platform for the production of engineered cardiac macrotissues from human pluripotent stem cells (PSCs), which we term "CardioSlice." PSC-derived cardiomyocytes, together with human fibroblasts, are seeded into large 3D porous scaffolds and cultured using a parallelized perfusion bioreactor with custom-made culture chambers. Continuous electrical stimulation for 2 weeks promotes cardiomyocyte alignment and synchronization, and the emergence of cardiac tissue-like properties. These include electrocardiogram-like signals that can be readily measured on the surface of CardioSlice constructs, and a response to proarrhythmic drugs that is predictive of their effect in human patients.

Electromyography-Based Respiratory Onset Detection in COPD Patients on Non-Invasive Mechanical Ventilation

To optimize long-term nocturnal non-invasive ventilation in patients with chronic obstructive pulmonary disease, surface diaphragm electromyography (EMGdi) might be helpful to detect patient-ventilator asynchrony. However, visual analysis is labor-intensive and EMGdi is heavily corrupted by electrocardiographic (ECG) activity. Therefore, we developed an automatic method to detect inspiratory onset from EMGdi envelope using fixed sample entropy (fSE) and a dynamic threshold based on kernel density estimation (KDE). Moreover, we combined fSE with adaptive filtering techniques to reduce ECG interference and improve onset detection. The performance of EMGdi envelopes extracted by applying fSE and fSE with adaptive filtering was compared to the root mean square (RMS)-based envelope provided by the EMG acquisition device. Automatic onset detection accuracy, using these three envelopes, was evaluated through the root mean square error (RMSE) between the automatic and mean visual onsets (made by two observers). The fSE-based method provided lower RMSE, which was reduced from 298 ms to 264 ms when combined with adaptive filtering, compared to 301 ms provided by the RMS-based method. The RMSE was negatively correlated with the proposed EMGdi quality indices. Following further validation, fSE with KDE, combined with adaptive filtering when dealing with low quality EMGdi, indicates promise for detecting the neural onset of respiratory drive.

Performance Evaluation of Fixed Sample Entropy in Myographic Signals for Inspiratory Muscle Activity Estimation

Fixed sample entropy (fSampEn) has been successfully applied to myographic signals for inspiratory muscle activity estimation, attenuating interference from cardiac activity. However, several values have been suggested for fSampEn parameters depending on the application, and there is no consensus standard for optimum values. This study aimed to perform a thorough evaluation of the performance of the most relevant fSampEn parameters in myographic respiratory signals, and to propose, for the first time, a set of optimal general fSampEn parameters for a proper estimation of inspiratory muscle activity. Different combinations of fSampEn parameters were used to calculate fSampEn in both non-invasive and the gold standard invasive myographic respiratory signals. All signals were recorded in a heterogeneous population of healthy subjects and chronic obstructive pulmonary disease patients during loaded breathing, thus allowing the performance of fSampEn to be evaluated for a variety of inspiratory muscle activation levels. The performance of fSampEn was assessed by means of the cross-covariance of fSampEn time-series and both mouth and transdiaphragmatic pressures generated by inspiratory muscles. A set of optimal general fSampEn parameters was proposed, allowing fSampEn of different subjects to be compared and contributing to improving the assessment of inspiratory muscle activity in health and disease.

Surface mechanomyography and electromyography provide non-invasive indices of inspiratory muscle force and activation in healthy subjects

The current gold standard assessment of human inspiratory muscle function involves using invasive measures of transdiaphragmatic pressure (Pdi) or crural diaphragm electromyography (oesEMGdi). Mechanomyography is a non-invasive measure of muscle vibration associated with muscle contraction. Surface electromyogram and mechanomyogram, recorded transcutaneously using sensors placed over the lower intercostal spaces (sEMGlic and sMMGlic respectively), have been proposed to provide non-invasive indices of inspiratory muscle activation, but have not been directly compared to gold standard Pdi and oesEMGdi measures during voluntary respiratory manoeuvres. To validate the non-invasive techniques, the relationships between Pdi and sMMGlic, and between oesEMGdi and sEMGlic were measured simultaneously in 12 healthy subjects during an incremental inspiratory threshold loading protocol. Myographic signals were analysed using fixed sample entropy (fSampEn), which is less influenced by cardiac artefacts than conventional root mean square. Strong correlations were observed between: mean Pdi and mean fSampEn |sMMGlic| (left, 0.76; right, 0.81), the time-integrals of the Pdi and fSampEn |sMMGlic| (left, 0.78; right, 0.83), and mean fSampEn oesEMGdi and mean fSampEn sEMGlic (left, 0.84; right, 0.83). These findings suggest that sMMGlic and sEMGlic could provide useful non-invasive alternatives to Pdi and oesEMGdi for the assessment of inspiratory muscle function in health and disease.

Novel approach to continuous adventitious respiratory sound analysis for the assessment of bronchodilator response

Background

A thorough analysis of continuous adventitious sounds (CAS) can provide distinct and complementary information about bronchodilator response (BDR), beyond that provided by spirometry. Nevertheless, previous approaches to CAS analysis were limited by certain methodology issues. The aim of this study is to propose a new integrated approach to CAS analysis that contributes to improving the assessment of BDR in clinical practice for asthma patients.

Methods

Respiratory sounds and flow were recorded in 25 subjects, including 7 asthma patients with positive BDR (BDR+), assessed by spirometry, 13 asthma patients with negative BDR (BDR-), and 5 controls. A total of 5149 acoustic components were characterized using the Hilbert spectrum, and used to train and validate a support vector machine classifier, which distinguished acoustic components corresponding to CAS from those corresponding to other sounds. Once the method was validated, BDR was assessed in all participants by CAS analysis, and compared to BDR assessed by spirometry.

Results

BDR+ patients had a homogenous high change in the number of CAS after bronchodilation, which agreed with the positive BDR by spirometry, indicating high reversibility of airway obstruction. Nevertheless, we also found an appreciable change in the number of CAS in many BDR- patients, revealing alterations in airway obstruction that were not detected by spirometry. We propose a categorization for the change in the number of CAS, which allowed us to stratify BDR- patients into three consistent groups. From the 13 BDR- patients, 6 had a high response, similar to BDR+ patients, 4 had a noteworthy medium response, and 1 had a low response.

Conclusions

In this study, a new non-invasive and integrated approach to CAS analysis is proposed as a high-sensitive tool for assessing BDR in terms of acoustic parameters which, together with spirometry parameters, contribute to improving the stratification of BDR levels in patients with obstructive pulmonary diseases.

EMG-Derived Respiration Signal Using the Fixed Sample Entropy during an Inspiratory Load Protocol

Extracting clinical information from one single measurement represents a step forward in the assessment of the respiratory muscle function. This attracting idea entails the reduction of the instrumentation and fosters to develop new medical integrated technologies. We present the use of the fixed sample entropy (fSampEn) as a more direct method to non-invasively derive the breathing activity from the diaphragm electromyographic (EMGdi) signal, and thus to extract the respiratory rate, an important vital sign which is cumbersome and time-consuming to be measured by clinicians. fSampEn is a method to evaluate the EMGdi activity that is less sensitive to the cardiac activity (ECG) and its application has proven to be useful to evaluate the load of the respiratory muscles. The behavior of the proposed method was tested in signals from two subjects that performed an inspiratory load protocol, which consists of increments in the inspiratory mouth pressure (P mouth). Two respiratory signals were derived and compared to the P mouth signal: the ECG-derived respiration (EDR) signal from the lead-I configuration, and the EMG-derived respiration (EMGDR) signal by applying the fSampEn method over the EMGdi signal. The similitude and the lag between signals were calculated through the cross-correlation between each derived respiratory signal and the P mouth. The EMGDR signal showed higher correlation and lower lag values (≥ 0.91 and ≤ 0.70 s, respectively) than the EDR signal (≥ 0.83 and ≤ 0.99 s, respectively). Additionally, the respiratory rate was estimated with the P mouth, EDR and EMGDR signals showing very similar values. The results from this preliminary work suggest that the fSampEn method can be used to derive the respiration waveform from the respiratory muscle electrical activity.

Respiratory signal derived from the smartphone built-in accelerometer during a Respiratory Load Protocol

The scope of our work focuses on investigating the potential use of the built-in accelerometer of the smartphones for the recording of the respiratory activity and deriving the respiratory rate. Five healthy subjects performed an inspiratory load protocol. The excursion of the right chest was recorded using the built-in triaxial accelerometer of a smartphone along the x, y and z axes and with an external uniaxial accelerometer. Simultaneously, the respiratory airflow and the inspiratory mouth pressure were recorded, as reference respiratory signals. The chest acceleration signal recorded in the z axis with the smartphone was denoised using a scheme based on the ensemble empirical mode decomposition, a noise data assisted method which decomposes nonstationary and nonlinear signals into intrinsic mode functions. To distinguish noisy oscillatory modes from the relevant modes we use the detrended fluctuation analysis. We reported a very strong correlation between the acceleration of the z axis of the smartphone and the reference accelerometer across the inspiratory load protocol (from 0.80 to 0.97). Furthermore, the evaluation of the respiratory rate showed a very strong correlation (0.98). A good agreement was observed between the respiratory rate estimated with the chest acceleration signal from the z axis of the smartphone and with the respiratory airflow signal: Bland-Altman limits of agreement between -1.44 and 1.46 breaths per minute with a mean bias of -0.01 breaths per minute. This preliminary study provides a valuable insight into the use of the smartphone and its built-in accelerometer for respiratory monitoring.

Respiratory rate detection by empirical mode decomposition method applied to diaphragm mechanomyographic signals

Non-invasive evaluation of respiratory activity is an area of increasing research interest, resulting in the appearance of new monitoring techniques, ones of these being based on the analysis of the diaphragm mechanomyographic (MMGdi) signal. The MMGdi signal can be decomposed into two parts: (1) a high frequency activity corresponding to lateral vibration of respiratory muscles, and (2) a low frequency activity related to excursion of the thoracic cage. The purpose of this study was to apply the empirical mode decomposition (EMD) method to obtain the low frequency of MMGdi signal and selecting the intrinsic mode functions related to the respiratory movement. With this intention, MMGdi signals were acquired from a healthy subject, during an incremental load respiratory test, by means of two capacitive accelerometers located at left and right sides of rib cage. Subsequently, both signals were combined to obtain a new signal which contains the contribution of both sides of thoracic cage. Respiratory rate (RR) measured from the mechanical activity (RR(MMG)) was compared with that measured from inspiratory pressure signal (RR(P)). Results showed a Pearson's correlation coefficient (r = 0.87) and a good agreement (mean bias = -0.21 with lower and upper limits of -2.33 and 1.89 breaths per minute, respectively) between RR(MMG) and RR(P) measurements. In conclusion, this study suggests that RR can be estimated using EMD for extracting respiratory movement from low mechanical activity, during an inspiratory test protocol.

Characterization of laplacian surface electromyographic signals during isometric contraction in biceps brachii

Surface electromyography (sEMG) is a noninvasive technique for monitoring the electrical activity produced by the muscles. Usually, sEMG is performed by carrying out monopolar or bipolar recordings by means of conventional Ag/AgCl electrodes. In contrast, Laplacian recordings of sEMG could also be obtained by using coaxial ring electrodes. Laplacian recordings increase spatial resolution and attenuate other distant bioelectric interferences. Nevertheless, the spectral characteristics of this kind of recordings have been scarcely studied. The objective of this paper is to characterize the sEMG signals recorded with a Laplacian ring electrode and to compare them with traditional bipolar recordings with disc electrodes. Both kinds of signals were collected simultaneously in two healthy subjects during resting and sustained isometric voluntary contraction activities in biceps brachii. The conducted study computed the cumulative percentage of the power spectrum of sEMG so as to determine the energy bandwidth of the two kinds of recordings and the signal to noise ratio in different bands of the sEMG spectrum. Also, muscle fatigue, a condition when muscle force is reduced, was assessed using indexes from amplitude and frequency domain. The results of this study suggest that Laplacian sEMG has higher spectral bandwidth but a lower signal to noise ratio in comparison to bipolar sEMG. In addition, frequency fatigue indexes showed that Laplacian recording had better response than bipolar recording, which suggests that Laplacian electrode can be useful to study muscular fatigue due to better spatial resolution.

Cardiac interference reduction in diaphragmatic MMG signals during a Maintained Inspiratory Pressure Test

A recursive least square (RLS) adaptive filtering algorithm for reduction of cardiac interference in diaphragmatic mecanomyographic (MMGdi) signals is addressed in this paper. MMGdi signals were acquired with a capacitive accelerometer placed between 7th and 8th intercostal spaces, on the right anterior axillary line, during a maintained inspiratory pressure test. Subjects were asked to maintain a constant inspiratory pressure with a mouthpiece connected to a closed tube (without breathing). This maneuver was repeated at five different contraction efforts: apnea (no effort), 20 cmH2O, 40 cmH2O, 60 cmH2O and maximum voluntary contraction. An adaptive noise canceller (ANC) using the RLS algorithm was applied on the MMGdi signals. To evaluate the behavior of the ANC, the MMGdi signals were analyzed in two segments: with and without cardiac interference (WCI and NCI, respectively). In both segments it was analyzed the power spectral density (PSD), and the ARV and RMS amplitude parameters for each contraction effort. With the proposed ANC algorithm the amplitude parameters of the WCI segments were reduced to a level similar to the one of the NCI segments. The obtained results showed that ANC using the RLS algorithm allows to significantly reduce the cardiac interference in MMGdi signals.

Time-varying signal analysis to detect high-altitude periodic breathing in climbers ascending to extreme altitude

This work investigates the performance of cardiorespiratory analysis detecting periodic breathing (PB) in chest wall recordings in mountaineers climbing to extreme altitude. The breathing patterns of 34 mountaineers were monitored unobtrusively by inductance plethysmography, ECG and pulse oximetry using a portable recorder during climbs at altitudes between 4497 and 7546 m on Mt. Muztagh Ata. The minute ventilation (VE) and heart rate (HR) signals were studied, to identify visually scored PB, applying time-varying spectral, coherence and entropy analysis. In 411 climbing periods, 30-120 min in duration, high values of mean power (MP(VE)) and slope (MSlope(VE)) of the modulation frequency band of VE, accurately identified PB, with an area under the ROC curve of 88 and 89%, respectively. Prolonged stay at altitude was associated with an increase in PB. During PB episodes, higher peak power of ventilatory (MP(VE)) and cardiac (MP(LF)(HR) ) oscillations and cardiorespiratory coherence (MP(LF)(Coher)), but reduced ventilation entropy (SampEn(VE)), was observed. Therefore, the characterization of cardiorespiratory dynamics by the analysis of VE and HR signals accurately identifies PB and effects of altitude acclimatization, providing promising tools for investigating physiologic effects of environmental exposures and diseases.

Improvement in Neural Respiratory Drive Estimation From Diaphragm Electromyographic Signals Using Fixed Sample Entropy

Diaphragm electromyography is a valuable technique for the recording of electrical activity of the diaphragm. The analysis of diaphragm electromyographic (EMGdi) signal amplitude is an alternative approach for the quantification of the neural respiratory drive (NRD). The EMGdi signal is, however, corrupted by electrocardiographic (ECG) activity, and this presence of cardiac activity can make the EMGdi interpretation more difficult. Traditionally, the EMGdi amplitude has been estimated using the average rectified value (ARV) and the root mean square (RMS). In this study, surface EMGdi signals were analyzed using the fixed sample entropy (fSampEn) algorithm, and compared to the traditional ARV and RMS methods. The fSampEn is calculated using a tolerance value fixed and independent of the standard deviation of the analysis window. Thus, this method quantifies the amplitude of the complex components of stochastic signals (such as EMGdi), and being less affected by changes in amplitude due to less complex components (such as ECG). The proposed method was tested in synthetic and recorded EMGdi signals. fSampEn was less sensitive to the effect of cardiac activity on EMGdi signals with different levels of NRD than ARV and RMS amplitude parameters. The mean and standard deviation of the Pearson's correlation values between inspiratory mouth pressure (an indirect measure of the respiratory muscle activity) and fSampEn, ARV, and RMS parameters, estimated in the recorded EMGdi signal at tidal volume (without inspiratory load), were 0.38±0.12, 0.27±0.11 , and 0.11±0.13, respectively. Whereas at 33 cmH2O (maximum inspiratory load) were 0.83±0.02, 0.76±0.07, and 0.61±0.19 , respectively. Our findings suggest that the proposed method may improve the evaluation of NRD.

Automatic Differentiation of Normal and Continuous Adventitious Respiratory Sounds Using Ensemble Empirical Mode Decomposition and Instantaneous Frequency

Differentiating normal from adventitious respiratory sounds (RS) is a major challenge in the diagnosis of pulmonary diseases. Particularly, continuous adventitious sounds (CAS) are of clinical interest because they reflect the severity of certain diseases. This study presents a new classifier that automatically distinguishes normal sounds from CAS. It is based on the multiscale analysis of instantaneous frequency (IF) and envelope (IE) calculated after ensemble empirical mode decomposition (EEMD). These techniques have two major advantages over previous techniques: high temporal resolution is achieved by calculating IF-IE and a priori knowledge of signal characteristics is not required for EEMD. The classifier is based on the fact that the IF dispersion of RS signals markedly decreases when CAS appear in respiratory cycles. Therefore, CAS were detected by using a moving window to calculate the dispersion of IF sequences. The study dataset contained 1494 RS segments extracted from 870 inspiratory cycles recorded from 30 patients with asthma. All cycles and their RS segments were previously classified as containing normal sounds or CAS by a highly experienced physician to obtain a gold standard classification. A support vector machine classifier was trained and tested using an iterative procedure in which the dataset was randomly divided into training (65%) and testing (35%) sets inside a loop. The SVM classifier was also tested on 4592 simulated CAS cycles. High total accuracy was obtained with both recorded (94.6% ± 0.3%) and simulated (92.8% ± 3.6%) signals. We conclude that the proposed method is promising for RS analysis and classification.

Evidence towards improved estimation of respiratory muscle effort from diaphragm mechanomyographic signals with cardiac vibration interference using sample entropy with fixed tolerance values

The analysis of amplitude parameters of the diaphragm mechanomyographic (MMGdi) signal is a non-invasive technique to assess respiratory muscle effort and to detect and quantify the severity of respiratory muscle weakness. The amplitude of the MMGdi signal is usually evaluated using the average rectified value or the root mean square of the signal. However, these estimations are greatly affected by the presence of cardiac vibration or mechanocardiographic (MCG) noise. In this study, we present a method for improving the estimation of the respiratory muscle effort from MMGdi signals that is robust to the presence of MCG. This method is based on the calculation of the sample entropy using fixed tolerance values (fSampEn), that is, with tolerance values that are not normalized by the local standard deviation of the window analyzed. The behavior of the fSampEn parameter was tested in synthesized mechanomyographic signals, with different ratios between the amplitude of the MCG and clean mechanomyographic components. As an example of application of this technique, the use of fSampEn was explored also in recorded MMGdi signals, with different inspiratory loads. The results with both synthetic and recorded signals indicate that the entropy parameter is less affected by the MCG noise, especially at low signal-to-noise ratios. Therefore, we believe that the proposed fSampEn parameter could improve estimates of respiratory muscle effort from MMGdi signals with the presence of MCG interference.

Synergy analysis as a tool to design and assess an effective stroke rehabilitation

The poor rehabilitation success rate, including the cases of ineffective and detrimental adaptations, make stroke a leading cause of disability. Thus, it is essential to recognize the mechanisms driving healthy motor recovery to improve such rate. Stroke alters the Synergy Architecture (SA), the modular muscle control system. So SA analysis may constitute a powerful tool to design and assess rehabilitation procedures. However, current impairment scales do not consider the patient's neuromuscular state. To gain insights into this hypothesis, we recorded multiple myoelectric signals from upper-limb muscles, in healthy subjects, while executing a set of common rehabilitation exercises. We found that SA reveals optimized motor control strategies and the positive effects of the use of visual feedback (VF) on motor control. Furthermore we demonstrate that the right and left arm's SA share the basic structure within the same subject, so we propose using the unaffected limb's SA as a reference motion pattern to be reached through rehabilitation.

Estimation of instantaneous frequency from empirical mode decomposition on respiratory sounds analysis

Instantaneous frequency (IF) calculated by empirical mode decomposition (EMD) provides a novel approach to analyze respiratory sounds (RS). Traditionally, RS have been analyzed using classical time-frequency distributions, such as short-time Fourier transform (STFT) or wavelet transform (WT). However, EMD has become a powerful tool for nonlinear and non-stationary data analysis. IF estimated by EMD has two major advantages: its high temporal resolution and the fact that a priori knowledge of the signal characteristics is not required. In this study, we have estimated IF by EMD on real RS signals in order to identify continuous adventitious sounds (CAS), such as wheezes, within inspiratory sounds cycles. We show that there are differences in IF distribution among frequency scales of RS signal when CAS are within RS. Therefore, a new method for RS analysis and classification may be developed by combining both EMD and IF.

Feasibility of noninvasive single-channel automated differentiation of obstructive and central hypopneas with nasal airflow

BACKGROUND

The identification of obstructive and central hypopneas is considered challenging in clinical practice. Presently, obstructive and central hypopneas are usually not differentiated or scores lack reliability due to the technical limitations of standard polysomnography. Esophageal pressure measurement is the gold-standard for identifying these events but its invasiveness deters its usage in daily practice.

OBJECTIVES

To determine the feasibility and efficacy of an automatic noninvasive analysis method for the differentiation of obstructive and central hypopneas based solely on a single-channel nasal airflow signal. The obtained results are compared with gold-standard esophageal pressure scores.

METHODS

A total of 41 patients underwent full night polysomnography with systematic esophageal pressure recording. Two experts in sleep medicine independently differentiated hypopneas with the gold-standard esophageal pressure signal. Features were automatically extracted from the nasal airflow signal of each annotated hypopnea to train and test the automatic analysis method. Interscorer agreement between automatic and visual scorers was measured with Cohen's kappa statistic (ĸ).

RESULTS

A total of 1,237 hypopneas were visually differentiated. The automatic analysis achieved an interscorer agreement of ĸ = 0.37 and an accuracy of 69% for scorer A, ĸ = 0.40 and 70% for scorer B and ĸ = 0.41 and 71% for the agreed scores of scorers A and B.

CONCLUSIONS

The promising results obtained in this pilot study demonstrate the feasibility of noninvasive single-channel hypopnea differentiation. Further development of this method may help improving initial diagnosis with home screening devices and offering a means of therapy selection and/or control.

Normal non-regular snores as a tool for screening SAHS severity

Snoring is one of the earliest and most consistent sign of upper airway obstruction leading to Sleep Apnea-Hypopnea Syndrome (SAHS). Several studies on post-apneic snores, snores that are emitted immediately after an apnea, have already proven that this type of snoring is most distinct from that of normal snoring. However, post-apneic snores are more unlikely and sometimes even inexistent in simple snorers and mild SAHS subjects. In this work we address that issue by proposing the study of normal non-regular snores. They correspond to successive snores that are separated by normal breathing cycles. The results obtained establish the feasibility of acoustic parameters of normal non-regular snores as a promising tool for a prompt screening of SAHS severity.

Comparison of upper airway respiratory resistance measurements with the esophageal pressure/airflow relationship during sleep

Measurement of upper airway resistance is of interest in sleep disordered breathing to estimate upper airway patency. Resistance is calculated with the airflow and respiratory effort signals. However, there is no consensus on a standard for upper airway resistance measurement. This study proposes a new benchmarking method to objectively compare different upper airway resistance measurement methods by objectively differentiating between breaths with inspiratory flow limitation (high resistance) and non-limited breaths (low resistance). Resistance was measured at peak-Pes, at peak-flow, at the linear portion of a polynomial equation, as an area comparative and as average resistance for an inspiration. A total of 20 patients with systematic, gold-standard esophageal pressure and nasal airflow acquisition were analyzed and 109,955 breaths were automatically extracted and evaluated. Relative resistance values in relationship to a reference resistance value obtained during wakefulness were also analyzed. The peak-Pes measurement method obtained the highest separation index with significant (p < 0.001) differences to the other methods, followed by the area comparative and the peak-flow methods. As expected, average resistances were significantly (p < 0.001) lower for the non-IFL than for the IFL group. Hence, we recommend employing the peak-Pes for accurate upper airway resistance estimation.

Bayes classification of snoring subjects with and without Sleep Apnea Hypopnea Syndrome, using a Kernel method

The gold standard for diagnosing Sleep Apnea Hypopnea Syndrome (SAHS) is the Polysomnography (PSG), an expensive, labor-intensive and time-consuming procedure. It would be helpful to have a simple screening method that allowed to early determining the severity of a subject prior to his/her enrolment for a PSG. Several differences have been reported in the acoustic snoring characteristics between simple snorers and SAHS patients. Previous studies usually classify snoring subjects into two groups given a threshold of Apnea-Hypoapnea Index (AHI). Recently, Bayes multi-group classification with Gaussian Probability Density Function (PDF) has been proposed, using snore features in combination with apnea-related information. In this work we show that the Bayes classifier with Kernel PDF estimation outperforms the Gaussian approach and allows the classification of SAHS subjects according to their severity, using only the information obtained from snores. This could be the base of a single channel, snore-based, screening procedure for SAHS.

Snoring analysis for the screening of Sleep Apnea Hypopnea Syndrome with a single-channel device developed using polysomnographic and snoring databases

Several studies have shown differences in acoustic snoring characteristics between patients with Sleep Apnea-Hypopnea Syndrome (SAHS) and simple snorers. Usually a few manually isolated snores are analyzed, with an emphasis on postapneic snores in SAHS patients. Automatic analysis of snores can provide objective information over a longer period of sleep. Although some snore detection methods have recently been proposed, they have not yet been applied to full-night analysis devices for screening purposes. We used a new automatic snoring detection and analysis system to monitor snoring during full-night studies to assess whether the acoustic characteristics of snores differ in relation to the Apnea-Hypopnea Index (AHI) and to classify snoring subjects according to their AHI. A complete procedure for device development was designed, using databases with polysomnography (PSG) and snoring signals. This included annotation of many types of episodes by an expert physician: snores, inspiration and exhalation breath sounds, speech and noise artifacts, The AHI of each subject was estimated with classical PSG analysis, as a gold standard. The system was able to correctly classify 77% of subjects in 4 severity levels, based on snoring analysis and sound-based apnea detection. The sensitivity and specificity of the system, to identify healthy subjects from pathologic patients (mild to severe SAHS), were 83% and 100%, respectively. Besides, the Apnea Index (AI) obtained with the system correlated with the obtained by PSG or Respiratory Polygraphy (RP) (r=0.87, p<0.05).

All night analysis of time interval between snores in subjects with sleep apnea hypopnea syndrome

Sleep apnea–hypopnea syndrome (SAHS) is a serious sleep disorder, and snoring is one of its earliest and most consistent symptoms. We propose a new methodology for identifying two distinct types of snores: the so-called non-regular and regular snores. Respiratory sound signals from 34 subjects with different ranges of Apnea-Hypopnea Index (AHI = 3.7–109.9 h⁻¹) were acquired. A total number of 74,439 snores were examined. The time interval between regular snores in short segments of the all night recordings was analyzed. Severe SAHS subjects show a shorter time interval between regular snores (p = 0.0036, AHI cp: 30 h⁻¹) and less dispersion on the time interval features during all sleep. Conversely, lower intra-segment variability (p = 0.006, AHI cp: 30 h⁻¹) is seen for less severe SAHS subjects. Features derived from the analysis of time interval between regular snores achieved classification accuracies of 88.2 % (with 90 % sensitivity, 75 % specificity) and 94.1 % (with 94.4 % sensitivity, 93.8 % specificity) for AHI cut-points of severity of 5 and 30 h⁻¹, respectively. The features proved to be reliable predictors of the subjects’ SAHS severity. Our proposed method, the analysis of time interval between snores, provides promising results and puts forward a valuable aid for the early screening of subjects suspected of having SAHS.

Analysis of the respiratory flow cycle morphology in chronic heart failure patients applying principal components analysis

The study of flow cycle morphology provides new information about the breathing pattern. This study proposes the characterization of cycle morphology in chronic heart failure patients (CHF) patients, with periodic (PB) and non-periodic breathing (nPB) patterns, and healthy subjects. Principal component analysis is applied to extract a respiratory cycle model for each time segment defined by a 30-s moving window. To characterize morphology of the model waveform, a number of parameters are extracted whose significance is evaluated in terms of the following three classification problems: CHF patients with either PB or nPB, CHF patients versus healthy subjects, and nPB patients versus healthy subjects. 26 CHF patients (8 with PB and 18 with non-periodic breathing pattern (nPB)) and 35 healthy subjects are studied. The results show that a respiratory cycle compressed in time characterizes PB patients, i.e., shorter inspiratory and expiratory periods, and higher dispersion of the maximum inspiratory and expiratory flow value (accuracy of 87%). The maximal expiratory flow instant occurs earlier in CHF patients than in healthy subjects (accuracy of 87%), with a steeper slope between inspiration and expiration. It is also found that the standard deviation of the expiratory period, evaluated for each subject, is much lower in CHF patients than in healthy subjects. The maximal expiratory flow instant occurs earlier (accuracy of 84%) in nPB patients, when comparing subjects with similar respiratory pattern like nPB patients and healthy subjects.

Respiratory and spontaneous arousals in patients with Sleep Apnea Hypopnea Syndrome

Sleep in patients with Sleep Apnea-Hypopnea Syndrome (SAHS) is frequently interrupted with arousals. Increased amounts of arousals result in shortening total sleep time and repeated sleep-arousal change can result in sleep fragmentation. According to the American Sleep Disorders Association (ASDA) an arousal is a marker of sleep disruption representing a detrimental and harmful feature for sleep. The nature of arousals and its role on the regulation of the sleep process raises controversy and has sparked the debate in the last years. In this work, we analyzed and compared the EEG spectral content of respiratory and spontaneous arousals on a database of 45 SAHS subjects. A total of 3980 arousals (1996 respiratory and 1984 spontaneous) were analyzed. The results showed no differences between the spectral content of the two kinds of arousals. Our findings raise doubt as to whether these two kinds of arousals are truly triggered by different organic mechanisms. Furthermore, they may also challenge the current beliefs regarding the underestimation of the importance of spontaneous arousals and their contribution to sleep fragmentation in patients suffering from SAHS.

Evaluation of the respiratory muscles efficiency during an incremental flow respiratory test

The aim of this study was to evaluate the respiratory muscles efficiency during a progressive incremental flow (IF) respiratory test in healthy and Chronic Obstructive Pulmonary Disease (COPD) subjects. To achieve this, the relationship between mouth Inspiratory Pressure (IP) increment, which is a measure of the force produced by respiratory muscles, and respiratory muscular activity increment, evaluated by means of Mechanomyografic (MMG) signals of the diaphragm muscle, was analyzed. Moreover, the correlation between the respiratory efficiency measure and the obstruction severity of the subjects was also examined. Data from two groups of subjects were analyzed. One group consisted of four female subjects (two healthy subjects and two moderate COPD patients) and the other consisted of ten male subjects (six severe and four very severe COPD patients). All subjects performed an easy IF respiratory test, in which small IP values were reached. We have found that there is an increase of amplitude and a displacement towards low frequencies in the MMG signals when the IP increases. Furthermore, it has also been found that respiratory muscles efficiency is lower when greater the obstructive severity of the patients is, and it is lower in women than in men. These results suggest that the information provided by MMG signals could be used to evaluate the muscular efficiency in healthy and COPD subjects.

Analysis of QRS loop in the Vectorcardiogram of patients with Chagas' disease

In the present work, we have studied the QRS loop in the Vectorcardiogram (VCG) of 95 chronic chagasic patients classified in different groups (I, II and III) according to their degree of myocardial damage. For comparison, the VCGs of 11 healthy subjects used as control group (Group O) were also examined. The QRS loop was obtained for each patient from the XYZ orthogonal leads of their High-Resolution Electrocardiogram (HRECG) records. In order to analyze the variations of QRS loop in each detected beat, it has been proposed in this study the following vectorcardiographic parameters a) Maximum magnitude of the cardiac depolarization vector, b) Volume, c) Area of QRS loop, d) Ratio between the Area and Perimeter, e) Ratio between the major and minor axes of the QRS loop and f) QRS loop Energy. It has been found that one or more indexes exhibited statistical differences (p < 0.05) between groups 0-II, O-III, I-II, I-III and II-III. We concluded that the proposed method could be use as complementary diagnosis technique to evaluate the degree of myocardial damage in chronic chagasic patients.

Continuous analysis and monitoring of snores and their relationship to the apnea-hypopnea index

OBJECTIVES/HYPOTHESIS

We used a new automatic snoring detection and analysis system to monitor snoring during full-night polysomnography to assess whether the acoustic characteristics of snores differ in relation to the apnea-hypopnea index (AHI) and to classify subjects according to their AHI.

STUDY DESIGN

Individual Case-Control Study.

METHODS

Thirty-seven snorers (12 females and 25 males; ages 40-65 years; body mass index (BMI), 29.65 +/- 4.7 kg/m(2)) participated. Subjects were divided into three groups: G1 (AHI <5), G2 (AHI >or=5, <15) and G3 (AHI >or=15). Snore and breathing sounds were recorded with a tracheal microphone throughout 6 hours of nighttime polysomnography. The snoring episodes identified were automatically and continuously analyzed with a previously trained 2-layer feed-forward neural network. Snore number, average intensity, and power spectral density parameters were computed for every subject and compared among AHI groups. Subjects were classified using different AHI thresholds by means of a logistic regression model.

RESULTS

There were significant differences in supine position between G1 and G3 in sound intensity; number of snores; standard deviation of the spectrum; power ratio in bands 0-500, 100-500, and 0-800 Hz; and the symmetry coefficient (P < .03). Patients were classified with thresholds AHI = 5 and AHI = 15 with a sensitivity (specificity) of 87% (71%) and 80% (90%), respectively.

CONCLUSIONS

A new system for automatic monitoring and analysis of snores during the night is presented. Sound intensity and several snore frequency parameters allow differentiation of snorers according to obstructive sleep apnea syndrome severity (OSAS). Automatic snore intensity and frequency monitoring and analysis could be a promising tool for screening OSAS patients, significantly improving the managing of this pathology.

Time-varying respiratory pattern characterization in chronic heart failure patients and healthy subjects

Patients with chronic heart failure (CHF) with periodic breathing (PB) and Cheyne-Stokes respiration (CSR) tend to exhibit higher mortality and poor prognosis. This study proposes the characterization of respiratory patterns in CHF patients and healthy subjects using the envelope of the respiratory flow signal, and autoregressive (AR) time-frequency analysis. In time-varying respiratory patterns, the statistical distribution of the AR coefficients, pole locations, and the spectral parameters that characterize the discriminant band are evaluated to identify typical breathing patterns. In order to evaluate the accuracy of this characterization, a feature selection process followed by linear discriminant analysis is applied. 26 CHF patients (8 patients with PB pattern and 18 with non-periodic breathing pattern (nPB)) are studied. The results show an accuracy of 83.9% with the mean of the main pole magnitude and the mean of the total power, when classifying CHF patients versus healthy subjects, and 83.3% for nPB versus healthy subjects. The best result when classifying CHF patients into PB and nPB was an accuracy of 88.9%, using the coefficient of variation of the first AR coefficient and the mean of the total power.

An invasive and a noninvasive approach for the automatic differentiation of obstructive and central hypopneas

The automatic differentiation of obstructive and central respiratory events is a major challenge in the diagnosis of sleep-disordered breathing. Esophageal pressure (Pes) measurement is the gold-standard method to identify these events. This study presents a new classifier that automatically differentiates obstructive and central hypopneas with the Pes signal and a new approach for an automatic noninvasive classifier with nasal airflow. An overall of 28 patients underwent night polysomnography with Pes recording, and a total of 769 hypopneas were manually scored by human experts to create a gold-standard annotation set. Features were automatically extracted from the Pes signal to train and test the classifiers (discriminant analysis, support vector machines, and adaboost). After a significantly (p < 0.01) higher incidence of inspiratory flow limitation episodes in obstructive hypopneas was objectively, invasively assessed compared to central hypopneas, the feasibility of an automatic noninvasive classifier with features extracted from the airflow signal was demonstrated. The automatic invasive classifier achieved a mean sensitivity, specificity, and accuracy of 0.90 after a 100-fold cross validation. The automatic noninvasive feasibility study obtained similar hypopnea differentiation results as a manual noninvasive classification algorithm. Hence, both systems seem promising for the automatic differentiation of obstructive and central hypopneas.

Correntropy-based spectral characterization of respiratory patterns in patients with chronic heart failure

A correntropy-based technique is proposed for the characterization and classification of respiratory flow signals in chronic heart failure (CHF) patients with periodic or nonperiodic breathing (PB or nPB, respectively) and healthy subjects. The correntropy is a recently introduced, generalized correlation measure whose properties lend themselves to the definition of a correntropy-based spectral density (CSD). Using this technique, both respiratory and modulation frequencies can be reliably detected at their original positions in the spectrum without prior demodulation of the flow signal. Single-parameter classification of respiratory patterns is investigated for three different parameters extracted from the respiratory and modulation frequency bands of the CSD, and one parameter defined by the correntropy mean. The results show that the ratio between the powers in the modulation and respiratory frequency bands provides the best result when classifying CHF patients with either PB or nPB, yielding an accuracy of 88.9%. The correntropy mean offers excellent performance when classifying CHF patients versus healthy subjects, yielding an accuracy of 95.2% and discriminating nPB patients from healthy subjects with an accuracy of 94.4%.

Assessment of changes in upper airway obstruction by automatic identification of inspiratory flow limitation during sleep

New techniques for automatic invasive and noninvasive identification of inspiratory flow limitation (IFL) are presented. Data were collected from 11 patients with full nocturnal polysomnography and gold-standard esophageal pressure (Pes) measurement. A total of 38,782 breaths were extracted and automatically analyzed. An exponential model is proposed to reproduce the relationship between Pes and airflow of an inspiration and achieve an objective assessment of changes in upper airway obstruction. The characterization performance of the model is appraised with three evaluation parameters: mean-squared error when estimating resistance at peak pressure, coefficient of determination, and assessment of IFL episodes. The model's results are compared to the two best-performing models in the literature. The obtained gold-standard IFL annotations were then employed to train, test, and validate a new noninvasive automatic IFL classification system. Discriminant analysis, support vector machines, and Adaboost algorithms were employed to objectively classify breaths noninvasively with features extracted from the time and frequency domains of the breaths' flow patterns. The results indicated that the exponential model characterizes IFL and subtle relative changes in upper airway obstruction with the highest accuracy and objectivity. The new noninvasive automatic classification system also succeeded in identifying IFL episodes, achieving a sensitivity of 0.87 and a specificity of 0.85.

Automatic classification of inspiratory flow limitation assessed non-invasively during sleep

Detection of inspiratory flow limitation (IFL) is being recognized of increasing importance in order to diagnose pathologies related to sleep disordered breathing. Currently, IFL is usually identified with the help of invasive esophageal pressure measurement, still considered the gold-standard reference to assess respiratory effort. But the invasiveness of esophageal pressure measurement and its impact on sleep discourages its use in clinical routine. In this study, a new noninvasive automatic system is proposed for objective IFL classification. First, an automatic annotation system for IFL based on pressure/flow relationship was developed. Then, classifiers (Support Vector Machines and adaboost classifiers) were trained with these gold-standard references in order to objectively classify breaths non-invasively, solely based on the breaths' flow contours. The new non-invasive automatic classification system seems to be promising, as it achieved a sensitivity of 0.92 and a specificity of 0.89, outperforming prior classification results obtained by human experts.

Characterization of inspiratory flow limitation during sleep with an exponential model

Assessing incidence and severity of inspiratory flow limitation (IFL) is of importance for patients suffering of sleep disordered breathing (SDB) in order to diagnose a spectrum of different pathologies. In this study a new exponential equation is proposed to characterize the pressure/flow relationship of IFL and non-IFL breaths. Classical and alternative criteria are applied on the model's predictions in order to assess IFL, and its outcome is compared to the outcome of other models. The newly proposed exponential model seems to be promising, as it outperforms other models by achieving a global average sensitivity of 93% and specificity of 91%, and the lowest mean square error when estimating resistance at peak pressure. Additional statistical tests were performed on the exponential model's coefficients in order to determine if a coefficient based classification is possible.

Characterization of periodic and non-periodic breathing pattern in chronic heart failure patients

Periodic breathing (PB) has a high prevalence in chronic heart failure (CHF) patients with mild to moderate symptoms and poor ventricular function. This work proposes the analysis and characterization of the respiratory pattern to identify periodic breathing pattern (PB) and non-periodic breathing pattern (nPB) through the respiratory flow signal. The respiratory pattern analysis is based on the extraction and the study of the flow envelope signal. The flow envelope signal is modelled by an autoregressive model (AR) whose coefficients would characterize the respiratory pattern of each group. The goodness of the characterization is evaluated through a linear and non linear classifier applied to the AR coefficients. An adaptive feature selection is used before the linear and non linear classification, employing leave-one-out cross validation technique. With linear classification the percentage of well classified patients (8 PB and 18 nPB patients) is 84.6% using the statistically significant coefficients whereas with non linear classification, the percentage of well classified patients increase to more than 92% applying the best subset of coefficients extracted by a forward selection algorithm.

Correntropy-based analysis of respiratory patterns in patients with chronic heart failure

A correntropy-based technique is proposed for the analysis and characterization of respiratory flow signals in chronic heart failure (CHF) patients with both periodic and nonperiodic breathing (PB and nPB), and healthy subjects. Correntropy is a novel similarity measure which provides information on temporal structure and statistical distribution simultaneously. Its properties lend itself to the definition of the correntropy spectral density (CSD). An interesting result from CSD-based spectral analysis is that both the respiratory frequency and modulation frequency can be detected at their original positions in the spectrum without prior demodulation of the flow signal. The respiratory pattern is characterized by a number of spectral parameters extracted from the respiratory and modulation frequency bands. The results show that the power of the modulation frequency band offers excellent performance when classifying CHF patients versus healthy subjects, with an accuracy of 95.3%, and nPB patients versus healthy subjects with 90.7%. The ratio between the power in the modulation and respiration frequency bands provides the best results classifying CHF patients into PB and nPB, with an accuracy of 88.9%.

Sleep apnea detection based on spectral analysis of three ECG - derived respiratory signals

An apnea detection method based on spectral analysis was used to assess the performance of three ECG derived respiratory (EDR) signals. They were obtained on R wave area (EDR1), heart rate variability (EDR2) and R peak amplitude (EDR3) of ECG record in 8 patients with sleep apnea syndrome. The mean, central, peak and first quartile frequencies were computed from the spectrum every 1 min for each EDR. For each frequency parameter a threshold-based decision was carried out on every 1 min segment of the three EDR, classifying it as 'apnea' when its frequency value was below a determined threshold or as 'not apnea' in other cases. Results indicated that EDR1, based on R wave area has better performance in detecting apnea episodes with values of specificity (Sp) and sensitivity (Se) near 90%; EDR2 showed similar Sp but lower Se (78%); whereas EDR3 based on R peak amplitude did not detect appropriately the apneas episodes reaching Sp and Se values near 60%.

Inspiratory pressure evaluation by means of the entropy of respiratory mechanomyographic signals

The study of the mechanomyographic (MMG) signal of respiratory muscles is a promising technique in order to evaluate the respiratory muscles effort. The relationship between amplitude and power parameters of this signal with the respiratory effort performed during respiration is of great interest for researchers and physicians due to its diagnostic potentials. In this study, it was analyzed the MMG signal of the diaphragm muscle acquired by means of a capacitive accelerometer applied on the costal wall. The new methodology investigated was based in the calculation of the Shannon entropy of the MMG signal during the diaphragm muscle voluntary contraction. The method was tested in an animal model, with two incremental respiratory protocols performed by two non anesthetized mongrel dogs. The results obtained in the respiratory tests analyzed indicate that the Shannon entropy was superior to other amplitude parameter methods, obtaining higher correlation coefficients (with p-values lower than 0.001) with the mean and maximum inspiratory pressures. Furthermore in this study we have proposed a moving mode high pass filter in order to eliminate the very low frequency component recorded by the sensor and due to movement artifacts and the gross movement of the thorax during respiration. With this non linear filtering method we have obtained higher correlation coefficients (with both entropy and amplitude parameters) than with the Wavelet multiresolution technique proposed in a previous work.