A software toolkit for acoustic respiratory analysis

Millions of Americans suffer from pulmonary diseases. According to recent statistics, approximately 17 million people suffer from asthma, 16.4 million from chronic obstructive pulmonary disease, 12 million from sleep apnea, and 1.3 million from pneumonia - not to mention the prevalence of many other diseases associated with the lungs. Annually, the mortality attributed to pulmonary diseases exceeds 150,000. Clinical signs of most pulmonary diseases include irregular breathing patterns, the presence of abnormal breath sounds such as wheezes and crackles, and the absence of breathing entirely. Throughout the history of medicine, physicians have always listened for such sounds at the chest wall (or over the trachea) during patient examinations to diagnose pulmonary diseases - a procedure also known as auscultation. Recent advancements in computer technology have made it possible to record, store, and digitally process breath sounds for further analysis. Although automated techniques for lung sound analysis have not been widely employed in the medical field, there has been a growing interest among researchers to use technology to understand the subtler characteristics of lung sounds and their potential correlations with physiological conditions. Based on such correlations, algorithms and tools can be developed to serve as diagnostic aids in both the clinical and non-clinical settings. We developed a software toolkit, using MATLAB, to objectively characterize lung sounds. The toolkit includes a respiration detector, respiratory rate detector, respiratory phase onset detector, respiratory phase classifier, crackle and wheeze detectors and characterizers, and a time-scale signal expander. This document provides background on lung sounds, describes and evaluates our analysis techniques, and compares our work to approaches in other diagnostic tools.

[1]  Michael I. Jordan,et al.  An Introduction to Graphical Models , 2001 .

[2]  George R. Wodicka,et al.  An acoustic model of the respiratory tract , 2001, IEEE Transactions on Biomedical Engineering.

[3]  P. Forgacs.  Lung sounds. , 1969, British journal of diseases of the chest.

[4]  George R. Wodicka,et al.  Modeling and measurement of flow effects on tracheal sounds , 2003, IEEE Transactions on Biomedical Engineering.

[5]  E. H. Dooijes,et al.  Asthmatic airways obstruction assessment based on detailed analysis of respiratory sound spectra , 2000, IEEE Transactions on Biomedical Engineering.

[6]  Zahra Moussavi,et al.  Respiratory onset detection using variance fractal dimension , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  Stephen Kent Holford.  Discontinuous adventitious lung sounds: measurement, classification, and modeling. , 1981 .

[8]  Paul H. King,et al.  Representation and Classification of Breath Sounds Recorded in an Intensive Care Setting Using Neural Networks , 2004, Journal of Clinical Monitoring and Computing.

[9]  Antoni Homs-Corbera,et al.  Time-frequency detection and analysis of wheezes during forced exhalation , 2004, IEEE Transactions on Biomedical Engineering.

[10]  Jean Laroche,et al.  Improved phase vocoder time-scale modification of audio , 1999, IEEE Trans. Speech Audio Process..

[11]  Joo S. Chuah,et al.  AUTOMATED RESPIRATORY PHASE DETECTION BY ACOUSTICAL MEANS , 2001 .

[12]  David Malah,et al.  Time-domain algorithms for harmonic bandwidth reduction and time scaling of speech signals , 1979 .

[13]  H. Pasterkamp,et al.  Respiratory sounds. Advances beyond the stethoscope. , 1997, American journal of respiratory and critical care medicine.

[14]  P Hult,et al.  A bioacoustic method for timing of the different phases of the breathing cycle and monitoring of breathing frequency. , 2000, Medical engineering & physics.

[15]  J. E. Earis,et al.  Current methods used for computerized respiratory sound analysis , 2004 .

[16]  Zoltán Benyó,et al.  A novel method for the detection of apnea and hypopnea events in respiration signals , 2002, IEEE Transactions on Biomedical Engineering.

[17]  L.J. Hadjileontiadis,et al.  Separation of discontinuous adventitious sounds from vesicular sounds using a wavelet-based filter , 1997, IEEE Transactions on Biomedical Engineering.

[18]  David M. Baylon,et al.  Transform/subband analysis and synthesis of signals , 1990 .

[19]  Yves Verbandt,et al.  Automated breath detection on long-duration signals using feedforward backpropagation artificial neural networks , 2002, IEEE Transactions on Biomedical Engineering.

[20]  H. Harashima,et al.  Separation of fine crackles from vesicular sounds by a nonlinear digital filter , 1989, IEEE Transactions on Biomedical Engineering.

[21]  A. Cohen.  Signal processing methods for upper airway and pulmonary dysfunction diagnosis , 1990, IEEE Engineering in Medicine and Biology Magazine.

[22]  S. Lehrer.  Understanding Lung Sounds , 2002 .