Computerized respiratory sounds in patients with COPD: a systematic review

High performance method for COPD features extraction using complex network

Objectives. The paper proposes a novel methodology for the classification of Chronic Obstructive Pulmonary Disease (COPD) utilizing respiratory sound attributes.Methods. The approach involves segmenting respiratory sounds into individual breaths and conducting extensive studies on this dataset. Spectral Transforms, various Wavelet Transforms are applied to capture distinct signal features. Complex Network is also employed to extract characteristic elements, generating novel representations of spectrogram data based on graph factors, including entropy, density, and position. The normalized and enriched data is then used to develop COPD classifiers using six machine learning algorithms, fine-tuning with appropriate training details and hyperparameter tuning.Results. Our results demonstrate robust performance, with ROC curves consistently exhibiting an Area Under the Curve (AUC) > 96% across different time-frequency transformations. Notably, the Random Forest algorithm achieves an AUC of 99.67%, outperforming other algorithms. Moreover, the Wavelet Daubechies 2 (Db2) consistently approaches 98% accuracy, particularly noteworthy in conjunction with the Naive Bayes algorithm.Conclusion. This study diagnosis patients through spectrogram images extracted from lung sounds. The application of Inverse Transforms, Complex Network, and Optimized Classification Algorithms yielded results beyond expectations. This methodology provides a promising approach for accurate COPD diagnosis, leveraging Machine Learning techniques applied to respiratory sound analysis.

Respiratory Sound Intensity as a Noninvasive Acoustic Biomarker in COPD

Chronic obstructive pulmonary disease (COPD) is a common respiratory disease and a leading cause of death worldwide. Due to the clinical heterogeneity of COPD and the low specificity of the spirometric tests currently used for diagnosing COPD, it is often under-diagnosed. The aim of this work is to explore the potential use of respiratory sound (RS) intensity as a noninvasive acoustic biomarker for the diagnosis and monitoring of COPD. Flow and RS signals were recorded in 15 healthy controls, 7 mild COPD patients, and 5 severe COPD patients, during the performance of a variable inspiratory flow protocol. RS intensity was estimated using fixed sample entropy. RS intensity showed a very strong correlation with respiratory flow in all participants. RS intensity and flow increased similarly during the variable inspiratory flow protocol. However, the increasing pattern of the two measures was different between healthy controls and COPD patients, with lower increases in COPD patients. RS intensity is therefore sensitive to altered respiratory mechanics in COPD and could therefore be used as a noninvasive acoustic biomarker for monitoring COPD patients.

Comparative study of respiratory sounds classification methods based on cepstral analysis and artificial neural networks

In this paper, we investigated and evaluated various machine learning-based approaches for automatically detecting wheezing sounds. We conducted a comprehensive comparison of these proposed systems, assessing their classification performance through metrics such as Sensitivity, Specificity, and Accuracy. The main approach to developing a machine learning-based system for classifying respiratory sounds involved the combination of a technique for extracting features from an unknown input sound with a classification method to determine its belonging class. The characterization techniques used in this study are based on the cepstral analysis, which was extensively employed in the automatic speech recognition field. While MFCC (Mel-Frequency Cepstral Coefficients) feature extraction methods are commonly used in respiratory sounds classification, our study introduces a novelty by employing GFCC (Gammatone-Frequency Cepstral Coefficients) and BFCC (Bark-Frequency Cepstral Coefficients) for this purpose. For the classification task, we employed two types of neural networks: the MLP (Multilayer Perceptron), a feedforward neural network, and a variant of the LSTM (Long Short-Term Memory) recurrent neural network called BiLSTM (Bidirectional LSTM). The proposed classification systems are evaluated using a database consisting of 497 wheezing segments and 915 normal respiratory segments, which are recorded from individuals diagnosticated with asthma and individuals without any respiratory issues, respectively. The highest classification performance was achieved by the BFCC-BiLSTM model, which demonstrated an exceptional accuracy rate of 99.8%.

Deep learning-based lung sound analysis for intelligent stethoscope

Auscultation is crucial for the diagnosis of respiratory system diseases. However, traditional stethoscopes have inherent limitations, such as inter-listener variability and subjectivity, and they cannot record respiratory sounds for offline/retrospective diagnosis or remote prescriptions in telemedicine. The emergence of digital stethoscopes has overcome these limitations by allowing physicians to store and share respiratory sounds for consultation and education. On this basis, machine learning, particularly deep learning, enables the fully-automatic analysis of lung sounds that may pave the way for intelligent stethoscopes. This review thus aims to provide a comprehensive overview of deep learning algorithms used for lung sound analysis to emphasize the significance of artificial intelligence (AI) in this field. We focus on each component of deep learning-based lung sound analysis systems, including the task categories, public datasets, denoising methods, and, most importantly, existing deep learning methods, i.e., the state-of-the-art approaches to convert lung sounds into two-dimensional (2D) spectrograms and use convolutional neural networks for the end-to-end recognition of respiratory diseases or abnormal lung sounds. Additionally, this review highlights current challenges in this field, including the variety of devices, noise sensitivity, and poor interpretability of deep models. To address the poor reproducibility and variety of deep learning in this field, this review also provides a scalable and flexible open-source framework that aims to standardize the algorithmic workflow and provide a solid basis for replication and future extension: https://github.com/contactless-healthcare/Deep-Learning-for-Lung-Sound-Analysis .

Reliability and Validity of Computerized Adventitious Respiratory Sounds in People with Bronchiectasis

Background: Computerized adventitious respiratory sounds (ARS), such as crackles and wheezes, have been poorly explored in bronchiectasis, especially their measurement properties. This study aimed to test the reliability and validity of ARS in bronchiectasis. Methods: Respiratory sounds were recorded twice at 4 chest locations on 2 assessment sessions (7 days apart) in people with bronchiectasis and daily sputum expectoration. The total number of crackles, number of wheezes and wheeze occupation rate (%) were the parameters extracted. Results: 28 participants (9 men; 62 ± 12 y) were included. Total number of crackles and wheezes showed moderate within-day (ICC 0.87, 95% CI 0.74−0.94; ICC 0.86, 95% CI 0.71−0.93) and between-day reliability (ICC 0.70, 95% CI 0.43−0.86; ICC 0.78, 95% CI 0.56−0.90) considering all chest locations and both respiratory phases; wheeze occupation rate showed moderate within-day reliability (ICC 0.86, 95% CI 0.71−0.93), but poor between-day reliability (ICC 0.71, 95% CI 0.33−0.87). Bland−Altman plots revealed no systematic bias, but wide limits of agreement, particularly in the between-days analysis. All ARS parameters correlated moderately with the amount of daily sputum expectoration (r > 0.4; p < 0.05). No other significant correlations were observed. Conclusion: ARS presented moderate reliability and were correlated with the daily sputum expectoration in bronchiectasis. The use of sequential measurements may be an option to achieve greater accuracy when ARS are used to monitor or assess the effects of physiotherapy interventions in this population.

Detection of squawks in respiratory sounds of mechanically ventilated COVID-19 patients

Mechanically ventilated patients typically exhibit abnormal respiratory sounds. Squawks are short inspiratory adventitious sounds that may occur in patients with pneumonia, such as COVID-19 patients. In this work we devised a method for squawk detection in mechanically ventilated patients by developing algorithms for respiratory cycle estimation, squawk candidate identification, feature extraction, and clustering. The best classifier reached an F1 of 0.48 at the sound file level and an F1 of 0.66 at the recording session level. These preliminary results are promising, as they were obtained in noisy environments. This method will give health professionals a new feature to assess the potential deterioration of critically ill patients.

Inspiratory crackles-early and late-revisited: identifying COPD by crackle characteristics

BACKGROUND

The significance of pulmonary crackles, by their timing during inspiration, was described by Nath and Capel in 1974, with early crackles associated with bronchial obstruction and late crackles with restrictive defects. Crackles are also described as 'fine' or 'coarse'. We aimed to evaluate the usefulness of crackle characteristics in the diagnosis of chronic obstructive pulmonary disease (COPD).

METHODS

In a population-based study, lung sounds were recorded at six auscultation sites and classified in participants aged 40 years or older. Inspiratory crackles were classified as 'early' or 'late and into the types' 'coarse' and 'fine' by two observers. A diagnosis of COPD was based on respiratory symptoms and forced expiratory volume in 1 s/forced inspiratory vital capacity below lower limit of normal, based on Global Lung Function Initiative 2012 reference. Associations between crackle characteristics and COPD were analysed by logistic regression. Kappa statistics was applied for evaluating interobserver agreement.

RESULTS

Of 3684 subjects included in the analysis, 52.9% were female, 50.1% were ≥65 years and 204 (5.5%) had COPD. Basal inspiratory crackles were heard in 306 participants by observer 1 and in 323 by observer 2. When heard bilaterally COPD could be predicted with ORs of 2.59 (95% CI 1.36 to 4.91) and 3.20 (95% CI 1.71 to 5.98), annotated by observer 1 and 2, respectively, adjusted for sex and age. If bilateral crackles were coarse the corresponding ORs were 2.65 (95% CI 1.28 to 5.49) and 3.67 (95% CI 1.58 to 8.52) and when heard early during inspiration the ORs were 6.88 (95% CI 2.59 to 18.29) and 7.63 (95%CI 3.73 to 15.62). The positive predictive value for COPD was 23% when early crackles were heard over one or both lungs. We observed higher kappa values when classifying timing than type.

CONCLUSIONS

'Early' inspiratory crackles predicted COPD more strongly than 'coarse' inspiratory crackles. Identification of early crackles at the lung bases should imply a strong attention to the possibility of COPD.

Automatic Classification of Adventitious Respiratory Sounds: A (Un)Solved Problem?

(1) Background: Patients with respiratory conditions typically exhibit adventitious respiratory sounds (ARS), such as wheezes and crackles. ARS events have variable duration. In this work we studied the influence of event duration on automatic ARS classification, namely, how the creation of the Other class (negative class) affected the classifiers’ performance. (2) Methods: We conducted a set of experiments where we varied the durations of the other events on three tasks: crackle vs. wheeze vs. other (3 Class); crackle vs. other (2 Class Crackles); and wheeze vs. other (2 Class Wheezes). Four classifiers (linear discriminant analysis, support vector machines, boosted trees, and convolutional neural networks) were evaluated on those tasks using an open access respiratory sound database. (3) Results: While on the 3 Class task with fixed durations, the best classifier achieved an accuracy of 96.9%, the same classifier reached an accuracy of 81.8% on the more realistic 3 Class task with variable durations. (4) Conclusion: These results demonstrate the importance of experimental design on the assessment of the performance of automatic ARS classification algorithms. Furthermore, they also indicate, unlike what is stated in the literature, that the automatic classification of ARS is not a solved problem, as the algorithms’ performance decreases substantially under complex evaluation scenarios.

Applications of artificial intelligence and machine learning in respiratory medicine

The past 5 years have seen an explosion of interest in the use of artificial intelligence (AI) and machine learning techniques in medicine. This has been driven by the development of deep neural networks (DNNs)-complex networks residing in silico but loosely modelled on the human brain-that can process complex input data such as a chest radiograph image and output a classification such as 'normal' or 'abnormal'. DNNs are 'trained' using large banks of images or other input data that have been assigned the correct labels. DNNs have shown the potential to equal or even surpass the accuracy of human experts in pattern recognition tasks such as interpreting medical images or biosignals. Within respiratory medicine, the main applications of AI and machine learning thus far have been the interpretation of thoracic imaging, lung pathology slides and physiological data such as pulmonary function tests. This article surveys progress in this area over the past 5 years, as well as highlighting the current limitations of AI and machine learning and the potential for future developments.

Prevalence and clinical associations of wheezes and crackles in the general population: the Tromsø study

BACKGROUND

Wheezes and crackles are well-known signs of lung diseases, but can also be heard in apparently healthy adults. However, their prevalence in a general population has been sparsely described. The objective of this study was to determine the prevalence of wheezes and crackles in a large general adult population and explore associations with self-reported disease, smoking status and lung function.

METHODS

We recorded lung sounds in 4033 individuals 40 years or older and collected information on self-reported disease. Pulse oximetry and spirometry were carried out. We estimated age-standardized prevalence of wheezes and crackles and associations between wheezes and crackles and variables of interest were analyzed with univariable and multivariable logistic regressions.

RESULTS

Twenty-eight percent of individuals had wheezes or crackles. The age-standardized prevalence of wheezes was 18.6% in women and 15.3% in men, and of crackles, 10.8 and 9.4%, respectively. Wheezes were mostly found during expiration and crackles during inspiration. Significant predictors of expiratory wheezes in multivariable analyses were age (10 years increase - OR 1.18, 95%CI 1.09-1.30), female gender (1.45, 1.2-1.8), self-reported asthma (1.36, 1.00-1.83), and current smoking (1.70, 1.28-2.23). The most important predictors of inspiratory crackles were age (1.76, 1.57-1.99), current smoking, (1.94, 1.40-2.69), mMRC ≥2 (1.79, 1.18-2.65), SpO₂ (0.88, 0.81-0.96), and FEV₁ Z-score (0.86, 0.77-0.95).

CONCLUSIONS

Nearly over a quarter of adults present adventitious lung sounds on auscultation. Age was the most important predictor of adventitious sounds, particularly crackles. The adventitious sounds were also associated with self-reported disease, current smoking and measures of lung function. The presence of findings in two or more auscultation sites was associated with a higher risk of decreased lung function than solitary findings.

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.

Reliability, validity and minimal detectable change of computerized respiratory sounds in patients with chronic obstructive pulmonary disease

INTRODUCTION

Computerized respiratory sounds (CRS) are closely related to the movement of air within the tracheobronchial tree and are promising outcome measures in patients with chronic obstructive pulmonary disease (COPD). However, CRS measurement properties have been poorly tested.

OBJECTIVE

The aim of this study was to assess the reliability, validity and the minimal detectable changes (MDC) of CRS in patients with stable COPD.

METHODS

Fifty patients (36♂, 67.26 ± 9.31y, FEV₁ 49.52 ± 19.67%predicted) were enrolled. CRS were recorded simultaneously at seven anatomic locations (trachea; right and left anterior, lateral and posterior chest). The number of crackles, wheeze occupation rate, median frequency (F50) and maximum intensity (Imax) were processed using validated algorithms. Within-day and between-days reliability, criterion and construct validity, validity to predict exacerbations and MDC were established.

RESULTS

CRS presented moderate-to-excellent within-day reliability (ICC_1,3  ≥ 0.51; P < .05) and moderate-to-good between-days reliability (ICC_1,2  ≥ 0.47; P < .05) for most locations. Negligible-to-moderate correlations with FEV₁ %predicted were found (-0.53 < r_s  < -0.28; P < .05), and the inspiratory number of crackles were the best discriminator between mild-to-moderate and severe-to-very severe airflow limitations (area under the curve >0.78). CRS correlated poorly with patient-reported outcomes (r_s  < 0.48; P < .05) and did not predict exacerbations. Inspiratory number of crackles at posterior right chest, inspiratory F50 at trachea and anterior left chest and expiratory Imax at anterior right chest were simultaneously reliable and valid, and their MDC were 2.41, 55.27, 29.55 and 3.98, respectively.

CONCLUSION

CRS are reliable and valid. Their use, integrated with other clinical and patient-reported measures, may fill the gap of assessing small airways and contribute toward a patient's comprehensive evaluation.

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.

Design of Wearable Breathing Sound Monitoring System for Real-Time Wheeze Detection

In the clinic, the wheezing sound is usually considered as an indicator symptom to reflect the degree of airway obstruction. The auscultation approach is the most common way to diagnose wheezing sounds, but it subjectively depends on the experience of the physician. Several previous studies attempted to extract the features of breathing sounds to detect wheezing sounds automatically. However, there is still a lack of suitable monitoring systems for real-time wheeze detection in daily life. In this study, a wearable and wireless breathing sound monitoring system for real-time wheeze detection was proposed. Moreover, a breathing sounds analysis algorithm was designed to continuously extract and analyze the features of breathing sounds to provide the objectively quantitative information of breathing sounds to professional physicians. Here, normalized spectral integration (NSI) was also designed and applied in wheeze detection. The proposed algorithm required only short-term data of breathing sounds and lower computational complexity to perform real-time wheeze detection, and is suitable to be implemented in a commercial portable device, which contains relatively low computing power and memory. From the experimental results, the proposed system could provide good performance on wheeze detection exactly and might be a useful assisting tool for analysis of breathing sounds in clinical diagnosis.

Computerised Analysis of Telemonitored Respiratory Sounds for Predicting Acute Exacerbations of COPD

Chronic obstructive pulmonary disease (COPD) is one of the commonest causes of death in the world and poses a substantial burden on healthcare systems and patients' quality of life. The largest component of the related healthcare costs is attributable to admissions due to acute exacerbation (AECOPD). The evidence that might support the effectiveness of the telemonitoring interventions in COPD is limited partially due to the lack of useful predictors for the early detection of AECOPD. Electronic stethoscopes and computerised analyses of respiratory sounds (CARS) techniques provide an opportunity for substantial improvement in the management of respiratory diseases. This exploratory study aimed to evaluate the feasibility of using: (a) a respiratory sensor embedded in a self-tailored housing for ageing users; (b) a telehealth framework; (c) CARS and (d) machine learning techniques for the remote early detection of the AECOPD. In a 6-month pilot study, 16 patients with COPD were equipped with a home base-station and a sensor to daily record their respiratory sounds. Principal component analysis (PCA) and a support vector machine (SVM) classifier was designed to predict AECOPD. 75.8% exacerbations were early detected with an average of 5 ± 1.9 days in advance at medical attention. The proposed method could provide support to patients, physicians and healthcare systems.

Computerized respiratory sounds: a comparison between patients with stable and exacerbated COPD

INTRODUCTION

Diagnosis of acute exacerbations of chronic obstructive pulmonary disease (AECOPD) is often challenging as it relies on patients' clinical presentation. Computerized respiratory sounds (CRS), namely crackles and wheezes, may have the potential to contribute for the objective diagnosis/monitoring of an AECOPD.

OBJECTIVES

This study explored if CRS differ during stable and exacerbation periods in patients with COPD.

METHODS

13 patients with stable COPD and 14 with AECOPD were enrolled. CRS were recorded simultaneously at trachea, anterior, lateral and posterior chest locations using seven stethoscopes. Airflow (0.4-0.6l/s) was recorded with a pneumotachograph. Breathing phases were detected using airflow signals; crackles and wheezes with validated algorithms.

RESULTS

At trachea, anterior and lateral chest, no significant differences were found between the two groups in the number of inspiratory/expiratory crackles or inspiratory wheeze occupation rate. At posterior chest, the number of crackles (median 2.97-3.17 vs. 0.83-1.2, P < 0.001) and wheeze occupation rate (median 3.28%-3.8% vs. 1.12%-1.77%, P = 0.014-0.016) during both inspiration and expiration were significantly higher in patients with AECOPD than in stable patients. During expiration, wheeze occupation rate was also significantly higher in patients with AECOPD at trachea (median 3.12% vs. 0.79%, P < 0.001) and anterior chest (median 3.55% vs. 1.28%, P < 0.001).

CONCLUSION

Crackles and wheezes are more frequent in patients with AECOPD than in stable patients, particularly at posterior chest. These findings suggest that these CRS can contribute to the objective diagnosis/monitoring of AECOPD, which is especially valuable considering that they can be obtained by integrating computerized techniques with pulmonary auscultation, a noninvasive method that is a component of patients' physical examination.