scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Respiratory Sound Analysis for Detection of Pulmonary Diseases

01 Nov 2018-
TL;DR: A very simple yet effective method for the second stage analysis- characterization of waveform of the filtered LS for some of the male and female age groups to obtain power spectrum plot of a particular LS.
Abstract: Large number of people die every year of Pulmonary chronic lung diseases irrespective of their age. Lung sound analysis has been a key diagnostic aid to accurately detect Pulmonary Diseases. Earlier, manual detection was used which was not a dependable method to detect lung diseases due to various reasons like low audibility and difference in perceptions of different physicians for different sounds. Modern computerized analysis yield results with much higher accuracy and thus a better treatment can be given to patients suffering from various kinds of lung diseases. These disorders include Asthma, Bronchitis, Emphysema, Tuberculosis and Pneumonia. Some of the symptoms are wheezing, shortness of breath, rhonchi and chronic cough. In general, the analysis is carried out in two stages- Separation of Heart Sound (HS) from the Lung Sound (LS) and the characterization of waveform of the filtered LS. In this paper, we propose a very simple yet effective method for the second stage analysis- characterization of waveform of the filtered LS for some of the male and female age groups. We have taken the filtered Lung sounds from different online repositories and performed Welch method. This method helps to obtain power spectrum plot of a particular LS. Different diseases have peaks in different frequency ranges of the power spectrum plot. This helps in identification of a particular disease.
Citations
More filters
Journal ArticleDOI
14 Nov 2020-Sensors
TL;DR: A novel framework is presented to perform a diagnosis of COPD and Pneumonia via application of the signal processing and machine learning approach and will help the pulmonologist to accurately detect disease A and B.
Abstract: Chronic obstructive pulmonary disease (COPD) and pneumonia are two of the few fatal lung diseases which share common adventitious lung sounds. Diagnosing the disease from lung sound analysis to design a noninvasive technique for telemedicine is a challenging task. A novel framework is presented to perform a diagnosis of COPD and Pneumonia via application of the signal processing and machine learning approach. This model will help the pulmonologist to accurately detect disease A and B. COPD, normal and pneumonia lung sound (LS) data from the ICBHI respiratory database is used in this research. The performance analysis is evidence of the improved performance of the quadratic discriminate classifier with an accuracy of 99.70% on selected fused features after experimentation. The fusion of time domain, cepstral, and spectral features are employed. Feature selection for fusion is performed through the back-elimination method whereas empirical mode decomposition (EMD) and discrete wavelet transform (DWT)-based techniques are used to denoise and segment the pulmonic signal. Class imbalance is catered with the implementation of the adaptive synthetic (ADASYN) sampling technique.

24 citations


Cites background from "Respiratory Sound Analysis for Dete..."

  • ...The effect of diverse focus groups in each disease is overlooked which could vary the spectrum position of abnormal LS in diverse bands with the same illness [21]....

    [...]

Journal ArticleDOI
TL;DR: In this article , the authors compared intermittent auscultation using a conventional stethoscope with continuous annealing using wearable stethoscopes for wheeze detection in patients who present with acute respiratory distress.
Abstract: Auscultation for an extended period of time using a wearable stethoscope enables objective computerized analysis and longitudinal assessment of lung sounds. However, this auscultation method differs from bedside auscultation in that clinicians are not present to optimize the quality of auscultation. No prior studies have compared these two auscultation methods.The aim of this study was to compare intermittent auscultation using a conventional stethoscope with continuous auscultation using a wearable stethoscope for wheeze detection in patients who present with acute respiratory distress.Patients presenting to the emergency department with acute respiratory distress were enrolled. The Strados Remote Electronic Stethoscope Platform (RESP™) was used for continuous auscultation, and intermittent auscultation was performed using a U.S. Food and Drug Administration-cleared electronic stethoscope. A recording was made with an electronic stethoscope. Subsequently, continuous recording was made using RESP™, which continued until the patient was admitted or discharged from the emergency department. The number of captured wheezes in each recording was counted and validated by two board-certified physicians.From May 2018 to May 2019, 43 patients were enrolled in the study. Three patients were excluded from analysis due to incomplete audio recording data. The mean length of recording was 62.3 min for continuous auscultation and 0.7 min for intermittent auscultation; 77.5% (31 of 40) of intermittent recordings contained wheezes, in contrast to 85% (34 of 40) of continuous recordings.Extending the duration of auscultation using a wearable stethoscope in a noisy clinical environment showed comparable performance to standard of care intermittent auscultation in identifying patients who have wheezes.

2 citations

Proceedings ArticleDOI
21 Dec 2020
TL;DR: In this article, a non-invasive, non-hazardous way of collecting and analyzing lung sounds by the Digital Signal Processing (DSP) method is proposed, which can be used for assessment of lung diseases.
Abstract: Air movement through the respiratory system generates sound commonly known as breath sounds or Lung sounds (LS). Auscultation can detect abnormalities in airflow in the respiratory system, which is caused by lung diseases. Change in airflow patterns can also change the sounds generated in the respiratory process, causing abnormal or adventitious Lung sounds. Traditional analog auditory stethoscopes require profound concentration by expert physicians and acquired data can't be stored. In this paper, a non-invasive, non-hazardous way of collecting and analyzing lung sounds by the Digital signal processing (DSP) method is proposed. Lung sounds collected by the auscultation process were then digitized. Various features (Rms, Zero Crossings, Turn Count, Mean, Variance, Form Factor) were extracted from the digitized data stream using DSP methods. The developed system uses significant components like-(1) traditional listening, (2) visual presentation of raw data, and (3) extracted features using DSP methods, which then can be used for assessment of lung diseases.

2 citations

Proceedings ArticleDOI
15 Sep 2021
TL;DR: In this paper, a simple self-made stethoscope was designed to digitize medical sound data, and the sounds were then analyzed to give preliminary diagnosis to track health condition.
Abstract: Traditionally, doctors have used stethoscopes for chest auscultation to diagnose respiratory and heart diseases. Auscultation can be used to initially diagnose the status of the patient, but this depends on the doctor's experience and waste time. Recently, electronic auscultation is proposed to diagnose the condition more carefully by sampling and processing sound signals. This paper designs a simple self-made stethoscope to digitize medical sound data. The sounds are then analyzed to give preliminary diagnosis to track health condition. The wave of monitored sounds and analyzed results can be displayed on mobile phones, so that patients can know health status immediately. In addition, an e-health home gateway and cloud-based AI system are also proposed for home-care patients to monitor health condition of chronic patients anytime at home or long-care center.

1 citations

Proceedings ArticleDOI
05 Apr 2023
TL;DR: In this paper , a method for acquiring lung sound signals and classifying the top five lung diseases, namely COPD, Pneumonia, Bronchiolitis, Bronchiectasis, and URTI, has been proposed.
Abstract: As the third biggest cause of death in the globe, lung illnesses are a serious issue. Auscultation using a stethoscope is the primary diagnostic approach for assessing lung conditions as it is non-invasive, inexpensive, and widely used. However, the manual auscultation-based diagnostic method is prone to mistakes, and its precision depends on the doctor's training and hearing ability. Additionally, the stethoscope recording can be distorted by external noises, which can mask important features of lung sounds, leading to misdiagnosis. To address this issue, a method for acquiring lung sound signals and classifying the top five lung diseases, namely COPD, Pneumonia, Bronchiolitis, Bronchiectasis, and URTI, has been proposed in this paper. The proposed method seeks to improve the efficacy of auscultation diagnosis of pulmonary disease.
References
More filters
Journal ArticleDOI
TL;DR: While quality data on CLSA are relatively limited, analysis of existing information suggests that CLSA can provide a relatively high specificity for detecting abnormal lung sounds such as crackles and wheezes.

175 citations


"Respiratory Sound Analysis for Dete..." refers background in this paper

  • ...Frequency of all lung sounds lie in the range of 50-2500Hz [9]....

    [...]

Journal ArticleDOI
01 Dec 1995-Thorax
TL;DR: The observed differences in frequency content of breath sounds in patients with asthma and COPD may reflect altered sound generation or transmission due to structural changes of the bronchi and the surrounding lung tissue in these diseases.
Abstract: BACKGROUND--Spectral characteristics of breath sounds in asthma and chronic obstructive pulmonary disease (COPD) have not previously been compared, although the structural differences in these disorders might be reflected in breath sounds. METHODS--Flow standardised inspiratory breath sounds in patients with COPD (n = 17) and stable asthma (n = 10) with significant airways obstruction and in control patients without any respiratory disorders (n = 11) were compared in terms of estimates of the power spectrum. Breath sounds were recorded simultaneously at the chest and at the trachea. RESULTS--The median frequency (F50) of the mean (SD) breath sound spectra recorded at the chest was higher in asthmatics (239 (19) Hz) than in both the control patients (206 (14) Hz) and the patients with COPD (201 (21) Hz). The total spectral power of breath sounds recorded at the chest in terms of root mean square (RMS) was higher in asthmatics than in patients with COPD. In patients with COPD the spectral parameters were not statistically different from those of control patients. The F50 recorded at the trachea in the asthmatics was significantly related to forced expiratory volume in one second (FEV1) (r = -0.77), but this was not seen in the other groups. CONCLUSIONS--The observed differences in frequency content of breath sounds in patients with asthma and COPD may reflect altered sound generation or transmission due to structural changes of the bronchi and the surrounding lung tissue in these diseases. Spectral analysis of breath sounds may provide a new non-invasive method for differential diagnosis of obstructive pulmonary diseases.

69 citations

Journal ArticleDOI
TL;DR: A wheezing detection algorithm based on the order truncate average method and a back-propagation neural network (BPNN) is proposed, which shows a high sensitivity and high specificity for wheeze recognition.
Abstract: Wheezing is a common clinical symptom in patients with obstructive pulmonary diseases such as asthma. Automatic wheezing detection offers an objective and accurate means for identifying wheezing lung sounds, helping physicians in the diagnosis, long-term auscultation, and analysis of a patient with obstructive pulmonary disease. This paper describes the design of a fast and high-performance wheeze recognition system. A wheezing detection algorithm based on the order truncate average method and a back-propagation neural network (BPNN) is proposed. Some features are extracted from processed spectra to train a BPNN, and subsequently, test samples are analyzed by the trained BPNN to determine whether they are wheezing sounds. The respiratory sounds of 58 volunteers (32 asthmatic and 26 healthy adults) were recorded for training and testing. Experimental results of a qualitative analysis of wheeze recognition showed a high sensitivity of 0.946 and a high specificity of 1.0.

36 citations


"Respiratory Sound Analysis for Dete..." refers methods in this paper

  • ...Usage of combination of BPF, LPF and HPF adaptive filters [7]....

    [...]

  • ...Machine learning algorithm Back-Propagation Neural Network [7] is used to match the recorded waveform from the standardized waveforms of different diseases....

    [...]

Book ChapterDOI
01 Jan 2010
TL;DR: In order to benefit fully from computer-aided auscultation, both heart and lung sounds should be extracted or blindly separated from breath sound recordings, namely, wavelet filtering, independent component analysis, and more recently, modulation domain filtering.
Abstract: Auscultation is a useful procedure for diagnostics of pulmonary or cardiovascular disorders. The effectiveness of auscultation depends on the skills and experience of the clinician. Further issues may arise due to the fact that heart sounds, for example, have dominant frequencies near the human threshold of hearing, hence can often go undetected (1). Computer-aided sound analysis, on the other hand, allows for rapid, accurate, and reproducible quantification of pathologic conditions, hence has been the focus of more recent research (e.g., (1–5)). During computer-aided auscultation, however, lung sounds are often corrupted by intrusive quasiperiodic heart sounds, which alter the temporal and spectral characteristics of the recording. Separation of heart and lung sound components is a difficult task as both signals have overlapping frequency spectra, in particular at frequencies below 100 Hz (6). For lung sound analysis, signal processing strategies based on conventional time, frequency, or time-frequency signal representations have been proposed for heart sound cancelation. Representative strategies include entropy calculation (7) and recurrence time statistics (8) for heart sound detection-and-removal followed by lung sound prediction, adaptive filtering (e.g., (9; 10)), time-frequency spectrogram filtering (11), and time-frequency wavelet filtering (e.g., (12–14)). Subjective assessment, however, has suggested that due to the temporal and spectral overlap between heart and lung sounds, heart sound removal may result in noisy or possibly “non-recognizable" lung sounds (15). Alternately, for heart sound analysis, blind source extraction based on periodicity detection has recently been proposed for heart sound extraction from breath sound recordings (16); subjective listening tests, however, suggest that the extracted heart sounds are noisy and often unintelligible (17). In order to benefit fully from computer-aided auscultation, both heart and lung sounds should be extracted or blindly separated from breath sound recordings. In order to achieve such a difficult task, a few methods have been reported in the literature, namely, wavelet filtering (18), independent component analysis (19; 20), and more recently, modulation domain filtering (21). The motivation with wavelet filtering lies in the fact that heart sounds contain large components over several wavelet scales, while coefficients associated with lung sounds quickly decrease with increasing scale. Heart and lung sounds are iteratively separated based on an adaptive hard thresholding paradigm. As such, wavelet coefficients at each scale with amplitudes above the threshold are assumed to correspond to heart sounds and the remaining coefficients are associated with lung sounds. Independent component analysis, in turn, makes use

19 citations


"Respiratory Sound Analysis for Dete..." refers methods in this paper

  • ...Filtering techniques used are Modulation Domain filtering [5] that filters the temporal trajectories of shortterm spectral components....

    [...]

  • ...Benchmark Separation algorithm for wavelet-based analysis [5] for characterization of LS is used....

    [...]

Proceedings ArticleDOI
25 Oct 2012
TL;DR: This research develops a new diagnosis tool with a new front-end equipment for the lung diseases diagnosis application: hand-phone equipped with a highly sensitive microphone, to record the breath-sound and the lung-sound is analysed to diagnose whether the patient's lung is healthy or not.
Abstract: This research paper describes the study of the breath sound analysis and application development for two fold purposes: (1) for diseases diagnosis tool, specifically the lung and respiratory diseases; and (2) for stress measurement. The Lung Diseases Diagnosis Application consists of software and hardware components which formed a first-hand diagnosis tool of the lung diseases, to support the paramedics/doctors in lung diseases diagnosis. One of the most common and proven technique for lung disease diagnosis is the Auscultation, the term refers to listening to the internal sounds of the respiratory system (breath sounds), usually by using a stethoscope. However, this diagnosis way depends heavily on the listening skills and judgment of the paramedics/doctors only. In this research, we develop a new diagnosis tool with a new front-end equipment for the lung diseases diagnosis application: hand-phone equipped with a highly sensitive microphone, to record the breath-sound. This recorded breath-sound is then processed to generate the lung sound, which is approximately similar with the lung-sound heard and recorded by a stethoscope and the lung-sound is analysed to diagnose whether the patient's lung is healthy or not. This application would hopefully support the paramedics/doctors mobility to rural areas as well as remote diagnosis. The requirement is to create a first-hand diagnostic tool which allows paramedic mobility to rural areas for lung diseases diagnostic purposes. The study first describes about the existing lung diseases diagnostic tools and researches, stress measurement, then analysis and preliminary design of lung diseases diagnosis application. To enable each Lung Health Public Council (Balai Besar Kesehatan Paru Masyarakat) and Hospitals as data owner to maintain its own data, and to provide the data confidentiality as well, the cloud computing environment is then applied. Hopefully this research could serve both purposes: the lung diseases diagnosis and stress measurement.

7 citations


"Respiratory Sound Analysis for Dete..." refers methods in this paper

  • ...A first-hand diagnosis tool is made for lung sound analysis [12] where results are obtained based on different scans like CT scan and X-ray....

    [...]