Analysis device and auscultation support system

Abstract

To make a user such as a doctor easily grasp temporal change of a patient's condition (e.g., respiratory condition).SOLUTION: An analyzer comprises an analysis unit and an output unit. The analysis unit analyzes respiratory sound data representing a patient's respiratory sound and adventitious sound to acquire, as analysis results, frequency components constituting the adventitious sound, duration of the adventitious sound, and the number of times of the adventitious sound detected per unit time, at a plurality of points of time. The output unit outputs a plurality of analysis results at the plurality of points of time acquired by the analysis by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The embodiments disclosed in the present specification and drawings relate to an analysis device and an auscultation support system. [Background technology]

[0002] A doctor performs auscultation by placing a stethoscope on the patient's chest or back and listening to the patient's auscultatory sounds (breathing sounds) with the doctor's ears. In this case, only the doctor who performed the auscultation can hear the actual auscultatory sounds of the patient and determine what sounds were confirmed. Therefore, the diagnosis after auscultation is heavily influenced by the skill of the doctor who performed the auscultation. Therefore, in order to make a diagnosis that does not depend on the doctor's skill, there is a technology that can, for example, distinguish the type of adventitious sound from the patient's auscultatory sounds.

[0003] However, it is difficult for a doctor to judge whether a patient's condition (e.g., respiratory condition) is improving or deteriorating just from the type of the adventitious noise at a certain point in time. In other words, it is difficult for a doctor to grasp the change over time of a patient's condition just from the type of the adventitious noise at a certain point in time. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-021169 A [Patent Document 2] JP 2013-123494 A [Patent Document 3] JP 2017-118927 A Summary of the Invention [Problem to be solved by the invention]

[0005] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to allow a user such as a doctor to easily grasp the change over time in a patient's condition (e.g., respiratory condition). However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems. [Means for solving the problem]

[0006] The analysis device according to the embodiment includes an analysis unit and an output unit. The analysis unit analyzes respiratory sound data indicating respiratory sounds and adventitious noises of a patient, and obtains, as analysis results, frequency components constituting the adventitious noises at multiple time points, durations of the adventitious noises, and the number of times the adventitious noises are detected per unit time. The output unit outputs the analysis results at the multiple time points obtained by the analysis by the analysis unit. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of an auscultation support system according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a configuration of the analysis device according to the embodiment. [Diagram 3] FIG. 3 is a flowchart showing a processing procedure of processing performed by each processing function of the processing circuitry of the analysis device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a data structure of a table according to the embodiment. [Diagram 5] FIG. 5 is a diagram showing an example of a graph generated by the analysis function according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a data structure of a table according to the first modification of the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a message generated by the analysis function according to the first modification of the embodiment. [Figure 8]FIG. 8 is a diagram illustrating an example of a message generated by the analysis function according to the second modification of the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of a message generated by the analysis function according to the second modification of the embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of a table generated by the analysis function according to the third modification of the embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of a trained model according to the fourth modification of the embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of a table generated by the analysis function according to the fourth modification of the embodiment. [Figure 13] FIG. 13 is a diagram for explaining an example of a process executed by an analysis device according to the fifth modification of the embodiment. [Figure 14] FIG. 14 is a diagram for explaining an example of a process executed by an analysis device according to the sixth modification of the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, embodiments and modifications of the analysis device and auscultation support system will be described in detail with reference to the drawings. Note that the analysis device and auscultation support system according to the present application are not limited to the embodiments and modifications shown below. Furthermore, the embodiments can be combined with modifications or conventional techniques as long as no inconsistencies arise in the processing content. Similarly, the modifications can be combined with the embodiments, other modifications, or conventional techniques as long as no inconsistencies arise in the processing content.

[0009] (Embodiment) Fig. 1 is a diagram showing an example of the configuration of an auscultation support system 1 according to an embodiment. As shown in Fig. 1, the auscultation support system 1 according to this embodiment includes an electronic stethoscope 80, an analysis device 10, and a terminal 81. The analysis device 10 and the electronic stethoscope 80 are connected to each other so as to be able to communicate with each other wirelessly or via a wire. The analysis device 10 and the terminal 81 are also connected to each other so as to be able to communicate with each other wirelessly or via a wire.

[0010] The electronic stethoscope 80 acquires respiratory sound data (auscultation sound data) of a patient (subject) and transmits the acquired respiratory sound data to the analysis device 10. For example, the electronic stethoscope 80 transmits the respiratory sound data of the patient in real time to the analysis device 10. To explain by taking a specific example, the electronic stethoscope 80 transmits the acquired respiratory sound data to the analysis device 10 every time it acquires the respiratory sound data of the patient. The respiratory sound data is data indicating the respiratory sounds and accessory sounds of the patient. More specifically, the respiratory sound data is data indicating the waveforms of the respiratory sounds and the accessory sounds of the patient. For example, the electronic stethoscope 80 stores the respiratory sound data of the patient in a memory in the electronic stethoscope 80 while being held by a doctor against a part of the patient to be auscultated, such as the chest of the patient. Then, the electronic stethoscope 80 transmits the respiratory sound data stored in the memory to the analysis device 10. The electronic stethoscope 80 is an example of an acquisition device that acquires respiratory sound data.

[0011] The respiratory sound data includes information indicating the auscultation target site to which the electronic stethoscope 80 is applied when the respiratory sound data is acquired. Two specific examples of a method for the electronic stethoscope 80 to identify the auscultation target site will be described below. First, the first specific example will be described. For example, the electronic stethoscope 80 includes a position sensor that detects the position of the electronic stethoscope 80. Before acquiring the respiratory sound data, the electronic stethoscope 80 calibrates the coordinate system of the position sensor so that the position of a specific part of the patient (e.g., the neck) becomes the origin of the three-dimensional coordinate system of the position sensor. The electronic stethoscope 80 then acquires the position of the electronic stethoscope 80 indicated by a detection signal from the position sensor while acquiring the respiratory sound data. Here, the acquired position is a three-dimensional position relative to the specific part of the patient. The electronic stethoscope 80 then identifies the part of the patient indicated by the acquired position as the auscultation target site based on the acquired position and the relative positional relationship between the known specific part of the patient and other parts (e.g., the upper part of the left lung, the lower part of the left lung, etc.). Then, the electronic stethoscope 80 adds the identified auscultation target area to the respiratory sound data, and stores the respiratory sound data with the auscultation target area added in the memory within the electronic stethoscope 80.

[0012] Next, a second specific example will be described. The order of auscultation of multiple auscultation target sites may be predetermined. That is, a doctor may auscultate multiple auscultation target sites in a predetermined order. Therefore, the electronic stethoscope 80 is provided with a contact sensor that detects whether or not it is in contact with a patient (whether or not it is placed against a patient). When the electronic stethoscope 80 is in contact with a patient, the contact sensor outputs a detection signal indicating contact. When the electronic stethoscope 80 is not in contact with a patient, the contact sensor outputs a detection signal indicating non-contact. Then, the electronic stethoscope 80 identifies the auscultation target site based on the change over time of contact or non-contact indicated by the detection signal from the contact sensor.

[0013] For example, a case will be described in which it is predetermined that the "upper left lung" is auscultated first, the "lower left lung" is auscultated second, and the "abdomen" is auscultated third. In this case, when the change over time indicated by the detection signal from the contact sensor is only "contact", it is considered that the first "upper left lung" is auscultated. At this time, the electronic stethoscope 80 specifies the "upper left lung" as the auscultated region. Also, when the change over time indicated by the detection signal from the contact sensor changes from "contact" to "non-contact" and then becomes "contact" again, it is considered that after auscultating the first "upper left lung", the electronic stethoscope 80 moves away from the patient, and then the electronic stethoscope 80 is placed against the patient again to auscultate the second "lower left lung". At this time, the electronic stethoscope 80 specifies the "lower left lung" as the auscultated region. After identifying the auscultation target area in this manner, the electronic stethoscope 80 adds the identified auscultation target area to the respiratory sound data and stores the respiratory sound data with the auscultation target area added in the memory within the electronic stethoscope 80.

[0014] The method by which the electronic stethoscope 80 identifies the auscultation target site is not limited to the above-mentioned method. For example, the electronic stethoscope 80 may identify the auscultation target site using a known method for identifying the auscultation target site.

[0015] The analysis device 10 analyzes the respiratory sound data to obtain the respiratory state of the patient. Then, the analysis device 10 outputs the current respiratory state and the past respiratory state of the patient in a comparable manner. For example, the analysis device 10 displays the current respiratory state and the past respiratory state of the patient on a display 14 (see FIG. 2) in the analysis device 10 in a comparable manner, or transmits the current respiratory state and the past respiratory state of the patient to a terminal 81. This allows a user such as a doctor of the auscultation support system 1 and the analysis device 10 to easily grasp the change over time of the respiratory state of the patient. The analysis device 10 is realized by a portable terminal such as a smartphone or a tablet terminal held by a user, or a computer device such as a personal computer, a server, or a workstation. A detailed description of the analysis device 10 will be given later.

[0016] The terminal 81 includes a display and displays, in a comparable manner, the current respiratory state and the past respiratory state of the patient transmitted by the analysis device 10. The terminal 81 is realized by a portable terminal such as a smartphone or a tablet terminal, or a computer device such as a personal computer, a server, or a workstation.

[0017] 2 is a diagram showing an example of a configuration of an analysis device 10 according to an embodiment. As shown in FIG. 2, the analysis device 10 includes a network (NW) interface 11, a memory circuitry 12, an input interface 13, a display 14, and a processing circuitry 15.

[0018] The NW interface 11 controls the transmission and communication of various information and data transmitted and received between the analysis device 10 and the electronic stethoscope 80. Similarly, the NW interface 11 controls the transmission and communication of various information and data transmitted and received between the analysis device 10 and the terminal 81. The NW interface 11 is connected to the processing circuit 15. The NW interface 11 receives data transmitted by the electronic stethoscope 80 and the terminal 81. In this case, the NW interface 11 transmits the received data to the processing circuit 15. For example, the NW interface 11 receives respiratory sound data transmitted by the electronic stethoscope 80 and transmits the received respiratory sound data to the processing circuit 15. The NW interface 11 also receives data transmitted by the processing circuit 15. In this case, the NW interface 11 transmits the received data to the electronic stethoscope 80 or the terminal 81. For example, the NW interface 11 is realized by a network card, a network adapter, a NIC (Network Interface Controller), or the like.

[0019] The memory circuitry 12 stores various data and various programs. The memory circuitry 12 is connected to the processing circuitry 15. The memory circuitry 12 is controlled by the processing circuitry 15 and stores data transmitted by the processing circuitry 15. The data stored in the memory circuitry 12 is read by the processing circuitry 15. For example, the memory circuitry 12 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, a hard disk, an optical disk, or the like.

[0020] The input interface 13 accepts input operations of various instructions and various information from a user. The input interface 13 is connected to the processing circuit 15. The input interface 13 converts the operation accepted by the user into an electrical signal and transmits it to the processing circuit 15. For example, the input interface 13 is realized by a trackball, a switch button, a mouse, a keyboard, a touch pad that accepts operations by touching the operation surface, a touch screen in which a display screen and a touch pad are integrated, a non-contact input interface using an optical sensor, a voice input interface, and the like. Note that in this specification, the input interface 13 is not limited to only those that have physical operation parts such as a mouse and a keyboard. For example, an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the analysis device 10 and transmits the electrical signal to the processing circuit 15 is also included as an example of the input interface 13.

[0021] The display 14 displays various images, various information, and various data. The display 14 is connected to the processing circuit 15. The display 14 is controlled by the processing circuit 15 and displays various images, various information, and various data transmitted by the processing circuit 15. For example, the display 14 is realized by a liquid crystal display, a CRT (Cathode Ray Tube) display, a touch panel, etc. The display 14 is both an example of a display unit and an example of an output unit.

[0022] The processing circuitry 15 controls the entire analysis device 10. For example, the processing circuitry 15 performs various processes in response to an operation received from a user via the input interface 13. The processing circuitry 15 also acquires respiratory sound data transmitted by the NW interface 11. Then, the processing circuitry 15 stores the acquired respiratory sound data in the memory circuitry 12.

[0023] The above describes an example of the configuration of the auscultation support system 1 and the analysis device 10 according to this embodiment. For example, the auscultation support system 1 and the analysis device 10 according to this embodiment are installed in medical facilities such as hospitals and clinics, and support auscultation performed by a user.

[0024] 2, the processing circuit 15 of the analysis device 10 has an acquisition function 15a, an analysis function 15b, and an output function 15c. The acquisition function 15a is an example of an acquisition unit. The analysis function 15b is an example of an analysis unit. The output function 15c is an example of an output unit.

[0025] The processing circuitry 15 is realized by, for example, a processor. In this case, each of the above-mentioned processing functions is stored in the storage circuitry 12 in the form of a program executable by a computer. The processing circuitry 15 then reads out each program stored in the storage circuitry 12 and executes the read out program to realize each processing function corresponding to each program. In other words, the processing circuitry 15 has each processing function shown in FIG. 2 in a state where each program is read out.

[0026] The processing circuit 15 may be configured by combining a plurality of independent processors, and each processor may execute a program to realize each processing function. Each processing function of the processing circuit 15 may be distributed or integrated into a single or a plurality of processing circuits. Each processing function of the processing circuit 15 may be realized by a combination of hardware such as a circuit and software. Although an example in which each program corresponding to each processing function is stored in a single storage circuit 12 has been described here, the embodiment is not limited to this. For example, each program corresponding to each processing function may be distributed and stored in a plurality of storage circuits, and the processing circuit 15 may read and execute each program from each storage circuit.

[0027] Next, the procedure of the process executed by the analysis device 10 will be described with reference to Fig. 3. Fig. 3 is a flowchart showing the procedure of the process performed by each processing function of the processing circuitry 15 of the analysis device 10 according to the embodiment.

[0028] The processing circuitry 15 performs the process shown in Fig. 3 in real time. That is, every time the processing circuitry 15 receives respiratory sound data transmitted by the electronic stethoscope 80, the processing circuitry 15 performs the process shown in Fig. 3 on the received respiratory sound data. The processing circuitry 15 may also perform the process shown in Fig. 3 not in real time but when the processing circuitry 15 receives an instruction to perform the process shown in Fig. 3, which is input by the user via the input interface 13. That is, the processing circuitry 15 may perform the process shown in Fig. 3 asynchronously with the timing at which the respiratory sound data is transmitted by the electronic stethoscope 80.

[0029] (Step S101) 3, first, in step S101, the acquisition function 15a acquires respiratory sound data stored in the memory circuitry 12. The acquired respiratory sound data is used in the processes from step S102 onward.

[0030] (Step S102) Then, in step S102, the analysis function 15b analyzes the acquired respiratory sound data and classifies the type of the respiratory sound and the auxiliary noises indicated by the respiratory sound data. FIG. 4 is a diagram showing an example of the data structure of the table 12a according to the embodiment. In this embodiment, for example, the table 12a is stored in advance in the memory circuitry 12. Also, for example, the type of the auxiliary noise is classified according to the time (duration) that the auxiliary noise lasts and the frequency components of the waveform indicating the auxiliary noise. Therefore, the analysis function 15b reads out the table 12a shown in FIG. 4 from the memory circuitry 12 and identifies the type of the auxiliary noise using the read out table 12a, thereby classifying the type of the auxiliary noise. In the table 12a, the type of the auxiliary noise corresponding to each combination of frequency and duration is registered.

[0031] As shown in FIG. 4, table 12a has registered therein a plurality of records each having the items of "frequency," "duration," and "adjacent noise." A range of frequency components is registered in the "frequency" item. For example, in the example of FIG. 4, a range of frequency components equal to or greater than "f1" and less than "f2" is registered in the "frequency" item of the first record. Also, a range of frequency components equal to or greater than "f3" and less than "f4" is registered in the "frequency" item of the second record.

[0032] The "Duration" field contains a range of durations. For example, in the example in Figure 4, the "Duration" field of the first record contains a range of durations from "t1" to "t2". The "Duration" field of the second record contains a range of durations from "t3" to "t4".

[0033] In the "adjacent noise" field, the type of adjacent noise is registered. For example, in the example of FIG. 4, in the "adjacent noise" field of the first record, the type of adjacent noise "a1" is registered in association with the combination of the frequency component range of "f1" or more and less than "f2" and the duration range of "t1" or more and less than "t2". In addition, in the "adjacent noise" field of the second record, the type of adjacent noise "a2" is registered in association with the combination of the frequency component range of "f3" or more and less than "f4" and the duration range of "t3" or more and less than "t4". In other words, the first record indicates that a sound whose frequency component is in the range of "f1" or more and less than "f2" and whose duration is in the range of "t1" or more and less than "t2" is an adjacent noise of type "a1". Similarly, the second record indicates that a sound whose frequency component is in the range of "f3" or more and less than "f4" and whose duration is in the range of "t3" or more and less than "t4" is an adjacent noise of type "a2".

[0034] A specific example of how the analysis function 15b classifies types of side noises using the table 12a will be described. For example, the analysis function 15b analyzes respiratory sound data to obtain a plurality of frequency components constituting the sound indicated by the respiratory sound data. Here, the sound indicated by the respiratory sound data includes respiratory sounds and side noises as described above. Therefore, the plurality of frequency components obtained by the analysis function 15b include frequency components constituting respiratory sounds and frequency components constituting side noises.

[0035] Therefore, the analysis function 15b performs the following process to obtain the frequency components constituting the auxiliary noise and the duration of the auxiliary noise.

[0036] For example, the analysis function 15b identifies, among the acquired frequency components, frequency components included in the range of frequency components registered in the "frequency" field of the table 12a as candidates for frequency components constituting the auxiliary noise. In this way, the analysis function 15b identifies one or more candidates for frequency components constituting the auxiliary noise.

[0037] Then, the analysis function 15b analyzes the respiratory sound data and acquires, for each candidate of frequency components constituting the adjunct noise, the time (duration) during which the sound composed of the candidate of frequency components constituting the adjunct noise continues. In this way, the analysis function 15b acquires, for each candidate of frequency components constituting the adjunct noise, a combination of the candidate of frequency components constituting the adjunct noise and the duration. In this way, the analysis function 15b acquires one or more combinations. Then, the analysis function 15b acquires from the table 12a the type of adjunct noise that matches each of the acquired one or more combinations.

[0038] More specifically, the analysis function 15b identifies, for each combination, from among all records in the table 12a, a record in which a frequency component range including the frequency components constituting the combination is registered in the "frequency" field, and a duration range including the durations constituting the combination is registered in the "duration" field. In this way, the analysis function 15b identifies one or more records. Then, for each identified record, the analysis function 15b identifies the type of adjunct noise registered in the "adjunct noise" field of the identified record. In this way, the analysis function 15b identifies one or more types of adjunct noise. In this way, in step S102, the analysis function 15b identifies one or more current types of adjunct noise by analyzing the current (current time) respiratory sound data transmitted by the electronic stethoscope 80 in real time.

[0039] Then, the analysis function 15b identifies the number of times that each type of ad-hoc noise is detected (identified) per unit time (for example, 10 seconds).

[0040] Then, the analysis function 15b acquires the above-mentioned frequency component candidates as the frequency components constituting the adjoint noise for each of the adjoint noises whose type has been specified. Also, the analysis function 15b acquires the duration of the sound composed of the above-mentioned frequency component candidates as the duration of the adjoint noise for each of the adjoint noises whose type has been specified. In this way, in step S102, the analysis function 15b analyzes in real time the current (current time) respiratory sound data transmitted by the electronic stethoscope 80 to acquire the frequency components constituting the adjoint noise, the duration of the adjoint noise, and the number of detected adjoint noises for each type of adjoint noise. That is, the analysis function 15b acquires the frequency components of the current adjoint noise, the duration of the current adjoint noise, and the number of detected adjoint noises for each type of adjoint noise.

[0041] Then, the analysis function 15b stores the frequency components of the current side-noise, the duration of the current side-noise, and the number of occurrences of the current side-noise in the memory circuitry 12 in association with the current time for each type of side-noise. The process shown in FIG. 3 is repeatedly executed in real time. Therefore, every time the process of step S102 is repeatedly executed, the memory circuitry 12 stores the frequency components, duration, and number of occurrences in association with the time at which step S102 is executed. That is, the analysis function 15b repeatedly executes the process of step S102 to obtain the frequency components, duration, and number of occurrences at multiple time points, and stores the obtained frequency components, duration, and number of occurrences at multiple time points in the memory circuitry 12. Therefore, the memory circuitry 12 stores the frequency components, duration, and number of occurrences corresponding to the current time, and the frequency components, duration, and number of occurrences corresponding to past times as history data.

[0042] In addition, an example has been described in which the analysis function 15b identifies the type of side noise using the table 12a in which the type of side noise is registered in association with a combination of a frequency component range and a duration range. However, the table used when identifying the type of side noise is not limited to the table 12a. For example, the analysis function 15b may identify the type of side noise using a table in which the type of side noise is registered in association with a combination of a frequency component range, a duration range, and an amplitude range. In this case, the analysis function 15b analyzes the respiratory sound data and further acquires the amplitude of a waveform indicating a sound indicated by the respiratory sound data. Then, the analysis function 15b may identify the type of side noise that matches the frequency component, duration, and amplitude acquired by analyzing the respiratory sound data from the above table. For example, the analysis function 15b may identify the type of side noise using the frequency component, duration, amplitude, and the above table in a manner similar to the method of identifying the type of side noise using the table 12a. The above table is stored in advance in the storage circuit 12, similar to the table 12a.

[0043] (Step S103) Next, in step S103, the analysis function 15b generates a graph in a manner that allows comparison between the current respiratory state and the past respiratory state of the patient to be displayed on the display 14. Note that, hereinafter, a case where the analysis function 15b generates a three-dimensional bar graph as a three-dimensional graph in step S103 will be described, but the graph generated by the analysis function 15b is not limited to a three-dimensional bar graph.

[0044] An example of a graph generated by the analysis function 15b in step S103 will be described. The analysis function 15b plots (draws) a square prism-shaped bar indicating the frequency component of the current side-noise, the duration of the current side-noise, and the number of times of the current side-noise for each type of side-noise on a three-dimensional coordinate system consisting of three axes, an axis indicating the frequency component, an axis indicating the duration, and an axis indicating the number of times. Fig. 5 is a diagram showing an example of a graph generated by the analysis function 15b according to the embodiment. For example, the analysis function 15b plots a square prism-shaped bar 21 indicating the frequency component, duration, and number of times of the current side-noise on a three-dimensional coordinate system.

[0045] The analysis function 15b also plots square prism-shaped bars indicating the frequency components, duration and number of occurrences of past side-noises in a three-dimensional coordinate system. For example, a case where the past refers to one month ago will be described. In this case, the analysis function 15b acquires the frequency components, duration and number of occurrences of side-noises one month ago from the storage circuit 12. Then, the analysis function 15b plots square prism-shaped bars 22 indicating the acquired frequency components, duration and number of occurrences of side-noises one month ago in a three-dimensional coordinate system. In this way, the analysis function 15b generates a three-dimensional graph (specifically, a three-dimensional bar graph) in which information indicating the patient's current respiratory state and information indicating the patient's past respiratory state are depicted in a manner that allows them to be compared. That is, the analysis function 15b generates a three-dimensional graph indicating multiple analysis results at multiple analyzed time points. The analysis function 15b generates a three-dimensional graph so that the frequency components, duration and number of occurrences of the current side-noise and the frequency components, duration and number of occurrences of the past side-noises are displayed in different manners. For example, the analysis function 15b generates a three-dimensional graph such that the color of the bar 21 is different from the color of the bar 22. In this manner, the analysis function 15b according to the present embodiment generates a three-dimensional graph by plotting the rectangular prism-shaped bars 21 and 22, which indicate a plurality of frequency components, a plurality of durations, and a plurality of occurrences at a plurality of time points, on an axis indicating the frequency components, an axis indicating the duration, and an axis indicating the occurrences. The bars 21 and 22 are an example of information indicating a plurality of frequency components, a plurality of durations, and a plurality of occurrences at a plurality of time points.

[0046] In this embodiment, the three axes constituting the three-dimensional graph on which the bars 21 are plotted are the same as the three axes constituting the three-dimensional graph on which the bars 22 are plotted. That is, the three axes on which the bars 21 are plotted are the same as the three axes on which the bars 22 are plotted. In this way, in this embodiment, since the three axes are commonly used, the bars 21 indicating the frequency components, durations, and number of occurrences of the current sub-noise are plotted in one three-dimensional graph, and the bars 22 indicating the frequency components, durations, and number of occurrences of the past sub-noises are plotted. That is, the analysis function 15b according to this embodiment generates a three-dimensional graph by plotting the bars 21 and 22 indicating multiple frequency components, multiple durations, and multiple occurrences at multiple time points on a single axis indicating the frequency components, a single axis indicating the duration, and a single axis indicating the number of occurrences.

[0047] Here, a comparative example will be described in which a three-dimensional graph on which rectangular prism-shaped bars indicating the frequency components, duration, and number of occurrences of the current side-noise are plotted is different from a three-dimensional graph on which rectangular prism-shaped bars indicating the frequency components, duration, and number of occurrences of the past side-noise are plotted. In the comparative example, three axes constituting a three-dimensional graph on which rectangular prism-shaped bars indicating the frequency components, duration, and number of occurrences of the current side-noise are plotted are different from three axes constituting a three-dimensional graph on which rectangular prism-shaped bars indicating the frequency components, duration, and number of occurrences of the past side-noise are plotted. Thus, in the comparative example, two three-dimensional graphs are displayed, but it is difficult for the user to compare the two three-dimensional graphs because the two three-dimensional graphs are displayed separately. Therefore, in the comparative example, it is difficult for the user to easily grasp the change over time in the patient's respiratory condition.

[0048] In contrast, in this embodiment, as described above, bars 21 indicating the frequency components, duration and number of occurrences of the current side-noise are plotted in one three-dimensional graph, and bars 22 indicating the frequency components, duration and number of occurrences of the past side-noise are plotted. Therefore, according to this embodiment, compared to the comparative example, it is easier for the user to compare the frequency components, duration and number of occurrences of the current side-noise with the frequency components, duration and number of occurrences of the past side-noise. Therefore, the user can easily grasp the change over time in the patient's respiratory condition.

[0049] (Step S104) Next, in step S104, the output function 15c outputs the three-dimensional graph generated in step S103. For example, the output function 15c outputs the three-dimensional graph shown in FIG. 5 to the display 14, causing the display 14 to output the three-dimensional graph. Specifically, the output function 15c causes the display 14 to display the three-dimensional graph. In this manner, the output function 15c and the display 14 output a plurality of analysis results at a plurality of analyzed time points. Therefore, as described above, the analysis device 10 and the auscultation support system 1 according to this embodiment can allow the user to easily grasp the change over time of the patient's respiratory condition. Therefore, the analysis device 10 and the auscultation support system 1 can support the user in auscultation.

[0050] In addition, in step S104, the output function 15c may control the NW interface 11 to output the three-dimensional graph generated in step S103 to the terminal 81. That is, the output function 15c may output the three-dimensional graph generated in step S103 to the terminal 81 via the NW interface 11. In this case, the terminal 81 receives the three-dimensional graph and outputs the received three-dimensional graph. Specifically, the terminal 81 displays the three-dimensional graph. Therefore, even in this case, the auscultation support system 1 can allow the user to easily grasp the change over time of the patient's respiratory condition. In addition, the auscultation support system 1 can support the user in auscultation. In addition, the terminal 81 is an example of an output unit.

[0051] Also, in step S104, the output function 15c may output the three-dimensional graph generated in step S103 to an electronic medical record system connected to the analysis device 10 via a network via the NW interface 11. In this case, the electronic medical record system receives the three-dimensional graph and outputs the received three-dimensional graph. Specifically, the electronic medical record system displays the three-dimensional graph on the electronic medical record displayed on the display in the electronic medical record system. Therefore, even in this case, the auscultation support system 1 can allow the user to easily grasp the change over time of the patient's respiratory condition. Then, after grasping the change over time of the patient's respiratory condition, the user inputs the auscultation result to the electronic medical record via an input interface in the electronic medical record system. Therefore, the auscultation support system 1 can support the user in auscultation. The electronic medical record system is an example of an output unit.

[0052] In step S104, at least one of the display 14, the terminal 81, and the electronic medical record system may switch between the bars 21 and 22 in the three-dimensional graph at predetermined time intervals. That is, at least one of the display 14, the terminal 81, and the electronic medical record system may output each of a plurality of analysis results at a plurality of time points in the three-dimensional graph by switching between them for each time point.

[0053] The auscultation support system 1 and the analysis device 10 according to the embodiment have been described above. According to the embodiment, as described above, the user can easily grasp the change over time of the patient's respiratory condition. In the embodiment, the processing circuit 15 performs the process shown in FIG. 3 in real time. For example, the acquisition function 15a acquires the received respiratory sound data every time the respiratory sound data transmitted from the electronic stethoscope 80 is received. The analysis function 15b analyzes the respiratory sound data every time the acquisition function 15a acquires the respiratory sound data. The output function 15c outputs a plurality of analysis results at a plurality of time points acquired by the analysis every time the analysis function 15b analyzes the respiratory sound data. Therefore, according to the embodiment, the user can easily grasp the change over time of the patient's respiratory condition immediately in real time.

[0054] (First Modification of the Embodiment) In the above-described embodiment, the analysis device 10 outputs a three-dimensional graph as a plurality of analysis results at a plurality of time points. However, the analysis device 10 may output a plurality of scores indicating the respiratory state of the patient at a plurality of time points as a plurality of analysis results at a plurality of time points. Therefore, such a modification will be described as Modification 1 of the embodiment. Note that in the description of Modification 1 of the embodiment, differences from the embodiment will be mainly described, and a description of the same configuration as the embodiment may be omitted.

[0055] Fig. 6 is a diagram showing an example of a data structure of table 12b according to Modification 1 of the embodiment. In Modification 1, table 12b shown in Fig. 6 is stored in the memory circuitry 12. Table 12b is a table for deriving a score indicating the respiratory state of the patient from the frequency, duration, and number of occurrences of the side-noise acquired in step S102. In table 12b, scores are registered in association with combinations of the frequency, duration, and number of occurrences of the side-noise.

[0056] Table 12b has a plurality of records registered therein, each of which has the fields "frequency," "duration," "number of occurrences," and "score." The "frequency" field registers a range of frequency components. The "duration" field registers a range of durations.

[0057] The "number of times" field contains a range of times. For example, in the example in Figure 6, the "number of times" field of the first record contains a range of times from "n1" to "n2". The "number of times" field of the second record contains a range of times from "n3" to "n4".

[0058] In the "score" field, a score indicating the patient's respiratory condition is registered. For example, the score is an integer between "1" and "10." In this case, the smaller the score value, the worse the respiratory condition indicated by the score. Also, the larger the score value, the better the respiratory condition indicated by the score.

[0059] For example, in the example of FIG. 6, the score "6" is registered in the "score" field of the first record in association with the combination of the frequency component range of "f1" or more and less than "f2", the duration range of "t1" or more and less than "t2", and the number of times "n1" or more and less than "n2". Also, the score "3" is registered in the "score" field of the second record in association with the combination of the frequency component range of "f3" or more and less than "f4", the duration range of "t3" or more and less than "t4", and the number of times "n3" or more and less than "n4". That is, the first record indicates that the score is "6" when the frequency component is in the range of "f1" or more and less than "f2", the duration is in the range of "t1" or more and less than "t2", and the number of times is in the range of "n1" or more and less than "n2". Similarly, the second record indicates that the score is "3" when the frequency components are within the range of "f3" or greater and less than "f4", the duration is within the range of "t3" or greater and less than "t4", and the number of occurrences is within the range of "n3" or greater and less than "n4".

[0060] (Step S102 in Modification 1) A specific example will be described in which the analysis function 15b derives a score indicating the current respiratory state and a score indicating the past respiratory state by using the table 12b in step S102 of the modified example 1. For example, the analysis function 15b acquires the frequency component of the current side-noise, the duration of the current side-noise, and the number of times of the current side-noise by a method similar to that described in the embodiment.

[0061] Then, the analysis function 15b derives a score that matches the frequency components of the current side-noise, the duration of the current side-noise, and the current number of side-noises from the table 12b. Specifically, the analysis function 15b identifies, from all the records in the table 12b, a record in which a frequency component range including the frequency components of the current side-noise is registered in the "frequency" field, a duration range including the duration of the current side-noise is registered in the "duration" field, and a number range including the current number of side-noises is registered in the "number of times" field. The analysis function 15b then obtains the score registered in the "score" field of the identified record, and derives the obtained score as a score indicating the current respiratory condition.

[0062] Then, the analysis function 15b stores the score indicating the current respiratory state in the memory circuitry 12 in association with the current time. As described above, the process shown in FIG. 3 is repeatedly executed in real time. In this way, each time the process of step S102 is repeatedly executed, the score is stored in the memory circuitry 12 in association with the time at which step S102 is executed. That is, the analysis function 15b repeatedly executes the process of step S102 to derive multiple scores at multiple time points based on the frequency components, durations, and counts at multiple time points. Then, the analysis function 15b stores the derived multiple scores at multiple time points in the memory circuitry 12. Therefore, the memory circuitry 12 stores the score corresponding to the current time and the scores corresponding to past times as history data.

[0063] (Step S103 in Modification 1) Next, in step S103 of the first modification, the analysis function 15b generates a message indicating a score indicating the current respiratory state of the patient and a message indicating a score indicating the past respiratory state to be displayed on the display 14.

[0064] 7 is a diagram showing an example of a message generated by the analysis function 15b according to the first modification of the embodiment. For example, in step S103, the analysis function 15b acquires a score "6" indicating the current respiratory condition of the patient from the memory circuitry 12. Then, the analysis function 15b generates a message "Current respiratory condition score: 6" 23 indicating the score "6" indicating the current respiratory condition of the patient.

[0065] Also, in step S103, the analysis function 15b acquires a score indicating the patient's past respiratory condition from the memory circuitry 12. For example, a case will be described where the past refers to one month ago from the present time. In this case, the analysis function 15b acquires a score of "3" indicating the patient's respiratory condition one month ago from the memory circuitry 12. Then, the analysis function 15b generates a message "Respiratory condition score one month ago: 3" 24 indicating the score of "3" indicating the patient's respiratory condition one month ago.

[0066] (Step S104 in Modification 1) Next, in step S104 of the first modification, the output function 15c outputs a plurality of scores at a plurality of time points derived. Specifically, the output function 15c outputs a plurality of messages indicating a plurality of scores at a plurality of time points derived. For example, the output function 15c outputs the message 23 and the message 24 shown in FIG. 7 to the display 14, and causes the message 23 and the message 24 to be output to the display 14. Specifically, the output function 15c causes the message 23 and the message 24 to be displayed on the display 14 side by side so as to be comparable. In this way, the output function 15c and the display 14 output a plurality of scores as a plurality of analysis results at a plurality of time points analyzed. Thereby, for example, a user who has confirmed the message 23 and the message 24 can easily understand that the respiratory condition of the patient is improving. Therefore, the analysis device 10 and the auscultation support system 1 according to this embodiment can allow the user to easily understand the change over time of the respiratory condition of the patient. Therefore, the analysis device 10 and the auscultation support system 1 can support the auscultation by the user.

[0067] In step S104, the output function 15c may output the message 23 and the message 24 to the terminal 81 via the NW interface 11. In this case, the terminal 81 receives the message 23 and the message 24, and outputs (displays) the received message 23 and the message 24. Therefore, even in this case, the auscultation support system 1 can allow the user to easily grasp the change over time in the respiratory condition of the patient. In turn, the auscultation support system 1 can support the user in auscultation.

[0068] In step S104, the output function 15c may output the message 23 and the message 24 to the electronic medical record system via the NW interface 11. In this case, the electronic medical record system receives the message 23 and the message 24, and outputs (displays) the received message 23 and the message 24 on the electronic medical record displayed on the display. Therefore, even in this case, the auscultation support system 1 can allow the user to easily grasp the change over time of the patient's respiratory condition. Then, after grasping the change over time of the patient's respiratory condition, the user inputs the auscultation result into the electronic medical record via the input interface. Therefore, the auscultation support system 1 can support the user in auscultation.

[0069] In step S104, at least one of the display 14, the terminal 81, and the electronic medical record system may switch between displaying the message 23 and the message 24 at predetermined time intervals. That is, at least one of the display 14, the terminal 81, and the electronic medical record system may output a plurality of analysis results at a plurality of time points by switching between them at each time point.

[0070] The above describes the auscultation supporting system 1 and the analysis device 10 according to the first modification of the embodiment. As described above, the first modification allows the user to easily grasp the change over time in the respiratory condition of the patient.

[0071] (Modification 2 of the embodiment) In the above-mentioned modified example 1, the analysis device 10 outputs a plurality of scores as a plurality of analysis results at a plurality of time points. However, the analysis device 10 may further determine whether the patient's respiratory condition is improving or worsening from the plurality of scores, and output the determination result. Therefore, such a modified example will be described as modified example 2 of the embodiment. Note that in the description of modified example 2 of the embodiment, differences from modified example 1 will be mainly described, and the description of the same configuration as modified example 1 may be omitted.

[0072] Analysis device 10 according to Modification 2 executes the processes described below in addition to the processes executed by analysis device 10 according to Modification 1.

[0073] (Step S102 in Modification 2) For example, in step S102 of the second modification, the analysis function 15b compares a score indicating the patient's current respiratory condition with a score indicating the patient's past respiratory condition to determine whether the patient's respiratory condition is improving or worsening. That is, the analysis function 15b determines whether the patient's respiratory condition is improving or worsening based on multiple scores at multiple points in time.

[0074] For example, the analysis function 15b determines that the patient's respiratory condition has improved when the score indicating the patient's current respiratory condition is greater than the score indicating the patient's past respiratory condition. On the other hand, the analysis function 15b determines that the patient's respiratory condition has worsened when the score indicating the patient's current respiratory condition is smaller than the score indicating the patient's past respiratory condition. In addition, the analysis function 15b may determine that the patient's respiratory condition has not changed when the score indicating the patient's current respiratory condition is the same as the score indicating the patient's past respiratory condition.

[0075] (Step S103 in Modification 2) Then, in step S103 of the second modification, the analysis function 15b generates a message indicating the determination result to be displayed on the display 14. Figs. 8 and 9 are diagrams showing an example of a message generated by the analysis function 15b according to the second modification of the embodiment. For example, if it is determined in step S102 that the respiratory condition of the patient has improved, the analysis function 15b generates in step S103 a message "respiratory condition is improving" 25 indicating the determination result, as shown in Fig. 8.

[0076] Also, if it is determined in step S102 that the patient's respiratory condition is worsening, it is considered necessary to perform a new examination or treatment on the patient. For example, it is possible to perform various examinations such as a CT scan examination, a biopsy to check lung function, and a sample test such as blood sampling, or to perform treatment on the patient. Therefore, in step S103, the analysis function 15b generates a message that indicates the determination result and encourages the patient to be examined or treated. For example, in step S103, the analysis function 15b generates a message "The respiratory condition is worsening. Please perform additional CT scan." 26 that indicates the determination result and encourages the patient to be examined, as shown in FIG. 9. The analysis function 15b may also generate a message "The respiratory condition is worsening. Please treat the patient." that indicates the determination result and encourages the patient to be treated. In the following description, the two messages, the message 26 and the message "The respiratory condition is worsening. Please treat the patient," are simply referred to as "message 26, etc."

[0077] (Step S104 in Modification 2) Next, in step S104 of the second modification, the output function 15c outputs the determination result. Specifically, the output function 15c outputs a message indicating the determination result. For example, when the message 25 shown in FIG. 8 is generated, the output function 15c outputs the message 25 to the display 14, and causes the message 25 to be output to the display 14. Specifically, the output function 15c causes the message 25 to be displayed on the display 14. In this manner, the output function 15c and the display 14 output the message 25. Thereby, for example, a user who checks the message 25 can easily understand that the patient's respiratory condition has improved.

[0078] 9 is generated, the output function 15c outputs the message 26, etc. to the display 14, causing the message 26, etc. to be output to the display 14. Specifically, the output function 15c causes the message 26, etc. to be displayed on the display 14. In this manner, the output function 15c and the display 14 output the message 26, etc. As a result, for example, a user who checks the message 26, etc. can easily understand that the patient's respiratory condition is worsening.

[0079] Therefore, the analysis device 10 and the auscultation support system 1 according to the second modification of the embodiment can allow the user to easily grasp the change over time in the respiratory condition of the patient. Therefore, the analysis device 10 and the auscultation support system 1 can support the user in auscultation.

[0080] Furthermore, the user who has checked the message 26 or the like can easily understand that an examination or treatment is necessary. Therefore, the analysis device 10 and the auscultation support system 1 according to the second modification can support the user to proceed to the next diagnostic workflow.

[0081] In step S104, the output function 15c may output the message 25, the message 26, etc. to the terminal 81 via the NW interface 11. In this case, the terminal 81 receives the message 25, the message 26, etc., and outputs (displays) the received message 25, the message 26, etc. Therefore, even in this case, the auscultation support system 1 can allow the user to easily grasp the change over time in the respiratory condition of the patient. In turn, the auscultation support system 1 can support the user in auscultation.

[0082] In step S104, the output function 15c may output the message 25 or the message 26 to the electronic medical record system via the NW interface 11. In this case, the electronic medical record system receives the message 25 or the message 26, and displays the received message 25 or the message 26 on the electronic medical record displayed on the display in the electronic medical record system. Therefore, even in this case, the auscultation support system 1 allows the user to easily grasp the change over time of the patient's respiratory condition. Then, after grasping the change over time of the patient's respiratory condition, the user inputs the auscultation result to the electronic medical record via the input interface. Therefore, the auscultation support system 1 can support the user in auscultation.

[0083] The above describes the auscultation support system 1 and the analysis device 10 according to the second modification of the embodiment. As described above, the second modification allows the user to easily grasp the change over time in the respiratory condition of the patient.

[0084] (Modification 3 of the embodiment) In the above-described embodiment, the analysis device 10 outputs a three-dimensional graph as a plurality of analysis results at a plurality of time points. However, the analysis device 10 may output, as a plurality of analysis results at a plurality of time points, a type of adventitious noise whose frequency is equal to or exceeds a threshold value for each of the plurality of time points. Therefore, such a modification will be described as Modification 3 of the embodiment. Note that in the description of Modification 3 of the embodiment, differences from the embodiment will be mainly described, and a description of the same configuration as the embodiment may be omitted.

[0085] (Step S102 in Modification 3) In step S102 of the third modification, the analysis function 15b identifies one or more current types of side-noises by a method similar to that described in the above-mentioned embodiment. The analysis function 15b also acquires the current number of side-noises for each identified type of side-noise by a method similar to that described in the above-mentioned embodiment.

[0086] Then, the analysis function 15b identifies a type of side-noise whose number of occurrences is equal to or greater than the threshold α among the one or more current types of side-noise. Then, the analysis function 15b stores the identified type of side-noise (the type of side-noise whose number of occurrences is equal to or greater than the threshold α) and the number of occurrences in the memory circuit 12 in association with the current time. As described above, the process shown in FIG. 3 is repeatedly executed in real time. In this way, each time the process of step S102 is repeatedly executed, the memory circuit 12 stores the type of side-noise whose number of occurrences is equal to or greater than the threshold α and the number of occurrences in association with the time at which step S102 is executed. That is, the analysis function 15b repeatedly executes the process of step S102 to store the type of side-noise whose number of occurrences is equal to or greater than the threshold α and the number of occurrences at multiple points in time in the memory circuit 12. Therefore, the memory circuit 12 stores the type of side-noise whose number of occurrences is equal to or greater than the threshold α corresponding to the current time and the number of occurrences of side-noise whose number of occurrences is equal to or greater than the threshold α and the type of side-noise whose number of occurrences is equal to or greater than the threshold α corresponding to the past time as history data.

[0087] (Step S103 in Modification 3) Next, in step S103 of the third modification, the analysis function 15b generates a table showing types of adjunct noises corresponding to the current time and whose frequency is equal to or exceeds the threshold value α, to be displayed on the display 14. Furthermore, in step S103 of the third modification, the analysis function 15b also generates a table showing types of adjunct noises corresponding to past times and whose frequency is equal to or exceeds the threshold value α, to be displayed on the display 14.

[0088] 10 is a diagram showing an example of a table generated by the analysis function 15b according to the third modified example of the embodiment. For example, in step S103, the analysis function 15b generates a table 27 in which types of adjunct noises corresponding to the current time and whose frequency is equal to or exceeds a threshold value α are associated with the frequency and registered.

[0089] For example, in Table 27, the type of adjunct-noise "a2" corresponding to the current time and having a frequency "n5" equal to or greater than the threshold value α is associated with the frequency "n5." Also, in Table 27, the type of adjunct-noise "a7" corresponding to the current time and having a frequency "n6" equal to or greater than the threshold value α is associated with the frequency "n6."

[0090] Also, in step S103, the analysis function 15b generates the message "present" shown in FIG.

[0091] In step S103, the analysis function 15b acquires from the memory circuit 12 the type and number of times of the adjunct-noise that corresponds to a time in the past and that is equal to or greater than the threshold value α. For example, a case will be described where the past refers to one month ago from the present time. In this case, the analysis function 15b acquires from the memory circuit 12 the types of adjunct-noises "a2", "a7", etc. that correspond to the time one month ago of the patient and that are equal to or greater than the threshold value α. The analysis function 15b also acquires the numbers "n7", "n8" of these numbers from the memory circuit 12. Then, the analysis function 15b generates a table 28 in which the type of adjunct-noise "a2" and the number of times "n7" are associated and registered, and the type of adjunct-noise "a7" and the number of times "n8" are associated and registered, as shown in FIG. 10.

[0092] Also, in step S103, the analysis function 15b generates the message "One month ago" shown in FIG.

[0093] (Step S104 in Modification 3) Next, in step S104 of the third modification, the output function 15c outputs the type of the adventitious noise whose frequency is equal to or greater than the threshold value α for each of the multiple time points. Specifically, the output function 15c outputs multiple tables for the multiple time points. For example, the output function 15c associates the message "present" with the table 27 shown in FIG. 10 and outputs it to the display 14, and causes the table 27 and the message "present" to be output to the display 14. Also, the output function 15c associates the message "one month ago" with the table 28 shown in FIG. 10 and outputs it to the display 14, and causes the table 28 and the message "one month ago" to be output to the display 14. Specifically, the output function 15c associates the table 27 with the message "present" and displays them on the display 14, and also associates the table 28 with the message "one month ago" and displays them on the display 14. Here, the output function 15c causes the table 27 and the table 28 to be displayed side by side on the display 14 so that they can be compared. In this way, the output function 15c and the display 14 output a plurality of tables 27, 28 as a plurality of analysis results at a plurality of analyzed time points. This allows, for example, a user who checks tables 27, 28 to easily understand the change over time in the patient's respiratory condition. Therefore, the analysis device 10 and the auscultation support system 1 according to this embodiment can allow the user to easily understand the change over time in the patient's respiratory condition. Therefore, the analysis device 10 and the auscultation support system 1 can support the user in auscultation.

[0094] In step S104, the output function 15c may output the tables 27 and 28 and the messages "now" and "one month ago" to the terminal 81 via the NW interface 11. In this case, the terminal 81 displays the tables 27 and 28 and the messages "now" and "one month ago" in the same way as the display 14. Therefore, even in this case, the auscultation support system 1 can allow the user to easily grasp the change over time in the patient's respiratory condition. In turn, the auscultation support system 1 can support the user in auscultation.

[0095] In step S104, the output function 15c may output the tables 27 and 28 and the messages "Current" and "One month ago" to the electronic medical record system via the NW interface 11. In this case, the electronic medical record system displays the tables 27 and 28 and the messages "Current" and "One month ago" in the same way as the display 14. Specifically, the electronic medical record system displays the tables 27 and 28 and the messages "Current" and "One month ago" on the electronic medical record displayed on the display. Therefore, even in this case, the auscultation support system 1 can allow the user to easily grasp the change over time of the patient's respiratory condition. Then, the user inputs the auscultation result into the electronic medical record via the input interface after grasping the change over time of the patient's respiratory condition. Therefore, the auscultation support system 1 can support the user in auscultation.

[0096] Also, in step S104, at least one of the display 14, the terminal 81, and the electronic medical record system may switch between displaying Table 27 and Table 28 at predetermined time intervals. That is, at least one of the display 14, the terminal 81, and the electronic medical record system may output a plurality of analysis results at a plurality of time points by switching between them at each time point. In this case, at least one of the display 14, the terminal 81, and the electronic medical record system may switch between displaying the message "Current" and the message "One month ago" at predetermined time intervals in synchronization with the display timing of Table 27 and Table 28.

[0097] The above describes the auscultation support system 1 and the analysis device 10 according to the third modification of the embodiment. As described above, the third modification allows the user to easily grasp the change over time in the respiratory condition of the patient.

[0098] (Fourth Modification of the Embodiment) In the above-described embodiment, the analysis device 10 outputs a three-dimensional graph as a plurality of analysis results at a plurality of time points. However, the analysis device 10 may output a possibility that the patient is affected by a disease for each disease at each of the plurality of time points as a plurality of analysis results at the plurality of time points. Therefore, such a modification will be described as Modification 4 of the embodiment. Note that in the description of Modification 4 of the embodiment, differences from the embodiment will be mainly described, and a description of the same configuration as the embodiment may be omitted.

[0099] Fig. 11 is a diagram for explaining an example of a trained model 12c according to Modification 4 of the embodiment. In Modification 4, the trained model 12c shown in Fig. 11 is stored in the storage circuitry 12. When respiratory sound data is input, the trained model 12c outputs the possibility that the patient suffers from each of a plurality of diseases corresponding to the input respiratory sound data.

[0100] The trained model 12c is generated by training using machine learning. For example, the trained model 12c is generated by an external device. Here, the external device generates the trained model 12c by, for example, learning the relationship between the respiratory sound data of a patient and the disease (disease name) of the patient from which the respiratory sound data was obtained. In this way, the external device generates the trained model 12c by learning the respiratory sound data and the disease name in association with each other. For example, the external device performs machine learning by inputting the respiratory sound data as input data and the disease name as teacher data into a machine engine. For example, the machine learning engine performs machine learning using various algorithms such as deep learning, neural network, logistic regression analysis, nonlinear discriminant analysis, support vector machine (SVM), random forest, and naive Bayes. The external device generates the trained model 12c as a result of such machine learning.

[0101] (Step S102 in Modification 4) In step S102 of the fourth modification, the analysis function 15b inputs the respiratory sound data to the trained model 12c. Then, the analysis function 15b obtains the possibility that the patient is affected by each of the multiple diseases output from the trained model 12c.

[0102] Then, the analysis function 15b stores the possibility that the patient is affected by each of the multiple diseases in the memory circuitry 12 in association with the current time. As described above, the process shown in FIG. 3 is repeatedly executed in real time. In this way, each time the process of step S102 is repeatedly executed, the memory circuitry 12 stores the possibility that the patient is affected by each of the multiple diseases in association with the time at which step S102 is executed. That is, the analysis function 15b repeatedly executes the process of step S102, thereby storing the possibility that the patient is affected by each of the multiple diseases at each of the multiple time points in the memory circuitry 12. Therefore, the memory circuitry 12 stores the possibility that the patient is affected by each of the multiple diseases corresponding to the current time and the possibility that the patient is affected by each of the multiple diseases corresponding to the past time as history data.

[0103] (Step S103 in Modification 4) Next, in step S103 of the fourth modification, the analysis function 15b generates a table showing the possibility that the patient has each of a plurality of diseases corresponding to the current time to be displayed on the display 14. Furthermore, in step S103 of the fourth modification, the analysis function 15b also generates a table showing the possibility that the patient has each of a plurality of diseases corresponding to past times to be displayed on the display 14.

[0104] 12 is a diagram showing an example of a table generated by the analysis function 15b according to the modified example 4 of the embodiment. For example, in step S103, the analysis function 15b generates a table 29 in which the possibility that the patient is affected by each of a plurality of diseases corresponding to the current time is registered.

[0105] For example, Table 29 registers a message "Possibility of pneumothorax: 60%" indicating that the possibility of pneumothorax is 60% at the current time. Also, Table 29 registers a message "Possibility of interstitial pneumonia: 40%" indicating that the possibility of interstitial pneumonia is 40% at the current time.

[0106] Also, in step S103, the analysis function 15b generates the message "present" shown in FIG.

[0107] Also, in step S103, the analysis function 15b acquires from the memory circuitry 12 the possibility that the patient is suffering from each of a plurality of diseases corresponding to a time in the past. For example, a case will be described where the past here refers to one month ago. In this case, the analysis function 15b acquires from the memory circuitry 12 the possibility that the patient is suffering from each of a plurality of diseases corresponding to a time one month ago. Then, the analysis function 15b generates a table 30 in which the possibility that the patient is suffering from each of a plurality of diseases corresponding to a time one month ago is registered.

[0108] For example, a message "Possibility of pneumothorax: 80%" indicating that the possibility of pneumothorax is 80% one month ago is registered in Table 30. Also, a message "Possibility of interstitial pneumonia: 60%" indicating that the possibility of interstitial pneumonia is 60% one month ago is registered in Table 30.

[0109] Also, in step S103, the analysis function 15b generates the message "One month ago" shown in FIG.

[0110] (Step S104 in Modification 4) Next, in step S104 of the fourth modification, the output function 15c outputs the possibility that the patient is suffering from each of the multiple diseases at each of the multiple time points. Specifically, the output function 15c outputs multiple tables for the multiple time points. For example, the output function 15c associates the message "present" with the table 29 shown in FIG. 12. Then, the output function 15c outputs the table 29 associated with the message "present" to the display 14, and causes the table 29 and the message "present" to be output to the display 14. The output function 15c also associates the message "one month ago" with the table 30 shown in FIG. 12. Then, the output function 15c outputs the table 30 associated with the message "one month ago" to the display 14, and causes the table 30 and the message "one month ago" to be output to the display 14. Specifically, the output function 15c displays the table 29 and the message "present" in association with each other on the display 14, and also displays the table 30 and the message "one month ago" in association with each other on the display 14. Here, the output function 15c displays the table 29 and the table 30 side by side on the display 14 so that they can be compared. As a result, the display 14 displays the table 29 and the message "present" in association with each other, and also displays the table 30 and the message "one month ago" in association with each other. In this way, the output function 15c and the display 14 output a plurality of tables 29 and 30 as a plurality of analysis results at a plurality of time points. As a result, for example, a user who checks the tables 29 and 30 can easily grasp the change over time in the respiratory condition of the patient. Therefore, the analysis device 10 and the auscultation support system 1 according to the fourth modification can allow the user to easily grasp the change over time in the respiratory condition of the patient. Therefore, the analysis device 10 and the auscultation support system 1 can support the user in auscultation.

[0111] In step S104, the output function 15c may output the tables 29 and 30 and the messages "now" and "one month ago" to the terminal 81 via the NW interface 11. In this case, the terminal 81 displays the tables 29 and 30 and the messages "now" and "one month ago" in the same manner as the display 14. Therefore, even in this case, the auscultation support system 1 can allow the user to easily grasp the change over time in the patient's respiratory condition. In turn, the auscultation support system 1 can support the user in auscultation.

[0112] In step S104, the output function 15c may output the tables 29 and 30 and the messages "now" and "one month ago" to the electronic medical record system via the NW interface 11. In this case, the electronic medical record system displays the tables 29 and 30 and the messages "now" and "one month ago" on the electronic medical record displayed on the display in the electronic medical record system, similar to the display 14. Therefore, even in this case, the auscultation support system 1 can allow the user to easily grasp the change over time of the patient's respiratory condition. Then, after grasping the change over time of the patient's respiratory condition, the user inputs the auscultation result into the electronic medical record via the input interface. Therefore, the auscultation support system 1 can support the user in auscultation.

[0113] Also, in step S104, at least one of the display 14, the terminal 81, and the electronic medical record system may switch between displaying Table 29 and Table 30 at predetermined time intervals. That is, at least one of the display 14, the terminal 81, and the electronic medical record system may output a plurality of analysis results at a plurality of time points by switching between them at each time point. In this case, at least one of the display 14, the terminal 81, and the electronic medical record system may switch between displaying the message "Current" and the message "One month ago" at predetermined time intervals in synchronization with the display timing of Table 29 and Table 30.

[0114] The above describes the auscultation supporting system 1 and the analysis device 10 according to the fourth modification of the embodiment. As described above, the fourth modification allows the user to easily grasp the change over time in the respiratory condition of the patient.

[0115] In addition, in the fourth modification, the trained model 12c may be configured to output the possibility that the patient suffers from each of a plurality of diseases corresponding to the inputted respiratory sound data and the main complaint when the respiratory sound data and the main complaint are input. The trained model 12c may be configured to output the possibility that the patient suffers from each of a plurality of diseases corresponding to the inputted frequency components, duration and number of times when the frequency components, duration and number of times obtained by analyzing the respiratory sound data are input. The trained model 12c may be configured to output the possibility that the patient suffers from each of a plurality of diseases corresponding to the inputted frequency components, duration and number of times when the frequency components, duration and number of times obtained by analyzing the respiratory sound data and the main complaint are input.

[0116] (Fifth Modification of the Embodiment) The analysis device 10 may perform other processing after executing the processing of the above-mentioned embodiment or the processing of any one of the above-mentioned modified examples 1 to 4. For example, the analysis device 10 may associate the type of adjunct noise acquired by analyzing the respiratory sound data with a corresponding position on a human body simulation image (illustration image) that simulates the patient's body. Then, the analysis device 10 may output the human body simulation image to which the type of adjunct noise is associated. Therefore, such a modified example will be described as modified example 5 of the embodiment. Note that in the description of modified example 5 of the embodiment, differences from the embodiment or any one of the modified examples 1 to 4 will be mainly described, and a description of the same configuration as the embodiment or any one of the modified examples 1 to 4 may be omitted.

[0117] 13 is a diagram for explaining an example of a process executed by the analysis device 10 according to the fifth modification of the embodiment. In the fifth modification, a human body simulation image 31 that simulates a patient's body is stored in the memory circuitry 12. The analysis function 15b acquires the human body simulation image 31 stored in the memory circuitry 12. The human body simulation image 31 is an example of an image.

[0118] Then, the analysis function 15b acquires the auscultation target site added to the respiratory sound data. Then, the analysis function 15b superimposes elliptical marks 32 and 33 on the positions on the human body simulation image 31 that correspond to the auscultation target site. Then, the analysis function 15b connects each of the types of accessory noises "high-pitched discontinuous rales" and "continuous rales" acquired by analyzing the respiratory sound data to the marks 32 and 33 with a line segment. In this embodiment, the analysis function 15b connects the message "high-pitched discontinuous rales have been detected" indicating that high-pitched discontinuous rales have been detected to the mark 32 with a line segment. In addition, the analysis function 15b connects the message "continuous rales have been detected" indicating that continuous rales have been detected to the mark 33 with a line segment. In this way, the analysis function 15b associates each of the types of accessory noises "high-pitched discontinuous rales" and "continuous rales" acquired by analyzing the respiratory sound data with the corresponding positions on the human body simulation image 31.

[0119] Then, the output function 15c outputs to the display 14 the human body simulating image 31 associated with the positions corresponding to the types of adventitious noises "high-pitched intermittent rales" and "continuous rales". As a result, the display 14 outputs (displays) the human body simulating image 31. In this manner, the output function 15c and the display 14 output the human body simulating image 31 associated with the positions corresponding to the types of adventitious noises. This allows, for example, a user who checks the human body simulating image 31 to easily grasp the area where the adventitious noise is occurring. Therefore, the analysis device 10 and the auscultation support system 1 according to this embodiment can support auscultation by the user.

[0120] The output function 15c may output the human body simulation image 31 associated with the position corresponding to the type of adventitious noise to the terminal 81 via the NW interface 11. In this case, the terminal 81 displays the human body simulation image 31 associated with the position corresponding to the type of adventitious noise. Therefore, even in this case, the auscultation support system 1 can support the auscultation by the user.

[0121] In step S104, the output function 15c may output the human body simulation image 31 associated with the position corresponding to the type of adventitious noise to the electronic medical record system via the NW interface 11. In this case, the electronic medical record system displays the human body simulation image 31 associated with the position corresponding to the type of adventitious noise on the electronic medical record displayed on the display. Therefore, even in this case, the auscultation support system 1 can support the user in auscultation.

[0122] The auscultation support system 1 and the analysis device 10 according to the fifth modification of the embodiment have been described above. According to the fifth modification, like the above-mentioned embodiment or any one of the modifications of the first to fourth modifications, the user can easily grasp the change over time in the respiratory condition of the patient. Furthermore, according to the fifth modification, as described above, it is possible to support the user in auscultation.

[0123] (Sixth Modification of the Embodiment) The analysis device 10 may perform other processes after executing the process of the above-mentioned modified example 5. For example, the analysis device 10 may output a human body simulation image in which the type of adjunct noise is associated with a corresponding position, and a medical image in which a position (site) corresponding to the position (site) on the human body simulation image to which the type of adjunct noise is associated is depicted in a comparable manner. Therefore, such a modified example will be described as modified example 6 of the embodiment. Note that in the description of modified example 6 of the embodiment, differences from modified example 5 will be mainly described, and a description of the same configuration as modified example 5 may be omitted.

[0124] In the sixth modification, a clinical image such as a CT image that triggered auscultation is stored in the memory circuitry 12. For example, a doctor may determine that auscultation of a part of a patient (e.g., lungs) is necessary after checking a clinical image depicting the part. In the sixth modification, such a clinical image is stored in the memory circuitry 12. In the following description, a case will be described in which the clinical image stored in the memory circuitry 12 is a CT image, but the clinical image stored in the memory circuitry 12 is not limited to this. A clinical image is an example of a medical image.

[0125] In the sixth modification, the analysis device 10 performs the same process as in the fifth modification, and then executes the process described below.

[0126] Fig. 14 is a diagram for explaining an example of processing executed by the analysis device 10 according to the sixth modification of the embodiment. In the sixth modification, the output function 15c acquires a CT image 34 stored in the memory circuitry 12. In the CT image 34, a position (site) corresponding to a position (site) on the human body simulation image 31 to which the type of accessory noise is associated is depicted. In the example of Fig. 14, a shadow 35 is depicted at a position on the CT image 34 that corresponds to a position on the human body simulation image 31 to which the type of accessory noise is associated.

[0127] Then, as shown in FIG. 14, the output function 15c outputs the human body simulation image 31 associated with the position corresponding to the type of the adventitious noise to the display 14. Furthermore, the output function 15c outputs the acquired CT image 34 to the display 14. As a result, the display 14 outputs (displays) the human body simulation image 31 and the CT image 34 in a comparable manner. In this way, the output function 15c and the display 14 output the human body simulation image 31 and the CT image 34 associated with the position corresponding to the type of the adventitious noise. As a result, for example, a user who has confirmed the human body simulation image 31 can make a more comprehensive diagnosis by taking into account the part where the adventitious noise is generated and the location of the shadow 35. Therefore, the analysis device 10 and the auscultation support system 1 according to this embodiment can support the auscultation by the user.

[0128] The output function 15c may output the human body simulation image 31 and the CT image 34 associated with the positions corresponding to the types of adventitious noise to the terminal 81 via the NW interface 11. In this case, the terminal 81 displays the human body simulation image 31 and the CT image 34 associated with the positions corresponding to the types of adventitious noise in a comparable manner. Therefore, even in this case, the auscultation support system 1 can support the user in auscultation.

[0129] In step S104, the output function 15c may output the human body simulation image 31 and the CT image 34 associated with the positions corresponding to the types of adventitious noise to the electronic medical record system via the NW interface 11. In this case, the electronic medical record system displays the human body simulation image 31 and the CT image 34 associated with the positions corresponding to the types of adventitious noise on the electronic medical record displayed on the display. Therefore, even in this case, the auscultation support system 1 can support the user in auscultation.

[0130] The auscultation support system 1 and the analysis device 10 according to the sixth modification of the embodiment have been described above. According to the sixth modification, similarly to the fifth modification, the user can easily grasp the change over time in the respiratory condition of the patient. Furthermore, according to the sixth modification, as described above, it is possible to support the user in auscultation.

[0131] (Seventh Modification of the Embodiment) After executing the process of the above-mentioned modification 5, the analysis device 10 may further perform a process different from that of modification 6. For example, in modification 5, the position (site) on the human body simulation image 31 to which the type of the adjunct noise is associated is the position where the adjunct noise was detected, and is considered to require detailed examination. Therefore, the analysis device 10 may further output a message to prompt the examination of the position where the adjunct noise was detected. Therefore, such a modification will be described as modification 7 of the embodiment. Note that in the description of modification 7 of the embodiment, differences from modification 5 will mainly be described, and a description of the same configuration as modification 5 may be omitted.

[0132] In the seventh modification, the analysis device 10 performs the same process as in the fifth modification, and then executes the process described below.

[0133] In the seventh modification, the output function 15c outputs to the display 14 the human body simulation image 31 in which the type of adventitious noise is associated with the corresponding position, as in the fifth modification. Furthermore, the output function 15c outputs to the display 14 a message to encourage the user to examine the position where the adventitious noise was detected. For example, if the position where the adventitious noise was detected is the "upper left lung", the output function 15c outputs to the display 14 the message "Please take a CT scan of the upper left lung" to encourage the user to examine the upper left lung where the adventitious noise was detected. As a result, the display 14 outputs (displays) the human body simulation image 31 and the message "Please take a CT scan of the upper left lung."

[0134] In this way, the output function 15c and the display 14 output the human body simulation image 31 associated with the position corresponding to the type of the adventitious noise and a message for encouraging the user to inspect the position where the adventitious noise was detected. This allows, for example, a user who has confirmed such a message to easily understand that a CT scan of the position where the adventitious noise was detected needs to be performed. Therefore, the analysis device 10 and the auscultation support system 1 according to the seventh modification can support the user to proceed to the next diagnostic workflow. Therefore, the analysis device 10 and the auscultation support system 1 according to the seventh modification can support the user in auscultation.

[0135] The output function 15c may output to the terminal 81 via the NW interface 11 the human body simulating image 31 associated with the position corresponding to the type of adjunct noise and a message for encouraging the user to inspect the position where the adjunct noise was detected. In this case, the terminal 81 displays the human body simulating image 31 associated with the position corresponding to the type of adjunct noise and a message for encouraging the user to inspect the position where the adjunct noise was detected. Therefore, even in this case, the auscultation support system 1 can support the user in auscultation.

[0136] In step S104, the output function 15c may output, to the electronic medical record system via the NW interface 11, a message for encouraging the user to inspect the human body simulating image 31 associated with the position corresponding to the type of adjunct noise and the position where the adjunct noise was detected. In this case, the electronic medical record system displays a message for encouraging the user to inspect the human body simulating image 31 associated with the position corresponding to the type of adjunct noise and the position where the adjunct noise was detected on the electronic medical record displayed on the display. Therefore, even in this case, the auscultation support system 1 can support the user in auscultation.

[0137] The auscultation support system 1 and the analysis device 10 according to the seventh modification of the embodiment have been described above. According to the seventh modification, similarly to the above-mentioned fifth modification, the user can easily grasp the change over time in the respiratory condition of the patient. Furthermore, according to the seventh modification, as described above, it is possible to support the user in auscultation.

[0138] (Eighth Modification of the Embodiment) In the process of the above-mentioned embodiment and the above-mentioned modified examples 1 to 7, the analysis device 10 may structure the data of the analysis result in step S103 so that the analysis result can be displayed in a display mode similar to the display mode of the above-mentioned analysis result on a plurality of devices (diverse devices) including the display 14, the terminal 81, the electronic medical record system, and other devices. Then, the analysis device 10 may output the structured data of the analysis result to a plurality of devices in step S104. Therefore, such a modified example will be described as modified example 8 of the embodiment. Note that the description of modified example 8 of the embodiment will describe a case where the process related to modified example 8 is applied to the analysis device 10 according to the above-mentioned embodiment. Therefore, the description of modified example 8 will mainly describe the points different from the embodiment, and the description of the same configuration as the embodiment may be omitted. However, the process related to modified example 8 described below may be applied to the analysis device 10 according to any one of modified examples 1 to 7.

[0139] In the eighth modification, in step S103, the analysis function 15b structures the data of the analysis result in a format that allows the analysis result to be displayed in a similar (identical) display mode to the analysis result according to the above-described embodiment on a plurality of devices. For example, the analysis function 15b converts the data of the analysis result such as frequency components, duration, and number of times into a file in a data format such as CSV format or XML format, thereby structuring the data of the analysis result in a format that allows the analysis result to be displayed in a similar display mode to the analysis result according to the above-described embodiment on a plurality of devices. Then, the analysis function 15b stores the file in a data format such as CSV format or XML format indicating the analysis result in the storage circuit 12.

[0140] Then, in step S104, the output function 15c outputs the structured data to at least one of the multiple devices. For example, the output function 15c reads a file in a data format such as CSV format or XML format indicating the analysis result from the storage circuitry 12, and outputs the read file to at least one of the multiple devices. As a result, the device that receives the file displays the analysis result indicated by the file in a display format similar to the display format of the analysis result according to the embodiment. Therefore, according to the eighth modification, the analysis result can be displayed in a similar display format on multiple devices.

[0141] The term "processor" used in the description of the above-mentioned embodiment means a circuit such as a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)). Here, instead of storing a program in the memory circuit 12, the program may be directly built into the circuit of the processor. In this case, the processor realizes its function by reading and executing the program built into the circuit. In addition, each processor in the present embodiment is not limited to being configured as a single circuit for each processor, and may be configured as a single processor by combining multiple independent circuits to realize its function.

[0142] Here, the program executed by the processor is provided in advance in a ROM (Read Only Memory) or a storage circuit. The program may be provided by being recorded in a computer-readable non-transitory storage medium such as a CD (Compact Disk)-ROM, a FD (Flexible Disk), a CD-R (Recordable), or a DVD (Digital Versatile Disk) in a format that can be installed in these devices or in a format that can be executed. The program may also be provided or distributed by being stored on a computer connected to a network such as the Internet and downloaded via the network. For example, the program is composed of modules including each of the above-mentioned processing functions. As actual hardware, a CPU reads out the program from a storage medium such as a ROM and executes it, so that each module is loaded onto a main storage device and generated on the main storage device.

[0143] According to at least one of the embodiments described above, it is possible for a user to easily grasp changes over time in a patient's condition (eg, respiratory condition).

[0144] Although some embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents as described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0145] 1. Auscultation Support System 10 Analysis device 15b Analysis function 15c Output Function

Claims

1. an analysis unit that analyzes respiratory sound data indicating the patient's respiratory sounds and adventitious sounds, and obtains, as analysis results, frequency components constituting the adventitious sounds at multiple time points, durations of the adventitious sounds, and the number of times the adventitious sounds are detected per unit time; an output unit that outputs a plurality of analysis results at the plurality of time points obtained by the analysis by the analysis unit; Equipped with the analysis unit generates a three-dimensional graph by plotting information indicating the plurality of frequency components, the plurality of durations, and the plurality of occurrences at the plurality of time points on an axis indicating the frequency components, an axis indicating the duration, and an axis indicating the occurrence; The output unit outputs the three-dimensional graph. Analysis device.

2. 2. The analysis device according to claim 1, wherein the analysis unit generates the three-dimensional graph by plotting information indicating the multiple frequency components, the multiple durations, and the multiple occurrences at the multiple time points on a single axis indicating the frequency components, a single axis indicating the duration, and a single axis indicating the occurrence.

3. The analysis device according to claim 1 , wherein the output unit outputs each of the plurality of analysis results at the plurality of time points in the three-dimensional graph by switching between them for each time point.

4. The analysis unit derives a plurality of scores indicating a respiratory state of the patient at the plurality of time points based on the plurality of frequency components, the plurality of durations, and the plurality of counts at the plurality of time points; The analysis device according to claim 1 , wherein the output unit outputs the scores.

5. The analysis unit further determines whether a respiratory condition of the patient is improving or worsening based on the plurality of scores; The analysis device according to claim 4 , wherein the output unit outputs a result of the determination.

6. The analysis device according to claim 5 , wherein the output unit further outputs a message urging the patient to be examined or treated when the patient's respiratory condition deteriorates.

7. The analysis device according to claim 1 , wherein the output unit outputs, for each of the plurality of time points, a type of the sub-noise corresponding to the frequency component and duration whose number of times is equal to or greater than a threshold value.

8. The analysis unit obtains, for each disease, a possibility that the patient is suffering from the disease based on the respiratory sound data; The analysis device according to claim 1 , wherein the output unit outputs a plurality of the probabilities at the plurality of time points.

9. The analysis unit acquires the type of the incidental noise, and associates the identified type of incidental noise with a corresponding position on an image simulating a human body, The analysis device according to claim 1 , wherein the output unit outputs the image associated with the acquired type of auxiliary noise.

10. The analysis device according to claim 9 , wherein the output unit further outputs a medical image depicting a position corresponding to the position.

11. The analysis device according to claim 9 , wherein the output unit further outputs a message to prompt the user to check the position where the auxiliary noise is detected.

12. An acquisition unit that acquires the received respiratory sound data each time the respiratory sound data is received from the acquisition device that acquires the respiratory sound data from the patient, The analysis unit analyzes the acquired respiratory sound data every time the acquisition unit acquires the respiratory sound data, The output unit outputs a plurality of analysis results at a plurality of time points obtained by the analysis each time the analysis unit analyzes the respiratory sound data. The analysis device according to any one of claims 1 to 11.

13. the analysis unit structures the data of the analysis result in a format that enables the analysis result to be displayed in the same display mode on a plurality of devices; The analysis device according to any one of claims 1 to 12, wherein the output section outputs the structured data to at least one device of the plurality of devices.

14. An auscultation support system including an analysis device and a display device, The analysis device includes: an analysis unit that analyzes respiratory sound data indicating the patient's respiratory sounds and adventitious sounds, and obtains, as analysis results, frequency components constituting the adventitious sounds at multiple time points, durations of the adventitious sounds, and the number of times the adventitious sounds are detected per unit time; an output unit that outputs the analysis results at the multiple time points acquired by the analysis unit to the display device so that the display device displays the analysis results; Equipped with the analysis unit generates a three-dimensional graph by plotting information indicating the plurality of frequency components, the plurality of durations, and the plurality of occurrences at the plurality of time points on an axis indicating the frequency components, an axis indicating the duration, and an axis indicating the occurrence; The output unit outputs the three-dimensional graph to the display device so that the display device displays the three-dimensional graph. Auscultation support system.

Images