Original Research ArticleAutomatic identification of respiratory diseases from stethoscopic lung sound signals using ensemble classifiers
Introduction
According to a recent report published by the Forum of International Respiratory Societies (FIRS), respiratory diseases (RDs) are among the leading causes of severe illness worldwide, with a death toll exceeding 4 million lives annually [1]. In 2017, the World Health Organization (WHO) declared that chronic RDs accounted for more than 10% of the global disease burden, second only to cardiovascular diseases [2].
The diagnostic process of RD involves auscultation, which is a clinical examination that involves listening to the internal sounds of moving air inside and outside the lungs. Pulmonary sounds are commonly auscultated through the anterior and posterior chest walls or the trachea using a stethoscope [3]. During auscultation, a medical practitioner examines a patient to identify adventitious (atypical) lung sounds superimposing regular breathing patterns. Examples of commonly heard adventitious lung sounds (ALS) include coarse or fine crackles, pleural rubs, wheezes, and stridors [3], [4]. Many RDs causing obstructed or restricted respiratory pathways are characterized by the existence of ALS while breathing. These sound types can be distinctly identified based on their characteristic frequency, pitch, intensity, and energy. For example, both wheezes and stridors are continuous high-pitched sounds occurring at a frequency range of 400 and 500 Hz, respectively. Lower pitched wheeze sounds are also known as rhonchi. High-pitched wheeze sounds may be present as a result of inflamed or narrowed bronchial tubules and are thus an indication of asthma or chronic obstructive pulmonary disease [5]. Stridors usually occur due to tracheal or laryngeal edema [6]. On the other hand, crackles are discontinuous high-pitched (fine) or low-pitched (coarse) waves associated with pneumonia, bronchitis, or heart failure conditions [7]. Similarly, pleural rubs are low-pitched rhythmic sounds associated with inflamed lung lining due to pleural effusion.
Regardless of the type of stethoscopic system used, auscultation is considered one of the safest, easiest, and cheapest examination procedures. Moreover, it provides a patient-friendly and non-invasive solution to monitoring the function of the lungs and other respiratory organs [4]. These qualities are of great value in resource-constrained primary care settings where advanced diagnostic tools are technologies, such as spirometry and radiography, are inaccessible. However, despite being routinely used in healthcare settings, it is a consensus among clinicians that standard pulmonary auscultation has some notable limitations. Firstly, acquiring good auscultatory skills requires extensive training and expertise. Moreover, efficient detection of adventitious sounds is sensitive to the level of experience and auditory acuity of the healthcare professional. Even if auscultation is performed by an expert practitioner, abnormal patterns are sometimes overlooked or misinterpreted during the examination [8]. Thus, subjectivity and inter-variability in observations and interpretations may limit the diagnostic effectiveness of such an approach. These challenges have given rise to the significance of computer-aided auscultation systems that can perform automated identification of ALS and RDs.
Recently, researchers have proposed various artificial intelligence solutions for the identification of adventitious lung sounds. Generally, proposed approaches were based on feature extraction paired with different classification models. At the feature extraction stage, breathing sounds were commonly characterized using several signal processing techniques, including higher-order statistics [9], spectrograms or scalograms [10], [11], wavelet transform coefficients [12], [13], Hilbert–Huang transform [14], and mel-frequency cepstral coefficients (MFCC) [15]. These feature extraction methods have been utilized in conjunction with the standard machine or deep learning methods such as naive Bayes classifiers [9], k-nearest neighbors [14], support vector machines [16], artificial neural networks (ANN) [13], convolutional neural networks (CNN) [17], and recurrent neural networks (RNN) [18]. Generally, obtained accuracy results varied between 97% and 70.2% for wheeze [19], [20], [21], [22], 97.5% and 86% for crackle [23], [24], and 99% for normal sound types. In [9], discriminating between normal, fine crackles, coarse crackles, mono-wheezes, and ploy-wheezes sound using a tree-based classifier provided an overall accuracy of 94%.
Despite the various efforts to develop automated adventitious lung sound detection algorithms, their usefulness in identifying RDs is still limited. Recent studies have shown that the presence of abnormal respiratory sounds is not a distinctive characteristic of impaired respiratory functions [3], [25]. For example, atypical respiratory sounds might not reflect impaired breathing patterns, and abnormalities do not always translate into audible sounds. These findings necessitate the need for first-hand computer-aided tools that are capable of identifying RDs directly from lung sound signals regardless of the existence of adventitious sounds. In this regard, a recent subclass of studies in the literature focused on exploring different machines and deep learning techniques to perform binary (normal vs. pathological) [26], [27], ternary (normal vs. chronic vs. non-chronic) [28], or multi-class [28], [29] classification of RDs. Investigated disease conditions included respiratory tract infections, pneumonia, bronchiectasis, bronchiolitis, asthma, and COPD. These studies reported accuracies up to 93.3%, 99%, and 98% for binary, ternary, and multi-class classification, respectively.
It is worth noting that most of the achieved satisfactory results in the context of multi-class classification were based on hybrid deep learning approaches. Despite exhibiting a highly promising performance without the need to incorporate sophisticated feature engineering techniques, training a reliable deep network architecture can be time-consuming and requires significant computational resources. Besides, the training process is iterative, and it involves multiple model parameters and enormous datasets. In clinical contexts, the lack of sufficient high-quality, diverse, and annotated training data is considered among the main limitations. To address the issue of data available, previous studies have employed several data augmentation techniques to over-sample minority classes such as variational autoencoder, adaptive synthetic sampling, and synthetic minority oversampling. However, minority oversampling techniques can introduce data leakage during the validation process, and thus, obtained results might be biased towards high fake accuracies. In fact, the majority of data augmentation approaches are mainly employed to improve the classification performance, without addressing the imperative requirement of using fine-grained datasets that represent the studied population.
In this study, we carried out a multi-class RD classification task considering six different conditions, namely normal, asthma, pneumonia, heart failure, bronchiectasis and bronchitis (BRON disorders), and chronic obstructive pulmonary disease (COPD). To this end, a novel stethoscopic lung sound dataset was collected locally at King Abdullah University Hospital, Jordan University of Science and Technology, Irbid, Jordan. This dataset was complemented by the publicly available ICBHI Challenge database to obtain a more balanced distribution among the respiratory disease classes. In terms of validity in the context of clinical applications, we believe that this data fusion approach provides a better alternative to data augmentation techniques employed in the literature. We propose to tackle the classification problem through a simple yet effective framework utilizing entropy features along with homogeneous ensemble classification methods. Subsequently, a comparative investigation is carried out to compare the proposed ensemble models to several baseline machine learning classifiers that were repeatedly employed in previous works.
The rest of this paper is organized as follows. Section 2 describes the methods used to acquire the lung sound signals along with the mathematical formulation of the entropy features. A brief overview touching on the mathematical groundwork and the implementation of the classification models is also provided. Section 3 presents the experimental results, and Section 4 provides a discussion of these results. Finally, Section 5 concludes this paper.
Section snippets
Materials and methods
As shown in Fig. 1, the adopted methodology consists of the following main phases: data acquisition and preparation, feature extraction, construction and training of the ensemble and baseline classifiers, and finally performance evaluation. These steps are detailed below.
Experimental results
The investigated models were trained tested using a computer with an Intel(R) Core TM i7-8750H (Intel Corporation, Santa Clara, USA), a 2.20 GHz CPU, 16 GB of RAM, and an NVIDIA GeForce GTX 1050 TI GPU (NVIDIA, California USA). The training process for all the ensemble models lasted around 15.38 min, while the baseline models needed around 2.02 min to train in total. The complete analysis was performed via Matlab software (R2020a, Natick, Massachusetts, USA).
Discussion
Computer-aided detection of respiratory diseases can expedite diagnostic and treatment decisions and support the study of physiological patterns associated with various respiratory pathologies. In this work, we propose to combine entropy-based features and homogeneous ensemble classifiers to perform multi-class classification of a wide range of respiratory diseases.
As imperative to all machine learning frameworks, the feature extraction stage aims at providing a better representation of the
Conclusion
To sum up, this paper investigated the use of ensemble classifiers with a dataset of lung sounds obtained via a stethoscope to perform multi-class classification. The dataset included a total of 215 subjects with 308 clinically acquired lung sound recordings, in addition to the 1176 recordings obtained from the ICBHI Challenge database. Entropy was the central feature representation used, more specifically Shannon entropy, logarithmic energy entropy, and spectrogram-based spectral entropy.
Authors’ contribution
Dr. Luay Fraiwan: project administration and supervision; fund acquisition, Abu Dhabi University Fund; conceptualization; methodology; writing. Eng. Omnia Hassanin: conceptualization, creating training and testing models; software: Matlab programming (ensemble classifier); methodology; formal analysis; writing. Dr. Mohammed Fraiwan: investigation: building the data acquisition system and measurement protocol; formal analysis: analyzing the recorded sound signal and clinical data verification;
Funding
This research is supported by the Deanship of Scientific Research at Jordan University of Science and Technology, Jordan, grant no. 20180356, and the Office of Research and Sponsored Programs (ORSP) Abu Dhabi University's, UAE.
Conflict of interest
The authors declare no conflict of interest associated with this work.
References (53)
- et al.
Classification of lung sounds using higher-order statistics: a divide-and-conquer approach
Comput Methods Programs Biomed
(2016) - et al.
Pulmonary crackle detection using time-frequency and time-scale analysis
Dig Signal Process
(2013) Pattern recognition methods applied to respiratory sounds classification into normal and wheeze classes
Comput Biol Med
(2009)- et al.
New approaches for spectro-temporal feature extraction with applications to respiratory sound classification
Neurocomputing
(2014) - et al.
Multi-channel lung sound classification with convolutional recurrent neural networks
Comput Biol Med
(2020) - et al.
Wheezing recognition algorithm using recordings of respiratory sounds at the mouth in a pediatric population
Comput Biol Med
(2016) - et al.
The detection of crackles based on mathematical morphology in spectrogram analysis
Technol Health Care: Off J Eur Soc Eng Med
(2015) - et al.
Pulmonary crackle detection using timeâfrequency and time scale analysis
Dig Signal Process
(2013) - et al.
Multichannel lung sound analysis for asthma detection
Comput Methods Programs Biomed
(2018) - et al.
Respiratory rate assessments using a dual-accelerometer device
Respir Physiol Neurobiol
(2014)
Selecting the number of bins in a histogram: a decision theoretic approach
J Stat Plan Inference
A decision-theoretic generalization of on-line learning and an application to boosting
J Comput Syst Sci
Global surveillance, prevention and control of chronic respiratory diseases: a comprehensive approach
Projections of global mortality and burden of disease from 2002 to 2030
PLOS Med
Auscultation of the respiratory system
Ann Thorac Med
Respiratory sound analysis in the era of evidence-based medicine and the world of medicine 2.0
J Med Life
Evaluation of features for classification of wheezes and normal respiratory sounds
PLOS ONE
Respiratory sounds: advances beyond the stethoscope
Am J Respir Crit Care Med
Analysis of respiratory sounds: state of the art
Clin Med Circ Respir Pulmon Med
Lung sound recognition algorithm based on vggish-bigru
IEEE Access
Feature extraction techniques for low-power ambulatory wheeze detection wearables
Wavelet scalogram analysis of phonopulmonographic signals
Int J Med Eng Informatics
Classifying respiratory sounds with different feature sets
2006 International Conference of the IEEE Engineering in Medicine and Biology Society
Artificial neural networks for acoustic lung signals classification
Ibero-American Congress on Pattern Recognition
Classification of lung sounds using convolutional neural networks
EURASIP J Image Video Process
An alternative respiratory sounds classification system utilizing artificial neural networks
Biomed J
Cited by (52)
SUPER-COUGH: A Super Learner-based ensemble machine learning method for detecting disease on cough acoustic signals
2024, Biomedical Signal Processing and ControlTRespNET: A dual-route exploratory CNN model for pediatric adventitious respiratory sound identification
2024, Biomedical Signal Processing and ControlPre-processing techniques to enhance the classification of lung sounds based on deep learning
2024, Biomedical Signal Processing and ControlLung disease detection using EasyNet
2024, Biomedical Signal Processing and ControlWeighted aggregation through probability based ranking: An optimized federated learning architecture to classify respiratory diseases
2023, Computer Methods and Programs in Biomedicine