JP6333599B2 - Heart noise determination device, program, medium, and heart noise determination method - Google Patents

Description

  The present invention relates to a cardiac noise determination device, a program, a medium, and a cardiac noise determination method.

A technique for determining the type of heart noise included in a heart sound is known (see, for example, Patent Document 1).
Patent Document 1 Japanese Patent Laid-Open No. 2013-34670 Non-Patent Document 1 Toshimi Sawayama, “Auscultation Training by CD <Heart Sound Edition”, Revised Second Edition, Nanedo, February 1994

  In the above-described technique, the shape of the heart noise is determined along the shape described in Non-Patent Document 1 based on the derivative of the volume transition obtained by connecting the differential coefficients of each frame obtained by dividing the heart noise by a predetermined time. ing. For example, in the above-described technique, when 90% or more of the derivative of the heart noise is positive, it is determined as a gradual increase type. However, when the heart noise is determined only by the derivative, there is a problem that the shape of the heart noise cannot be accurately determined.

  In the first aspect of the present invention, a heart sound data acquisition unit that acquires heart noise data of a heart sound of a living body, a power transition calculation unit that calculates a temporal power transition of the heart noise data, and the time series A cardiac noise determination apparatus comprising: a moment calculation unit that calculates a multi-order moment of the power transition from a distribution of power transition; and a determination unit that determines a type of cardiac noise of the living body based on the multi-order moment. , A program, a medium, and a method for determining cardiac noise.

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

1 is an overall configuration diagram of a cardiac noise determination device 10. FIG. 1 is a schematic diagram of a human heart 200. FIG. It is a heart sound waveform. 4 is a flowchart of a determination process performed by the cardiac noise determination device 10. The heart sound data within one heartbeat is shown. The heart sound data which processed the heart sound data of FIG. 5 with the band pass filter are shown. The heart noise data included in the heart sound data is shown. The power spectrum of heart noise is shown. The shape of the heart murmur is shown. The grounds for determining the shape of the heart murmur will be shown. It is the table | surface which linked | related the shape of the heart murmur and the disease name. The shape of the heart murmur is shown. The shape of the heart murmur is shown. The shape of the heart murmur is shown. 2 shows an exemplary hardware configuration of a computer 1900 according to the present embodiment.

  Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. In addition, not all the combinations of features described in the embodiments are essential for the solving means of the invention.

  FIG. 1 is an overall configuration diagram of a heart disease determination system 100. The heart disease determination system 100 determines the type of heart noise included in the heart sound, for example, the shape of the heart noise waveform, and determines whether or not the heart noise is normal. The heart disease determination system 100 includes a heart sound sensor 102, an input signal processing unit 104, a heart noise determination device 10, and a display unit 106.

  The heart sound sensor 102 detects a heart sound vibration that propagates through the chest of the living body BD. The heart sound sensor 102 converts the detected heart sound vibration into heart sound data of an electrical signal. As the heart sound sensor 102, a sensor that can output an electrical signal corresponding to vibration, such as a microphone type, an acceleration sensor type, or a pressure sensor type, can be applied. The heart sound sensor 102 outputs heart sound data to the input signal processing unit 104.

  The input signal processing unit 104 performs predetermined signal processing on the heart sound data detected by the heart sound sensor 102 and outputs the heart sound data to the heart noise determination device 10. For example, the input signal processing unit 104 includes a filter circuit, an amplifier, and an A / D converter. The filter circuit removes DC frequency components included in the heart sound data and frequency components unnecessary for heart sound analysis. The amplifier amplifies the heart sound signal in accordance with the input range of the A / D converter. The A / D converter converts the heart sound data amplified by the amplifier into a digital signal and outputs the digital signal to the heart noise determination device 10.

  An example of the heart noise determination apparatus 10 is a computer that acquires heart sound data from the heart sound sensor 102 via the input signal processing unit 104 and executes signal processing and the like. The heart noise determination device 10 is connected to the heart sound sensor 102, the input signal processing unit 104, and the display unit 106 so as to be able to transmit and receive data. The cardiac noise determination device 10 includes a control unit 12 and a storage unit 14. The heart noise determination device 10 may include a heart sound sensor 102, an input signal processing unit 104, and a display unit 106.

  An example of the control unit 12 is an arithmetic processing device including a CPU (Central Processing Unit) and the like. The control unit 12 includes a heart sound data acquisition unit 20, a power transition calculation unit 22, a moment calculation unit 24, and a determination unit 26. The control unit 12 is configured to function as a heart sound data acquisition unit 20, a power transition calculation unit 22, a moment calculation unit 24, and a determination unit 26 by reading and executing a determination program from the storage unit 14 or the network. May be. Part or all of the heart sound data acquisition unit 20, the power transition calculation unit 22, the moment calculation unit 24, and the determination unit 26 may be configured as hardware such as a circuit.

  The heart sound data acquisition unit 20 acquires heart sound data of a living body, for example, a human heart sound, from the heart sound sensor 102 via the input signal processing unit 104. The heart sound data is data in which the intensity of the heart sound is associated with the time. The heart sound data acquisition unit 20 extracts and acquires heart noise data of heart noise from the acquired heart sound data. The heart sound data acquisition unit 20 outputs the extracted heart noise data to the power transition calculation unit 22. The heart sound data acquisition unit 20 acquires a plurality of heart sound data measured in advance and stored in an external storage device or the like instead of directly acquiring the heart sound data from the heart sound sensor 102 and the input signal processing unit 104. Also good.

  The power transition calculation unit 22 acquires heart noise data from the heart sound data acquisition unit 20. The power transition calculation unit 22 calculates the temporal power transition of the cardiac noise data. For example, the power transition calculation unit 22 calculates a power spectrum that is an example of a power transition of cardiac noise data. The power transition calculation unit 22 outputs the calculated power spectrum to the moment calculation unit 24.

  The moment calculation unit 24 acquires a power spectrum from the power transition calculation unit 22. The moment calculator 24 calculates a multi-order moment of the power spectrum from the power spectrum distribution on the time series. For example, the moment calculator 24 regards the power spectrum as a frequency distribution with each time as a variable, and calculates a multi-order moment. For example, the moment calculator 24 calculates the degree of distortion, which is the third moment of the power spectrum. Alternatively, the moment calculator 24 calculates kurtosis, which is a fourth-order moment of the power spectrum. The moment calculation unit 24 outputs the calculated multi-order moment to the determination unit 26.

  The determination unit 26 acquires a multi-order moment from the moment calculation unit 24. The determination unit 26 determines the type of cardiac noise in the living body based on the multi-order moment. For example, the determination unit 26 determines the waveform shape of the heart noise of the living body based on the third-order moment or the fourth-order moment. The determination unit 26 may determine whether the heart noise of the living body is harmful or harmless from the shape of the heart noise. The determination unit 26 outputs the determination result to the display unit 106 as image information. The determination unit 26 may output the determination result to the storage unit 14 and store it.

  The storage unit 14 stores data necessary for the determination process by the heart sound data acquisition unit 20, the power transition calculation unit 22, the moment calculation unit 24, and the determination unit 26. For example, the storage unit 14 stores a program for determination processing. Further, the storage unit 14 stores a threshold value necessary for executing the program for determination processing. The threshold value may be acquired via a network.

  The display unit 106 displays at least one of an image and a text indicating the determination result based on the image information acquired from the determination unit 26.

  Next, the human heart 200 and heart sounds I and II will be described. FIG. 2 is a schematic view of the human heart 200 as viewed from the front. FIG. 3 shows a heart sound waveform. In FIG. 3, the horizontal axis represents time, and the vertical axis represents intensity. The upper diagram of FIG. 3 shows a heart sound waveform of one heartbeat or more. The lower diagram of FIG. 3 shows the waveform of the heart sound near the II sound.

  As shown in FIG. 2, the human heart 200 includes a right ventricle 202, a left ventricle 204, a right atrium 206, a left atrium 208, a pulmonary valve 210, an aortic valve 212, a tricuspid valve 214, a monk. And a cap valve 216. The pulmonary valve 210 is provided between the right ventricle 202 and the pulmonary artery 218 so as to be opened and closed. The aortic valve 212 is provided between the left ventricle 204 and the aorta 220 so as to be opened and closed. The tricuspid valve 214 is provided between the right ventricle 202 and the right atrium 206 so as to be opened and closed. The mitral valve 216 is provided between the left ventricle 204 and the left atrium 208 so as to be opened and closed.

  As shown in FIG. 3, the heart 200 generates I sound and II sound within one heartbeat. The I sound separates the tricuspid valve 214 that separates the right ventricle 202 and the right atrium 206 from the left ventricle 204 and the left atrium 208 at the start of contraction to send blood of the right ventricle 202 and the left ventricle 204 to the body and lungs. Occurs when the mitral valve 216 closes. The II sound is a pulmonary valve 210 that separates the right ventricle 202 and the pulmonary artery 218 and an aortic valve 212 that separates the left ventricle 204 and the aorta 220 at the start of dilation in which blood is stored in the right ventricle 202 and the left ventricle 204 from the body and lungs. Occurs when and closes.

  Here, because abnormal hemodynamics such as blood regurgitation and turbulence occur inside the heart with diseases such as valve stenosis, insufficiency, and ventricular (atrial) septal defect, I sound and II In addition to the heartbeat of the sound, a heart murmur is heard. Specifically, the heart murmur that occurs during the systole between the I and II sounds is called systolic murmur. In addition, the heart noise that occurs in the diastole between the II sound and the I sound is called diastole heart noise. Note that the cardiac noise occurs not only when the living body is abnormal but also when it is normal. These heart noises are useful judgment materials in diagnosis of heart disease by auscultation. In the auscultation method, heart noise is classified according to four characteristics of time phase, volume, shape, and tone by disease. In the present embodiment, features of cardiac noise data are digitized by multi-order moments to determine the type of cardiac noise.

  FIG. 4 is a flowchart of the determination process performed by the cardiac noise determination apparatus 10. FIG. 5 shows heart sound data within one heartbeat. FIG. 6 shows heart sound data obtained by processing the heart sound data of FIG. 5 using a bandpass filter. FIG. 7 shows cardiac noise data included in the heart sound data. FIG. 8 shows the power spectrum of heart noise. FIG. 9 shows the shape of the heart noise. In FIG. 9, a waveform of a typical example of cardiac noise is shown adjacent to each shape. FIG. 10 shows the basis for determining the shape of the heart noise. FIG. 11 is a table in which the shape of the heart murmur and the disease name are associated with each other. The control unit 12 starts the determination process by reading the determination processing program stored in the storage unit 14.

  In the determination process, the heart sound data acquisition unit 20 acquires heart sound data associating the intensity of the heart sound of the living body with the time from the heart sound sensor 102 and the input signal processing unit 104 as shown in FIG. 5 (S10). For example, the heart sound sensor 102 detects heart sound vibration of the living body with the heart sound sensor 102 of the acceleration sensor and outputs heart sound data converted into an electrical signal to the input signal processing unit 104. The input signal processing unit 104 filters the heart sound data with a bandpass filter that passes a frequency component of 100 Hz to 500 Hz, and then performs sampling processing at 2 kHz and digitization with 16 bits. Thereby, as shown in FIG. 6, the input signal processing unit 104 generates heart sound data in which heart noise of 100 Hz to 500 Hz is emphasized. The heart sound data acquisition unit 20 acquires heart sound data in which heart noise is emphasized from the input signal processing unit 104. Note that the input signal processing unit 104 may appropriately change the order of the filter process, the sampling process, and the digitization process. The heart sound data acquisition unit 20 may execute part or all of the filtering process, the sampling process, and the digitizing process.

  The heart sound data acquisition unit 20 extracts and acquires heart noise data in which heart noise intensity is associated with time from heart sound data (S12). For example, the heart sound data acquisition unit 20 extracts a plurality of maximum points from the heart sound data in which heart noise is emphasized, and extracts the maximum points of the I sound and the II sound from the maximum points. Furthermore, the heart sound data acquisition unit 20 identifies the I sound and the II sound from the difference between the time interval between the I sound and the II sound and the time interval between the II sound and the I sound. The heart sound data acquisition unit 20 extracts at least one heart noise data between the I sound and the II sound and between the II sound and the I sound. As a result, the heart sound data acquisition unit 20 acquires the heart noise data shown in FIG. 7 and outputs it to the power transition calculation unit 22. The heart sound data acquisition unit 20 may acquire heart sound data or heart noise data from an external device via a network.

  The power transition calculation unit 22 calculates a power spectrum as a temporal power transition of heart noise from the heart noise data acquired from the heart sound data acquisition unit 20 (S14). For example, the power transition calculation unit 22 divides the heart noise data by a window having a predetermined time width, and calculates the power of the heart noise from the intensity of the heart sound in the window. The power of heart noise is the square of the intensity of heart sounds. Instead of the heart noise power, the absolute value of the heart noise intensity may be used. Therefore, the power of the heart noise is a positive value. An example of the predetermined time width of the window is 30 milliseconds. The power transition calculation unit 22 generates a power spectrum by calculating the sum of power in each time for each window and arranging them in time series. Thereby, the power transition calculation unit 22 calculates the power spectrum shown in FIG. 8 and outputs it to the moment calculation unit 24.

The moment calculation unit 24 calculates a multi-order moment of the power spectrum from the power spectrum distribution on the time series (S16). For example, the moment calculation unit 24 regards the power spectrum as a frequency distribution with each time as a variable, and calculates a skewness γ that is a third-order moment and a kurtosis β that is a fourth-order moment. Specifically, the moment calculator 24 calculates the skewness γ from the following equation (1).
E is an expected value. X is a random variable, that is, time. μ is an expected value of the random variable X. μ _n is the nth moment around the expected value. σ is a standard deviation. κ _r is an r th order cumulant.

Next, the moment calculator 24 calculates the kurtosis β from the following equation (2). In addition, Formula (2) is a case where the kurtosis of normal distribution is set to 0.
The moment calculating unit 24 outputs the calculated multi-order moments skewness γ and kurtosis β to the determining unit 26.

  The determination unit 26 determines the type of cardiac noise of the living body based on the multi-order moment acquired from the moment calculation unit 24 (S18). An example of the type of biological heart noise is represented by the type of shape in the temporal waveform of the cardiac noise. As shown in FIG. 9, the shape of the heart noise can be roughly classified into a gradually increasing type, a gradually decreasing type, a pointed type, a diamond type, a normal distribution type, a plateau type (that is, a uniform amplitude type), and the like. The gradually increasing type is a type in which a peak exists in the latter half of the power spectrum. The gradual reduction type is a type in which a peak exists in the first half of the power spectrum. The diamond type is a type in which the waveform of the heart noise is approximately a diamond shape. The pointed type is a type having a sharper point than the diamond type. The plateau type is a flat type with a sharper point than the diamond type. The diamond type and the normal distribution type are examples of a gradually increasing and decreasing type. The determination unit 26 may acquire each threshold value for classifying the measured heart noise into any shape from the storage unit 14 or may be acquired from a network. For example, the determination unit 26 determines whether the shape of the heart noise is a gradual increase type, a gradual decrease type, or another type based on the skewness γ that is a third moment. Further, the determination unit 26 determines whether the shape of the heart noise is a diamond type, a pointed type, a plateau type, or another type based on the kurtosis β that is a fourth-order moment. To do.

  When the skewness γ is larger than the threshold for gradual decrease, the determination unit 26 determines the shape of the heart noise as the gradual decrease type shown on the right side of FIG. The determination unit 26 may determine that the shape of the heart noise is a gradual decrease type when the kurtosis β is substantially 0 and the skewness γ is larger than the threshold for gradual decrease. The gradual decrease threshold is a positive value. This determination is based on the tendency that the gradual decrease type has a strong tendency to become positive as shown in the upper right of FIG.

  For example, when the skewness γ is smaller than the threshold for gradual increase, the determination unit 26 determines the shape of the heart noise as the gradual increase type shown on the left side of FIG. The determination unit 26 may determine that the shape of the heart noise is a gradual increase type when the kurtosis β is substantially 0 and the skewness γ is smaller than the gradual increase threshold. The threshold for gradual increase is a negative value. This determination is based on the fact that the gradual increase type has a strong tendency for the skewness γ to become negative, as shown in the upper left of FIG.

  When the skewness γ is equal to or less than the threshold for gradual decrease and equal to or greater than the threshold for gradual increase, the determination unit 26 determines that the shape of the heart noise is a diamond shape shown in the center of FIG. The determination unit 26 may determine that the shape of the heart noise is a diamond shape when the kurtosis β is approximately 0 and the skewness γ is equal to or less than the threshold for gradual decrease and equal to or greater than the threshold for gradual increase. This determination is based on the fact that the diamond type has a strong tendency for both the skewness γ and the kurtosis β to be substantially zero as shown in the lower left of FIG.

  Further, when the kurtosis β is smaller than the plateau threshold, the determination unit 26 determines that the shape of the heart noise is a flat plateau type shown on the lower side of FIG. Note that the determination unit 26 may determine that the shape of the cardiac noise is a plateau type when the skewness γ is approximately 0 and the kurtosis β is smaller than the plateau threshold. The plateau threshold is a negative value. This determination is based on the fact that the plateau type has a strong tendency for the kurtosis β to become negative, as shown in the lower right of FIG.

  When the kurtosis β is larger than the cusp threshold, the determination unit 26 determines that the shape of the heart noise is a pointed cusp type shown on the upper side of FIG. Note that the determination unit 26 may determine that the shape of the heart noise is a cusp type when the skewness γ is substantially 0 and the kurtosis β is larger than the cusp threshold. The cusp threshold is a positive value.

  When the standard deviation σ is 1 and the kurtosis β is equal to or greater than the plateau threshold and equal to or less than the cusp threshold, the determination unit 26 determines that the shape of the heart noise is a normal distribution type.

  The determination unit 26 may further determine a disease name from the determined heart noise shape. For example, as shown in FIG. 11, when the shape of the cardiac noise during systole is any one of a gradually increasing type, a gradually decreasing type, and a plateau type, the determination unit 26 performs a reflux mitral regurgitation, a tricuspid valve. It is determined that the patient has either a regurgitation or a ventricular septal defect. Further, the determination unit 26 determines that the aortic valve insufficiency or pulmonary valve insufficiency is obtained when the shape of the diastolic heart noise is a gradual decrease type or a diamond type.

  The determination unit 26 converts the determined determination result into image information and text and outputs the image information and text to the display unit 106, and outputs and stores the determination result to the storage unit 14 (S20). Note that the determination unit 26 may output all of a plurality of possible shapes and disease names to the display unit 106 as determination results without specifying the shape of the heart noise and the disease name as one.

  As described above, since the cardiac noise determination device 10 determines the shape of the cardiac noise based on the multi-order moment, the accuracy can be improved. The heart noise determination device 10 can also determine the local smoothness and sharpness of the waveform of the heart noise based on the skewness γ of the third-order moment and the kurtosis β of the fourth-order moment, which are higher-order statistics. .

  Next, the comparison form in which the shape of the heart noise is determined by the derivative is compared with the present embodiment, and the improvement in accuracy of the determination of the shape of the heart noise by the heart noise determination device 10 of the present embodiment will be described. FIGS. 12, 13, and 14 show the shape of the power spectrum of heart noise.

  The heart noise derivative having the shape shown in the left diagram of FIG. 12 and the heart noise derivative having the shape shown in the right diagram both have substantially the same positive / negative ratio, and the number of zero crossings is also substantially the same. Therefore, in the comparison form based on the derivative, the difference in the shape of the left and right heart noises cannot be determined. On the other hand, in the cardiac noise determination device 10 of the present embodiment, the kurtosis β of the heart noise shape shown in the right figure is larger than the kurtosis β of the heart noise shape shown in the left figure. Therefore, the cardiac noise determination device 10 can determine, for example, the shape of the left figure as a diamond-type or normal distribution type heart noise, and can determine the shape of the right figure as a cusp-shaped heart noise. Furthermore, the cardiac noise determination apparatus 10 can determine the degree of sharpness according to the magnitude of the kurtosis β.

  The heart noise derivative shown in the left diagram of FIG. 13 and the heart noise derivative shown in the right diagram both have approximately the same positive / negative ratio, and the number of zero crossings is also substantially the same. Therefore, in the comparison form based on the derivative, the difference in the shape of the left and right heart noises cannot be determined. On the other hand, in the cardiac noise determination device 10 of the present embodiment, the skewness γ of the heart noise shape shown in the right figure is larger than the skewness γ of the heart noise shape shown in the left hand figure. Accordingly, the cardiac noise determination device 10 can determine, for example, the shape of the left figure as gradually increasing and gradually decreasing heart noise, the right figure as the gradually increasing heart noise, and the shape of the left figure as It can be determined as a gradually decreasing type. Furthermore, the cardiac noise determination device 10 determines the degree of distortion according to the magnitude of the degree of distortion γ, and determines whether the peak of the cardiac noise is temporally close to the I sound or the II sound. be able to.

  Since the derivative of the heart noise having the shape shown in the left diagram of FIG. 14 repeats minute increases and decreases at the center, the number of zero crossings increases. Further, since the derivative of the cardiac noise shown in the right figure repeats minute increase / decrease due to noise or the like in the latter half of the cardiac noise, the number of zero crossings increases (for example, 3 times or more). Accordingly, the left and right diagrams in FIG. 14 are determined to be plateau types because the number of zero crossings of the derivative increases. On the other hand, in the cardiac noise determination device 10 of the present embodiment, the kurtosis β is small in the left figure, so it is determined as a plateau type, and the kurtosis β is large in the right figure, so it can be determined as a diamond type or a pointed type. . Thereby, the cardiac noise determination apparatus 10 is robust against a small unevenness of a part of the cardiac noise caused by noise or the like, and can accurately determine the shape of the cardiac noise.

  The functions, numerical values, connection relationships, and the like of the components of the above-described embodiments may be changed as appropriate.

  The determination method of the determination unit 26 may be changed as appropriate. For example, the determination unit 26 may harmful the heart noise in response to the skewness γ being larger than a predetermined first threshold and the kurtosis β being larger than a predetermined second threshold. Otherwise, the heart noise may be determined as harmless. Furthermore, when the determination unit 26 determines that the shape of the heart noise is harmful, the determination unit 26 may determine the disease name based on FIG.

  Further, the determination unit 26 may determine the type of cardiac noise based on the standard deviation σ that is a second moment. For example, when the standard deviation σ is larger than the standard deviation threshold, the determination unit 26 may determine that the type of cardiac noise is harmful.

  FIG. 15 shows an example of a hardware configuration of a computer 1900 according to this embodiment. A computer 1900 according to the present embodiment is an example of the cardiac noise determination device 10. The computer 1900 includes a CPU peripheral unit having a CPU 2000, a RAM 2020, a graphic controller 2075, and a display unit 2080 that are connected to each other by a host controller 2082, and a communication interface 2030 that is connected to the host controller 2082 by an input / output controller 2084. And an input / output unit having a hard disk drive 2040 and a legacy input / output unit having a ROM 2010, a memory drive 2050 and an input / output chip 2070 connected to the input / output controller 2084.

  The host controller 2082 connects the RAM 2020 to the CPU 2000 and the graphic controller 2075 that 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 and controls each unit. 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 displays it on the display unit 2080. Instead of this, the graphic controller 2075 may 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 to the communication interface 2030 and the hard disk drive 2040 that 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 such as a display program used by the CPU 2000 in the computer 1900.

  The input / output controller 2084 is connected to the ROM 2010, the memory drive 2050, and the relatively low-speed input / output device of the input / output chip 2070. The ROM 2010 stores a boot program that the computer 1900 executes at startup and / or a program that depends on the hardware of the computer 1900. The memory drive 2050 reads a program or data such as a display program from the memory card 2090 and provides it to the hard disk drive 2040 via the RAM 2020. The input / output chip 2070 connects the memory drive 2050 to the input / output controller 2084, and also connects various input / output devices to the input / output controller 2084 via, for example, a parallel port, a serial port, a keyboard port, a mouse port, and the like. Connect to.

  A program provided to the hard disk drive 2040 via the RAM 2020 is stored in a recording medium such as a memory card 2090 or an IC card and provided by a user. A program such as a display program is read from a 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 the heart noise determination device 10 includes a heart sound data acquisition module, a power transition calculation module, a moment calculation module, and a determination module. These programs or modules work with the CPU 2000 or the like to cause the computer 1900 to function as a heart sound data acquisition module, a power transition calculation module, a moment calculation module, and a determination module.

  The information processing described in these programs is read by the computer 1900, whereby the heart sound data acquisition module, the power transition calculation module, the moment, which are specific means in which the software and the various hardware resources described above cooperate with each other. It functions as a calculation module and a determination module. And the specific cardiac noise determination apparatus 10 according to the intended use is constructed | assembled by implement | achieving the calculation or processing of the information according to the intended use of the computer 1900 in this embodiment by these specific means.

  As an example, when communication is performed between the computer 1900 and an external device or the like, the CPU 2000 executes a communication program loaded on the RAM 2020 and executes a communication interface based on the processing content described in the communication program. A communication process is instructed to 2030. Under the control of the CPU 2000, the communication interface 2030 reads 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, or the memory card 2090, and transmits it to the network. The reception data received from the network is written 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 a DMA (direct memory access) method. Instead, the CPU 2000 transfers the storage device or the communication interface 2030 as a transfer source. The transmission / reception data may be transferred by reading the data from the data and writing the data to the communication interface 2030 or the storage device of the transfer destination.

  Further, the CPU 2000 causes the RAM 2020 to read all or necessary portions from the files or databases stored in the external storage device such as the hard disk drive 2040 and the memory drive 2050 (memory card 2090) into the RAM 2020 by DMA transfer or the like. Various processes are performed on the data on the RAM 2020. Then, CPU 2000 writes the processed data back to the external storage device by DMA transfer or the like. In such processing, since the RAM 2020 can be regarded as temporarily holding the contents of the external storage device, 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 types of information such as various programs, data, tables, and databases in the present embodiment are stored on such a storage device and are subjected to information processing. Note that the CPU 2000 can also store a part of the RAM 2020 in the cache memory and perform reading and writing on the cache memory. Even in such a form, the cache memory bears a part of the function of the RAM 2020. Therefore, in the present embodiment, the cache memory is also included in the RAM 2020, the memory, and / or the storage device unless otherwise indicated. To do.

  In addition, the CPU 2000 performs various operations, such as various operations, information processing, condition determination, information search / replacement, etc., described in the present embodiment, specified for the data read from the RAM 2020 by the instruction sequence of the program. Is written back to the RAM 2020. For example, when performing the condition determination, the CPU 2000 determines whether the various variables shown in the present embodiment satisfy the conditions such as large, small, above, below, equal, etc., compared to other variables or constants. When the condition is satisfied (or not satisfied), the program branches to a different instruction sequence or calls a subroutine. Further, the CPU 2000 can search for information stored in a file or database in the storage device.

  The program or module shown above may be stored in an external recording medium. As the recording medium, in addition to the memory card 2090, 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, or the like can be used. Further, a storage device such as a hard disk or 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 will be apparent to those skilled in the art that various modifications or improvements can be added to the above-described embodiment. It is apparent from the scope of the claims that the embodiments added with such changes or improvements can be included in the technical scope of the present invention.

  The order of execution of each process such as operations, procedures, steps, and stages in the apparatus, system, program, and method shown in the claims, the description, and the drawings is particularly “before” or “prior to”. It should be noted that the output can be realized in any order unless the output of the previous process is used in the subsequent process. Regarding the operation flow in the claims, the description, 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.

  DESCRIPTION OF SYMBOLS 10 Heart noise determination apparatus, 12 Control part, 14 Storage part, 20 Heart sound data acquisition part, 22 Power transition calculation part, 24 Moment calculation part, 26 Determination part, 100 Heart disease determination system, 102 Heart sound sensor, 104 Input signal processing part , 106 display, 200 heart, 202 right ventricle, 204 left ventricle, 206 right atrium, 208 left atrium, 210 pulmonary valve, 212 aortic valve, 214 tricuspid valve, 216 mitral valve, 218 pulmonary artery, 220 aorta, 1900 computer 2000 CPU, 2010 ROM, 2020 RAM, 2030 communication interface, 2040 hard disk drive Bed, 2050 memory drive, 2070 output chip, 2075 graphic controller, 2080 display portion, 2082 host controller 2084 output controller, 2090 a memory card

Claims (9)

A heart sound data acquisition unit for acquiring heart noise data of a heart sound of a living body;
A power transition calculating unit for calculating temporal power transition of the cardiac noise data;
A moment calculation unit for calculating a multi-order moment of the power transition from the distribution of the power transition on the time series;
A determination unit for determining a type of cardiac noise of the living body based on the multi-order moment;
A cardiac noise determination apparatus comprising: The moment calculation unit calculates a third moment of the power transition,
The cardiac noise determination device according to claim 1, wherein the determination unit determines the shape of the cardiac noise based on the third-order moment.   The cardiac noise determination device according to claim 2, wherein the determination unit determines whether the shape of the cardiac noise is a gradually increasing type, a gradually decreasing type, or another type based on the third-order moment. . The moment calculation unit calculates a fourth moment of the power transition,
The cardiac noise determination apparatus according to claim 1, wherein the determination unit determines the shape of the cardiac noise based on the fourth-order moment. The heart noise determination according to claim 4, wherein the determination unit determines whether the shape of the heart noise is a pointed type, a plateau type, or another type based on the fourth-order moment. apparatus. The moment calculation unit calculates a third moment and a fourth moment of the power transition,
The determination unit determines that the cardiac noise is harmful in response to the third-order moment being greater than a first threshold value and the fourth-order moment being greater than a second threshold value. In any other case, the heart noise determination device according to any one of claims 1 to 5, wherein the heart noise is determined to be harmless. A step of calculating a temporal power transition of heart noise data of a heart sound of a living body;
A computer calculating a multi-order moment of the power transition from the distribution of the power transition on a time series;
Computer, wherein the multi-order based on the moment, and a determining a type of heart murmurs of the biological, heart murmur determination method by a computer. Calculating a temporal power transition of heart noise data of a heart sound of a living body,
Calculating a multi-order moment of the power transition from the distribution of the power transition on a time series;
Determining a type of cardiac noise of the living body based on the multi-order moment;
A program that causes a computer to execute. A medium for storing the program according to claim 8.