Claims:1. A method for determining respiratory condition of a subject, the method comprising:
acquiring a respiratory sample from the subject using a respiration analysis system, wherein the respiratory sample comprises one or more acoustic signals representative of at least one respiratory event;
computing an acoustic pressure associated with the respiratory sample based on a particle velocity corresponding to the respiratory sample;
generating a customizable respiratory tract model of the subject based on the particle velocity and the acoustic pressure;
determining at least one of, one or more airway resistance values and one or more compliance values, corresponding to the subject using the respiratory tract model; and
identifying the respiratory condition of the subject based on at least one of the airway resistance values and the compliance values.

2. The method as claimed in claim 1, wherein generating the respiratory tract model comprises:
determining a transfer function based on the acoustic pressure; and
generating the respiratory tract model based on the transfer function.

3. The method as claimed in claim 1, further comprising customizing the respiratory tract model based on one or more characteristics of the subject, wherein the characteristics comprise one or more of age, gender, past history of respiratory conditions, clinically relevant information, and habitus of the subject.

4. The method as claimed in claim 1, wherein identifying the respiratory condition comprises:
comparing at least one of, the one or more airway resistance values and the one or more compliance values with corresponding, one or more reference values of airway resistance and one or more values of compliance, defined for a healthy subject; and
identifying the respiratory condition of the subject based on the comparison.

5. The method as claimed in claim 1, wherein identifying the respiratory condition of the subject comprises:
performing a spectral and a temporal analysis of the respiratory sample;
identifying an origin of the respiratory event based on the one or more airway resistance values and the temporal analysis of the respiratory sample;
determining one or more acoustic frequencies of the respiratory sample originating from different regions of respiratory tract based on the spectral analysis; and
determining the respiratory condition of the subject based on the origin of the respiratory event and the acoustic frequencies originating from different regions of the respiratory tract.

6. The method as claimed in claim 5, further comprising generating a colored pattern indicative of the respiratory condition of the subject based on the spectral analysis of the respiratory sample and the origin of the respiratory event.

7. A respiration analysis system for determining respiratory condition of a subject, comprising:
a signal acquisition subsystem configured to acquire a respiratory sample from the subject, wherein the respiratory sample comprises one or more acoustic signals representative of at least one respiratory event;
a processing subsystem communicatively coupled to the signal acquisition subsystem; and
a memory subsystem communicatively coupled to the processing subsystem, wherein the memory subsystem stores one or more instructions, which on execution, cause the processing subsystem to:
compute an acoustic pressure associated with the respiratory sample based on a particle velocity corresponding to the respiratory sample;
generate a customizable respiratory tract model of the subject based on the particle velocity and the acoustic pressure;
determine at least one of, one or more airway resistance values, and one or more compliance values, corresponding to the subject using the respiratory tract model; and
identify the respiratory condition of the subject based on a comparison of at least one of, the airway resistance values and the compliance values, with one or more reference values of airway resistance and compliance defined for a healthy subject.

8. The respiration analysis system as claimed in claim 7, wherein the respiration analysis system is a portable computing device.

9. The respiration analysis system as claimed in claim 7, wherein the processing subsystem is configured to:
determine a transfer function based on the acoustic pressure; and
generate the respiratory tract model based on the transfer function.

10. The respiration analysis system as claimed in claim 7, wherein the processing subsystem is configured to:
perform a spectral and a temporal analysis of the respiratory sample;
identify an origin of the respiratory event based on the one or more airway resistance values and the temporal analysis of the respiratory sample;
identify one or more acoustic frequencies of the respiratory sample originating from one or more regions of respiratory tract based on the spectral analysis; and
determine the respiratory condition of the subject based on the origin of the respiratory event and the acoustic frequencies.

11. The respiration analysis system as claimed in claim 10, further comprising an output unit configured to provide a colored pattern, which is indicative of the respiratory condition of the subject based on the spectral analysis of the respiratory sample and the origin of the respiratory event. , Description:METHOD AND SYSTEM FOR DETERMINING RESPIRATORY CONDITION OF A SUBJECT

TECHNICAL FIELD

[0001] The present specification is generally related to diagnostic systems, and more particularly, to a method and system for determining a respiratory condition of a subject.

BACKGROUND

[0002] Clinical diagnoses continue to rely on large and expensive hospital equipment and/or a medical professional’s subjective assessment. For example, a medical practitioner may diagnose a respiratory condition of a subject from a cough sample based on his or her experience and expertise. Alternatively, internal or external acquisition units such as an acoustic sensor implant, body-worn sensors, a mouthpiece, and/or one or more tubes may be used for acquiring coughs sound samples and/or measuring desired physiological data.
[0003] Use of these conventional internal and external acquisition units is cumbersome, expensive, and may require the subject to wear customized clothing. Additionally, these units may restrict movement and are prone to measurement errors owing to improper mounting and/or movement of the subject. Moreover, the conventional cough sound acquisition systems work optimally only in a clinical setting under expert supervision. Conventional cough sound acquisition systems thus, are typically unavailable in many rural areas where hospitals and expert medical practitioners may be in short supply.
[0004] Accordingly, it may be desirable to develop a cost-efficient system for detecting a respiratory condition of subject that is simple to implement and use by both medical practitioners and laypersons for identifying a respiratory condition of the subject with greater accuracy.

SUMMARY

[0005] In accordance with an aspect of the present specification, a method for determining respiratory condition of a subject is disclosed. The method includes acquiring a respiratory sample from a subject using a respiration analysis system, where the respiratory sample includes one or more acoustic signals representative of at least one respiratory event. Further, the method computes an acoustic pressure associated with the respiratory sample based on a particle velocity corresponding to the respiratory sample. Further, the method generates a customizable respiratory tract model of the subject based on the acoustic pressure. The method further determines at least one of, one or more airway resistance values and compliance values, corresponding to the subject using the respiratory tract model. On determining at least one of airway resistance and compliance values, the method identifies the respiratory condition of the subject based on at least one of the airway resistance values and the compliance values.
[0006] In one embodiment, the method identifies the respiratory condition of the subject by comparing at least one of the airway resistance values and/or the compliance values with one or more reference values of airway resistance and/or compliance defined for a healthy subject. Further, the method identifies an origin of the respiratory event based on the airway resistance values and a temporal analysis of the respiratory sample. Additionally, the method determines acoustic frequencies of the respiratory sample originating from different regions of respiratory tract based on a spectral analysis of the respiratory sample. Subsequently, the method determines the respiratory condition of the subject based on the acoustic frequencies of the respiratory sample and the origin of the respiratory event.
[0007] In accordance with a further aspect of the present specification, a respiration analysis system for determining the respiratory condition of the subject is presented. The respiration analysis system includes a processing subsystem and a memory unit communicatively coupled to the processing subsystem. The memory unit stores processor executable instructions, which on execution, cause the respiration analysis system to acquire a respiratory sample from a subject, where the respiratory sample includes one or more acoustic signals representative of at least one respiratory event. The processing subsystem configures the respiration analysis system to compute an acoustic pressure corresponding to the respiratory sample based on a particle velocity corresponding to the respiratory sample. The processing subsystem further configures the respiration analysis system to generate a customizable respiratory tract model of the subject based on the acoustic pressure, and determine at least one of, one or more airway resistance values and compliance values, corresponding to the subject using the respiratory tract model. Further, the processing subsystem configures the respiration analysis system to identify respiratory condition of the subject based on at least one of the airway resistance values and the compliance values.
[0008] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS

[0009] These and other features, aspects, and advantages of the claimed subject matter will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:
[0010] FIG. 1 shows an exemplary environment including a system for determining respiratory condition of a subject, in accordance with certain aspects of the present specification;
[0011] FIG. 2 illustrates a flowchart of an exemplary method for generating a respiratory tract model, in accordance with certain aspects of the present specification;
[0012] FIG. 3 illustrates a flowchart depicting an embodiment of a method for determining respiratory condition of a subject, in accordance with certain aspects of the present specification;
[0013] FIG. 4 illustrates a flowchart showing an exemplary method for determining respiratory condition from a respiratory sample of a subject, in accordance with certain aspects of the present specification;
[0014] FIG. 5 illustrates an exemplary colored pattern that visualizes characteristics of the respiratory sample in an intuitive manner for identifying respiratory condition of a subject, in accordance with certain aspects of the present specification; and
[0015] FIG. 6 illustrates a block diagram of an exemplary system for detecting a respiratory condition of the subject, in accordance with certain aspects of the present specification.
[0016] It should be appreciated that any block diagrams herein represent conceptual views of illustrative systems embodying principles of the claimed subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like, represent various processes, which may be substantially represented in computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.

DETAILED DESCRIPTION

[0017] The following description presents exemplary systems and methods for determining a respiratory condition of a subject. Particularly, embodiments described herein disclose a method and system that employ spectral and temporal analyses of a respiratory sample along with a customizable respiratory tract model to identify an origin of a respiratory event, and in turn, a respiratory condition of the subject.
[0001] Although, the embodiments of the present systems and methods are described with reference to analysis of a cough sound sample, other acoustic signals such as those corresponding to breathing may be similarly evaluated to diagnose a respiratory condition of the subject. An exemplary environment that is suitable for practicing various implementations of the present system and method is discussed in the following sections with reference to FIG. 1.
[0018] FIG. 1 depicts an exemplary environment 100 including a respiration analysis system 101 for determining a respiratory condition of a subject. In one embodiment, the respiration analysis system 101 may be implemented on any computing platform such as a desktop computer system, a portable computing device, a mobile phone, a laptop, a tablet, and/or a palmtop computing device.
[0019] Further, in certain embodiments, the respiration analysis system 101 may be communicatively coupled to a storage subsystem 103 configured to store patient data and/or other operational information. Particularly, in one embodiment, the storage subsystem 103 may be an external device in communication with the respiration analysis system 101 and configured to store patient information from a plurality of patients. In an alternative embodiment, however, the storage subsystem 103 may be incorporated as part of the system 101. Accordingly, in certain embodiments, the respiration analysis system 101 may be communicatively coupled to the storage subsystem 103 via one or more wired and/or a wireless communication links 104 such as a data bus, a local area network, a cellular network, and/or the Internet. In one embodiment, the storage subsystem 103 stores reference values or ranges of airway resistance and/or compliance defined for a healthy person, age, gender, medical history, and/or other patient information. The storage subsystem 103 may also include clinically-specified correlations between cough sound characteristics such as frequencies, pitch, and/or timbre and corresponding disease indicators for use in diagnoses.
[0020] In certain embodiments, the respiration analysis system 101 includes a signal acquisition subsystem 105 for acquiring a respiratory sample of the subject. To that end, the signal acquisition subsystem 105 may include devices, such as, but not limited to, one or more microphones, analog sound recorders, digital sound recorders, an accelerometer-based recording device, an optical measurement device, a contact-based sensor, and/or other devices suited for acquiring a wide range of respiratory samples. In an exemplary implementation, the respiratory sample acquired by the signal acquisition subsystem 105 includes cough sound signals received from the subject. However, in certain other implementations, the respiratory samples may include other respiratory sounds such as general inspiration and expiration samples corresponding to the subject.
[0021] Further, in one embodiment, the respiratory signal acquisition subsystem 105 receives and/or acquires the cough sound signal of the subject via an input/output (I/O) interface 107. The I/O interface 107, for example, may include devices such as a graphical user interface, a touchscreen, a sound recorder, a display device, a printer, and/or other suitable I/O devices configured to receive cough sound signals and output patient and/or other clinical information.
[0022] Additionally, the system 101 further includes a processing subsystem 111 operatively coupled to the signal acquisition subsystem 105 and/or the I/O interface 107 for processing the cough sound signal and outputting resulting diagnostic information via one or more input/output (I/O) devices 113. To that end, the processing subsystem 111 includes, for example, one or more general-purpose processors, specialized processors, graphical processing units, microprocessors, programming logic arrays, field programming gate arrays, and/or other suitable computing devices.
[0023] In one embodiment, the processing subsystem 111 is configured to compute an acoustic pressure (cough sound pressure) associated with the cough sound signal. Particularly, the processing subsystem 111 computes the cough sound pressure based on a particle velocity of the cough sample acquired by the signal acquisition subsystem 105.
[0024] In one embodiment, the particle velocity may be received as an input from an external source or device. Alternatively, the particle velocity may be computed by the processing subsystem 111. Particularly, in certain embodiments, the external source and/or the processing subsystem 111 may determine the particle velocity using specific velocimetry techniques, for example, using spectrometry, and/or a complex of laser and/or optical means. In certain other embodiments, the velocity may be computed based on a difference in sample acquisition times at a pair of microphones positioned at a determined distance from each other. The particle velocity, thus determined, may be used to compute the acoustic pressure (cough sound pressure) corresponding to the cough sample.
[0025] Further, in certain embodiments, the processing subsystem 111 generates a customizable respiratory tract model of the subject using the cough sound pressure. Specifically, the processing subsystem 111 uses the cough sound pressure to determine values of volume velocity at two or more different junctions of the respiratory tract, which in turn, may be used to determine a transfer function. Subsequently, the processing subsystem 111 generates the respiratory tract model as a combination of lossless tubes based on the transfer function of volume velocity and pressure at different junctions of respiratory tract.
[0026] In one embodiment, the respiratory tract can be represented by a series of concatenated lossless tubes. Specifically, in one embodiment, the respiratory tract model is generated by modeling the respiratory tract from the lips to the end of the lungs using simple acoustic tubes, which are multiple short segments of pipes or tubes with different diameters and lengths. Accordingly, the model may be generated using one or more equations that describe how sound propagates in the concatenated lossless tubes, where the equations, inter alia, include simple wave equations and boundary conditions at the tube junctions. The equations may also allow for determination of volume velocities at two different junctions of tube, which in turn, may be used to calculate the transfer function. Certain exemplary equations and the transfer function used to generate the customizable model of the respiratory tract may be described in greater detail with reference to FIG. 2.
[0027] In one embodiment, the generated respiratory tract model may be further customized based on one or more characteristics of the subject, such as, age, gender, patient habitus, past history of respiratory conditions, and/or other clinically relevant information. The respiratory tract model may then be used to determine airway resistance and/or compliance values that are associated with the cough sample, in turn, aiding in identifying disease indicators corresponding to the subject. Customization of the respiratory tract model based on subject characteristics, thus, allows for accurate determination of airway resistance and/or compliance values for providing accurate patient diagnosis.
[0028] In certain embodiments, the diagnosis may entail a comparison of determined airway resistance and/or compliance values with a reference range of airway resistance and compliance defined for a healthy subject. In one embodiment, the pre-defined airway resistance and compliance values may be stored in the storage subsystem 103 for use during diagnosis. Particularly, the pre-defined values may include details about clinically specified reference ranges of airway resistance and/or compliance values defined for healthy subjects having different characteristics such as age weight, shape, size, gender, medical history, and/or other physiological characteristics.
[0029] In one embodiment, if one or more airway resistance and/or compliance values are determined to be within the reference range of airway resistance and compliance values defined for healthy subjects, the subject may be identified to have normal respiratory condition. Alternatively, if the airway resistance and/or compliance values are outside the clinically defined ranges for normal airway resistance and compliance values, the subject may be determined to have an abnormal respiratory condition.
[0030] In one embodiment, the processing subsystem 111 augments the diagnosis of the respiratory condition by performing a spectral and a temporal analysis of the respiratory sample of the subject. Specifically, the processing subsystem 111 performs the temporal analysis by providing an amplitude versus time evaluation of the cough sample that aids in identification of the origin of the cough sound in the respiratory tract in view of airway resistance values determined using the customizable respiratory tract model.
[0031] Further, the processing subsystem 111 performs the spectral analysis by time decomposition of respiratory sample into composite signals of finite length and determining dominant frequencies and associated with the decomposed respiratory sample. The dominant frequencies are then correlated with corresponding time of occurrence in the respiratory sample. For example, if duration of the respiratory signal is about 10 seconds, then the spectral analysis identifies dominant frequencies, for example, for each second of the respiratory sample. Particularly, the spectral analysis provides frequency-versus-time information that may be used to determine specific characteristics of the respiratory sample such as frequencies, loudness, pitch, and timbre with respect to origin of the respiratory sample in the respiratory tract. Subsequently, the respiratory condition of the subject is determined based on the origin of the respiratory event determined via the temporal analysis and cough sound frequencies determined via the spectral analysis of the cough sample.
[0032] In one embodiment, the respiratory event is indicated by airflow changes within the respiratory tract. Specifically, a narrowing of airways may cause turbulence of airflow through the respiratory tract, thereby giving rise to a typical respiratory event. Identifying the airflow changes in specific regions of the respiratory tract, thus, may provide an indication to a corresponding respiratory condition of the subject. In particular, the airflow changes may be correlated with physical manifestations such as change in lung volume, pressure, or other hemodynamic properties such as blood pressure and arterial oxygenation, that may provide disease indicators. By way of example, evaluating changes in the airflow may allow identification of a first respiratory event that may reveal a pathological situation below the level of tracheal bifurcation. Similarly, a second respiratory event may provide information about an area of the larynx.
[0033] Additionally, the changes in the airflow may be correlated with the identified origin of respiratory event via evaluation of temporal characteristics of the cough sample. For example, in one embodiment, if it is determined that the initial part of the respiratory event originated in the upper respiratory tract, for example, from alveoli in lungs while subsequent phases originated from lower levels of respiratory system like trachea and larynx, the subject may be diagnosed to be suffering from common cold and/or tonsillitis.
[0034] In one embodiment, the processing subsystem 111 may be configured to display the determined diagnosis with other user-defined and/or clinically relevant information via the I/O interface 107. As previously noted, the diagnosis and/or the relevant information may be communicated via an audio and/or visual means. For example, in certain embodiments, the processing subsystem 111 may be configured to generate a colored pattern indicative of one or more spectral characteristics of the cough sample. Particularly, the colored pattern is useful for visualization of the cough sample when the subject is not suited to an acoustical account involving spectral analysis. Thus, the colored pattern provides a medical practitioner, a caregiver, and/or the subject with an easy and intuitive way to identify the respiratory condition. An example of a colored pattern will be discussed in greater detail with reference to FIG. 6.
[0035] Further, FIGs. 2-7 illustrate different functionalities and components of the respiration analysis systems of FIG. 1 in greater detail.
[0036] Particularly, FIG. 2 illustrates a flowchart 200 of an exemplary method for generating a respiratory tract model for use by the respiration analysis system 101 of FIG. 1. The method begins at block 201, where the respiratory sample of the subject is acquired by the respiration analysis system 101. In one embodiment, the respiratory sample, for example, may be a cough sound signal of the subject. Moreover, the respiratory sample may be acquired, for example, using one or more microphones, sound recorders, an accelerometer-based recording device, an optical measurement device, a contact-based sensor, and/or other devices suited for acquiring a wide range of respiratory samples.
[0037] Further, at block 203, the acoustic pressure (cough sound pressure) of the respiratory sample is computed by the respiration analysis system 101 based on a particle velocity associated with the cough sample. The particle velocity may be determined using specific velocimetry techniques and/or may be received via an associated signal recording and/or processing system. Subsequently, in one embodiment, the cough sound pressure of the respiratory sample may be computed based on the received or computed particle velocity. An exemplary computation of the cough sound pressure based on the particle velocity of the respiratory sample is depicted using equations (1), (2), and (3):

u(x,t)=vp(x,t)*A (1)

where u is representative of the function u(x,t) that corresponds to volume velocity at a junction of the respiratory tract at position x and time t, vp(x,t) corresponds to particle velocity at the junction of the respiratory tract, and A corresponds to area of cross section of tube.

-dp/dx=? d(u/A)/dt (2)

-?u/?x= 1/(?c^2 ) ?(pA)/?t+ ?A/?t (3)

[0038] In equations (2) and (3), p is representative of the function p(x, t) and corresponds to a sound pressure in a selected tube at position x and time t, c corresponds to velocity of sound, and ? corresponds to density of air in the selected tube. Moreover, A is representative of the function A(x, t) that corresponds to area function of the tube, that is, the cross-sectional area normal to axis of the tube as a function of distance along the tube and as a function of time.
[0039] Further, at block 205, a transfer function is generated based on the cough sound pressure computed at block 203. By way of example, equation (4) is used to compute the transfer function based on the cough sound pressure of the respiratory sample.

Va (?) = U2j (I, ?)/ U1j (?) = I/ Cos (? I/c) (4)

where ? corresponds to a frequency component of airflow, I corresponds to length between two junctions in the respiratory tract, and U1j & U2j correspond to volume velocities in frequency domain at different junctions of the respiratory tract.

[0040] At block 207, a customizable model of the respiratory tract is generated by the respiration analysis system 101 based on the transfer function. Particularly, the respiratory tract model may be generated by using equations (1)-(5). In one embodiment, variations of the respiratory tract along the length are accounted for during model generation. Additionally, a related inertance that opposes acceleration is also addressed during model generation owing to mass of air in each segment of the pipe model. Similarly, compliance related to the compressibility of air and elasticity of the pipe wall is also represented in the customizable model.
[0041] In certain embodiments, generation of the respiratory tract model customized to a patient habitus and history aids in estimating suitable pressure to be exerted by respiratory muscles for coughing for use in a medical examination of a patient. This estimated pressure may then be provided by a cough inducing medical device for inducing cough or clearing the airways by mucous suctioning in the patient.
[0042] Additionally, the customizable respiratory tract model also aids in determining at least one of airway resistance and compliance values associated with the respiratory sample of a subject. Generally, for smooth tubes having hard walls, loss of energy occurs via viscous friction at the walls of the tube and heat conduction. In one embodiment, this viscous loss is proportional to the square of the particle velocity, whereas the loss due to heat conduction is proportional to the square of the pressure.
[0043] Accordingly, the airway resistance may be computed from the respiratory tract model of the subject, for example, using equation (5):

Ra= (US/A2) (v? ? µ/2) (5) (5)

where Ra corresponds to Airway resistance
U corresponds to Acoustic volume velocity
S corresponds to Circumference of pipe
? corresponds to frequency component of airflow
µ corresponds to viscosity co-efficient
? corresponds to density of the air
A corresponds to area of cross section of tube.

[0044] Similarly, acoustic equivalents of compliance values may be determined, for example, using equation (6).

Ca = Va/P? (6)

where Ca corresponds to the acoustic equivalent of capacitance
Va corresponds to the volume of the gas under pressure P
? corresponds to the adiabatic constant

[0045] As previously noted, one or more of the airway resistance and/or compliance values may then be used to identify a respiratory condition of the subject.
[0046] FIG. 3 illustrates a flowchart 300 depicting an embodiment of a method for determining respiratory condition of a subject in greater detail. At block 301, a spectral and a temporal analysis of the respiratory sample are performed. The spectral analysis of the respiratory sample is performed by time decomposition of the respiratory signal into composite signals of finite length and determining dominant or fundamental frequencies associated with the respiratory sample of the subject. The fundamental frequencies may then be correlated with their time of occurrence in the cough signal (Frequency v/s. Time). Additionally, the temporal analysis entails an amplitude versus time evaluation of the cough sample, which in turn, aids in identification of the origin of the cough sound in the respiratory tract.
[0047] At block 303, an origin of the respiratory event based on the airway resistance and the temporal analysis of the respiratory sample is determined. Typically, different phases of the cough sound may be correlated with one or more regions of the respiratory tract. For example, in one scenario, an initial part of the cough sound may originate from alveoli in lungs, while the subsequent phases may originate from higher levels of respiratory system like trachea and larynx. The areas of respiratory tract with different airway resistances modulate the length of the cough sound in different ways with the length of the cough sound increasing with increase in the airway resistance. For example if the airway resistance of trachea is greater than airway resistance of larynx, then the length of cough signal originating from trachea shall be greater than that of the larynx. Accordingly, the airway resistance values combined with the amplitude versus time information may allow for identification of the origin of the cough sound from one or more regions in the respiratory tract. Particularly, the origin of the cough sound may be identified by comparing the measured values with known or clinically-specified values corresponding to airway resistance and temporal characteristics defined for subjects of a similar demographics.
[0048] At block 305, acoustic frequencies (cough sound frequencies) of the respiratory sample originating from one or more regions of respiratory tract is determined based on the spectral analysis. Specifically, the spectral analysis of the respiratory sample is performed by time decomposition of respiratory sample for determining fundamental frequencies associated with the respiratory sample of the subject. For example, if the respiratory signal is of 10 seconds, then the frequencies are found for each seconds of the signal. The spectral analysis aids in identifying specific characteristics of the respiratory sample such as sound, intensity, duration, frequencies, loudness, pitch, and timbre. In one embodiment, known values of spectral characteristics associated with samples originating from different regions of the respiratory tract may be determined and stored in a database for comparison.
[0049] Generally, cough sound frequencies and/or timbre may be studied by assessing intensity bands at several levels. The cough sound timbre is determined based on fundamental frequency of the cough sample. The fundamental frequency with corresponding overtones and harmonics are produced by narrow parts of airways and by periodic vibrations of the vocal cords due to mechanical interaction between expired air and the vocal cords. A comparison of spectral characteristics such as the identified frequency and/or timbre values with corresponding clinical ranges specified for various respiratory illness may allow for an efficient diagnosis of the subject.
[0050] Accordingly, at block 307, the respiratory condition of the subject may be identified based on the cough sound frequencies of the respiratory sample and origin of the respiratory event. Both, the cough sound frequencies and the origin of the respiratory event correlated with the respiratory tract model are compared with clinical specified information corresponding to origin and range of frequencies for known health conditions
[0051] Typically, frequencies between 200,300,500 Hz may be defined as most expressive in healthy subjects. However, in an exemplary scenario, the spectral analysis may identify frequencies from 50-300 Hz as being accentuated, while, the temporal analysis indicates origin of the cough sound sample in bronchioles. By comparing the identified frequency values with corresponding clinical ranges specified for various respiratory illness and the origin of the cough, the subject may be diagnosed to suffer from bronchitis. Similarly, timbre values differ for cough samples having different nosological units, and thus, may be correlated to different respiratory conditions. In one example, timbre of a cough sample matching a brassy/bitonal sound combined with a cough originating from upper respiratory tract may indicate lymphoid gland tuberculosis and bronchial compression.
[0052] Further, FIG. 4 illustrates a flowchart 400 depicting an exemplary method for determining a respiratory condition of a subject. The method may be described in the general context of computer executable instructions, for example, including routines, programs, objects, components, data structures, procedures, modules, and functions, which perform particular functions or implement particular abstract data types. The order in which the method is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, certain blocks may be added or deleted from the methods without departing from the spirit and scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combinations thereof.
[0053] The method begins at block 401, where a respiratory sample is acquired from the subject using a respiration analysis system 101, the respiratory sample including one or more acoustic signals representative of at least one respiratory event. As previously noted, the respiratory sample, for example, may correspond to a cough sample or a breath sample, and the respiratory event, for example, may correspond to a cough, a sneeze, or a hiccup. For clarity of description, the present embodiment is described with reference to evaluation of a cough sound sample for determining a respiratory condition of the subject.
[0054] At block 403, an acoustic pressure (cough sound pressure) associated with the respiratory sample is computed based on a particle velocity associated with the respiratory sample. In one embodiment, the cough sound pressure may be determined, for example, using equations (1), (2), and (3) described with reference to FIG. 2.
[0055] At block 405, a customizable respiratory tract model of the subject is generated based on the cough sound pressure. The customizable respiratory tract model may be generated based on the cough sound pressure, for example, using equation (4) described with reference to FIG. 2.
[0056] At block 407, one or more airway resistance values and/or compliance values corresponding to the subject is determined using the respiratory tract model. In one embodiment, the airway resistance values and/or compliance values may be computed, for example, using equations (5) and (6) described with reference to FIG. 2.
[0057] At block 409, a respiratory condition of the subject is identified based on at least one of the airway resistance values and/or the compliance values. In one embodiment, the respiratory condition is identified by comparing at least one of the airway resistance values and the compliance values with one or more reference values of airway resistance and compliance defined for a healthy subject, and identifying the respiratory condition of the subject based on the comparison.
[0058] Certain clinical specifications define reference values of airway resistance for a healthy individual to be about 0.049 kilopascals/liter/second (kPa/L/s) to about 0.245 kPa/L/s .(“Wilkins' Clinical Assessment in Respiratory Care - Al Heuer et al, edition 7.page 194”). In contrast, threshold airway resistance (Ra) for abnormal respiratory condition (“Airways resistance and specific conductance for the diagnosis of obstructive airways diseases,” Marko Topalovic et al, 2015) may be around 0.38 kPa /L/s.
[0059] Similar clinically specified values of normal and abnormal airway resistance and/or compliance values may be identified from medical literature for different patient characteristics, such as, age, gender, past history of respiratory illness. Thus, if the airway resistance determined using the respiratory tract model exceeds beyond specified threshold values defined for a patient of a similar demographic, the subject is diagnosed as suffering from respiratory illness. Comparing the airway resistance values determined using the customized model with corresponding clinically specified values for similar patient demographics provides specific pathology details that allow for diagnosis that is more accurate for different kinds of patients.
[0060] Particularly, in certain embodiments, the airway resistance values, in conjunction with the temporal analysis of the cough sample identify an origin of the cough in the respiratory tract. Additionally, the spectral analysis of the cough sample identifies cough sound frequencies originating from one or more regions of the respiratory tracts. The respiratory condition of the subject may then be determined based on the origin of the respiratory event and determining the cough sound frequencies originating from different regions of the respiratory tract.
[0061] In certain embodiments, the determined respiratory condition may be communicated to a user and/or a medical practitioner via an audio and/or a visual medium such as via a display device associated with the system 100 of FIG. 1. Additionally, the cough sound may be converted into a colored pattern that may be indicative of the determined respiratory condition of the subject.
[0062] FIG. 5 depicts an exemplary colored pattern 500 representing a loudness, pitch, and/or timbre of the cough sound sample. In one implementation, for example, the loudness of the cough sound may be represented via a brightness and saturation of colors in the colored pattern. Further, the timbre of the cough sound may be represented via a selection of colors. For example, cough sounds having predominantly bass characteristics may be represented using a red color shade, whereas cough sounds having predominantly treble characteristics may be represented using a blue color shade. Moreover, the pitch of the cough sound may be represented using horizontal banding patterns 501 and 502. In one embodiment, when the pitch of the cough sound is low, as depicted by the pattern 501, bands are large and far apart. Alternatively, when the pitch of the cough sound is high, as depicted by the pattern 502, the bands are narrow and close together.
[0063] In one embodiment, sound characteristics such as loudness, pitch, and/or timbre may be correlated with the different types of cough sounds caused by different respiratory conditions. The correlations between the cough sound characteristics and respiratory conditions may be determined using historical patient information, and/or may be available as part of clinical studies and specifications. Accordingly, the pattern, color, and/or saturation of the colors in the colored pattern may provide a user-friendly visualization of the cough sound characteristics, which in turn, may be used to aid in identification of the corresponding respiratory condition based on the stored correlations. Embodiments described herein, thus, provide a portable device that aids a medical practitioner and/or an attendant to determine the respiratory condition of a subject in a simple and intuitive manner.

COMPUTING SYSTEM

[0064] Figure 6 illustrates a block diagram of an exemplary computer system 600 for implementing embodiments of the respiration analysis system 101 of FIG. 1 that that allows for determining the respiratory condition of a subject in a simple and intuitive manner. To that end, in one embodiment, the computer system 600 includes at least one processing unit (“processor”) 602. The processor 602 may include at least one signal processor for determining a respiratory condition by using respiratory sample of a subject. Additionally, the processor 602 may include specialized processing units such as integrated system (bus) controllers, memory management control units, floating point units, graphics processing units, and/or digital signal processing units.
[0065] Further, in certain embodiments, the processor 602 communicates with one or more I/O devices (not shown) via I/O interface 601 for acquiring the cough sample and/or communicating the corresponding diagnosis to a medical practitioner. The I/O interface 601 may employ communication protocols/methods such as audio, analog, digital, monoaural, RCA, stereo, IEEE-1394, serial bus, universal serial bus (USB), infrared, PS/2, BNC, coaxial, component, composite, digital visual interface (DVI), high-definition multimedia interface (HDMI), RF antennas, S-Video, VGA, IEEE 802.n /b/g/n/x, Bluetooth, cellular (e.g., code-division multiple access (CDMA), high-speed packet access (HSPA+), global system for mobile communications (GSM), long-term evolution (LTE), WiMAX, and/or the like.
[0066] Using the I/O interface 601, the computer system 600 may communicate with one or more I/O devices. For example, the I/O devices may include input devices such as an antenna, keyboard, mouse, joystick, (infrared) remote control, camera, card reader, fax machine, dongle, biometric reader, microphones, touch screen, touchpad, trackball, stylus, scanner, storage device, transceiver, video device/source, etc. Further, the I/O devices may include output devices such as a printer, fax machine, video display (e.g., cathode ray tube (CRT), liquid crystal display (LCD), light-emitting diode (LED), Plasma display panel (PDP), Organic light-emitting diode display (OLED) or, and/ audio speaker.
[0067] In certain embodiments, the processor 602 may be disposed in communication with the communication network 609 via a network interface 603 for receiving patient information and/or communicating diagnostic information. Particularly, the network interface 603 may employ connection protocols including, without limitation, a direct connection, Ethernet (e.g., twisted pair 10/100/1000 Base T), transmission control protocol/internet protocol (TCP/IP), token ring, and/or IEEE 802.11a/b/g/n/x, for the communications. The communication network 609 may include, without limitation, a direct interconnection, local area network (LAN), wide area network (WAN), wireless network (e.g., using Wireless Application Protocol), the Internet, etc. Using the network interface 603 and the communication network 609, the computer system 600 may communicate with the database 614. The network interface 603 may employ connection protocols including, but not limited to, a direct connection, Ethernet (e.g., twisted pair 10/100/1000 Base T), transmission control protocol/internet protocol (TCP/IP), Wireless Application Protocol (WAP), etc., token ring, IEEE 802.11a/b/g/n/x, etc. to communicate with a plurality of network devices in the communication network 609. These network devices, for example, may include routers, bridges, servers, computing devices, storage devices, etc.
[0068] In some embodiments, the processor 602 is communicatively coupled to a memory 605 (e.g., RAM, ROM, etc.) via a storage interface 604. The storage interface 604 may connect to memory 605 devices such as storage drives, removable disc drives, etc., employing connection protocols such as serial advanced technology attachment (SATA), Integrated Drive Electronics (IDE), IEEE-1394, Universal Serial Bus (USB), fiber channel, Small Computer Systems Interface (SCSI), etc. The memory 605 may further include a drum, magnetic disc drive, magneto-optical drive, optical drive, Redundant Array of Independent Discs (RAID), solid-state memory devices, solid-state drives, etc.
[0069] Further, the memory 605 may store a collection of program or database components, including, without limitation, user interface 606, an operating system 607, web server 608 etc. In some embodiments, computer system 600 may store user/application data 606, such as the data, variables, records, etc. as described in this disclosure. Such databases may be implemented as fault-tolerant, relational, scalable, secure databases such as Oracle or Sybase.
[0070] The operating system 607 may facilitate resource management and operation of the computer system 600. Examples of operating systems include, without limitation, Apple Macintosh OS X, Unix, Unix-like system distributions (e.g., Berkeley Software Distribution (BSD), FreeBSD, NetBSD, OpenBSD, etc.), Linux distributions (e.g., Red Hat, Ubuntu, Kubuntu, etc.), IBM OS/2, Microsoft Windows (XP, Vista/7/8, etc.), Apple iOS, Google Android, Blackberry OS, or the like.
[0071] In certain embodiments, the computer system 600 may implement a web browser 608 stored program component. The web browser 608 may be a hypertext viewing application, such as Microsoft Internet Explorer, Google Chrome, Mozilla Firefox, Apple Safari, etc. Secure web browsing may be provided using Secure Hypertext Transport Protocol (HTTPS), Secure Sockets Layer (SSL), Transport Layer Security (TLS), etc. Web browsers 608 may utilize facilities such as AJAX, DHTML, Adobe Flash, JavaScript, Java, Application Programming Interfaces (APIs), etc.
[0072] In certain other embodiments, the computer system 600 may implement a mail server stored program component. The mail server may be an Internet mail server such as Microsoft Exchange, or the like. The mail server may utilize facilities such as ASP, ActiveX, ANSI C++/C#, Microsoft .NET, CGI scripts, Java, JavaScript, PERL, PHP, Python, WebObjects, etc. The mail server may utilize communication protocols such as Internet Message Access Protocol (IMAP), Messaging Application Programming Interface (MAPI), Microsoft Exchange, Post Office Protocol (POP), Simple Mail Transfer Protocol (SMTP), or the like. In some embodiments, the computer system 600 may implement a mail client stored program component. The mail client may be a mail viewing application, such as Apple Mail, Microsoft Entourage, Microsoft Outlook, Mozilla Thunderbird, etc.
[0073] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., non-transitory items. Examples include Random Access Memory (RAM), Read-Only Memory (ROM), volatile memory, non-volatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.

ADVANTAGES OF THE PRESENT METHOD AND SYSTEM

[0074] An embodiment of the present disclosure determines a respiratory condition by using respiratory sample of a subject.
[0075] The present disclosure allows for provision of faster medical assistance to the subject by aiding even a layperson to determine the respiratory condition of the subject using a simple portable system.
[0076] The present disclosure does not require external provisions like mouthpiece and tubes and does not incorporate any body-worn, physiological sensors etc.
[0077] In an embodiment of the present disclosure, the overall cost of building and using respiration analysis system is low.
[0078] The present disclosure displays the cough sound as colored pattern, which provides users friendly approach for visualization.
[0079] Furthermore, the embodiments described herein, may be implemented as a method, system, or article of manufacture using suitable programming and/or engineering techniques to produce software, firmware, hardware, or any combination thereof. The described operations may be implemented as code maintained in a “non-transitory computer readable medium,” where a processor may read and execute the code from the computer readable medium. The processor is at least one of a microprocessor and a processor capable of processing and executing the queries. A non-transitory computer readable medium may comprise media such as magnetic storage medium (e.g., hard disk drives, floppy disks, tape, etc.), optical storage (CD-ROMs, DVDs, optical disks, etc.), volatile and non-volatile memory devices (e.g., EEPROMs, ROMs, PROMs, RAMs, DRAMs, SRAMs, Flash Memory, firmware, programmable logic, etc.), etc. The code implementing the described operations may further be implemented in hardware logic (e.g., an integrated circuit chip, Programmable Gate Array (PGA), Application Specific Integrated Circuit (ASIC), etc.).
[0080] Still further, the code implementing the described operations may be implemented in “transmission signals,” where transmission signals may propagate through space or through a transmission media, such as an optical fiber, copper wire, etc. The transmission signals in which the code or logic is encoded may further comprise a wireless signal, satellite transmission, radio waves, infrared signals, Bluetooth, etc. The transmission signals in which the code or logic is encoded is capable of being transmitted by a transmitting station and received by a receiving station, where the code or logic encoded in the transmission signal may be decoded and stored in hardware or a non-transitory computer readable medium at the receiving and transmitting stations or devices. An “article of manufacture” comprises non-transitory computer readable medium, hardware logic, and/or transmission signals in which code may be implemented. A device in which the code implementing the described embodiments of operations is encoded may comprise a computer readable medium or hardware logic. Of course, those skilled in the art will recognize that many modifications may be made to this configuration without departing from the scope of the invention, and that the article of manufacture may comprise suitable information bearing medium known in the art.
[0081] Additionally, as used herein, the terms “an embodiment”, “embodiment”, “embodiments”, “the embodiment”, “the embodiments”, “one or more embodiments”, “some embodiments”, and “one embodiment” mean “one or more (but not all) embodiments of the invention(s)” unless expressly specified otherwise.
[0082] Further, the terms “including”, “comprising”, “having” and variations thereof mean “including but not limited to”, unless expressly specified otherwise.
[0083] The terms “a,” “an” and “the” mean “one or more,” unless expressly specified otherwise.
[0084] A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optional components is described to illustrate the wide variety of possible embodiments of the invention.
[0085] Moreover, when a single device or article is described herein, it will be readily apparent that more than one device/article (whether or not they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it will be readily apparent that a single device/article may be used in place of the more than one device or article or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or the features of a device may be alternatively embodied by one or more other devices, which are not explicitly described as having such functionality/features. Thus, other embodiments of the invention need not include the device itself.
[0086] It may be noted that the foregoing examples, demonstrations, and process steps that may be performed by certain components of the present systems, for example, by the signal acquisition subsystem 105 and/or the processing subsystem 111 of FIG. 1, the computer system 600 of FIG. 6, and the like, may be implemented by suitable code on a processor-based system, such as a general-purpose or a special-purpose computer. It may also be noted that different implementations of the present specification may perform some or all of the steps described herein in different orders or substantially concurrently.
[0087] Additionally, various functions and/or method steps described in may be implemented in a variety of programming languages, including but not limited to Ruby, Hypertext Pre-processor (PHP), Perl, Delphi, Python, C, C++, or Java. Such code may be stored or adapted for storage on one or more tangible, machine-readable media, such as on data repository chips, local or remote hard disks, optical disks (that is, CDs or DVDs), solid-state drives, or other media, which may be accessed by the processor-based system to execute the stored code.
[0088] Although specific features of various embodiments of the present systems and methods may be shown in and/or described with respect to some drawings and not in others, this is for convenience only. It is to be understood that the described features, structures, and/or characteristics may be combined and/or used interchangeably in any suitable manner in the various embodiments, for example, to construct additional assemblies and techniques for use in wireless communications.
[0089] While only certain features of the present systems and methods have been illustrated and described herein, many modifications and changes will occur to those skilled in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention.