JP6534566B2 - Heart disease diagnostic device, heart disease diagnostic program and medium - Google Patents

Description

  The present invention relates to a heart disease diagnostic device, a heart disease diagnostic program and a medium.

  FIG. 1 shows the internal structure of a heart 200. The inside of the heart 200 has a structure divided into four chambers of a right ventricle 202, a left ventricle 204, a right atrium 206, and a left atrium 208. A pulmonary valve 210, an aortic valve 212, a tricuspid valve 214, and a mitral valve 216 are provided at the outlets of the right ventricle 202, left ventricle 204, right atrium 206, and left atrium 208, respectively, to prevent regurgitation.

  FIG. 2 shows an example of a heart sound signal waveform for two heartbeats. The horizontal axis represents time (seconds) and the vertical axis represents the intensity of the heart sound signal. Usually, heart sound signals of healthy persons include I sound and II sound. Sound I is a heart sound that occurs when the tricuspid valve 214 and the mitral valve 216 close. Sound II is a heart sound that occurs when the pulmonary valve 210 and the aortic valve 212 close.

  The magnitudes of I sound and II sound vary depending on the hardness of the valve and the closing speed of the valve. The case where I sound and II sound become louder is called enhancement, and the case where it becomes small is called attenuation. Enhancement or attenuation of I sound or II sound may occur depending on the type of heart disease, and is used as a clue for diagnosis. For example, in rheumatic mitral stenosis, the I-enhancement is enhanced by rapid closure of the mitral valve hardened by rheumatic changes. In pulmonary hypertension, the pressure difference between the right ventricle and the pulmonary artery enlarges the closing speed of the pulmonary valve and sounds II increase. Heretofore, several devices and methods have been proposed to analyze heart sounds and determine the presence or absence of abnormalities.

The conventional heart sound information processing apparatus detects I sound and II sound from heart sound, and calculates the power ratio of I sound to II sound and the power ratio of II sound to I sound for each of I sound and II sound. . If the power ratio is below a certain reference value or above a certain reference value, it is judged as an abnormal sound (for example, refer to Patent Document 1). In addition, the conventional heart sound information processing apparatus obtains a spectrogram of heart sound, calculates an average value of spectrograms within a predetermined frequency band in a section before the spectrogram maximum peak and a section after the spectrogram maximum peak, (See, for example, Patent Document 2).
Patent Document 1 Patent No. 5673429 Patent Document 2 Patent No. 5190954

  However, the heart sound determination described in Patent Document 1 determines whether each of the I sound and the II sound is abnormal or normal, and only counts the number of heart sounds determined as abnormal to determine heart disease. Do not do. Further, the heart sound determination described in Patent Document 2 is for detecting an abnormality of a heart prosthetic valve of a user wearing a heart prosthetic valve, and can not be applied when the heart prosthetic valve is not mounted.

  In a first aspect of the present invention, a heart sound detection unit that detects an electrical signal based on heart sound of a living body, an input signal processing unit that outputs heart sound data by performing predetermined signal processing on the electric signal, and heart sound data And at least one of the I sound signal and the II sound signal is extracted, and the amplitude and the power of the first frequency band between the first frequency and the second frequency higher than the first frequency in the sound signal are extracted. And a heart sound analysis unit that diagnoses a heart disease of a living body by comparison based on at least one of the above and the first reference value.

  In a second aspect of the present invention, there is provided a heart disease diagnostic program which causes a computer to function as an input signal processing part and a heart sound analysis part according to the first aspect.

  In a third aspect of the present invention, there is provided a computer readable medium having the heart disease diagnostic program according to the second aspect.

  The above summary of the invention does not enumerate all of the features of the present invention. In addition, a subcombination of these feature groups can also be an invention.

The internal structure of the heart 200 is shown. An example of a waveform of a heart sound signal for two heartbeats is shown. An example of a structure of the heart disease diagnostic apparatus 1 is shown. 2 shows a flowchart of a heart disease diagnosis process by the heart disease diagnosis device 1. An example of a waveform of a heart sound signal for 10 heartbeats is shown. It is an example of the extraction method of heart sound interval data. 7 shows a single logarithmic power spectrum of I sound interval data. The single log power spectrum of 10 beat I sound interval data and its average are shown. The single log power spectrum of 10 beats II sound interval data and its average are shown. The flowchart which applies the heart disease presence diagnostic method which concerns on Example 1 to I sound is shown. An example of the diagnostic frequency band set in step S201 is shown. It is an example of the graph showing relative frequency distribution of I sound average power. It is an example of the graph showing the relationship between the value of reference value 2, and sensitivity and specificity. The flowchart which applies the heart disease presence diagnostic method which concerns on Example 1 to sound II is shown. It is an example of the graph showing relative frequency distribution of II sound average power. It is an example of the graph showing the relationship of the value of reference value 4, and sensitivity and specificity. The set of I sound average power and II sound average power on a two-dimensional space is shown. It is an example which applies the standard function for heart disease judgment. The average logarithmic power spectrum of I sound regarding 5 positive examples and 5 negative examples is shown. The average logarithmic power spectrum of sound II is shown for 5 positive cases and 5 negative cases. The flowchart which applies the heart disease presence diagnostic method which concerns on Example 2 to I sound is shown. An example of the diagnostic frequency band 1 and the diagnostic frequency band 2 is shown. It is an example of the graph showing relative frequency distribution of I sound average power. It is an example of the graph showing the relationship of the value of reference value 6, and sensitivity and specificity. The flowchart which applies the heart disease presence diagnostic method which concerns on Example 2 to sound II is shown. It is an example of the graph showing relative frequency distribution of II sound average power ratio. It is an example of the graph showing the relationship between the value of reference value 8, and sensitivity and specificity. The pair of I sound average power ratio and II sound average power ratio on a two-dimensional space is shown. It is an example which applies the standard function for heart disease judgment. 1 shows an example of a hardware configuration of a heart disease diagnosis apparatus 1 according to an embodiment of the present invention. 17 shows an example of a hardware configuration of a computer 1900 according to an embodiment of the present invention.

  Hereinafter, the present invention will be described through the embodiments of the invention, but the following embodiments do not limit the invention according to the claims. Moreover, not all combinations of features described in the embodiments are essential to the solution of the invention.

  FIG. 3 is a schematic configuration view showing an example of the heart disease diagnosis device 1. FIG. 4 shows a flowchart of a heart disease diagnosis process by the heart disease diagnosis device 1. The heart disease diagnosis apparatus 1 executes step S10-50 by reading a program for heart sound analysis. In the present specification, each step of the program executed by the heart disease diagnosis apparatus 1 is shown in parentheses.

  The heart disease diagnosis apparatus 1 diagnoses the presence or absence of a heart disease in a subject based on heart sound signals in the I sound section and the II sound section. The heart disease diagnosis apparatus 1 includes a heart sound detection unit 11, an input signal processing unit 12, a heart sound analysis unit 13, and an output unit 14.

  The heart sound detection unit 11 is attached to the subject and detects an electrical signal based on the heart sound of the subject. The heart sound detection unit 11 may measure heart sound vibration propagating in the chest. For example, the heart sound detection unit 11 outputs an electrical signal according to heart sound vibration that propagates the chest of the subject. The heart sound detection unit 11 includes a microphone, an acceleration sensor, a pressure sensor, and the like.

  The input signal processing unit 12 outputs heart sound data by performing predetermined signal processing on the electric signal output from the heart sound detection unit 11 (step S10). Heart sound data is digitalized electrical signals based on heart sound signals. The input signal processing unit 12 performs removal of unnecessary frequency components included in the electrical signal, signal amplification, and conversion to a digital signal. For example, the input signal processing unit 12 includes a filter circuit, an amplifier, and an A / D converter. The filter circuit removes DC frequency components contained in the heart sound signal, high frequency components that may cause aliasing, and high frequency components unnecessary for heart sound analysis. Also, the amplifier amplifies the heart sound signal in accordance with the input range of the A / D converter. The A / D converter outputs heart sound data obtained by converting the heart sound signal amplified by the amplifier into a digital signal.

  The heart sound analysis unit 13 analyzes heart sound data to diagnose the possibility of heart disease. For example, the heart sound analysis unit 13 is configured by an arithmetic processing unit such as a microcomputer. The heart sound analysis unit 13 includes a heart sound interval extraction unit 131, a frequency analysis unit 132, and a heart disease diagnosis unit 133.

  The heart sound section extraction unit 131 extracts heart sound section data from the heart sound data output by the input signal processing section 12 (step S20). The heart sound section data is data of an arbitrary section in the digitized heart sound data. For example, extraction of heart sound interval data refers to extraction of at least one of I sound interval data and II sound interval data from heart sound data. The I sound section data refers to data of the I sound section in heart sound data. The II sound section data refers to data of the II sound section in heart sound data.

  The frequency analysis unit 132 performs frequency analysis on each of the extracted heart sound segment data to calculate a logarithmic power spectrum (step S30). For example, the frequency analysis unit 132 calculates the logarithmic power spectrum of the I sound section from the plurality of I sound section data, and calculates the logarithmic power spectrum of the II sound section from the plurality of II sound section data. Also, the frequency analysis unit 132 averages the logarithmic power spectrum for each of the I sound section and the II sound section in a plurality of heartbeats. This reduces the effects of environmental noise. The frequency analysis unit 132 in this example performs frequency analysis after extracting a part of the frequency by the filter circuit provided in the input signal processing unit 12. However, the heart disease diagnosis apparatus 1 may extract a part of the frequency after performing frequency analysis of heart sound data by arranging a filter circuit at a stage subsequent to the frequency analysis unit 132.

  The heart disease diagnosis unit 133 diagnoses the possibility of heart disease from the logarithmic power spectrum of the averaged I sound section and the logarithmic power spectrum of the II sound section (step S40). More specifically, the heart disease diagnosis unit 133 compares the averaged logarithmic power spectrum of the I sound segment and the II sound segment with the heart disease diagnosis criteria prepared in advance, thereby determining the presence or absence of heart disease. Diagnose.

  The output unit 14 outputs the result diagnosed by the heart disease diagnosis unit 133 to the outside (step S50). For example, the output unit 14 includes a display that displays the diagnosis result. In addition, the output unit 14 may output to an external storage device such as a hard disk.

  FIG. 5 shows an example of a heart sound signal waveform for 10 heartbeats. The waveform of the heart sound signal of this example is detected by the heart sound detection unit 11 provided with an acceleration sensor. The heart sound detection unit 11 is attached to a subject and collects heart sound as vibration. The heart sound detection unit 11 converts the collected heart sound into an electrical signal and outputs it as a heart sound signal waveform. The systolic heart sound signal can be obtained 10 times from the heart sound signal waveform for 10 heartbeats. The input signal processing unit 12 digitizes the heart sound signal of 10 heartbeats of the subject with 2 kHz sampling and 16 bits. In FIG. 5, the horizontal axis represents time [seconds], and the vertical axis represents the intensity of the heart sound signal.

  FIG. 6 is an example of a method of extracting heart sound interval data. The heart sound data digitized by the input signal processing unit 12 is input to the heart sound section extraction unit 131 of the heart sound analysis unit 13, and the I sound section data and the II sound section data are respectively extracted from the I sound section and the II sound section. Ru. The I sound segment data and the II sound segment data are examples of heart sound segment data. The detection of the I sound section and the II sound section can be performed, for example, by the method described in Patent Document 1. The extracted heart sound interval data is input to the frequency analysis unit 132.

  FIG. 7 shows a single log power spectrum of I sound interval data. The single log power spectrum is a logarithmic power spectrum of heart sound interval data for one heartbeat. In FIG. 7, the horizontal axis represents frequency [Hz], and the vertical axis represents logarithmic power spectrum.

  The frequency analysis unit 132 multiplies the I sound section data extracted for each heartbeat by an appropriate window function. The frequency analysis unit 132 of this example multiplies the first I sound interval data of the 2 kHz sampling heart sound data in FIG. 5 by a Hamming window function of 128 milliseconds (256 samples). After that, the frequency analysis unit 132 Fourier-transforms the I sound segment data multiplied by the Hamming window function to calculate a single logarithmic power spectrum. A single log power spectrum includes local frequency variations that occur due to the influence of background noise and the like, but the variations can be removed by averaging the log power spectra of multiple heartbeats.

  FIG. 8 shows a logarithmic power spectrum of 10 beats of I sound. A thick line shows the average logarithmic power spectrum which averaged the logarithmic power spectrum of 10 beats of 1 sound. The average log power spectrum of the I sound section in the present specification is an average of single log power spectra of 10 heartbeats, but it may be an average of single log power spectra of any heartbeat as needed.

  In the single log power spectrum (FIG. 8), the frequency characteristics of the I sound section data can not be accurately represented due to the local frequency fluctuation caused by the influence of background noise and the like. On the other hand, since the average logarithmic power spectrum (thick line in FIG. 8) is averaged by the single logarithmic power spectrum of a plurality of heartbeats, it is possible to suppress the locally generated power spectrum generated randomly.

  FIG. 9 shows a logarithmic power spectrum of 10 beats of II sound. The heavy line shows the average logarithmic power spectrum obtained by averaging the logarithmic power spectrum of 10 beats of II sound. The average log power spectrum of sound II in the present specification is an average of single log power spectra of 10 heartbeats, but it may be an average of single log power spectra of any heartbeat as needed. The average logarithmic power spectrum of the II sound is calculated by the same procedure as the average logarithmic power spectrum of the I sound. Next, the heart disease diagnosis unit 133 diagnoses the presence or absence of the possibility of the heart disease based on the average logarithmic power spectrum of the heart sound section and the diagnosis criteria of the heart disease presence or absence prepared in advance.

Example 1
FIG. 10 illustrates an example of the operation of the heart disease diagnosis unit 133 according to the first embodiment. The heart disease diagnosis unit 133 of this example applies a diagnosis criterion of the presence or absence of heart disease to sound I. In the heart disease diagnosis method according to the first embodiment, the presence or absence of the possibility of heart disease is diagnosed by executing steps S201 to S203.

  The heart disease diagnosis unit 133 sets a diagnostic frequency band for the average logarithmic power spectrum of the I sound calculated by the frequency analysis unit 132 (step S201). Next, the average power of the average logarithmic power spectrum of I sound (hereinafter referred to as “I sound average power”) is calculated by calculating the average value of the power of each frequency bin included in the diagnostic frequency band set in step S201. ) Is calculated (step S202). Finally, the average sound power I is compared with the reference value 1 and the reference value 2 to diagnose the possibility of heart disease (step S203). The reference value 1 is a reference for detecting the I sound attenuation, and the reference value 2 is a reference for detecting the I sound acceleration. The heart disease diagnosis unit 133 diagnoses that there is a possibility of heart disease, when the I sound average power is equal to or less than the reference value 1, or when the I sound average power is equal to or more than the reference value 2.

  Although the heart disease diagnosis unit 133 of this example calculates the I sound average power corresponding to the diagnostic frequency band, it may calculate the amplitude of the frequency corresponding to the diagnostic frequency band. In this case, the heart disease diagnosis unit 133 diagnoses the presence or absence of heart disease by comparing at least one of the amplitude of the diagnostic frequency band and the average sound power I with the reference value 2.

  For example, the heart disease diagnosis unit 133 diagnoses that the living body is healthy when at least one of the amplitude of the diagnostic frequency band and the average sound power I is smaller than the reference value 2. In addition, the heart disease diagnosis unit 133 diagnoses that there is a heart disease in the living body when at least one of the amplitude of the diagnostic frequency band and the average sound power I is 2 or more.

  In addition, when the heart disease diagnosis unit 133 determines that at least one of the amplitude of the diagnostic frequency band and the I sound average power is smaller than the reference value 2 and larger than the reference value 1 smaller than the reference value 2, The living body may be diagnosed as healthy. Then, the heart disease diagnosis unit 133 may diagnose that there is a heart disease in the living body when at least one of the amplitude of the diagnostic frequency band and the I sound average power is 2 or more or 1 or less. .

  FIG. 11 shows a setting example of a diagnostic frequency band. The diagnostic frequency band is arbitrarily set according to the characteristics of heart sound data. For example, the diagnostic frequency band is any band between 200 Hz and 1 kHz. The heart disease diagnosis unit 133 of this example sets 250 Hz to 400 Hz as a frequency band for diagnosis.

  FIG. 12 shows relative frequency distribution with respect to I sound average power for each positive and negative case. In this example, the relative frequency distribution for each of negative and positive heart disease cases is shown. The heart sound data of 387 healthy persons is used as a negative example of this example, and the heart sound data of 42 heart disease patients is used as a positive example.

  The heart sound detection unit 11 measures heart sound of 10 seconds at a site between the second left intercostal region (hereinafter referred to as “2L”) for each of the negative and positive cases. The heart sound analysis unit 13 calculates the I sound average power with 250 Hz to 400 Hz as the frequency band for diagnosis. In this case, both the positive and negative examples show a convex distribution. Although positive cases have overlapping parts with negative cases, there is a tendency for the increase of the I sound average power to be negative with respect to negative cases. That is, by setting the appropriate reference value 2, the heart disease diagnosis unit 133 can accurately diagnose the presence or absence of the possibility of heart disease.

  FIG. 13 shows the relationship of sensitivity and specificity to reference value 2. The sensitivity is the proportion of positive cases diagnosed as a possible heart disease. The specificity is the proportion of negative cases diagnosed as having no possibility of heart disease. The reference value 2 may be set according to the application. If you want to increase both sensitivity and specificity, set reference value 2 at the point where sensitivity and specificity intersect. For example, if the reference value 2 is set to around 5.3, both the sensitivity and the specificity become about 80%, and it can be seen that the I sound average power is effective for a heart disease diagnosis. In addition, the reference value 2 is set to a value larger than 5.3 when it is desired to erroneously diagnose a positive case as a possible disease, ie, to increase the specificity. For example, if the reference value 2 is set to about 5.5, the sensitivity is about 70%, but the specificity can be raised to about 90%. As described above, by changing the magnitude of the reference value 2, it is possible to adjust the magnitude of sensitivity and specificity when using the I sound average power.

  FIG. 14 illustrates an example of the operation of the heart disease diagnosis unit 133 according to the first embodiment. The heart disease diagnosis unit 133 of this example applies a diagnosis criterion of the presence or absence of heart disease to sound II. In the heart disease diagnosis method according to the first embodiment, the presence or absence of the possibility of heart disease is diagnosed by executing steps S301 to S303.

  The heart disease diagnosis unit 133 sets a diagnostic frequency band for the averaged single logarithmic power spectrum of the II sound section calculated by the frequency analysis unit 132 (step S301). Next, the average power of the average logarithmic power spectrum of II sound (hereinafter referred to as “II sound average power”) is calculated by calculating the average value of the power of each frequency bin included in the diagnostic frequency band set in step S301. ) Is calculated (step S302). Finally, the average power of the II sound is compared with the reference value 3 and the reference value 4 to diagnose the possibility of heart disease (step S303). Reference value 3 is a reference for detecting attenuation of II sound, and reference value 4 is a reference for detecting enhancement of II sound. The heart disease diagnosis unit 133 diagnoses that there is a possibility of heart disease, when the average sound power of II sound is equal to or less than the reference value 3 or when the average power of II sound sound is equal to or more than the reference value 4.

  FIG. 15 shows relative frequency distribution to the average power of II sound for each positive and negative case. The relative frequency distribution of this example is calculated using 250 Hz to 400 Hz as the diagnostic frequency band for heart sound data of the same negative example and positive example as described in FIG.

  FIG. 16 shows the relationship of sensitivity and specificity to reference value 4. The reference value 4 may be set according to the application. If you want to increase both sensitivity and specificity, set reference value 4 at the point where sensitivity and specificity intersect. For example, if the reference value 4 is set to around 6.0, both the sensitivity and the specificity become about 70%, and it can be seen that the average sound of II sound is effective for heart disease diagnosis. If you want to increase the specificity, you can set the reference value 4 to a value larger than 6.0, and by changing the magnitude of the reference value 4, the sensitivity and the singularity when using the II sound average power You can adjust the size of the degree.

  FIG. 17 is a graph in which the I sound average power and the II sound average power are plotted in a two-dimensional space. The horizontal axis indicates the I sound average power calculated in FIG. 12, and the vertical axis indicates the II sound average power calculated in FIG. Also, each plot shows positive examples in triangles and negative examples in circles. It can be seen that the distribution area is different between negative and positive cases.

  FIG. 18 shows an example of a reference function for heart disease determination. The heart disease diagnosis apparatus 1 diagnoses the possibility of heart disease by applying a reference function to a graph in which I sound average power and II sound average power are plotted. The reference function is set according to the distribution characteristics of the negative and positive cases. The reference function of this example is indicated by an ellipse in a plot of the I sound average power and the II sound average power. The heart disease diagnosis unit 133 diagnoses that there is a possibility of heart disease when it is plotted in one of the spaces separated by the reference function (for example, outside the ellipse). In addition, the heart disease diagnosis unit 133 diagnoses that there is no possibility of heart disease when it is plotted in one other space (for example, inside of an ellipse).

  FIG. 19 shows the average log power spectra of the I sound of 5 positive and 5 negative examples. FIG. 20 shows the average log power spectra of sound II of 5 positive and 5 negative cases.

  The power difference between positive and negative cases tends to begin to expand from around 200 Hz and decrease as it approaches 1 kHz. This tendency is seen in both the average log power spectrum of the I sound and the average log power spectrum of the II sound. The heart disease diagnosis unit 133 uses the signal after the band pass filter processing such that the power difference between the positive example and the negative example becomes large. For example, the heart disease diagnosis unit 133 uses a signal in a frequency band including part or all of 200 Hz to 1 kHz. Thereby, the heart disease diagnosis unit 133 is compared to the case where the signal after low-pass filter processing of 300 Hz or less of Patent Document 1 is used, or the signal after the high-pass filter processing of 1 kHz or more of Patent Document 2 is used. Can diagnose heart disease more accurately.

  In the first embodiment, frequency analysis is performed on the data of the I sound section and the data of the II sound section, and the components of the diagnostic frequency band are extracted in the frequency domain to calculate the average power. However, the heart disease diagnosis apparatus 1 may calculate the average power by extracting the components of the diagnostic frequency band in the time domain using a band pass filter.

(Example 2)
FIG. 21 illustrates an example of the operation of the heart disease diagnosis unit 133 according to the second embodiment. The heart disease diagnosis unit 133 of this example applies a diagnosis criterion of the presence or absence of heart disease to the sound I. In the heart disease diagnosis method according to the second embodiment, the presence or absence of the possibility of heart disease is diagnosed by executing steps S401 to S403.

  The heart disease diagnosis unit 133 has a diagnostic frequency band lower than the diagnostic frequency band 1 and the diagnostic frequency band 1 with respect to the averaged single log power spectrum of the I sound section calculated by the frequency analysis unit 132. 2 is set (step S401). Next, the average value of the power of each frequency bin included in the diagnostic frequency band 1 set in step S401 (hereinafter referred to as “I sound average power 1”) and the diagnostic frequency band 2 set in step S401 A power ratio obtained by calculating an average value of power of each frequency bin included (hereinafter referred to as “I sound average power 2”) and dividing I sound average power 1 by I sound average power 2 (hereinafter referred to as “I sound average The power ratio is called (step S402). Finally, the I sound average power ratio is compared with each of the reference value 5 and the reference value 6 to diagnose the possibility of heart disease (step S403). The reference value 5 is a reference for detecting attenuation of the I sound, and the reference value 6 is a reference for detecting enhancement of the I sound. The heart disease diagnosis unit 133 diagnoses that there is a possibility of heart disease when the average I sound power ratio is 5 or less or 6 or more.

  For example, in the diagnostic frequency band 1 and the diagnostic frequency band 2, the influence of the heart disease of the living body in the diagnostic frequency band 1 on the amplitude or power is on the amplitude or power of the living body in the diagnostic frequency band 2. Set to be greater than the impact. As a result, even if a signal unrelated to the heart disease of the living body, such as displacement of the measurement position or cardiac noise, is generated, the amplitude ratio and the I sound average power ratio in the diagnostic frequency band 1 and the diagnostic frequency band 2 It becomes easy to detect the component regarding the heart disease of the living body.

  The heart disease diagnosis unit 133 of this example calculates the I sound average power ratio which is the ratio of the I sound average power 1 corresponding to the diagnostic frequency band 1 to the I sound average power 2 corresponding to the diagnostic frequency band 2 However, the amplitude ratio of the frequency of the diagnostic frequency band 1 to the diagnostic frequency band 2 may be calculated. In this case, the heart disease diagnosis unit 133 compares the heart disease diagnosis criteria with at least one of the amplitude ratio of the frequency of the diagnosis frequency band 1 to the diagnosis frequency band 2 and the average sound power ratio of I sound. To diagnose the presence or absence of

  For example, the heart disease diagnosis unit 133 determines that the living body is healthy when at least one of the amplitude ratio of the frequency of the diagnostic frequency band 1 to the diagnostic frequency band 2 and the I sound average power ratio is smaller than the reference value 6 Diagnose that there is. In addition, the heart disease diagnosis unit 133 causes the heart disease in the living body when at least one of the amplitude ratio of the frequency of the diagnosis frequency band 1 to the diagnosis frequency band 2 and the I sound average power ratio is 6 or more. Diagnose that there is.

  The heart disease diagnosis unit 133 has at least one of the amplitude ratio of the frequency of the diagnostic frequency band 1 to the diagnostic frequency band 2 and the I sound average power ratio smaller than the reference value 6 and more than the reference value 6. If the value is larger than the small reference value 5, the living body may be diagnosed as healthy. Then, when at least one of the amplitude ratio of the frequency of the diagnostic frequency band 1 to the diagnostic frequency band 2 and the I sound average power ratio to the diagnostic frequency band 2 is the reference value 6 or more or the reference value 5 or less, It may be diagnosed that there is a heart disease in the living body. The heart disease diagnosis unit 133 may combine the heart disease diagnosis methods according to the first embodiment and the second embodiment.

  FIG. 22 shows a setting example of the diagnostic frequency band 1 and the diagnostic frequency band 2. The diagnostic frequency band 1 and the diagnostic frequency band 2 are arbitrarily set according to the characteristics of heart sound data. The heart disease diagnosis apparatus 1 of this example performs frequency analysis on the I sound interval data and the II sound interval data, extracts components of the diagnostic frequency band in the frequency domain, and calculates an average power. For example, the diagnostic frequency band 1 and the diagnostic frequency band 2 are any band between 200 Hz and 1 kHz. The heart disease diagnosis unit 133 of this example sets 250 Hz to 400 Hz as the diagnostic frequency band 1 and sets 50 Hz to 200 Hz as the diagnostic frequency band 2. The components of the diagnostic frequency band may be extracted by a band pass filter in the time domain.

  FIG. 23 shows relative frequency distribution to I sound average power ratio for each positive and negative example. In this example, the relative frequency distribution for each of negative and positive heart disease cases is shown. The heart sound data of 387 healthy persons is used as a negative example of this example, and the heart sound data of 42 heart disease patients is used as a positive example.

  The heart sound detection unit 11 measures heart sound for 10 seconds at a site of 2 L for each of the negative example and the positive example. The heart sound analysis unit 13 calculates the I sound average power ratio with 250 Hz to 400 Hz as the diagnostic frequency band 1 and 50 Hz to 200 Hz as the diagnostic frequency band 2. In this case, both the positive and negative examples show a convex distribution. Although positive cases have overlapping parts with negative cases, there is a tendency for an increase in the I sound average power ratio to negative cases. That is, by setting the appropriate reference value 6, the heart disease diagnosis unit 133 can accurately diagnose the presence or absence of the possibility of heart disease.

  FIG. 24 shows the relationship of sensitivity and specificity to reference value 6. The reference value 6 may be set according to the application. If you want to increase both sensitivity and specificity, set reference value 6 at the point where sensitivity and specificity intersect. For example, if the reference value 6 is set to about 0.73, both sensitivity and specificity will be about 80%, and it can be seen that the I sound average power ratio is effective for heart disease diagnosis. Also, to increase the specificity, the reference value 6 is set to a value larger than 0.73. For example, if the reference value 6 is set to around 0.75, the sensitivity is about 70%, but the specificity can be raised to about 90%. Thus, by changing the magnitude of the reference value 6, it is possible to adjust the magnitude of sensitivity and specificity when using the I sound average power ratio.

  FIG. 25 illustrates an example of the operation of the heart disease diagnosis unit 133 according to the second embodiment. The heart disease diagnosis unit 133 of this example applies a diagnosis criterion of the presence or absence of heart disease to sound II. In the heart disease diagnosis method according to the second embodiment, the presence or absence of the possibility of heart disease is diagnosed by executing steps S501 to S503.

  The heart disease diagnosis unit 133 sets the diagnostic frequency band 1 and the diagnostic frequency band 2 for the averaged single logarithmic power spectrum of the II sound section calculated by the frequency analysis unit 132 (step S501). . Next, the average value of the power of each frequency bin included in the diagnostic frequency band 1 set in step S501 (hereinafter referred to as “II sound average power 1”) and the diagnostic frequency band 2 set in step S501 The average value of the power of each frequency bin included (hereinafter referred to as “II sound average power 2”) is calculated. Then, a power ratio obtained by dividing the II sound average power 1 by the II sound average power 2 (hereinafter referred to as “II sound average power ratio”) is calculated (step S 502). Finally, the average power ratio of the II sound is compared with the reference value 7 and the reference value 8 to diagnose the possibility of heart disease (step S503). Reference value 7 is a reference for detecting attenuation of II sound, and reference value 8 is a reference for detecting enhancement of II sound. The heart disease diagnosis unit 133 diagnoses that there is a possibility of heart disease, when the average sound power of II sound is 7 or less or 8 or more.

  FIG. 26 shows relative frequency distribution to the average sound power ratio of II sound for each positive and negative example. The relative frequency distribution of this example is calculated with the frequency band 1 for diagnosis from 250 Hz to 400 Hz and the frequency band 2 for diagnosis from 50 Hz to 200 Hz for heart sound data of the same negative example and positive example as described in FIG. .

  FIG. 27 shows the relationship of sensitivity and specificity to reference value 8. The reference value 8 may be set according to the application. If you want to increase both sensitivity and specificity, set reference value 8 at the point where sensitivity and specificity intersect. For example, if the reference value 8 is set to around 0.77, both sensitivity and specificity will be about 70%, and it can be seen that the II sound average power ratio is effective for heart disease diagnosis. In order to increase the specificity, the reference value 8 may be set to a value larger than 0.77, and by changing the magnitude of the reference value 8, the sensitivity at the time of using the II sound average power ratio and The magnitude of specificity can be adjusted.

  FIG. 28 is a graph in which the I sound average power and the II sound average power are plotted in a two-dimensional space. The horizontal axis represents the I sound average power ratio calculated in FIG. 23, and the vertical axis represents the II sound average power ratio calculated in FIG. Also, each plot shows positive examples in triangles and negative examples in circles. It can be seen that the distribution area is different between negative and positive cases.

  FIG. 29 shows an example of a reference function for heart disease determination. The heart disease diagnosis apparatus 1 diagnoses the possibility of heart disease by applying a reference function to a graph in which the I sound average power ratio and the II sound average power ratio are plotted. The reference function is set according to the distribution characteristics of the negative and positive cases. The reference function of this example is indicated by an ellipse in a plot of the I sound average power ratio and the II sound average power ratio. If the heart disease diagnosis unit 133 of this example is plotted in one of the spaces separated by the reference function (for example, outside the ellipse), the heart disease diagnosis unit 133 diagnoses that there is a possibility of heart disease, and the other space (for example, the ellipse). If it is plotted on the inside of), it may be diagnosed that there is no possibility of heart disease.

  The power of sound I and the power of sound II are affected by the skin thickness of the subject, the wearing state of the device for detecting heart sound, and the like. In order to offset these effects, Patent Document 1 determines the power ratio of I sound to II sound and the power ratio of II sound to I sound, and sets a reference value for these power ratios to determine whether or not it is abnormal. It is judged. Moreover, in patent document 2, the power ratio before and behind the heart sound generation time is used.

  However, the power ratio of I sound to II sound and the power ratio of II sound to I sound vary depending on the measurement position. Therefore, when a shift occurs in the measurement position, it may not be possible to correctly determine the presence or absence of heart disease. Further, in a heart disease patient having heart noise, if heart noise is included in the heart sound power calculation section, the power ratio can not be calculated accurately, and there is a possibility that the presence or absence of heart disease can not be determined correctly.

  On the other hand, in the heart disease diagnosis device 1 of this example, in each of the I sound and the II sound, the average power of the frequency band where the power difference between positive and negative examples is large and the power difference between positive and negative examples are small Since the presence or absence of heart disease is determined using the ratio of the average power of the frequency band, heart disease can be diagnosed with high accuracy without being affected by measurement position deviation, heart noise and the like.

  As described above, the heart disease diagnosis apparatus 1 disclosed in the present specification accurately diagnoses the possibility of heart disease with a simple diagnostic criterion from analysis data of a limited frequency band of the subjects I and II sounds. it can. In addition, even when the heart disease diagnosis device 1 is not equipped with a heart artificial valve, the heart disease diagnosis can be performed accurately from the I sound and the II sound. As a result, the heart disease diagnosis device 1 becomes a low-cost heart disease diagnosis device that is useful for mass examinations such as school heart examinations.

  FIG. 30 shows an example of the hardware configuration of the heart disease diagnosis apparatus 1. The heart disease diagnosis apparatus 1 includes an acceleration sensor 1700, an input signal processing circuit 1800, and a computer 1900. The acceleration sensor 1700 functions as a heart sound detection unit 11 that detects the heart sound of the subject as an electrical signal. The input signal processing circuit 1800 includes a filter circuit 1820, an amplification circuit 1840, and an A / D conversion circuit 1860, and functions as the input signal processing unit 12. The filter circuit 1820 removes DC frequency components included in the heart sound signal, high frequency components that may cause aliasing, and high frequency components unnecessary for heart sound analysis. The amplification circuit 1840 amplifies the heart sound signal in accordance with the input range of the A / D conversion circuit 1860. The A / D conversion circuit 1860 converts the heart sound signal amplified by the amplification circuit 1840 into a digital signal. Then, the computer 1900 functions as the heart sound analysis unit 13 and the output unit 14 and performs calculation or processing on the digitized heart sound data.

  FIG. 31 shows an example of a hardware configuration of a computer 1900 according to the present embodiment. The computer 1900 according to this embodiment is connected to the host controller 2082 by the input / output controller 2084 and a CPU peripheral unit having the CPU 2000, the RAM 2020, the graphic controller 2075, and the display device 2080 mutually connected by the host controller 2082. Legacy input / output unit having a communication interface 2030, a hard disk drive 2040, and a CD-ROM drive 2060, a ROM 2010 connected to the input / output controller 2084, a flexible disk drive 2050, and an input / output chip 2070. And

  The host controller 2082 connects the RAM 2020 to the CPU 2000 and the graphic controller 2075 which access the RAM 2020 at a high transfer rate. The CPU 2000 operates based on programs stored in the ROM 2010 and the RAM 2020 to control each part. The graphic controller 2075 acquires image data generated by the CPU 2000 or the like on a frame buffer provided in the RAM 2020 and causes the display device 2080 to display the image data. Instead of this, the graphic controller 2075 may internally include a frame buffer for storing image data generated by the CPU 2000 or the like.

  The input / output controller 2084 connects the host controller 2082 with the communication interface 2030, the hard disk drive 2040, and the CD-ROM drive 2060, which are relatively high-speed input / output devices. The communication interface 2030 communicates with other devices via a network. The hard disk drive 2040 stores programs and data used by the CPU 2000 in the computer 1900. The CD-ROM drive 2060 reads a program or data from the CD-ROM 2095 and provides it to the hard disk drive 2040 via the RAM 2020.

  Further, to the input / output controller 2084, the ROM 2010, the flexible disk drive 2050, and relatively low-speed input / output devices of the input / output chip 2070 are connected. The ROM 2010 stores a boot program executed when the computer 1900 starts up, and / or a program depending on the hardware of the computer 1900, and the like. The flexible disk drive 2050 reads a program or data from the flexible disk 2090 and provides it to the hard disk drive 2040 via the RAM 2020. The input / output chip 2070 connects the flexible disk drive 2050 to the input / output controller 2084 and, for example, inputs / outputs various input / output devices via parallel port, serial port, keyboard port, mouse port, etc. Connect to the controller 2084. The input / output chip 2070 is also connected to the input signal processing circuit 1800.

  The program provided to the hard disk drive 2040 through the RAM 2020 is stored in a recording medium such as the flexible disk 2090, the CD-ROM 2095, or an IC card and provided by the user. The program is read from the recording medium, installed in the hard disk drive 2040 in the computer 1900 via the RAM 2020, and executed by the CPU 2000.

  A program installed in the computer 1900 and causing the computer 1900 to function as a part of the heart disease diagnosis apparatus comprises a heart sound analysis module and an output module. These programs or modules operate the CPU 2000 and the like to cause the computer 1900 to function as part of the heart disease diagnosis apparatus.

  The information processing described in these programs functions as a heart sound analysis unit 13 and an output unit 14 which are specific means in which software and the various hardware resources described above cooperate by being read into the computer 1900. . Then, by realizing calculation or processing of information according to the purpose of use of the computer 1900 in this embodiment by these specific means, as an acceleration sensor 1700 functioning as a heart sound detection unit 11 and as an input signal processing unit 12 In combination with the functional input signal processing circuit 1800, a unique cardiac disease diagnosis device according to the purpose of use is constructed.

  As an example, when communication is performed between the computer 1900 and an external device etc., the CPU 2000 executes the communication program loaded on the RAM 2020, and based on the processing content described in the communication program, the communication interface It instructs communication processing to 2030. Under the control of the CPU 2000, the communication interface 2030 reads out transmission data stored in a transmission buffer area or the like provided on a storage device such as the RAM 2020, the hard disk drive 2040, the flexible disk 2090, or the CD-ROM 2095, to the network. Alternatively, it writes data received or received from the network into a reception buffer area or the like provided on the storage device. As described above, the communication interface 2030 may transfer transmission / reception data to / from the storage device by the DMA (direct memory access) method, and instead, the storage device or communication interface 2030 of the transfer source from the CPU 2000. The transmission / reception data may be transferred by reading the data from the memory and writing the data to the communication interface 2030 or storage device of the transfer destination.

  The CPU 2000 may be all or necessary among files or databases stored in an external storage device such as a hard disk drive 2040, a CD-ROM drive 2060 (CD-ROM 2095), a flexible disk drive 2050 (flexible disk 2090). This part is read into the RAM 2020 by DMA transfer or the like, and various processing is performed on the data on the RAM 2020. Then, the CPU 2000 writes the processed data back to the external storage device by DMA transfer or the like. In such processing, the RAM 2020 can be regarded as temporarily holding the contents of the external storage device, so in the present embodiment, the RAM 2020 and the external storage device are collectively referred to as a memory, a storage unit, or a storage device. Various kinds of information such as various kinds of programs, data, tables, databases, and the like in the present embodiment are stored on such a storage device and become an object of information processing. The CPU 2000 can hold a part of the RAM 2020 in a cache memory, and can read and write on the cache memory. Even in such a mode, since the cache memory bears a part of the function of the RAM 2020, in the present embodiment, the cache memory is also included in the RAM 2020, the memory, and / or the storage device unless otherwise indicated. Do.

  In addition, the CPU 2000 performs various operations described in this embodiment on data read from the RAM 2020 and specified by a program instruction sequence, including various operations, information processing, condition determination, information search / replacement, etc. And write back to the RAM 2020. For example, in the case where the CPU 2000 makes a condition determination, whether the various variables described in the present embodiment satisfy the condition such as greater than, less than, equal to, or less than or equal to other variables or constants. If the condition is satisfied (or not satisfied), the process branches to a different instruction sequence or calls a subroutine.

  The CPU 2000 can also search information stored in a file or database in the storage device. For example, in the case where a plurality of entries in which the attribute value of the second attribute is associated with the attribute value of the first attribute are stored in the storage device, the CPU 2000 can generate a plurality of entries stored in the storage device. Search for an entry that matches the condition for which the attribute value of the first attribute is specified from among them, and by reading out the attribute value of the second attribute stored in the entry, it is associated with the first attribute that satisfies the predetermined condition An attribute value of the second attribute can be obtained.

  In addition, the order of execution of processes such as operations, procedures, steps, and steps in the apparatuses, systems, programs, and methods shown in the claims, the specification, and the drawings is particularly “before”, “ It should be noted that it can be realized in any order, unless it is explicitly stated as "preceding" etc. and the output of the previous process is not used in the later process. With regard to the operation flow in the claims, the specification, and the drawings, even if it is described using “first,” “next,” etc. for convenience, it means that it is essential to carry out in this order. It is not a thing.

  The programs or modules described above may be stored in an external recording medium. As the recording medium, in addition to the flexible disk 2090 and the CD-ROM 2095, an optical recording medium such as DVD or CD, a magneto-optical recording medium such as MO, a tape medium, a semiconductor memory such as an IC card, etc. can be used. Alternatively, a storage device such as a hard disk or a RAM provided in a server system connected to a dedicated communication network or the Internet may be used as a recording medium, and the program may be provided to the computer 1900 via the network.

  As mentioned above, although this invention was demonstrated using embodiment, the technical scope of this invention is not limited to the range as described in the said embodiment. It is apparent to those skilled in the art that various changes or modifications can be added to the above embodiment. It is also apparent from the scope of the claims that the embodiments added with such alterations or improvements can be included in the technical scope of the present invention.

DESCRIPTION OF SYMBOLS 1 ... heart disease diagnostic apparatus, 11 ... heart sound detection part, 12 ... input signal processing part, 13 ... heart sound analysis part, 14 ... output part, 131 ... heart sound section extraction part, 132 ... frequency analysis unit, 133 ... heart disease diagnosis unit, 200 ... heart, 202 ... right ventricle, 204 ... left ventricle, 206 ... right atrium, 208 ... left atrium 210: pulmonary artery valve 212: aortic valve 214: tricuspid valve 216: mitral valve 1700: acceleration sensor 1800: input signal processing circuit 1820. Filter circuit 1840 Amplifier circuit 1860 A / D conversion circuit 1900 Computer 2000 CPU 2010 ROM 2020 RAM 2030 Communication Interface, 2040 ... Hard Disk drive, 2050 ... flexible disk drive, 2060 ... CD-ROM drive, 2070 ... input / output chip, 2075 ... graphic controller, 2080 ... display device, 2082 ... host ... Controller, 2084 ... I / O controller, 2090 ... flexible disk, 2095 ... CD-ROM

Claims (14)

A heart sound detection unit that detects an electrical signal based on heart sounds of a living body;
An input signal processing unit that performs predetermined signal processing on the electrical signal to output heart sound data;
Both sound signals of the I sound signal and the II sound signal are extracted from the heart sound data, and the amplitude and power of the first frequency band between the first frequency and the second frequency higher than the first frequency in the sound signal A heart sound analysis unit for diagnosing heart disease of the living body by comparison based on at least one of them and the first reference value;
Heart disease diagnostic device comprising: The heart sound analysis unit
When at least one of the amplitude and the power of the first frequency band is smaller than the first reference value, the living body is diagnosed as being healthy;
The cardiac disease diagnosis apparatus according to claim 1, wherein when at least one of the amplitude and the power of the first frequency band is larger than the first reference value, it is diagnosed that the living body has a heart disease. A heart sound detection unit that detects an electrical signal based on heart sounds of a living body;
An input signal processing unit that performs predetermined signal processing on the electrical signal to output heart sound data;
A sound signal of at least one of an I sound signal and an II sound signal is extracted from the heart sound data, and a first frequency band between a first frequency of the sound signal and a second frequency higher than the first frequency is extracted A heart sound analysis unit for diagnosing heart disease of the living body by comparison based on at least one of amplitude and power and a first reference value;
Equipped with
The heart sound analysis unit
The living body is healthy when at least one of the amplitude and the power of the first frequency band is smaller than the first reference value and larger than a second reference value smaller than the first reference value. To diagnose
If at least one of the amplitude and the power of the first frequency band is larger than the first reference value or smaller than the second reference value, the living body is diagnosed as having a heart disease
Heart disease diagnostic equipment. The heart sound analysis unit
Extracting both the I sound signal and the II sound signal,
If the two-dimensional plot of the amplitude or power of the I sound signal and the amplitude or power of the II sound signal is within a predetermined region, the living body is diagnosed as healthy.
The cardiac disease diagnosis apparatus according to claim 2 or 3, wherein when the two-dimensional plot is outside the predetermined area, the living body is diagnosed as having a cardiac disease. The heart sound analysis unit
The cardiac disease diagnosis apparatus according to claim 1, wherein the heart disease diagnosis device diagnoses heart disease of the living body further based on at least one of amplitude and power of a second frequency band different from the first frequency band of the sound signal. A heart sound detection unit that detects an electrical signal based on heart sounds of a living body;
An input signal processing unit that performs predetermined signal processing on the electrical signal to output heart sound data;
A sound signal of at least one of an I sound signal and an II sound signal is extracted from the heart sound data, and a first frequency band between a first frequency of the sound signal and a second frequency higher than the first frequency is extracted A heart sound analysis unit for diagnosing heart disease of the living body by comparison based on at least one of amplitude and power and a first reference value;
Equipped with
The heart sound analysis unit
Diagnosing heart disease of the living body based further on at least one of amplitude and power of a second frequency band different from the first frequency band of the sound signal;
The influence of the heart disease on the amplitude or power of the living body in the first frequency band is larger than the influence on the amplitude or power of the living body on the second frequency band
Heart disease diagnostic equipment. The first frequency band is a frequency band higher than the second frequency band,
The heart sound analysis unit
If at least one of an amplitude ratio and a power ratio of the first frequency band to the second frequency band is smaller than a predetermined third reference value, the living body is diagnosed as healthy.
It is diagnosed that the living body has a heart disease when at least one of an amplitude ratio and a power ratio of the first frequency band to the second frequency band is larger than the third reference value. Heart disease diagnostic equipment. The heart sound analysis unit
At least one of an amplitude ratio and a power ratio of the first frequency band to the second frequency band is smaller than a predetermined third reference value, and is smaller than a fourth reference value smaller than the third reference value. And the body is diagnosed as healthy if
The living body has a heart disease when at least one of the amplitude ratio and the power ratio of the first frequency band to the second frequency band is larger than the third reference value or smaller than the fourth reference value. The heart disease diagnosis device according to claim 6 or 7, wherein The heart sound analysis unit
Extracting both the I sound signal and the II sound signal,
If the two-dimensional plot of the amplitude ratio or power ratio of the I sound signal and the amplitude ratio or power ratio of the II sound signal is within a predetermined region, the living body is diagnosed as healthy.
The cardiac disease diagnosis apparatus according to any one of claims 6 to 8, wherein when the two-dimensional plot is outside the predetermined area, the living body is diagnosed as having a cardiac disease. The heart according to any one of claims 1 to 9, wherein the first reference value is a value at which the specificity of a plurality of healthy persons or the sensitivity of a plurality of heart disease patients is between 60% and 90%. Disease diagnosis device. The cardiac disease diagnosis apparatus according to claim 10, wherein the first reference value is a value that matches the specificity of the plurality of healthy persons with the sensitivity of the plurality of cardiac disease patients. The heart disease diagnostic device according to any one of claims 1 to 11, wherein the first frequency band is an arbitrary band between 200 Hz and 1 kHz.   A heart disease diagnostic program which causes a computer to function as the input signal processing unit and the heart sound analysis unit according to any one of claims 1 to 11.   A computer readable medium comprising the heart disease diagnosis program according to claim 13.