Analysis of wheezes using wavelet higher order spectral features

Investigation of the Evolution of Wavelet Higher-Order Dynamics in Atrial Fibrillation

Atrial fibrillation (AF) is the most common cardiac arrhythmia and is associated with significant morbidity and mortality. Owing to the advances in sensor technology and the emergence of wearable devices that enable daily self-monitoring, ECG signal processing methods for the automatic detection of AF are more pertinent than ever. In this paper, we investigate the use of wavelet higher-order statistics (WHOS) for feature extraction and differentiation between normal sinus rhythm and AF. The proposed approach captures the evolution of the WHOS dynamics and quantifies the changes in the time-varying characteristics of the frequency couplings caused by AF. Results obtained from the statistical analysis of a dataset of 5834 single-lead ECG recordings, reveal 46/50 statistically significant features and provide insight into the complexity of the evolution of the ECG non-linearities during AF.

Efficient syncope prediction from resting state clinical data using wavelet bispectrum and multilayer perceptron neural network

Neurally mediated syncope (NMS) is the most common type of syncope, and head up tilt test (HUTT) is, so far, the most appropriate tool to identify NMS. In this work, an effort to predict the NMS before performing the HUTT is attempted. To achieve this, the heart rate variability (HRV) at rest and during the first minutes of tilting position during HUTT was analyzed using both time and frequency domains. Various features from HRV regularity and complexity, along with wavelet higher-order spectrum (WHOS) analysis in low-frequency (LF) and high-frequency (HF) bands were examined. The experimental results from 26 patients with history of NMS have shown that at rest, a time domain entropy measure and WHOS-based features in LF band exhibit significant differences between positive and negative HUTT as well as among 10 healthy subjects and NMS patients. The best performance of multilayer perceptron neural network (MPNN) was achieved by using an input vector consisted of WHOS-based HRV features in the LF zone and systolic blood pressure from the resting period, yielding an accuracy of 89.7%, assessed by 5-fold cross-validation. The promising results presented here pave the way for an early prediction of the HUTT outcome from resting state, contributing to the identification of patients at higher risk NMS. The HRV analysis along with systolic blood pressure at rest predict NMS using a multilayer perceptron neural network.

Monophonic and Polyphonic Wheezing Classification Based on Constrained Low-Rank Non-Negative Matrix Factorization

The appearance of wheezing sounds is widely considered by physicians as a key indicator to detect early pulmonary disorders or even the severity associated with respiratory diseases, as occurs in the case of asthma and chronic obstructive pulmonary disease. From a physician's point of view, monophonic and polyphonic wheezing classification is still a challenging topic in biomedical signal processing since both types of wheezes are sinusoidal in nature. Unlike most of the classification algorithms in which interference caused by normal respiratory sounds is not addressed in depth, our first contribution proposes a novel Constrained Low-Rank Non-negative Matrix Factorization (CL-RNMF) approach, never applied to classification of wheezing as far as the authors' knowledge, which incorporates several constraints (sparseness and smoothness) and a low-rank configuration to extract the wheezing spectral content, minimizing the acoustic interference from normal respiratory sounds. The second contribution automatically analyzes the harmonic structure of the energy distribution associated with the estimated wheezing spectrogram to classify the type of wheezing. Experimental results report that: (i) the proposed method outperforms the most recent and relevant state-of-the-art wheezing classification method by approximately 8% in accuracy; (ii) unlike state-of-the-art methods based on classifiers, the proposed method uses an unsupervised approach that does not require any training.

Wheeze sound analysis using computer-based techniques: a systematic review

Wheezes are high pitched continuous respiratory acoustic sounds which are produced as a result of airway obstruction. Computer-based analyses of wheeze signals have been extensively used for parametric analysis, spectral analysis, identification of airway obstruction, feature extraction and diseases or pathology classification. While this area is currently an active field of research, the available literature has not yet been reviewed. This systematic review identified articles describing wheeze analyses using computer-based techniques on the SCOPUS, IEEE Xplore, ACM, PubMed and Springer and Elsevier electronic databases. After a set of selection criteria was applied, 41 articles were selected for detailed analysis. The findings reveal that 1) computerized wheeze analysis can be used for the identification of disease severity level or pathology, 2) further research is required to achieve acceptable rates of identification on the degree of airway obstruction with normal breathing, 3) analysis using combinations of features and on subgroups of the respiratory cycle has provided a pathway to classify various diseases or pathology that stem from airway obstruction.

Analysis of wheeze sounds during tidal breathing according to severity levels in asthma patients

Objective: This study aimed to statistically analyze the behavior of time-frequency features in digital recordings of wheeze sounds obtained from patients with various levels of asthma severity (mild, moderate, and severe), and this analysis was based on the auscultation location and/or breath phase. Method: Segmented and validated wheeze sounds were collected from the trachea and lower lung base (LLB) of 55 asthmatic patients during tidal breathing maneuvers and grouped into nine different datasets. The quartile frequencies F₂₅, F₅₀, F₇₅, F₉₀ and F₉₉, mean frequency (MF) and average power (AP) were computed as features, and a univariate statistical analysis was then performed to analyze the behavior of the time-frequency features. Results: All features generally showed statistical significance in most of the datasets for all severity levels [χ² = 6.021-71.65, p < 0.05, η² = 0.01-0.52]. Of the seven investigated features, only AP showed statistical significance in all the datasets. F₂₅, F₇₅, F₉₀ and F₉₉ exhibited statistical significance in at least six datasets [χ² = 4.852-65.63, p < 0.05, η² = 0.01-0.52], and F₂₅, F₅₀ and MF showed statistical significance with a large η² in all trachea-related datasets [χ² = 13.54-55.32, p < 0.05, η² = 0.13-0.33]. Conclusion: The results obtained for the time-frequency features revealed that (1) the asthma severity levels of patients can be identified through a set of selected features with tidal breathing, (2) tracheal wheeze sounds are more sensitive and specific predictors of severity levels and (3) inspiratory and expiratory wheeze sounds are almost equally informative.

Characterization and classification of asthmatic wheeze sounds according to severity level using spectral integrated features

OBJECTIVE

This study aimed to investigate and classify wheeze sounds of asthmatic patients according to their severity level (mild, moderate and severe) using spectral integrated (SI) features.

METHOD

Segmented and validated wheeze sounds were obtained from auscultation recordings of the trachea and lower lung base of 55 asthmatic patients during tidal breathing manoeuvres. The segments were multi-labelled into 9 groups based on the auscultation location and/or breath phases. Bandwidths were selected based on the physiology, and a corresponding SI feature was computed for each segment. Univariate and multivariate statistical analyses were then performed to investigate the discriminatory behaviour of the features with respect to the severity levels in the various groups. The asthmatic severity levels in the groups were then classified using the ensemble (ENS), support vector machine (SVM) and k-nearest neighbour (KNN) methods.

RESULTS AND CONCLUSION

All statistical comparisons exhibited a significant difference (p < 0.05) among the severity levels with few exceptions. In the classification experiments, the ensemble classifier exhibited better performance in terms of sensitivity, specificity and positive predictive value (PPV). The trachea inspiratory group showed the highest classification performance compared with all the other groups. Overall, the best PPV for the mild, moderate and severe samples were 95% (ENS), 88% (ENS) and 90% (SVM), respectively. With respect to location, the tracheal related wheeze sounds were most sensitive and specific predictors of asthma severity levels. In addition, the classification performances of the inspiratory and expiratory related groups were comparable, suggesting that the samples from these locations are equally informative.

Continuous wavelet transform and higher-order spectrum: combinatory potentialities in breath sound analysis and electroencephalogram-based pain characterization

The combination of the continuous wavelet transform (CWT) with a higher-order spectrum (HOS) merges two worlds into one that conveys information regarding the non-stationarity, non-Gaussianity and nonlinearity of the systems and/or signals under examination. In the current work, the third-order spectrum (TOS), which is used to detect the nonlinearity and deviation from Gaussianity of two types of biomedical signals, that is, wheezes and electroencephalogram (EEG), is combined with the CWT to offer a time-scale representation of the examined signals. As a result, a CWT/TOS field is formed and a time axis is introduced, creating a time-bifrequency domain, which provides a new means for wheeze nonlinear analysis and dynamic EEG-based pain characterization. A detailed description and examples are provided and discussed to showcase the combinatory potential of CWT/TOS in the field of advanced signal processing.This article is part of the theme issue 'Redundancy rules: the continuous wavelet transform comes of age'.

Automatic adventitious respiratory sound analysis: A systematic review

Background

Automatic detection or classification of adventitious sounds is useful to assist physicians in diagnosing or monitoring diseases such as asthma, Chronic Obstructive Pulmonary Disease (COPD), and pneumonia. While computerised respiratory sound analysis, specifically for the detection or classification of adventitious sounds, has recently been the focus of an increasing number of studies, a standardised approach and comparison has not been well established.

Objective

To provide a review of existing algorithms for the detection or classification of adventitious respiratory sounds. This systematic review provides a complete summary of methods used in the literature to give a baseline for future works.

Data sources

A systematic review of English articles published between 1938 and 2016, searched using the Scopus (1938-2016) and IEEExplore (1984-2016) databases. Additional articles were further obtained by references listed in the articles found. Search terms included adventitious sound detection, adventitious sound classification, abnormal respiratory sound detection, abnormal respiratory sound classification, wheeze detection, wheeze classification, crackle detection, crackle classification, rhonchi detection, rhonchi classification, stridor detection, stridor classification, pleural rub detection, pleural rub classification, squawk detection, and squawk classification.

Study selection

Only articles were included that focused on adventitious sound detection or classification, based on respiratory sounds, with performance reported and sufficient information provided to be approximately repeated.

Data extraction

Investigators extracted data about the adventitious sound type analysed, approach and level of analysis, instrumentation or data source, location of sensor, amount of data obtained, data management, features, methods, and performance achieved.

Data synthesis

A total of 77 reports from the literature were included in this review. 55 (71.43%) of the studies focused on wheeze, 40 (51.95%) on crackle, 9 (11.69%) on stridor, 9 (11.69%) on rhonchi, and 18 (23.38%) on other sounds such as pleural rub, squawk, as well as the pathology. Instrumentation used to collect data included microphones, stethoscopes, and accelerometers. Several references obtained data from online repositories or book audio CD companions. Detection or classification methods used varied from empirically determined thresholds to more complex machine learning techniques. Performance reported in the surveyed works were converted to accuracy measures for data synthesis.

Limitations

Direct comparison of the performance of surveyed works cannot be performed as the input data used by each was different. A standard validation method has not been established, resulting in different works using different methods and performance measure definitions.

Conclusion

A review of the literature was performed to summarise different analysis approaches, features, and methods used for the analysis. The performance of recent studies showed a high agreement with conventional non-automatic identification. This suggests that automated adventitious sound detection or classification is a promising solution to overcome the limitations of conventional auscultation and to assist in the monitoring of relevant diseases.

An analysis of sounds for lungs with excessive water

Excessive lung water occurs when too much water accumulates in the lung, causing breathing difficulty. Current diagnosis methods include X-rays and CT-scans. However, because of their bulk and the need for trained professionals to operate, physicians rely on auscultation for preliminary diagnosis. Recent attempts have been made to automate the auscultation process and some degree of success has been reported. Thus, it would be useful to provide more analysis of such lung sounds. This paper attempts to study the characteristics of breathing sounds from lungs with excessive water and compare them with breathing sounds from healthy lungs. Using a modified empirical mode decomposition to split the signals, the root-mean-squared energy (RMS) and kurtosis were used as characteristics. These characteristics were extracted from the intrinsic mode functions (IMF) and were analyzed. Results showed that certain IMF were effective in characterizing both kinds of sounds due to their small spread in RMS or kurtosis. Results also (using p-values from statistical tests) showed that for certain intrinsic mode functions, lung sounds with excessive lung water exhibit different medians from sounds of healthy lungs. There was strong linear independence between each IMF of the two sounds. Empirical mode decomposition was shown to be able to extract useful information for analyses.

Resonance based respiratory sound decomposition aiming at localization of crackles in noisy measurements

In this work, resonance based decomposition of lung sounds that aims to separate wheeze, crackle and vesicular sounds into three individual channels while automatically localizing crackles for both synthetic and real data is presented. Previous works focus on stationary-non stationary discrimination to separate crackles and vesicular sounds disregarding wheezes which are stationary as compared to crackles. However, wheeze sounds include important cues about the underlying pathology. Using two different threshold methods and synthetic sound generation scenarios in the presence of wheezes, resonance based decomposition performs 89.5 % crackle localization recall rate for white Gaussian noise and 98.6 % crackle localization recall rate for healthy vesicular sound treated as noise at low signal-to-noise ratios. Besides, an adaptive threshold determination which is independent from the channel at which it will be applied is used and is found to be robust to noise.

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.

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.

Joint application of audio spectral envelope and tonality index in an e-asthma monitoring system

This paper presents in detail a recently introduced highly efficient method for automatic detection of asthmatic wheezing in breathing sounds. The fluctuation in the audio spectral envelope (ASE) from the MPEG-7 standard and the value of the tonality index (TI) from the MPEG-2 Audio specification are jointly used as discriminative features for wheezy sounds, while the support vector machine (SVM) with a polynomial kernel serves as a classifier. The advantages of the proposed approach are described in the paper (e.g., detecting weak wheezes, very good ROC characteristics, independence from noise color). Since the method is not computationally complex, it is suitable for remote asthma monitoring using mobile devices (personal medical assistants). The main contribution of this paper consists of presenting all the implementation details concerning the proposed approach for the first time, i.e., the pseudocode of the method and adjusting the values of the ASE and TI parameters after which only one (not two) FFT is required for analysis of a next overlapping signal fragment. The efficiency of the method has also been additionally confirmed by the AdaBoost classifier with a built-in mechanism to feature ranking, as well as a previously performed minimal-redundancy-maximal-relevance test.

Applying cybernetic technology to diagnose human pulmonary sounds

Chest auscultation is a crucial and efficient method for diagnosing lung disease; however, it is a subjective process that relies on physician experience and the ability to differentiate between various sound patterns. Because the physiological signals composed of heart sounds and pulmonary sounds (PSs) are greater than 120 Hz and the human ear is not sensitive to low frequencies, successfully making diagnostic classifications is difficult. To solve this problem, we constructed various PS recognition systems for classifying six PS classes: vesicular breath sounds, bronchial breath sounds, tracheal breath sounds, crackles, wheezes, and stridor sounds. First, we used a piezoelectric microphone and data acquisition card to acquire PS signals and perform signal preprocessing. A wavelet transform was used for feature extraction, and the PS signals were decomposed into frequency subbands. Using a statistical method, we extracted 17 features that were used as the input vectors of a neural network. We proposed a 2-stage classifier combined with a back-propagation (BP) neural network and learning vector quantization (LVQ) neural network, which improves classification accuracy by using a haploid neural network. The receiver operating characteristic (ROC) curve verifies the high performance level of the neural network. To expand traditional auscultation methods, we constructed various PS diagnostic systems that can correctly classify the six common PSs. The proposed device overcomes the lack of human sensitivity to low-frequency sounds and various PS waves, characteristic values, and a spectral analysis charts are provided to elucidate the design of the human-machine interface.

Assessment of time-frequency representation techniques for thoracic sounds analysis

A step forward in the knowledge about the underlying physiological phenomena of thoracic sounds requires a reliable estimate of their time-frequency behavior that overcomes the disadvantages of the conventional spectrogram. A more detailed time-frequency representation could lead to a better feature extraction for diseases classification and stratification purposes, among others. In this respect, the aim of this study was to look for an omnibus technique to obtain the time-frequency representation (TFR) of thoracic sounds by comparing generic goodness-of-fit criteria in different simulated thoracic sounds scenarios. The performance of ten TFRs for heart, normal tracheal and adventitious lung sounds was assessed using time-frequency patterns obtained by mathematical functions of the thoracic sounds. To find the best TFR performance measures, such as the 2D local (ρ(mean)) and global (ρ) central correlation, the normalized root-mean-square error (NRMSE), the cross-correlation coefficient (ρ(IF)) and the time-frequency resolution (res(TF)) were used. Simulation results pointed out that the Hilbert-Huang spectrum (HHS) had a superior performance as compared with other techniques and then, it can be considered as a reliable TFR for thoracic sounds. Furthermore, the goodness of HHS was assessed using noisy simulated signals. Additionally, HHS was applied to first and second heart sounds taken from a young healthy male subject, to tracheal sound from a middle-age healthy male subject, and to abnormal lung sounds acquired from a male patient with diffuse interstitial pneumonia. It is expected that the results of this research could be used to obtain a better signature of thoracic sounds for pattern recognition purpose, among other tasks.

Adventitious sounds identification and extraction using temporal-spectral dominance-based features

Respiratory sound (RS) signals carry significant information about the underlying functioning of the pulmonary system by the presence of adventitious sounds (ASs). Although many studies have addressed the problem of pathological RS classification, only a limited number of scientific works have focused on the analysis of the evolution of symptom-related signal components in joint time-frequency (TF) plane. This paper proposes a new signal identification and extraction method for various ASs based on instantaneous frequency (IF) analysis. The presented TF decomposition method produces a noise-resistant high definition TF representation of RS signals as compared to the conventional linear TF analysis methods, yet preserving the low computational complexity as compared to those quadratic TF analysis methods. The discarded phase information in conventional spectrogram has been adopted for the estimation of IF and group delay, and a temporal-spectral dominance spectrogram has subsequently been constructed by investigating the TF spreads of the computed time-corrected IF components. The proposed dominance measure enables the extraction of signal components correspond to ASs from noisy RS signal at high noise level. A new set of TF features has also been proposed to quantify the shapes of the obtained TF contours, and therefore strongly, enhances the identification of multicomponents signals such as polyphonic wheezes. An overall accuracy of 92.4±2.9% for the classification of real RS recordings shows the promising performance of the presented method.