Classification of voluntary cough sound and airflow patterns for detecting abnormal pulmonary function

Abaza, Ayman; Day, Jeremy B.; Reynolds, Jeffrey; Mahmoud, Ahmed M.; Goldsmith, William T.; McKinney, Walter; Petsonk, Edward L.; Frazer, David G.

doi:10.1186/1745-9974-5-8

Cited by 50 publications

(33 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Publications from Korpas and coworkers have previously suggested that studying voluntary cough sounds known as tussophonography may be useful in diagnosing respiratory diseases [31] and recent work measuring voluntary cough sounds and flow measures found sound features may reflect pulmonary function abnormalities [51,52].…”

Section: Cough Qualitymentioning

confidence: 99%

See 1 more Smart Citation

Monitoring chronic cough: current and future techniques

Smith¹

2010

Expert Review of Respiratory Medicine

View full text Add to dashboard Cite

Coughing produces a characteristic sound that is readily recognized by the human ear and provides the opportunity to objectively quantify coughing through acoustic recordings. The development of digital recording technologies has facilitated such recordings over the extended time periods needed to capture symptom episodes. However, the manual counting of coughs by listening to long recordings is time-consuming, laborious and restricts usage to research studies. This article outlines the challenges in recording, analyzing and quantifying cough sounds and describes the systems under development. Progress is being made towards automated algorithms to identify and count cough sounds; however, current systems have only been tested over short time periods and in limited patient groups. Further work is required to achieve broadly applicable accurate cough monitoring systems.

show abstract

Section: Cough Qualitymentioning

confidence: 99%

“…Flow changes during a single voluntary cough (A) with the associated cough sound (B).Reproduced with permission from[51].…”

mentioning

confidence: 98%

Monitoring chronic cough: current and future techniques

Smith¹

2010

Expert Review of Respiratory Medicine

View full text Add to dashboard Cite

show abstract

“…The nature of the anomalous sounds varies between stationary events such as wheezes or rhonchus, to transient sounds such as crackles, both at fine and coarse scales. Of all lung sounds of interest for medical diagnosis, wheezes and crackles are the most studied components and are indicative of specific pathologies [3], [4]. Wheezes are generally louder than the underlying breathing sound with duration longer than 250ms and are usually signs of obstructive pulmonary diseases (such as asthma).…”

Section: Introductionmentioning

confidence: 99%

A multiresolution analysis for detection of abnormal lung sounds

Emmanouilidou¹,

Patil²,

West³

et al. 2012

2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

Automated analysis and detection of abnormal lung sound patterns has great potential for improving access to standardized diagnosis of pulmonary diseases, especially in low-resource settings. In the current study, we develop signal processing tools for analysis of paediatric auscultations recorded under non-ideal noisy conditions. The proposed model is based on a biomimetic multi-resolution analysis of the spectro-temporal modulation details in lung sounds. The methodology provides a detailed description of joint spectral and temporal variations in the signal and proves to be more robust than frequency-based techniques in distinguishing crackles and wheezes from normal breathing sounds.

show abstract

“…Here, abnormal spirometry is defined as less than the lower limit of normal (LLN) predicted by standard reference equations [1]. Cough airflow signals of 107 subjects (56 male, 51 female) were previously collected [2] from patients performing spirometry in a pulmonary function clinic. A variety of features were extracted from the airflow signal.…”

mentioning

confidence: 99%

“…Cough airflow signals of 107 subjects (56 male, 51 female) were previously collected [2] from patients performing spirometry in a pulmonary function clinic. A variety of features were extracted from the airflow signal.…”

mentioning

confidence: 99%

Classification of Voluntary Cough Airflow Patterns for Prediction of Abnormal Spirometry

Reynolds

Goldsmith

Day

et al. 2016

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Measurement of partial expiratory flow-volume curves has become an important technique in diagnosing lung disease, particularly in children and in the elderly. The objective of this study was to investigate the feasibility of predicting abnormal spirometry using the partial flow-volume curve generated during a voluntary cough. Here, abnormal spirometry is defined as less than the lower limit of normal (LLN) predicted by standard reference equations [1]. Cough airflow signals of 107 subjects (56 male, 51 female) were previously collected [2] from patients performing spirometry in a pulmonary function clinic. A variety of features were extracted from the airflow signal. A support vector machine (SVM) classifier was developed to predict abnormal spirometry. Airflow signal features and SVM parameters were selected using a genetic algorithm. The ability of the classifier to distinguish between normal and abnormal spirometry based on cough flow was evaluated by comparing the classifiers decisions with the LLN for the given subject’s spirometry, including forced expiratory volume in one second (FEV1), forced vital capacity (FV C), and their ratio (FEV1/FV C%). Findings indicated that it was possible to classify patients whose spirometry results were less than the LLN with an overall accuracy of 76% for FEV1, 65% for FV C, and 76% for the ratio FEV1/FV C%. Accuracies were determined by repeated double cross-validation [3]. This study demonstrates the potential of using airflow measured during voluntary coughing to identify test subjects with abnormal spirometry.

show abstract

Classification of voluntary cough sound and airflow patterns for detecting abnormal pulmonary function

Cited by 50 publications

References 18 publications

Monitoring chronic cough: current and future techniques

Monitoring chronic cough: current and future techniques

A multiresolution analysis for detection of abnormal lung sounds

Classification of Voluntary Cough Airflow Patterns for Prediction of Abnormal Spirometry

Contact Info

Product

Resources

About