Method and apparatus for displaying lung sounds and performing diagnosis based on lung sound analysis

• US 6,139,505 A
• Filed: 10/14/1998
• Issued: 10/31/2000
• Est. Priority Date: 10/14/1998
• Status: Expired due to Term

• Current Assignee: Stethographics, Inc.
• Original Assignee: Raymond L.H. Murphy
• Inventors: Murphy, Raymond L. H.
• Primary Examiner(s): O'Connor, Cary
• Assistant Examiner(s): CARTER, RYAN CHRISTOPHER
• Application Number:
  US09/172,343
• Time in Patent Office: 748 Days
• Field of Search: 600/508-509, 600/513, 600/528-529, 600/531-538, 381/67, 381/92
• US Class Current: 600/532
• CPC Class Codes: A61B 5/061 Determining position of a probe within the body employing means separate from the probe, e.g. sensing internal probe position employing impedance electrodes on the surface of the body A61B1/00158 takes precedence
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 7/003 Detecting lung or respiration noise

Abstract

A lung sound diagnostic system for use in collecting, organizing and analyzing lung sounds associated with the inspiration(s) and expiration(s) of a patient. The system includes a plurality of transducers that may be placed at various sites around the patient'"'"'s chest. The microphones are coupled to signal processing circuitry and A/D converters which digitize the data and preferably provides the digital data to a computer station. A data collection and organization program, executing on the computer station, organizes and formats the data into a combination display for display or printing. The combinational display includes at least two display elements. In a first display element, the data is shown for both inspiration and expiration combined in a first time scale. In a second display element, the data for inspiration and expiration are shown individually in a second time scale that is time-expanded relative to the first time scale. The system may also include application programs for detecting and classifying abnormal sounds. The resulting information may be displayed in a variety of formats to facilitate diagnosis. Additionally, the system may include an analysis program for comparing selected criteria corresponding to the detected abnormal sounds with predefined thresholds in order to provide a likely diagnosis.

Claims

1. A lung sound diagnostic system for use in analyzing lung sounds detected during the inspiration and expiration of a patient by a plurality of transducers placed at various sites around the patient'"'"'s chest, the system comprising:

means for receiving digital data corresponding to the lung sounds detected by each transducer; and

means, responsive to the digital data, for generating a combinational pulmonary display including a first display element having a time domain plot of the lung sounds detected by each transducer for inspiration and expiration separately as a function of a first time scale,

wherein the plot of lung sounds within the first element are simultaneously arranged in a vertical stack configuration.

2. The lung sound diagnostic system of claim 1 wherein the combinational pulmonary display further includes a second display element having a time domain plot of the lung sounds detected by each transducer for inspiration and expiration combined as a function of a second time scale, such that the first time scale is slightly expanded relative to the second time scale.

3. The lung sound diagnostic system of claim 2 wherein the first time scale is approximately 200-400 mm/sec.

4. The lung sound diagnostic system of claim 3 wherein the second time scale is approximately 20-50 mm/sec.

5. The lung sound diagnostic system of claim 2 wherein the transducers are placed at the sites concurrently.

6. The lung sound diagnostic system of claim 2 wherein the transducers are placed at the sites sequentially.

7. The lung sound diagnostic system of claim 2 further comprising means for calculating the duration of inspiration and expiration and the combinational pulmonary display further includes a data field having a first value corresponding to the calculated duration of inspiration and a second value corresponding to the calculated duration of expiration.

8. The lung sound diagnostic system of claim 7 further comprising means for calculating a root-mean-square (RMS) value at one or more sites and further wherein the data field includes a display of the RMS value as calculated for one or more sites.

9. The lung sound diagnostic system of claim 8 wherein the data field further includes a first computed quantity corresponding to the ratio of duration of inspiration to the duration of expiration.

10. The lung sound diagnostic system of claim 2 further comprising a computer station coupled to a graphical user interface, wherein the generating means is a data collection and organization application program executing on the computer station and the data collection and organization application program is configured to format the combinational pulmonary display to appear in one or two windows on the graphical user interface.

11. The lung sound diagnostic system of claim 10 further comprising a printer coupled to the computer station, wherein the data collection and organization application program is further configured to print the combinational display on one or two sheets of paper.

12. The lung sound diagnostic system of claim 11 wherein the combinational pulmonary display further includes a third display element having a separate plot of the lung sounds detected at each transducer for inspiration and expiration individually as function of a third time scale that is fully time-expanded relative to the first time scale.

13. The lung sound diagnostic system of claim 12 wherein the third time scale is approximately 800 mm/sec.

14. The lung sound diagnostic system of claim 11 wherein the data collection and organization program is further configured to calculate a root-mean-square (RMS) value of the data obtained at each site and to generate one or more body plots on the graphical user interface, each body plot having a marker associated with each site associated with the corresponding body plot, the markers reflecting the intensity of the RMS value as calculated for that site.

15. The lung sound diagnostic system of claim 10 further comprising an adventitious sound detection application program executing on the computer station, the adventitious sound detection program configured to examine the lung sound information detected by the transducers and to identify one or more adventitious portions of the detected lung sounds.

16. The lung sound diagnostic system of claim 15 wherein the adventitious sound detection system is further configured to label the portions of the lung sound tracings within the second plot element with an identifier corresponding to detected adventitious sounds.

17. The lung sound diagnostic system of claim 16 wherein the adventitious sound detection application program comprises:

means for generating an amplitude threshold trace for the lung sound information detected by each transducer;

means for identifying each segment of the lung sound information that exceeds the corresponding amplitude trace;

means for generating a slope threshold trace for the lung sound information detected by each transducer;

means for identifying each segment of the lung sound information that exceeds the corresponding slope threshold trace; and

means, responsive to predefined thresholds, for categorizing the previously identified amplitude exceeding segments as crackles if the predefined thresholds are satisfied.

18. The lung sound diagnostic system of claim 17 wherein the categorizing means comprises:

means for determining whether each previously identified amplitude exceeding segment has four to eight zero crossings;

means for determining one or more deflection widths of the previously identified amplitude exceeding segments; and

means for determining whether the one or more deflection widths of each previously identified amplitude exceeding segment exceed a predefined threshold.

19. The lung sound detection system of claim 18 wherein the adventitious sound detection application program further comprises means for classifying segments previously categorized as crackles as coarse, medium or fine crackles.

20. The lung sound detection system of claim 19 wherein the classifying means comprises:

means for classifying each crackle segment as a fine crackle if the average detection width is substantially in the range of 0.0015 and 0.0025 seconds;

means for classifying each crackle segment as a medium crackle if the average detection width is substantially in the range of 0.0025 and 0.0035 seconds; and

means for classifying each crackle segment as a coarse crackle if the average detection width is substantially in the range of 0.0035 and 0.0045 seconds.

21. The lung sound detection system of claim 20 wherein the adventitious sound detection application program further comprises means for identifying wheezes and rhonchi present within the detected lung sound information.

22. The lung sound detection system of claim 21 wherein the means for identifying wheezes and rhonchi comprises:

means for dividing the lung sound information corresponding to inspiration and expiration for each transducer into a plurality of sections;

means for determining half periods of zero crossings and the mean and standard deviations of the half periods for each section;

means for determining peak amplitude of each half cycle and mean and standard deviations of peak amplitudes; and

means for comparing the peak amplitudes, mean and standard deviations of peak amplitudes to predefined thresholds to identify sections as wheezes or rhonchi.

23. The lung sound detection system of claim 22 wherein the adventitious sound detection application program further comprises

means for calculating the average frequency of each identified segment;

means for classifying the segment as a rhonchi if the average frequency is less than 200 Hz; and

means for classifying the segment as a wheeze if the average frequency is greater than 200 Hz.

24. The lung sound detection system of claim 23 further comprising a probable-diagnosis prediction application program executing on the computer station, the probable-diagnosis prediction application program configured to review the previously identified crackles, wheezes and rhonchi, ratio of time of inspiration to time of expiration and amplitude distribution of the lung sound information and to present a probable-diagnosis in response to a data set of crackles, wheezes and rhonchi associated with one or more correct diagnoses.

25. The lung sound detection system of claim 24 wherein the probable-diagnosis prediction application program includes a neural network module coupled to a neural network training database.

26. The lung sound detection system of claim 24 wherein the probable-diagnosis prediction application program includes one or more multiple logistic regression models.

27. The lung sound diagnostic system of claim 1 wherein the transducers are analog microphones and the receiving means includes an analog-to-digital converter coupled to the microphones.

28. The lung sound detection system of claim 27 comprising eight microphones arranged as a group and applied to a first region at the patient'"'"'s chest.

29. A lung sound diagnostic system comprising:

a plurality of transducers that may be placed at various sites around a patient'"'"'s chest for generating signals responsive to lung sounds;

means, coupled to the plurality of transducers, for determining whether the signals generated by the transducers meet predefined criteria associated with one or more adventitious lung sounds; and

means for generating a common display having markers that identify patient chest locations at which the signals met the predefined criteria.

30. The lung sound diagnostic system of claim 29 wherein the common display includes at least one schematic representation of a patient'"'"'s chest area.

31. The lung sound diagnostic system of claim 29 wherein the common display includes at least one front view of a patient'"'"'s chest area.

32. The lung sound diagnostic system of claim 31, wherein the common display further includes at least one side view of a patient'"'"'s chest area.

33. The lung sound diagnostic system of claim 29, wherein a first marker identifies a point at which the corresponding signal met the predefined criteria for a crackle.

34. The lung sound diagnostic system of claim 33, wherein the first marker is the letter C.

35. The lung sound diagnostic system of claim 29 wherein a second marker identifies a point at which the corresponding signal met the predefined criteria for a wheeze.

36. The lung sound diagnostic system of claim 35, wherein the second marker is the letter W.

37. The lung sound diagnostic system of claim 29 wherein a third marker identifies a point at which the corresponding signal met the predefined criteria for a rhonchi.

38. The lung sound diagnostic system of claim 37, wherein the third marker is the letter R.

39. A method for collecting, organizing and displaying lung sound information during the inspiration and expiration of a patient as detected by a plurality of transducers placed at various sites around the patient'"'"'s chest, the method comprising the steps of:

receiving digital data corresponding to the lung sounds detected by the transducers; and

generating, in response to the digital data, a combinational pulmonary display for display on a graphical user interface, the combinational pulmonary display having

a first display element in which the detected lung sounds from each transducer are plotted as a function of amplitude versus time for inspiration and expiration separately relative to a first time scale.

40. The method of claim 39, wherein the combination pulmonary display further includes a second display element in which the detected lung sounds from each transducer are plotted as a function of amplitude versus time for both inspiration and expiration combined relative to a second time scale, such that the first time scale is slightly expanded relative to the second time scale.

41. A method for collecting, organizing and displaying lung sound information during the inspiration and expiration of a patient as detected by a plurality of transducers placed at various sites around the patient'"'"'s chest, the method comprising the steps of:

receiving digital data corresponding to the lung sounds detected by the transducers; and

generating, in response to the digital data, a combinational pulmonary display for display on a graphical user interface, wherein the detected lung sounds are arranged in a vertical stack configuration having;

a first display element in which at least a portion of the detected lung sounds from one or more transducers are plotted as a function of amplitude versus time relative to a first time scale; and

a second display element in which at least a portion of the detected lung sounds from one or more transducers are plotted as a function of amplitude versus time relative to a second time scale that is expanded relative to the first time scale.

42. The method of claim 41 further comprising the steps of:

calculating the duration of inspiration and expiration; and

displaying on the combinational pulmonary display a data field having a first value corresponding to the calculated duration of inspiration and a second data field having a second value corresponding to the calculated duration of expiration.

43. The method of claim 41 wherein the vertical stack configuration further has a third display element in which at least a portion of the detected lung sounds from one or more transducers are plotted as a function of amplitude versus time relative to a third time scale that is expanded relative to the second time scale.

44. The method of claim 41 further comprising the steps of:

evaluating at least a portion of the detected lung sounds from at least one transducer to identify one or more pre-determined adventitious lung sounds; and

labeling the lung sound plot for the at least one transducer with an identifier corresponding to an identified adventitious lung sound.