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...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2011-01-01
|
| Series: | Pulmonary Medicine |
| Online Access: | http://dx.doi.org/10.1155/2011/590506 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849408463497592832 |
|---|---|
| author | B. Flietstra N. Markuzon A. Vyshedskiy R. Murphy |
| author_facet | B. Flietstra N. Markuzon A. Vyshedskiy R. Murphy |
| author_sort | B. Flietstra |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-79e1d2cc96974234b9880c9142e2acfd |
| institution | Kabale University |
| issn | 2090-1836 2090-1844 |
| language | English |
| publishDate | 2011-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Pulmonary Medicine |
| spelling | doaj-art-79e1d2cc96974234b9880c9142e2acfd2025-08-20T03:35:47ZengWileyPulmonary Medicine2090-18362090-18442011-01-01201110.1155/2011/590506590506Automated Analysis of Crackles in Patients with Interstitial Pulmonary FibrosisB. Flietstra0N. Markuzon1A. Vyshedskiy2R. Murphy3The Charles Stark Draper Laboratories, Massachusetts Institute of Technology, Faulkner Hospital, 1153 Centre Street, Suite 4990 Boston, MA 02130, USAThe Charles Stark Draper Laboratories, Massachusetts Institute of Technology, Faulkner Hospital, 1153 Centre Street, Suite 4990 Boston, MA 02130, USAThe Charles Stark Draper Laboratories, Massachusetts Institute of Technology, Faulkner Hospital, 1153 Centre Street, Suite 4990 Boston, MA 02130, USAThe Charles Stark Draper Laboratories, Massachusetts Institute of Technology, Faulkner Hospital, 1153 Centre Street, Suite 4990 Boston, MA 02130, USABackground. 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.http://dx.doi.org/10.1155/2011/590506 |
| spellingShingle | B. Flietstra N. Markuzon A. Vyshedskiy R. Murphy Automated Analysis of Crackles in Patients with Interstitial Pulmonary Fibrosis Pulmonary Medicine |
| title | Automated Analysis of Crackles in Patients with Interstitial Pulmonary Fibrosis |
| title_full | Automated Analysis of Crackles in Patients with Interstitial Pulmonary Fibrosis |
| title_fullStr | Automated Analysis of Crackles in Patients with Interstitial Pulmonary Fibrosis |
| title_full_unstemmed | Automated Analysis of Crackles in Patients with Interstitial Pulmonary Fibrosis |
| title_short | Automated Analysis of Crackles in Patients with Interstitial Pulmonary Fibrosis |
| title_sort | automated analysis of crackles in patients with interstitial pulmonary fibrosis |
| url | http://dx.doi.org/10.1155/2011/590506 |
| work_keys_str_mv | AT bflietstra automatedanalysisofcracklesinpatientswithinterstitialpulmonaryfibrosis AT nmarkuzon automatedanalysisofcracklesinpatientswithinterstitialpulmonaryfibrosis AT avyshedskiy automatedanalysisofcracklesinpatientswithinterstitialpulmonaryfibrosis AT rmurphy automatedanalysisofcracklesinpatientswithinterstitialpulmonaryfibrosis |