Automated Analysis of Crackles in Patients with Interstitial Pulmonary Fibrosis

Background. The crackles in patients with interstitial pulmonary fibrosis (IPF) can be difficult to distinguish from those heard in patients with congestive heart failure (CHF) and pneumonia (PN). Misinterpretation of these crackles can lead to inappropriate therapy. The purpose of this study was to determine whether the crackles in patients with IPF differ from those in patients with CHF and PN. Methods. We studied 39 patients with IPF, 95 with CHF and 123 with PN using a 16-channel lung sound analyzer. Crackle features were analyzed using machine learning methods including neural networks and support vector machines. Results. The IPF crackles had distinctive features that allowed them to be separated from those in patients with PN with a sensitivity of 0.82, a specificity of 0.88 and an accuracy of 0.86. They were separated from those of CHF patients with a sensitivity of 0.77, a specificity of 0.85 and an accuracy of 0.82. Conclusion. Distinctive features are present in the crackles of IPF that help separate them from the crackles of CHF and PN. Computer analysis of crackles at the bedside has the potential of aiding clinicians in diagnosing IPF more easily and thus helping to avoid medication errors.

[1]  Zhongwei Jiang,et al.  Crackle analysis for chest auscultation and comparison with high-resolution CT findings. , 2003, Radiation medicine.

[2]  R. Baughman,et al.  Crackles in interstitial lung disease. Comparison of sarcoidosis and fibrosing alveolitis. , 1991, Chest.

[3]  R. Adolph,et al.  In defense of the stethoscope. , 1998, Chest.

[4]  Andrey Vyshedskiy,et al.  Automated lung sound analysis in patients with pneumonia. , 2004, Respiratory care.

[5]  George R. Wodicka,et al.  Breath sounds methodology , 1995, Annals of Biomedical Engineering.

[6]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[7]  R. Murphy,et al.  Crackles in the early detection of asbestosis. , 1984, The American review of respiratory disease.

[8]  Aintree Chest,et al.  Current methods used for computerized respiratory sound analysis , 2000 .

[9]  Andrey Vyshedskiy,et al.  Transmission of crackles in patients with interstitial pulmonary fibrosis, congestive heart failure, and pneumonia. , 2005, Chest.

[10]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[11]  H S Hira,et al.  LUNG SOUNDS , 1978, The Journal of the Association of Physicians of India.

[12]  W. Smither,et al.  SECULAR CHANGES IN ASBESTOSIS IN AN ASBESTOS FACTORY , 1965, Annals of the New York Academy of Sciences.

[13]  R. Murphy,et al.  Validation of an automatic crackle (rale) counter. , 1989, The American review of respiratory disease.

[14]  P Piirilä,et al.  Lung sounds in asbestos induced pulmonary disorders. , 2000, The European respiratory journal.

[15]  A. Vyshedskiy,et al.  Sound transmission in the lung as a function of lung volume. , 2002, Journal of applied physiology.

[16]  W. Knowler,et al.  Visual lung-sound characterization by time-expanded wave-form analysis. , 1977, The New England journal of medicine.

[17]  Andrey Vyshedskiy,et al.  Mechanism of inspiratory and expiratory crackles. , 2009, Chest.

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

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

[20]  R M Rudd,et al.  Diagnosis of asbestosis by a time expanded wave form analysis, auscultation and high resolution computed tomography: a comparative study. , 1993, Thorax.

[21]  R. Murphy,et al.  Computerized multichannel lung sound analysis. Development of acoustic instruments for diagnosis and management of medical conditions. , 2007, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.