Reliable system for respiratory pathology classification from breath sound signals
01 Nov 2016-pp 152-156
TL;DR: The experimental result shows that the proposed method for classification of normal, wheeze, rhonchi, line and coarse crackles using breath sound signal recording is considered as a reliable system to be used as a Computerized Decision Support System (CDSS).
Abstract: Analysis of breath sounds for the purpose of diagnosing respiratory pathology is of great interest in recent years. In this paper, classification of normal, wheeze, rhonchi, line and coarse crackles using breath sound signal recording is performed using signal processing and machine learning tools. Breath sounds were filtered from noise and segmented into breath cycles followed by feature extraction. AR Coefficients and Mel Frequency Cepstral Coefficients (MFCC) features were extracted from breath sound cycles. The extracted features are then classified using Support Vector Machine (SVM) classifier. A mean classification accuracy of 88.72% and 89.68% was reported for the features AR coefficients and MFCC features respectively. The individual classification accuracy for healthy (control subjects), wheeze, rhonchi, fine and coarse crackles are 93.75%, 87.50%, 91.66%, 87.50% and 91.66% respectively for the MFCC features. Similarly, the individual classification accuracy for healthy control, wheeze, rhonchi, fine and coarse crackles are 93.75%, 87.50%, 87.50%, 87.50% and 83.33% respectively for the AR coefficient features. The experimental result shows that the proposed method from an overall point of view can be considered as a reliable system to be used as a Computerized Decision Support System (CDSS).
Citations
More filters
TL;DR: Three machine learning approaches for lung sounds classification are compared based on the extraction of a set of handcrafted features trained by three different classifiers and the results show that CNN outperformed the handcrafted feature based classifiers.
132 citations
TL;DR: In this article , a novel approach is proposed to pre-process the data and pass it through a newly proposed CNN architecture, which helps to make an accurate diagnosis of lung sounds.
Abstract: Every respiratory-related checkup includes audio samples collected from the individual, collected through different tools (sonograph, stethoscope). This audio is analyzed to identify pathology, which requires time and effort. The research work proposed in this paper aims at easing the task with deep learning by the diagnosis of lung-related pathologies using Convolutional Neural Network (CNN) with the help of transformed features from the audio samples. International Conference on Biomedical and Health Informatics (ICBHI) corpus dataset was used for lung sound. Here a novel approach is proposed to pre-process the data and pass it through a newly proposed CNN architecture. The combination of pre-processing steps MFCC, Melspectrogram, and Chroma CENS with CNN improvise the performance of the proposed system, which helps to make an accurate diagnosis of lung sounds. The comparative analysis shows how the proposed approach performs better with previous state-of-the-art research approaches. It also shows that there is no need for a wheeze or a crackle to be present in the lung sound to carry out the classification of respiratory pathologies.
7 citations
TL;DR: Feature extraction methods used in the classification of single-channel lung sounds obtained by automatic identification of respiratory cycles were examined in detail in order to extract distinctive features at the lowest size to design a system for the detection of lung diseases, completely autonomously.
5 citations
12 Sep 2020
TL;DR: In this article, a machine learning algorithm operating on Mel-frequency Cepstral Coefficients of patients' cough and breath sounds was proposed to detect the effectiveness of inhaler usage.
Abstract: Chronic Obstructive Pulmonary Disease (COPD) is a major health concern for elders today. Chronic cough and wheezing, which occur in the lungs as a result of mucus buildup are the main symptoms of COPD. COPD patients are advised to regularly medicate themselves via an inhaler, which delivers medicine to the lungs to break down mucus and relieve wheezing. Unfortunately, many patients do not use their inhaler devices correctly, resulting in no improvement of COPD symptoms, and worsened health. In this paper, we design machine learning (Support Vector Machine) algorithms operating on Mel-frequency Cepstral Coefficients of cough and breath sounds of patients (recorded via smartphones before and after inhaler usage) to detect the effectiveness of inhaler usage. Using a cohort of 55 clinically diagnosed COPD patients, spread across both genders, we evaluate our system from multiple metrics, including Precision, Recall, Sensitivity and Specificity. Our system achieved accuracies close to 80% in detecting effectiveness of inhaler usage. Our proposed system can aid COPD patients in improved selfcare routines, and also reduce the rate of re-hospitalizations caused by exacerbated symptoms.
1 citations
20 May 2019
TL;DR: In this paper, the authors proposed novel approaches to recognize and classify children's breath sounds and obtain and analyze audio features of young children' breath sound signals in time and frequency domains, based on these features, classify breath signals to specific breath segments.
Abstract: One of the most common reasons for children consulting a general practitioner is respiratory morbidity. For healthcare providers, listening to breath sounds is an important diagnose method for respiration system diseases. However, parents and caregivers dont always have the required knowledge and experience to identify children's various breath sounds. Also, it is extremely hard to obtain feedback from young children about their physical conditions. Therefore, it is necessary to provide a tool to monitor young children healthy condition. In this paper, we propose novel approaches to recognize and classify children's breath sounds. We obtain and analyze audio features of young children's breath sound signals in time and frequency domains, based on these features, classify breath signals to specific breath segments. Nearest neighborhood (NN) and artificial neural network (ANN) were used for pattern recognition and classification. Clinical data were used to design and verify the proposed approaches. Experiments show that the proposed approaches offer accurate results.
Cites background from "Reliable system for respiratory pat..."
...Palaniappan proposed a system for respiratory pathology classification from breath sound signals [8]....
[...]
References
More filters
622 citations
Additional excerpts
...The characteristics of breath sounds for various breath sound types has been extensively given by Pasterkamp [2]....
[...]
TL;DR: Experimental results show that the approach based on MFCC coefficients combined to GMM is well adapted to classify respiratory sounds in normal and wheeze classes and an optimized threshold to discriminate the wheezing class from the normal one is proposed.
198 citations
"Reliable system for respiratory pat..." refers background in this paper
...A few previous woks on breath sound analysis have also implemented MFCC features for respiratory pathology detection and have achieved encouraging outcomes [16]....
[...]
TL;DR: The K-nn classifier was better than the SVM classifier for the discrimination of pulmonary acoustic signals from pathological and normal subjects obtained from the RALE database.
Abstract: Pulmonary acoustic parameters extracted from recorded respiratory sounds provide valuable information for the detection of respiratory pathologies. The automated analysis of pulmonary acoustic signals can serve as a differential diagnosis tool for medical professionals, a learning tool for medical students, and a self-management tool for patients. In this context, we intend to evaluate and compare the performance of the support vector machine (SVM) and K-nearest neighbour (K-nn) classifiers in diagnosis respiratory pathologies using respiratory sounds from R.A.L.E database. The pulmonary acoustic signals used in this study were obtained from the R.A.L.E lung sound database. The pulmonary acoustic signals were manually categorised into three different groups, namely normal, airway obstruction pathology, and parenchymal pathology. The mel-frequency cepstral coefficient (MFCC) features were extracted from the pre-processed pulmonary acoustic signals. The MFCC features were analysed by one-way ANOVA and then fed separately into the SVM and K-nn classifiers. The performances of the classifiers were analysed using the confusion matrix technique. The statistical analysis of the MFCC features using one-way ANOVA showed that the extracted MFCC features are significantly different (p < 0.001). The classification accuracies of the SVM and K-nn classifiers were found to be 92.19% and 98.26%, respectively. Although the data used to train and test the classifiers are limited, the classification accuracies found are satisfactory. The K-nn classifier was better than the SVM classifier for the discrimination of pulmonary acoustic signals from pathological and normal subjects obtained from the RALE database.
140 citations
"Reliable system for respiratory pat..." refers background in this paper
...Detailed information on the SVM classifier can be found in [17]....
[...]
TL;DR: This review examined specific lung sounds/disorders, the number of subjects, the signal processing and classification methods and the outcome of the analyses of lung sounds using machine learning methods that have been performed by previous researchers.
131 citations
"Reliable system for respiratory pat..." refers background in this paper
...In the past 35 years, the research on breath sound signal analysis has been done with a variety of signal processing and machine learning techniques [3]....
[...]
Journal Article•
TL;DR: A technical note looks at the trends and also explains the nature of involvement of multiple research areas with a case study of synthesis of bioactive peptides.
Abstract: Today, the inevitability of cross-disciplinary research as the single most important current trend across various research groups worldwide is plausible. Though thought about years ago, the impact has grown exponentially only in recent times and slowly but surely, the entire research community is accepting interdisciplinary research to be the need of the hour to explain complex findings. This technical note looks at the trends and also explains the nature of involvement of multiple research areas with a case study of synthesis of bioactive peptides.
95 citations