Respiratory sound determination device, respiratory sound determination program, and respiratory sound determination system

Abstract

To provide a respiratory sound determination device for detecting abnormal respiration caused by an event such as a meal.SOLUTION: A respiratory sound determination device 20 determines a respiratory sound in an acoustic signal SS received from the outside. The respiratory sound determination device 20 includes a display device 26. The respiratory sound determination device 20 performs a first determination process when the start instruction is made, and performs a second determination process when the end instruction is made after the start instruction is made. The respiratory sound determination device 20 displays, on a display device 26, a first determination result indicating whether the respiratory sound in a first predetermined period is normal or abnormal in the first determination process, The respiratory sound determination device 20 displays, on the display device 26, a second determination result indicating whether the respiratory sound in a second predetermined period is normal or abnormal in the second determination process.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a breath sound detection device that detects abnormal breathing caused by an event such as a meal. [Background technology]

[0002] For example, Patent Document 1 discloses a respiratory sound analysis system that detects abnormal breathing caused by aspiration or the like that occurs while sleeping.

[0003] The respiratory sound analysis system of Patent Document 1 includes a respiratory sound analyzer (breath sound determination device), a microphone, and a respiratory band sensor. The microphone and respiratory band sensor are worn by a sleeping subject. Specifically, the microphone is attached to the subject's throat, and the respiratory band sensor is wrapped around the subject's chest. The microphone converts collected sound into an electrical signal (acoustic signal) and transmits it to the respiratory sound determination device. The respiratory band sensor converts the subject's chest movement into an electrical signal (motion signal) and transmits it to the respiratory sound determination device. The respiratory sound determination device continues to extract the subject's respiratory sounds based on the received acoustic signal and motion signal. The respiratory sound determination device detects abnormal breathing by comparing the extracted multiple respiratory sounds using a predetermined algorithm. The detection results are displayed on a display device of the respiratory sound determination device.

[0004] The breath sound detection device of Patent Document 1 can detect abnormal breathing of a subject caused by events such as saliva entering the larynx. A caregiver for the subject can notice abnormal breathing of the subject on the display screen without having to be present with the sleeping subject. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2012-205693 A Summary of the Invention [Problem to be solved by the invention]

[0006] Abnormal breathing occurs not only during sleep but also due to various events. For example, abnormal breathing occurs when a foreign object remains in the respiratory tract due to eating. Furthermore, for example, the frequency and depth of breathing change due to exercise, bathing, or taking medication such as an asthma inhaler, causing abnormal breathing to occur or disappear. In other words, the presence or absence of abnormal breathing can change due to various events such as eating, exercise, bathing, and taking medication. Abnormal breathing may indicate an abnormality in the respiratory tract. Particularly in an aging society, there is a demand for easy detection of abnormal breathing caused by various events.

[0007] Therefore, an object of the present invention is to provide a breath sound detection device that detects abnormal breathing caused by an event such as eating. [Means for solving the problem]

[0008] The present invention provides a first respiratory sound determination device, A respiratory sound determination device for determining respiratory sounds in an acoustic signal received from an external device, comprising: The respiratory sound determination device includes a display device, The breath sound determination device performs a first determination process when instructed to start, and performs a second determination process when instructed to stop after being instructed to start, In the first determination process, the breath sound determination device displays a first determination result indicating whether the breath sounds in a first predetermined period are normal or abnormal on the display device; In the second determination process, the breath sound determination device displays, on the display device, a second determination result indicating whether the breath sounds in a second predetermined period are normal or abnormal. A breath sound determination device is provided.

[0009] The present invention provides a second respiratory sound determination device, which is the first respiratory sound determination device, After performing the second determination process, the respiratory sound determination device transmits the first determination result and the second determination result to a management device different from the respiratory sound determination device, depending on a combination of the first determination result and the second determination result. A breath sound determination device is provided.

[0010] The present invention provides a third respiratory sound determination device, which is the first respiratory sound determination device, the respiratory sound determination device is a mobile terminal, The display device is a screen of the mobile terminal. A breath sound determination device is provided.

[0011] The present invention provides a fourth respiratory sound determination device, which is any one of the first to third respiratory sound determination devices, When the breath sound determination device is unable to acquire the breath sound for a certain period of time after performing the first determination process and before receiving an instruction to terminate the process, the breath sound determination device displays information indicating that the breath sound cannot be acquired on the display device. A breath sound determination device is provided.

[0012] The present invention provides a fifth respiratory sound determination device, which is any one of the first to third respiratory sound determination devices, The respiratory sound determination device can perform the first determination process on the respiratory sounds in two or more of the acoustic signals whose first predetermined periods overlap each other, and can perform the second determination process on the respiratory sounds in two or more of the acoustic signals whose second predetermined periods overlap each other. A breath sound determination device is provided.

[0013] The present invention provides a first respiratory sound determination program for causing a mobile terminal to function as any one of the first to third respiratory sound determination devices. Provides a breath sound assessment program.

[0014] The present invention provides a first respiratory sound determination system including any one of first to third respiratory sound determination devices and two or more acoustic sensors, When each of the acoustic sensors starts operating, it collects surrounding sounds, converts them into acoustic signals, and transmits them to the outside. The respiratory sound determination device receives the acoustic signals transmitted by two or more of the acoustic sensors. A breath sound determination system is provided.

[0015] The present invention provides a first monitoring method for monitoring two or more subjects using a first breath sound determination system, comprising: The subject is respectively fitted with the acoustic sensor, Before all of the subjects perform a predetermined event, the acoustic sensor is started and a start instruction is given to the respiratory sound determination device; After all of the subjects have performed a predetermined event, an end instruction is given to the respiratory sound determination device. Provide a way to monitor.

[0016] The present invention provides a first acoustic sensor, An acoustic sensor having a sensor function of collecting sound and converting it into an acoustic signal, which is an electrical signal, and a transmission function of transmitting the acoustic signal, The acoustic sensor includes a sensor body and a base member, The sensor body has a contact portion, the contact portion protrudes downward from a bottom surface of the sensor body in a vertical direction and has a ring shape in a horizontal plane perpendicular to the vertical direction, The sensor body has a recess formed therein, the recess is recessed upward from the lower surface of the sensor body and is surrounded by the contact portion in the horizontal plane; A sound collection sheet is provided above the recess, A passage hole is formed in the base member, The sensor body is attached to the base member so that the contact portion passes through the through hole. An acoustic sensor is provided. [Effects of the Invention]

[0017] The breath sound determination device of the present invention can display two determination results: a first determination result for a first predetermined period and a second determination result for a second predetermined period after the first predetermined period. Therefore, by issuing a start instruction before an event such as a meal and an end instruction after the event, the determination results before and after the event can be compared. More specifically, if the determination result before the subject's meal is normal and the determination result after the subject's meal is abnormal, it can be determined that abnormal breathing occurred due to eating. For example, it can be determined that a foreign object caused by eating may remain in the upper respiratory tract of the subject. In other words, the present invention can provide a breath sound determination device that detects abnormal breathing caused by an event such as eating. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a diagram illustrating a respiratory sound determination system according to an embodiment of the present invention. [Figure 2] 2 is a perspective view showing an acoustic sensor of the breath sound determination system of FIG. 1. The position of a lamp housed inside the sensor body is drawn with a dashed line. [Figure 3] 3 is an exploded perspective view showing the acoustic sensor of Fig. 2. The position of the lamp is drawn with a dashed line. [Figure 4] 4 is a bottom view showing the sensor body of the acoustic sensor of FIG. 3. FIG. [Figure 5] FIG. 4 is a front view showing the sensor body of the acoustic sensor of FIG. 3. A portion of the outline of the base member is drawn with a dashed line. A portion of the acoustic sensor (the portion surrounded by a dashed line) is drawn in an enlarged view. In the enlarged view, the outline of a hidden recess is drawn with a two-dot chain line. [Figure 6] 2 is a block diagram showing the configuration of a respiratory sound determination device of the respiratory sound determination system of FIG. 1. FIG. [Figure 7] 7 is a diagram showing the structure of acoustic data stored in an auxiliary storage device of the respiratory sound determination device of FIG. 6. FIG. [Figure 8] 7 is a diagram showing timings at which the respiratory sound determination device of FIG. 6 determines a respiratory sound. [Figure 9]7 is a flowchart showing a control process of a breath sound determination program of the breath sound determination device of FIG. 6. [Figure 10] 10 is a flowchart showing an acoustic signal storage process of the breath sound determination program of FIG. 9. [Figure 11] 10 is a flowchart showing a first determination process of the breath sound determination program of FIG. 9. [Figure 12] 10 is a flowchart showing a second determination process of the breath sound determination program of FIG. 9. [Figure 13] 13 is a diagram illustrating the input / output layer of the anomaly determination model of FIG. 11 and FIG. 12. FIG. [Figure 14] FIG. 14 is a diagram illustrating an example of a convolutional network of the anomaly determination model of FIG. 13. [Figure 15] FIG. 13 is a diagram illustrating an example of a method for generating the anomaly determination model of FIGS. 11 and 12. [Figure 16] FIG. 2 is a diagram showing a modified example of the respiratory sound determination system of FIG. [Figure 17] FIG. 17 is a diagram showing timings at which the breath sound determination system of FIG. 16 determines breath sounds. DETAILED DESCRIPTION OF THE INVENTION

[0019] Referring to FIG. 1, a breath sound determination system 10 according to an embodiment of the present invention is a system for determining whether the breath sounds of a subject 70 are normal or abnormal. The breath sound determination system 10 of this embodiment is used in a nursing home. The subject 70 of this embodiment is an elderly person residing in the nursing home. However, the present invention is not limited to this and can be applied in various ways. For example, the breath sound determination system 10 may be used in a sports gym or in an ordinary home. For example, the breath sound determination system 10 may be used for home nursing in an ordinary home.

[0020] The respiratory sound determination system 10 of this embodiment includes a respiratory sound determination device 20, a management device 40, and an acoustic sensor 60.

[0021] The acoustic sensor 60 is a small electronic device that can be attached to and detached from the subject 70. More specifically, the acoustic sensor 60 can be attached to the skin of the throat of the subject 70. The acoustic sensor 60 includes various electronic components such as a microphone (not shown). The microphone of the acoustic sensor 60 collects sounds such as breathing sounds generated in the airway of the subject 70 and converts them into an acoustic signal SS, which is an electrical signal. The acoustic sensor 60 of this embodiment transmits the acoustic signal SS via short-range wireless communication such as Bluetooth (registered trademark).

[0022] As described above, the acoustic sensor 60 of this embodiment has a sensor function of collecting sound and converting it into an acoustic signal SS, and a transmission function of transmitting the acoustic signal SS via short-distance wireless communication. However, the present invention is not limited to this. For example, the acoustic sensor 60 may have other functions in addition to the sensor function and the transmission function. The acoustic sensor 60 may transmit the acoustic signal SS via wireless communication other than short-distance wireless communication, or may transmit it via a wired communication cable.

[0023] In the present embodiment, the respiratory sound determination device 20 and the management device 40 are each a mobile terminal such as a smartphone. The respiratory sound determination device 20 and the management device 40 are each easily portable. However, the present invention is not limited to this. For example, at least one of the respiratory sound determination device 20 and the management device 40 may be a portable personal computer (PC) or a desktop PC.

[0024] The respiratory sound determination device 20 is capable of receiving the acoustic signal SS. More specifically, the respiratory sound determination device 20 of this embodiment is paired with the acoustic sensor 60 and is located at a distance where it can receive the acoustic signal SS. However, the present invention is not limited to this. For example, if the acoustic signal SS is transmitted in a wired manner via a communication cable, the respiratory sound determination device 20 may be connected to the communication cable.

[0025] The respiratory sound determination device 20 can transmit various data to the management device 40. The management device 40 can receive data transmitted by the respiratory sound determination device 20. The method of transmission and reception between the respiratory sound determination device 20 and the management device 40 is not particularly limited.

[0026] The respiratory sound determination device 20 determines the respiratory sounds in the acoustic signal SS received from the outside. Specifically, the respiratory sound determination device 20 performs two determination processes: a first determination process and a second determination process following the first determination process. In each of the first determination process and the second determination process, the respiratory sound determination device 20 determines whether the respiratory sounds of the subject 70 included in the received acoustic signal SS are normal or abnormal, and displays the results. The respiratory sound determination device 20 also transmits the determination results of the first determination process and the second determination process to the management device 40.

[0027] In this embodiment, the breath sound determination device 20 is operated by a caregiver at a nursing facility, and the management device 40 is operated by an administrator of the nursing facility. For example, the breath sound determination device 20 determines the breath sounds of the subject 70 before a meal in a first determination process, and determines the breath sounds of the subject 70 after a meal in a second determination process. For example, if the breath sounds before a meal are normal and the breath sounds after a meal are abnormal, the caregiver and administrator can know that the abnormal breathing is caused by eating, and can thereby provide appropriate care to the subject 70. For example, the caregiver can have the subject 70 gargle to remove foreign objects from the subject's 70's respiratory tract. In addition, the administrator can consider whether or not to change the subject's 70's diet.

[0028] As described above, the operators of the respiratory sound determination device 20 and the management device 40 in this embodiment are the caregiver and the manager of the nursing facility, respectively. However, the present invention is not limited to this, and the operators of the respiratory sound determination device 20 and the management device 40 may differ depending on the application of the respiratory sound determination device 20. For example, when the respiratory sound determination system 10 is used in an ordinary home, a family member of the subject 70 may operate the respiratory sound determination device 20, or a staff member of a nursing facility located in a remote location may operate the management device 40.

[0029] The respiratory sound determination system 10 shown in FIG. 1 includes one respiratory sound determination device 20, one management device 40, and one acoustic sensor 60. However, the present invention is not limited to this. For example, the respiratory sound determination system 10 may further include another device in addition to the above-mentioned devices. The respiratory sound determination system 10 may include two or more respiratory sound determination devices 20 and two or more acoustic sensors 60. Furthermore, the respiratory sound determination system 10 does not necessarily have to include the management device 40.

[0030] The acoustic sensor 60 of this embodiment will be described below.

[0031] 2 and 3, the acoustic sensor 60 of this embodiment includes a sensor body 62 and a base member 67. The sensor body 62 is a member that performs the sensor function and transmission function of the acoustic sensor 60. The base member 67 is attached to the skin of the throat of a subject 70 (see FIG. 1).

[0032] 3 to 5, the sensor main body 62 of this embodiment has a thin, rectangular, flat plate shape. Specifically, the size of the sensor main body 62 in the front-to-rear direction (X direction) is approximately 45 mm, and the size of the sensor main body 62 in the lateral direction (Y direction) perpendicular to the front-to-rear direction is approximately 35 mm. The size of the sensor main body 62 in the up-down direction (Z direction) perpendicular to both the front-to-rear and lateral directions is approximately 8.5 mm. Terms such as up-down direction do not indicate an absolute positional relationship with respect to the ground, but merely indicate a relative positional relationship when the portion of the surface of the sensor main body 62 that faces the skin of the subject 70 (see FIG. 1) is defined as the bottom surface.

[0033] The sensor main body 62 of this embodiment has a switch 63, a lamp 64, a connector 65, and a contact portion 66, in addition to various electronic components such as a microphone (not shown) housed inside the sensor main body 62. Furthermore, four locked portions 624 are formed on the upper surface (surface on the +Z side) of the sensor main body 62, and a recess 662 is formed on the lower surface (surface on the -Z side) of the sensor main body 62.

[0034] Referring to Figure 3, switch 63 is a power switch for sensor body 62. Pressing switch 63 turns it on, and pressing it again turns it off. Sensor body 62 operates when switch 63 is on. Lamp 64 is housed inside sensor body 62 and lights up when sensor body 62 is operating. When lit, lamp 64 emits light above sensor body 62 through a translucent member. Connector 65 is used when charging sensor body 62.

[0035] 2 together with FIG. 1, the switch 63 and lamp 64 of this embodiment are also used when pairing the respiratory sound determination device 20 with the acoustic sensor 60. More specifically, when the switch 63 is pressed and held for about 5 to 7 seconds, the acoustic sensor 60 enters a standby state, and the lamp 64 flashes blue and red. When pairing is complete, the acoustic sensor 60 enters a usable state, and the lamp 64 lights up red. However, the present invention is not limited to this. For example, the conditions under which the lamp 64 lights up or flashes, and the color of the lamp 64, can be changed as needed.

[0036] 4 and 5, the contact portion 66 protrudes downward from the lower surface of the sensor main body 62 in the vertical direction and has a ring shape in a horizontal plane (XY plane) perpendicular to the vertical direction. The contact portion 66 in this embodiment has a continuous circular ring shape in the horizontal plane. However, the present invention is not limited to this. For example, the contact portion 66 may have a circular ring shape with a gap in the horizontal plane, or may have a rectangular ring shape.

[0037] The recess 662 is recessed upward from the lower surface of the sensor main body 62 and is surrounded by the contact portion 66 in the horizontal plane. A sound collection sheet 664 is provided above the recess 662. The sound collection sheet 664 vibrates when exposed to sound. The sound collection sheet 664 of this embodiment has a circular shape in the horizontal plane and is prone to vibrating uniformly. However, the present invention is not limited to this. For example, the shape of the sound collection sheet 664 can be modified as needed.

[0038] The sensor body 62 of this embodiment has the structure described above. However, the present invention is not limited to this, and the structure of the sensor body 62 can be modified as necessary.

[0039] Referring to FIG. 3, the base member 67 has a thin, flexible bottom portion 672 and four locking portions 674. The bottom portion 672 extends along a horizontal plane, and has a through hole 68 formed therein. That is, the base member 67 has the through hole 68 formed therein. The through hole 68 has a circular shape corresponding to the contact portion 66 (see FIG. 4) on the horizontal plane, and penetrates the bottom portion 672 in the vertical direction. The four locking portions 674 surround the through hole 68 on the horizontal plane and protrude upward from the bottom portion 672. In addition, a tag 69 is attached to the base member 67. For example, the identification name of the acoustic sensor 60 or a two-dimensional code corresponding to the identification name is printed on the tag 69.

[0040] The base member 67 of this embodiment has the structure described above. However, the present invention is not limited to this, and the structure of the base member 67 can be modified as needed. For example, the tag 69 may be provided as needed.

[0041] 2 and 3 together with FIG. 5, the sensor main body 62 is attached to the base member 67 so that the contact portion 66 passes through the through hole 68. When the sensor main body 62 is attached to the base member 67, the locking portions 674 lock the locked portions 624, respectively. At this time, the lower surface of the contact portion 66 is substantially flush with the lower surface of the bottom portion 672. When the bottom portion 672 is attached to the skin of the subject 70 (see FIG. 1), the sound collection sheet 664 faces the skin of the subject 70.

[0042] According to this embodiment, the base member 67 is attached to the skin of the throat of the subject 70 (see FIG. 1 ), and the sound collection sheet 664 faces the skin of the throat of the subject 70. The sound collection sheet 664 arranged in this manner can reliably transmit breathing sounds generated in the airway of the subject 70 to the inside of the sensor main body 62. On the other hand, noise such as conversation occurring around the subject 70 is less likely to be transmitted to the inside of the sensor main body 62. Therefore, the acoustic sensor 60 can effectively collect breathing sounds generated in the throat of the subject 70 while suppressing noise.

[0043] Referring to FIG. 2, the acoustic sensor 60 of this embodiment includes a noise cancellation circuit (not shown) and an external microphone 622. The noise cancellation circuit is mounted inside the sensor main body 62. The external microphone 622 has an opening on the top surface of the sensor main body 62 and is connected to the noise cancellation circuit. The external microphone 622 converts noise, such as conversation, occurring on the opposite side of the throat of the subject 70 into a signal and transmits it to the noise cancellation circuit. The noise cancellation circuit cancels the noise by generating a signal that is opposite in phase to the signal transmitted from the external microphone 622. As described above, the acoustic sensor 60 of this embodiment has a noise cancellation function and can selectively collect breathing sounds occurring in the throat of the subject 70.

[0044] The acoustic sensor 60 of this embodiment has the above-described structure and is attached to the subject 70 (see FIG. 1) as described above. However, the present invention is not limited to this. For example, the acoustic sensor 60 may be attached to a part of the subject 70 other than the skin of the throat.

[0045] A breath sound determination device 20 (see FIG. 1) according to this embodiment will be described below.

[0046] 6, the respiratory sound determination device 20 of this embodiment includes a processing device 21, a main memory device 22, an auxiliary memory device 23, an input device 25, a display device 26, an antenna 28, and an additional antenna 29. The processing device 21 is communicably connected to other devices via an internal bus. The illustrated respiratory sound determination device 20 includes only the above-mentioned devices. However, the present invention is not limited to this. For example, the respiratory sound determination device 20 may further include other devices, such as a speaker, in addition to the above-mentioned devices.

[0047] According to this embodiment, each of the above-mentioned devices is part of one mobile terminal. For example, the display device 26 is the screen of the mobile terminal. The input device 25 is a virtual input unit such as a keyboard or input buttons displayed on the screen of the mobile terminal. The antenna 28 is an antenna for short-range communication installed inside the mobile terminal. The antenna 28 receives the acoustic signal SS transmitted by the acoustic sensor 60 paired with the respiratory sound determination device 20. The additional antenna 29 is an antenna for communication installed inside the mobile terminal. The additional antenna 29 transmits the determination result of the respiratory sound of the subject 70 (see FIG. 1 ) to the management device 40.

[0048] The respiratory sound determination device 20 of this embodiment has the above-described structure. However, the present invention is not limited to this. For example, when the respiratory sound determination device 20 is a PC, the display device 26 may be a liquid crystal display separate from the processing device 21, and the input device 25 may be a keyboard or mouse separate from the processing device 21. In this case, the input device 25 and the display device 26 may each be connected to the processing device 21 via a communication cable so as to be able to communicate with each other.

[0049] The processing device 21 includes a CPU (Central Processing Unit, not shown). The auxiliary storage device 23 is, for example, an EEPROM (Electrically Erasable Programmable Read-Only Memory), and can store various files including an executable file of the respiratory sound determination program 30 and acoustic data 32. The auxiliary storage device 23 acquires and stores files in response to instructions from the processing device 21. The CPU of the processing device 21 acquires the executable file stored in the auxiliary storage device 23, loads it into the main storage device 22, and executes the commands in the executable file to realize various functions.

[0050] Input device 25 transmits input characters and designated positions and ranges to processing device 21. Display device 26 displays the characters and images transmitted from processing device 21. For example, a CPU (not shown) of processing device 21 loads respiratory sound determination program 30 into main storage device 22 in response to instructions input from input device 25 and executes respiratory sound determination processing. That is, respiratory sound determination program 30 is a program for causing a mobile terminal to function as respiratory sound determination device 20. Respiratory sound determination program 30 is installed in auxiliary storage device 23, for example, via the WEB (World Wide Web).

[0051] As described above, programs such as the respiratory sound detection program 30 are actually executed by the CPU (not shown) of the processing device 21. However, in the following description, there are cases where it is described as if a program such as the respiratory sound detection program 30 is the subject of execution, and cases where it is described as if the processing of a program such as the respiratory sound detection program 30 by the CPU itself is the subject of execution.

[0052] Referring to FIG. 7 together with FIG. 6, the acoustic data 32 is a file that stores the acoustic signal SS received by the respiratory sound determination device 20. The acoustic data 32 in this embodiment is created when the respiratory sound determination program 30 starts operating and is deleted before the respiratory sound determination program 30 ends operating. Therefore, the file name of the acoustic data 32 may be fixed. However, the present invention is not limited to this. For example, the respiratory sound determination program 30 does not need to delete the acoustic data 32. In other words, the acoustic data 32 may be added each time the respiratory sound determination program 30 starts operating. In this case, the file name of the acoustic data 32 may be a fixed name and the creation date.

[0053] As will be described later, the acoustic data 32 is empty when it is created. A start record 32S and an end record 32E are stored in the acoustic data 32 as the respiratory sound determination program 30 processes the acoustic data 32. Each of the start record 32S and the end record 32E stores partial acoustic data 328, which is a part of the acoustic signal SS received by the respiratory sound determination device 20, a start time 322 of the partial acoustic data 328, and an end time 324 of the partial acoustic data 328. The acoustic data 32 of this embodiment has the above-described data structure. However, the present invention is not limited to this. The data structure of the acoustic data 32 can be modified as needed. Furthermore, the acoustic data 32 may be provided as needed.

[0054] The breath sound determination program 30 of this embodiment will be described below.

[0055] The respiratory sound determination program 30 of this embodiment executes four processes: a control process (see FIG. 9), an acoustic signal storage process (see FIG. 10), a first determination process (see FIG. 11), and a second determination process (see FIG. 12). For example, the control process, the first determination process, and the second determination process are executed on one thread, and the acoustic signal storage process is executed on another thread. Once the acoustic signal storage process starts, the acoustic signal SS received by the antenna 28 continues to be stored in the main memory device 22 until the second determination process starts. However, the present invention is not limited to this. The structure and algorithm of the respiratory sound determination program 30 can be modified as necessary.

[0056] The control process of this embodiment will be described below.

[0057] 9 together with FIGS. 1, 6, and 7, when the breath sound determination program 30 starts operating, the control process continues to wait until the operator issues a start command (S910). For example, the control process displays an input button (start button) displaying "Start Recording" on the display device 26, and continues to wait for the start button to be pressed.

[0058] When the start command is given by pressing the start button (YES in S910), the control process creates new empty sound data 32 (i.e., sound data 32 that does not include a start record 32S or an end record 32E) (S915). Next, the control process starts sound signal storage process (S920). As will be described later, when the sound signal storage process starts, the start record 32S is stored in the sound data 32 based on the received sound signal SS.

[0059] Next, the control process waits until the acoustic signal SS for a certain period CP is stored in the acoustic data 32 (S930). The certain period CP is, for example, 30 seconds. More specifically, the control process waits until the start record 32S is recorded by the acoustic signal storage process. Once the start record 32S is stored, the control process performs a first determination process (S940). As will be described later, the first determination process obtains a first determination result indicating whether the breath sounds stored in the start record 32S are normal or abnormal. The first determination result is displayed on the display device 26.

[0060] 8 together with FIG. 1, according to this embodiment, the operator of the breath sound determination device 20 issues a start command before the subject 70 eats a meal. During the certain period CP, substantially no food remains in the mouth of the subject 70, and therefore, no abnormal breathing caused by eating occurs.

[0061] 9 together with FIGS. 1, 6, and 7, the control process then continues to wait until the operator issues an end instruction (S950). For example, the control process displays an input button (end button) displaying "start analysis" on the display device 26, and continues to wait for the end button to be pressed.

[0062] When the end instruction is given by pressing the end button (YES in S950), the control process notifies the sound signal storage process that the end instruction has been given (S960). As will be described later, when the end instruction is given, the sound signal storage process stores an end record 32E in the sound data 32 based on the received sound signal SS.

[0063] Next, the control process performs a second determination process (S970). As will be described later, the second determination process obtains a second determination result indicating whether the breath sounds stored in the end record 32E are normal or abnormal. The second determination result is displayed on the display device 26.

[0064] 8 together with FIG. 1, according to the present embodiment, the operator of the respiratory sound determination device 20 issues an end instruction after the subject 70 has finished eating. The operator may detach the acoustic sensor 60 from the subject 70 before issuing the end instruction, or may detach the acoustic sensor 60 from the subject 70 after issuing the end instruction.

[0065] Referring to FIG. 9 together with FIGS. 1, 6, and 7, the control process then transmits the determination result to the management device 40 (S980). The control process of this embodiment transmits both the first determination result and the second determination result depending on the combination of the first determination result and the second determination result. For example, the control process transmits both the first determination result and the second determination result only when the first determination result is "normal" and the second determination result is "abnormal." In this case, the operator of the management device 40 can know that abnormal breathing has occurred due to eating, and can thereby provide the necessary care to the subject 70.

[0066] Next, the control process deletes the acoustic data 32 (S990) and ends the operation.

[0067] The acoustic signal storage process of this embodiment will be described below.

[0068] 1, 6, and 7, once the acoustic signal storage process starts, the main memory device 22 continues to receive the acoustic signal SS while determining whether the acoustic signal SS has been interrupted (S1010) until the acoustic signal SS of the CP is received for a certain period of time (S1015). If the acoustic signal SS has not been interrupted, i.e., if the acoustic signal SS can be received (NO in S1010), the acoustic signal storage process determines whether the acoustic signal SS of the CP has been received for a certain period of time (S1015). If the acoustic signal SS of the CP has not been received for a certain period of time (NO in S1015), the acoustic signal storage process continues to receive the acoustic signal SS (S1010).

[0069] In the acoustic signal storage process, if an acoustic signal SS for a certain period CP has been received (YES in S1015), it is determined whether or not the received acoustic signal SS contains respiratory sounds (S1020). If respiratory sounds are contained (YES in S1020), the acoustic signal storage process records the received acoustic signal SS for a certain period CP in the start record 32S of the acoustic data 32 (S1025).

[0070] In more detail, the acoustic signal storage process adds a start record 32S to the acoustic data 32. At this time, the acoustic signal storage process stores a start time 322, an end time 324, and partial acoustic data 328 of the start record 32S. The acoustic signal storage process stores an acoustic signal SS for a certain period CP in the partial acoustic data 328. The acoustic signal storage process stores the time when reception of the acoustic signal SS to be stored started in the start time 322. The acoustic signal storage process stores the time when the acoustic signal SS to be stored was last received in the end time 324.

[0071] In this embodiment, the audio signal storage process determines that the audio signal SS contains breathing sounds if the intensity of the audio signal SS received at the CP for a certain period of time is high. More specifically, the audio signal storage process determines that the audio signal SS contains breathing sounds if the amplitude of the received audio signal SS exceeds a predetermined value even partially. However, the present invention is not limited to this. For example, the audio signal storage process may use a neural network model to determine whether breathing sounds are contained.

[0072] After storing the acoustic signal SS in the acoustic data 32, the acoustic signal storage process continues to receive the acoustic signal SS in the main memory device 22 while determining whether the acoustic signal SS has been interrupted (S1050) until it is notified that an end instruction has been issued from the control process (S1060). If the acoustic signal SS has not been interrupted (NO in S1050), the acoustic signal storage process determines whether breathing sounds are included in the acoustic signal SS for the last fixed period CP it received (S1055) every predetermined unit time (e.g., 2 seconds). If breathing sounds are included (YES in S1055), the acoustic signal storage process determines whether an end instruction has been issued from the control process (S1060). If an end instruction has not been issued (NO in S1060), the acoustic signal storage process continues to receive the acoustic signal SS (S1050).

[0073] When the control process instructs it to end (YES in S1060), the acoustic signal storage process records the acoustic signal SS of the last received certain period CP in the end record 32E of the acoustic data 32 (S1065), and ends the process.

[0074] If the acoustic signal SS is interrupted (NO in S1010 or S1050), the acoustic signal storage process displays a confirmation message (S1030 or S1070) on the display device 26. For example, the acoustic signal storage process displays a message such as "No sound is being received from the sensor. Please check the sensor" on the display device 26, along with a continue button and an end button, which are input buttons for selecting whether to continue or end the process.

[0075] If the received acoustic signal SS does not contain any breathing sounds (NO in S1020 or S1055), the acoustic signal storage process displays a confirmation message (S1040 or S1080) on the display device 26. For example, the acoustic signal storage process displays a message such as "Breath sounds cannot be heard. Please check the sensor" on the display device 26, along with a continue button and an end button, which are input buttons for selecting whether to continue or end the process.

[0076] The operator of the respiratory sound determination device 20 can be informed by the confirmation message that some problem has occurred with the acoustic sensor 60. For example, if the switch 63 (see FIG. 2) of the acoustic sensor 60 is in the OFF state, the operator can press the switch 63 to turn it ON. If the acoustic sensor 60 has peeled off, the operator can reattach the acoustic sensor 60. Furthermore, the operator can press the continue button or the end button depending on the situation.

[0077] If the continue button is pressed (YES in S1035, S1045, S1075, or S1085), the acoustic signal storage process continues receiving the acoustic signal SS again (S1010 or S1050). On the other hand, if the end button is pressed (NO in S1035, S1045, S1075, or S1085), the acoustic signal storage process notifies the control process of an error termination and terminates the process ("A"). Referring to Figure 9 together with Figure 6, when the control process is notified of the error termination ("A"), it deletes the acoustic data 32 (S990) and terminates the process.

[0078] 6 and 7, as can be seen from the above description, the start record 32S of the acoustic data 32 stores the acoustic signal SS received during a certain period CP after a start command is issued. The end record 32E of the acoustic data 32 stores the acoustic signal SS received during a certain period CP before a stop command is issued. According to this embodiment, a relatively simple acoustic signal storage process can store the necessary acoustic signal SS in the acoustic data 32. This makes it easy for the respiratory sound detection program 30 to detect respiratory sounds.

[0079] However, the present invention is not limited to this embodiment, and the sound signal storage process can be modified as necessary. For example, the sound signal storage process may store all sound signals SS received between a start instruction and an end instruction in the sound data 32 for each fixed period CP.

[0080] The first and second determination processes of this embodiment will be described below.

[0081] Referring to FIG. 11 together with FIGS. 6 and 7, the first determination process first creates an input layer of the abnormality determination model (S1110). As will be described later, the abnormality determination model is a neural network generated through machine learning. More specifically, the first determination process creates an input layer of the abnormality determination model based on the partial acoustic data 328 of the start record 32S stored in the acoustic data 32 (i.e., the acoustic signal SS for the certain period CP). Next, the first determination process obtains an output layer of the abnormality determination model using the created input layer (S1120). Next, the first determination process creates a first determination result from the output layer of the abnormality determination model (S1130). The first determination result indicates whether the respiratory sounds included in the acoustic signal SS for the certain period CP are normal or abnormal. Next, the first determination process displays the first determination result on the display device 26 (S1140).

[0082] Referring to FIG. 1, the first determination result of this embodiment is displayed as "normal" or "abnormal." If "abnormal" is displayed, the operator of the respiratory sound determination device 20 can provide necessary care to the subject 70. However, the present invention is not limited to this. For example, the first determination result may be displayed as "○" or "×."

[0083] Referring to FIG. 12 together with FIGS. 6 and 7, the second determination process first creates an input layer of the abnormality determination model (S1210). More specifically, the second determination process creates the input layer of the abnormality determination model based on the partial acoustic data 328 of the end record 32E (i.e., the acoustic signal SS for a certain period CP) stored in the acoustic data 32. Next, the second determination process obtains an output layer of the abnormality determination model using the created input layer (S1220). Next, the second determination process creates a second determination result from the output layer of the abnormality determination model (S1230). The second determination result indicates whether the respiratory sounds included in the acoustic signal SS for a second predetermined period are normal or abnormal. Next, the second determination process displays the second determination result on the display device 26 (S1240).

[0084] Referring to FIG. 1, the second determination result of this embodiment is displayed as "normal" or "abnormal." If "abnormal" is displayed, the operator of the respiratory sound determination device 20 can provide necessary care to the subject 70. However, the present invention is not limited to this. For example, the second determination result may be displayed as "○" or "×."

[0085] 1, 6, and 8, the above description of respiratory sound determination device 20 can be summarized as follows: when instructed to start, respiratory sound determination device 20 of the present embodiment performs a first determination process, and when instructed to stop after the start instruction, performs a second determination process. In the first determination process, respiratory sound determination device 20 displays a first determination result indicating whether the respiratory sounds in a first predetermined period are normal or abnormal on display device 26. In the second determination process, respiratory sound determination device 20 displays a second determination result indicating whether the respiratory sounds in a second predetermined period are normal or abnormal on display device 26.

[0086] The first and second predetermined periods in this embodiment are each equal to the fixed period CP in the acoustic signal storage process (see FIG. 10). That is, the first and second predetermined periods in this embodiment are each 30 seconds. However, the present invention is not limited to this. The first and second predetermined periods may be any period in which the acoustic sensor 60 can collect breathing sounds. For example, the first and second predetermined periods may each be shorter than the fixed period CP in the acoustic signal storage process. In other words, the fixed period CP in the acoustic signal storage process may be longer than the first and second predetermined periods. Furthermore, the first and second predetermined periods may be different from each other.

[0087] Breath sound assessment device 20 of this embodiment can display two assessment results: a first assessment result for a first predetermined period and a second assessment result for a second predetermined period after the first predetermined period. Therefore, by issuing a start instruction before an event such as a meal and an end instruction after the event, it is possible to compare the assessment results before and after the event. Comparing the assessment results reveals that the abnormal breath sounds in the second assessment result were caused by the event.

[0088] More specifically, if the determination result of the subject 70 before eating is normal and the determination result of the subject 70 after eating is abnormal, it can be determined that abnormal breathing has occurred due to eating. For example, it can be determined that there is a possibility that a foreign object caused by eating remains in the upper respiratory organs of the subject 70. In other words, according to this embodiment, it is possible to provide a breath sound determination device 20 that detects abnormal breathing caused by an event such as eating.

[0089] In this embodiment, the event is a meal. However, the present invention is not limited to this. For example, the event may be exercise, bathing, or taking medication such as an asthma inhalant. The first determination process may be performed before these events, and the second determination process may be performed after these events. By using the breath sound determination device 20 of this embodiment for such purposes, it is possible not only to detect abnormal breathing caused by an event, but also to detect the disappearance of abnormal breathing caused by an event such as light exercise or medication.

[0090] 10 together with FIG. 6, as described above, the acoustic signal storage process displays a confirmation message on the display device 26 if the acoustic signal SS cannot be received within a certain period of time CP, or if the received acoustic signal SS does not include breath sounds. Furthermore, the acoustic signal storage process is executed on a thread different from the control process (see FIG. 9), the first determination process (see FIG. 11), and the second determination process (see FIG. 12). Therefore, the acoustic signal storage process can display confirmation messages on the display device 26 at various times.

[0091] For example, the acoustic signal storage process can display a confirmation message on the display device 26 both before the first determination process (first timing) and before the second determination process (second timing). Furthermore, the acoustic signal storage process can change the content of the confirmation message depending on the timing. For example, if the respiratory sound determination device 20 is unable to acquire a CP of a respiratory sound for a certain period of time after performing the first determination process and before receiving an instruction to terminate the process, the respiratory sound determination device 20 can display information indicating that the respiratory sound cannot be acquired on the display device 26. Such a display allows the operator of the respiratory sound determination device 20 to be aware of various problems, such as a malfunction of the acoustic sensor 60, in a timely manner.

[0092] In addition to the various modifications already described, the respiratory sound determination device 20 of this embodiment can be further modified in various ways. Modifications of the respiratory sound determination device 20 will be described below.

[0093] 1, according to the present embodiment, the first determination result and the second determination result are each displayed on the display device 26. However, the present invention is not limited to this. For example, if the second determination result is "abnormal," the breath sound determination device 20 may output a sound from a speaker.

[0094] Referring to FIG. 8, the first predetermined period in this embodiment is a continuous period immediately after the operator of the respiratory sound determination device 20 issues a start command. However, the present invention is not limited to this. For example, the first predetermined period may be a discontinuous period starting several seconds after the operator issues a start command. The total time of two or more discontinuous periods may be the first predetermined period. In other words, the first predetermined period may be the period after the start command is issued. Also, referring to FIG. 9 in conjunction with FIG. 6, the respiratory sound determination program 30 may start the acoustic signal recording process (S920) immediately after starting its operation (i.e., before S910). Referring to FIG. 8, in this case, the first predetermined period may include the period before the operator issues a start command, or may be only the period before the operator issues a start command.

[0095] The second predetermined period in this embodiment is a continuous period immediately before the operator issues an end instruction. However, the present invention is not limited to this. For example, the second predetermined period may be a discontinuous period that ends several seconds before the operator issues an end instruction. The total time of two or more such discontinuous periods may be the second predetermined period. In other words, the second predetermined period may be the period before the end instruction is issued. Furthermore, the second predetermined period may include the period after the operator issues an end instruction, or may be only the period after the operator issues an end instruction.

[0096] 1 , as described above, after performing the second determination process, the respiratory sound determination device 20 of the present embodiment transmits the first determination result and the second determination result to the management device 40, which is different from the respiratory sound determination device 20, depending on the combination of the first determination result and the second determination result. However, the present invention is not limited to this. For example, the respiratory sound determination device 20 may transmit the first determination result and the second determination result to the management device 40 regardless of the contents of the first determination result and the second determination result. Furthermore, the respiratory sound determination device 20 may not transmit the first determination result and the second determination result to the management device 40.

[0097] The respiratory sound determination device 20 of this embodiment determines the presence of a respiratory sound only in the first determination process and the second determination process. That is, the respiratory sound determination device 20 of this embodiment obtains two determination results only in two predetermined periods, a first period and a second period, which are separated by an event. However, the present invention is not limited to this. For example, the respiratory sound determination device 20 may determine the presence of a respiratory sound only in the first determination process and the second determination process, and also in a third predetermined period during the event.

[0098] 11 and 12, the respiratory sound determination device 20 of this embodiment uses an abnormality determination model to determine whether a respiratory sound is normal or abnormal. The abnormality determination model of this embodiment is a neural network that has been machine-learned using deep learning. According to this embodiment, it is possible to determine whether a respiratory sound is normal or abnormal with an accuracy of, for example, 80% or more. However, the present invention is not limited to this, and the method for determining whether a respiratory sound is normal or abnormal is not particularly limited.

[0099] The abnormality determination model of this embodiment (see FIG. 13) will be described below.

[0100] 13 together with FIGS. 6, 11, and 12, respiratory sound determination device 20 performs a short-time Fourier transform (STFT) on the acoustic signal SS for the first or second predetermined period to create a spectrogram (S1110 in FIG. 11, S1210 in FIG. 12, and S1310 in FIG. 13). Respiratory sound determination device 20 obtains an output layer of an abnormality determination model using the created spectrogram as an input layer (S1130 in FIG. 11, S1230 in FIG. 12, and S1320 in FIG. 13).

[0101] The size of the spectrogram in this embodiment is 249 × 129 pixels and one channel. The abnormality discrimination model in this embodiment is a model using a convolutional network (CNN: Convolutional Neural Network). For example, the abnormality discrimination model in this embodiment is a machine-learned neural network having the layer structure shown in FIG. 14. The output layer of the abnormality discrimination model represents the probability that the respiratory sound is abnormal, and is a numerical value between 0 and 100%. However, the present invention is not limited to this. The abnormality discrimination model may be any type of model. The input layer and output layer of the abnormality discrimination model can be modified as necessary. For example, the input layer may be an inverted spectrogram.

[0102] The anomaly determination model of this embodiment can be generated, for example, as shown in FIG.

[0103] First, acoustic signals SS during a meal are collected, and a large number of acoustic signal files are created from these (S1510). Next, a speech-language-hearing therapist or other specialist listens to the acoustic signal files and extracts abnormal breathing (S1520). More specifically, the start and end times of abnormal breathing sounds are recorded in each acoustic signal file. Based on these start and end times, a large number of acoustic signal files are created from which the portions where abnormal breathing occurs are extracted. Next, each acoustic signal file is subjected to a short-time Fourier transform to create a large number of spectrograms for machine learning (S1530). Next, machine learning is performed using the created spectrograms as training data (S1540). As a result of this machine learning, an abnormality discrimination model is generated. Next, a converter converts the generated abnormality discrimination model into a lightweight anomaly discrimination model that can be installed on a mobile device.

[0104] The anomaly discrimination model of this embodiment can be generated as described above, but the method for generating the anomaly discrimination model according to the present invention is not particularly limited.

[0105] For example, instead of a lightweight anomaly discrimination model that does not learn, a continuous learning anomaly discrimination model may be installed on a mobile terminal. In this case, referring to FIG. 6, the respiratory sound discrimination program 30 may leave the acoustic data 32 rather than deleting it when it terminates its operation. That is, the acoustic data 32 may continue to be accumulated. By determining whether the respiratory sounds in the large amount of accumulated acoustic data 32 are normal or abnormal, the discrimination accuracy of the anomaly discrimination model can be improved.

[0106] The respiratory sound determination system 10 (see FIG. 1) of this embodiment can be modified as described below.

[0107] 16 , a modified respiratory sound determination system 10A includes a respiratory sound determination device 20 and two or more acoustic sensors 60. The acoustic sensors 60 are attached to two or more subjects 70, respectively. When each acoustic sensor 60 starts operating, it collects ambient sound, converts it into an acoustic signal SS, and transmits it to the outside. The respiratory sound determination device 20 is paired with each of the acoustic sensors 60. The respiratory sound determination device 20 receives the acoustic signals SS transmitted by the two or more acoustic sensors 60.

[0108] 16 and 17, the respiratory sound determination device 20 of this modification performs a control process (see FIG. 9), an acoustic signal storage process (see FIG. 10), a first determination process (see FIG. 11), and a second determination process (see FIG. 12) for each paired acoustic sensor 60. For example, the respiratory sound determination device 20 can perform parallel processing for two or more acoustic sensors 60 selected from a sensor list screen (not shown) displayed on the display device 26. That is, the respiratory sound determination device 20 of this modification can perform the first determination process on respiratory sounds in two or more acoustic signals SS whose first predetermined time periods overlap each other, and can perform the second determination process on respiratory sounds in two or more acoustic signals SS whose second predetermined time periods overlap each other.

[0109] When pairing respiratory sound determination device 20 of this modified example with each acoustic sensor 60, respiratory sound determination device 20 may read the two-dimensional code of tag 69 (see FIG. 2) attached to base member 67 (see FIG. 2) and store the identification name of acoustic sensor 60 in association with acoustic sensor 60. By storing the identification name of acoustic sensor 60 in association with acoustic sensor 60, for example, when respiratory sound determination device 20 displays the first determination result on display device 26, the identification name of acoustic sensor 60 can also be displayed.

[0110] According to this modification, abnormal breathing of two or more subjects 70 can be detected by one respiratory sound determination device 20. On the other hand, the respiratory sound determination system 10A may include two or more respiratory sound determination devices 20 and two or more acoustic sensors 60. In this case, the acoustic sensors 60 paired with the two or more respiratory sound determination devices 20 may be different from each other or may overlap with each other. When the acoustic sensors 60 paired with the respiratory sound determination devices 20 overlap with each other, abnormal breathing of one subject 70 can be detected by two or more respiratory sound determination devices 20. This reduces the possibility of overlooking abnormal breathing.

[0111] As can be seen from the above description, this modification provides a monitoring method for monitoring two or more subjects 70 using the respiratory sound determination system 10A. An acoustic sensor 60 is attached to each of the subjects 70. Before all of the subjects 70 perform a predetermined event, such as a meal, the acoustic sensor 60 is activated and a start instruction is given to the respiratory sound determination device 20. After all of the subjects 70 have performed the predetermined event, an end instruction is given to the respiratory sound determination device 20. This monitoring method allows the caregiver to provide efficient care. [Explanation of symbols]

[0112] 10,10A Breath Sound Assessment System 20 Breathing sound determination device 21 Processing equipment 22 Main storage 23 Auxiliary storage device 25 Input Devices 26 Display device 28 Antenna 29 Additional Antennas 30 Breath Sound Identification Program 32 Acoustic Data 32S Start Record 32E End Record 322 Start time 324 End Time 328 partial acoustic data 40 Management device 60 Acoustic Sensor 62 Sensor body 622 External Microphone 624 Locked part 63 Switch 64 Lamp 65 Connector 66 Contact area 662 recess 664 Sound collection sheet 67 Base member 672 Bottom 674 Rock Club 68 Passing hole 69 Tags 70 Target SS acoustic signal

Claims

1. A respiratory sound determination device for determining respiratory sounds in an acoustic signal received from an external device, comprising: The respiratory sound determination device includes a display device, The breath sound determination device performs a first determination process when instructed to start, and performs a second determination process when instructed to stop after being instructed to start, In the first determination process, the breath sound determination device displays, on the display device, a first determination result indicating whether the breath sounds in a first predetermined period are normal or abnormal; In the second determination process, the breath sound determination device displays, on the display device, a second determination result indicating whether the breath sounds in a second predetermined period are normal or abnormal. Breathing sound determination device.

2. The respiratory sound determination device according to claim 1, After performing the second determination process, the respiratory sound determination device transmits the first determination result and the second determination result to a management device different from the respiratory sound determination device, depending on a combination of the first determination result and the second determination result. Breathing sound determination device.

3. The respiratory sound determination device according to claim 1, the respiratory sound determination device is a mobile terminal, The display device is a screen of the mobile terminal. Breathing sound determination device.

4. The respiratory sound determination device according to any one of claims 1 to 3, When the breath sound determination device is unable to acquire the breath sound for a certain period of time after performing the first determination process and before receiving an instruction to terminate the process, the breath sound determination device displays information indicating that the breath sound cannot be acquired on the display device. Breathing sound determination device.

5. The respiratory sound determination device according to any one of claims 1 to 3, The respiratory sound determination device can perform the first determination process on the respiratory sounds in two or more of the acoustic signals whose first predetermined periods overlap each other, and can perform the second determination process on the respiratory sounds in two or more of the acoustic signals whose second predetermined periods overlap each other. Breathing sound determination device.

6. A program for causing a mobile terminal to function as the respiratory sound determination device according to any one of claims 1 to 3. Breath sound detection program.

7. A respiratory sound determination system comprising the respiratory sound determination device according to any one of claims 1 to 3 and two or more acoustic sensors, When each of the acoustic sensors starts operating, it collects surrounding sounds, converts them into acoustic signals, and transmits them to the outside. The respiratory sound determination device receives the acoustic signals transmitted by two or more of the acoustic sensors. Breath sound detection system.

Images