WO2021010150A1 - Respiratory function testing device, data processing method, and respiratory function testing system - Google Patents

Abstract

This respiratory function testing device processes additional data that indicates a new measurement result of a respiratory function of a subject on the basis of past data from which a spirogram can be derived and that indicates a result of measurement of the respiratory function performed in the past, the respiratory function testing device comprising: a storage unit that stores, as past data, data which indicates a measurement result in a case in which the respiratory function is normal and data which indicates a measurement result in a case in which the respiratory function is abnormal; and a control unit that determines at least one of correlations of the additional data and the past data.

Description

Pulmonary function test device, data processing method and respiratory function test system

The present invention relates to a respiratory function test device, a data processing method, and a respiratory function test system.

Spirometry is known as a method for testing human respiratory function (for example, Patent Document 1).

Japanese Unexamined Patent Publication No. 2007-83031

With the spiral, it was sometimes difficult for medical personnel to judge the validity of the respiratory function test and the condition of the subject even at first glance.

The present invention has been made in view of the above problems, and an object of the present invention is to provide a respiratory function test device, a data processing method, and a respiratory function test system capable of information processing to support judgment.

In order to achieve the above object, the respiratory function test apparatus according to the present invention is based on the data from which the spiral can be derived and the past data showing the measurement result of the respiratory function of the subject performed in the past. It is a respiratory function test device that processes additional data indicating the measurement result of the function, and stores the data indicating the measurement result when the respiratory function is normal and the data indicating the measurement result when there is an abnormality as the past data. A storage unit and a control unit that determines at least one of the correlations between the additional data and the past data are provided.

This makes it possible to determine the correlation between the additional data and the data stored in the storage unit. That is, it becomes easy to recognize whether normal additional data has been measured or additional data indicating some abnormality has been measured based on the level of correlation. Therefore, information processing that supports judgment is possible.

As a desirable embodiment of the respiratory function test apparatus, the past data includes first data showing a measurement result when an abnormality occurs in which the validity of the respiratory function test is lost, and the control unit is based on the first data. The validity of the respiratory function test from which the additional data was obtained is determined.

This requires remeasurement, which was previously performed by an examiner who guides a respiratory function test to a subject based on the numerical values obtained from the additional data and the flow volume curve before diagnosing the condition of the subject based on the additional data. It is possible to automate the judgment of whether or not. In addition, it is possible to standardize the accuracy of determining whether remeasurement is necessary, which varies depending on the inspector. Therefore, information processing that supports judgment is possible.

As a desirable embodiment of the respiratory function test device, a display unit is provided that displays a notification including a notification prompting the reacquisition of the additional data when it is determined that the respiratory function test for which the additional data has been obtained is not valid.

This can provide information that encourages another respiratory function test.

As a desirable embodiment of the respiratory function test device, the past data includes second data showing the measurement result of the respiratory function of a healthy person and third data showing the measurement result of the respiratory function of a subject suffering from a respiratory disease. Including, the control unit further determines whether the additional data corresponds to the second data or the third data when it is determined that the respiratory function test for which the additional data is obtained is appropriate. ..

This enables information processing that supports the diagnosis of the pathological condition of the subject.

As a preferred embodiment of the respiratory function test apparatus, the third data includes asthma data of a subject suffering from asthma and difficult-to-determine data which is difficult to determine whether it is asthma or other respiratory disease. The asthma data includes tested data determined to be asthma based on the results of remeasurement after undergoing an airway reversibility test, and the difficult-to-discriminate data is the airway reversibility test in which the subject from which the tested data was obtained The tested data and the untested data are associated with each other including the untested data before passing through, and the control unit can obtain the additional data based on the collation result of the additional data and the untested data. The adequacy of performing the airway reversibility test on the measured subject is further determined.

This will increase the accuracy of the diagnosis of asthma by performing an airway reversibility test. Therefore, information processing that supports diagnosis is possible.

As a preferred embodiment of the respiratory function test apparatus, the past data includes subject attribute information including at least one of the age, sex, height, and weight of each of the plurality of subjects, and the control unit controls the subject attributes. Based on the information, it is determined whether the additional data corresponds to the second data or the third data.

This can support pathological diagnosis corresponding to subject attribute information.

As a desirable embodiment of the respiratory function test device, when the additional data corresponds to the third data, the control unit uses the third data stored in the storage unit according to the severity of the respiratory disease. Based on this, the severity of the respiratory disease of the subject is determined.

This can support the diagnosis of the severity of respiratory diseases.

As a desirable embodiment of the respiratory function test device, the control unit generates a neural network in which the additional data is input, the data stored in the storage unit is used as teacher data, and the determination result of the additional data is output. ..

This makes it possible to support judgment using machine learning.

Further, in order to achieve the above object, the data processing method according to the present invention is data showing the measurement results of a subject performed in the past by the information processing apparatus using the respiratory function test apparatus, and is a respiratory function test. This is a data processing method for processing additional data indicating a new measurement result based on data including a first data indicating a measurement result when an abnormality occurs, based on the first data. Includes steps to determine the adequacy of the respiratory function test for which the additional data were obtained.

This requires remeasurement, which was previously performed by an examiner who guides a respiratory function test to a subject based on the numerical values obtained from the additional data and the flow volume curve before diagnosing the condition of the subject based on the additional data. It is possible to automate the judgment of whether or not. In addition, it is possible to standardize the accuracy of determining whether remeasurement is necessary, which varies depending on the inspector. Therefore, information processing that supports judgment is possible.

Further, in order to achieve the above object, the respiratory function testing system according to the present invention includes a respiratory function testing device including a measuring unit for measuring the flow volume curve of the subject, and data showing the measurement results of the subject performed in the past. A respiratory function testing system including an information processing device that processes additional data indicating new measurement results based on the above, and the information processing device is used when an abnormality occurs in which the validity of the respiratory function test is lost. It includes a storage unit that stores the first data indicating the measurement result, and a control unit that determines the validity of the respiratory function test for which the additional data is obtained based on the first data.

This requires remeasurement, which was previously performed by an examiner who guides a respiratory function test to a subject based on the numerical values obtained from the additional data and the flow volume curve before diagnosing the condition of the subject based on the additional data. It is possible to automate the judgment of whether or not. In addition, it is possible to standardize the accuracy of determining whether remeasurement is necessary, which varies depending on the inspector. Therefore, information processing that supports judgment is possible.

According to the present invention, it is possible to provide a respiratory function test device, a data processing method, and a respiratory function test system capable of information processing to support judgment.

FIG. 1 is a block diagram showing a main configuration example of the respiratory function test apparatus of the embodiment. FIG. 2 is a schematic view showing a main configuration example of the measuring unit. FIG. 3 is a schematic diagram showing an example of a spirogram and information obtained from the spirogram. FIG. 4 is a schematic diagram showing an example of a spirogram including a flow volume curve when a healthy subject performs measurement by a correct measurement method. FIG. 5 is a schematic diagram showing an example of a spirogram when a poor exhalation start occurs. FIG. 6 is a schematic diagram showing another example of a spirogram in the case of poor exhalation initiation. FIG. 7 is a schematic diagram showing an example of a spirogram when exhalation is weak and there is no PEF. FIG. 8 is a schematic diagram showing an example of a spirogram when cough is included in exhaled breath. FIG. 9 is a schematic diagram showing an example of a spirogram when glottic closure is included in exhalation. FIG. 10 is a schematic diagram showing an example of an effort expiratory curve. FIG. 11 is a schematic diagram showing an example of the relationship between the presence or absence of a disease, the type of disease, and the flow volume curve. FIG. 12 is a diagram showing an example when the additional data of the measurement data is expressed in the table data format. FIG. 13 is a flowchart showing an example of the flow of processing by the calculation unit. FIG. 14 is a flowchart showing an example of the flow of the diagnosis support process. FIG. 15 is a diagram showing an example of a display mode of the display unit. FIG. 16 is a diagram showing an example of a display mode including a notification prompting a reversibility test. FIG. 17 is a schematic diagram showing an example of a flow volume curve of additional data of a subject suffering from COPD. FIG. 18 is a schematic diagram showing an example of a flow volume curve of additional data of a subject suffering from COPD.

The embodiment (embodiment) for carrying out the present invention will be described in detail with reference to the drawings. The present invention is not limited to the contents described in the following embodiments. In addition, the components described below include those that can be easily assumed by those skilled in the art and those that are substantially the same. Furthermore, the components described below can be combined as appropriate.

FIG. 1 is a block diagram showing a main configuration example of the respiratory function test device 1 of the embodiment. The respiratory function test device 1 includes a measurement unit 10 and a data management unit 20. The respiratory function test device 1 of the present embodiment performs various processes based on the implementation of spirometry and the data of the subject obtained by the implementation of spirometry. Spirometry is a respiratory function test for examining a subject's lung volume and various matters related to the lung volume.

FIG. 2 is a schematic diagram showing a main configuration example of the measuring unit 10. The measuring unit 10 is used for a respiratory function test of a subject. The measuring unit 10 includes, for example, a resistor 11, a pressure difference measuring unit 12, and a mouthpiece 13. The resistor 11 imparts resistance to the flow of the respiratory organs of the subject, and causes a pressure difference (differential pressure) at positions before and after the passage of the resistor 11. The pressure difference measuring unit 12 detects the differential pressure generated by the resistor 11 and outputs a signal indicating the differential pressure to the data management unit 20. The data management unit 20 uses data based on the signal as additional data AD.

The additional data AD functions as data from which, for example, the spyloggram SG (see FIG. 3 and the like) described later, the effort exhalation curve, and various parameters related thereto can be derived. The additional data AD may be data indicating the signal itself capable of drawing a figure such as a spirogram SG or an effort expiratory curve, or may be a collection of data including various parameters derived from the signal. May be good. The measurement data 210 described later is different from the newly measured additional data AD only in that it is the data obtained by the past measurement, and the data components are the same as those of the additional data AD. Is.

The mouthpiece 13 forms an airway between the mouth of human H, the subject, and the resistor 11. In the respiratory function test using the measuring unit 10, the subject breathes while holding the mouthpiece 13 according to a predetermined breathing method. The pressure difference measuring unit 12 detects the differential pressure generated by the resistor 11 due to the breathing.

The measuring unit 10 shown in FIG. 2 is a spiral meter using a so-called Freish type air flow meter that employs a bundle of metal thin tubes for the resistor 11, but the specific form of the measuring unit 10 is not limited to this. The measuring unit 10 may be, for example, a Benedict-Loss type, a bellows type or other type of spirometer.

The data management unit 20 performs various processes using the data measured by the measurement unit 10. The data management unit 20 includes a storage unit 21, a calculation unit 22, a display unit 23, an input unit 24, and the like. The storage unit 21 has any one of a hard disk drive (HDD: Hard Disk Drive), a solid state drive (SSD: Solid State Drive), a flash memory, and other storage devices, and stores various types of data. The storage unit 21 stores, for example, the measurement data 210, the display program 220, the determination program 230, and the like.

The measurement data 210 is "past" data indicating the measurement results obtained by using the measurement unit 10 in the past. In addition, the data (additional data AD) indicating the new measurement result output from the measurement unit 10 to the data management unit 20 by the measurement newly performed by the subject is treated as one measurement data 210 for one subject. .. That is, each time the measurement is performed using the measurement unit 10, the subject data included in the measurement data 210 increases.

The display program 220 is a software program for performing display output based on the additional data AD and the measurement data 210. Hereinafter, when simply referred to as a program, it means a software program. The determination program 230 is a program for determining what kind of data the additional data AD is. The functions realized by these programs will be described later.

The arithmetic unit 22 has an arithmetic circuit such as a CPU (Central Processing Unit), reads out programs and data stored in the storage unit 21 and executes them, and performs various processes related to the operation of the data management unit 20. The display unit 23 has any of a liquid crystal display, an organic electroluminescence display, and other display devices, and outputs a display according to the processing content of the calculation unit 22. The input unit 24 has, for example, any of a touch panel, a keyboard, a mouse, and other input devices for detecting a touch operation on the display area of the display unit 23, and accepts a user's manual input operation to the data management unit 20.

Hereinafter, an outline of the spiralogram SG that can be drawn based on the additional data AD and the measurement data 210 will be described.

FIG. 3 is a schematic diagram showing an example of the information obtained from the Spylogum SG and the Spylogum SG. In spirometry, data capable of drawing the spirogram SG, which is a graph for drawing the flow volume curve L as shown in FIG. 3, is obtained as additional data AD (and measurement data 210). With respect to the horizontal axis of the origin (0), the upward vertical axis indicates the expiratory flow rate per unit time due to exhalation, that is, the air flow rate (flow), and the downward vertical axis indicates the air flow rate due to inspiration. The width D1 indicates the forced vital capacity (FVC: Forced Vital Capacity). FVC is treated as a reference for 100 [%] lung volume in V50 and V25, which will be described later. The "V" of V50 and V25 is correctly the V of the alphabet with emphasis marks on the upper side. In addition, V50 may be described as FEF50 (Forced Expiratory Flow at 50% of forced vital capacity). In addition, V25 may be described as FEF75 (Forced Expiratory Flow at 75% of forced vital capacity).

As shown by the width D2 in FIG. 3, the air flow rate at the moment when the intake flow is maximum with respect to the horizontal axis of the origin (0) is the peak flow (PEF: Peak Expiratory Flow). Subjects suffering from respiratory diseases such as asthma, chronic obstructive pulmonary disease (COPD: Chronic Obstructive Pulmonary Disease), ACO (Asthma and COPD Overlap), and pulmonary fibrosis were generally compared with healthy subjects. In some cases, it is said that the PEF and the like tend to decrease.

Further, the flow of exhaled air at the position corresponding to the midpoint of the width D1, that is, the width D3 in FIG. 3 indicates the expiratory flow rate (V50) when the lung air volume is 50 [%]. Further, the exhaled flow at a position 1/4 of the width D1 and far from the PEF, that is, the expiratory flow rate (V25) when the width D4 in FIG. 3 is 25 [%] lung air volume. Shown. The expiratory flow rates of V50 and V25 are expiratory flow rates per predetermined unit time (for example, 1 second). V50 and V25 generally tend to be used diagnostically as measurements that are unaffected by the efforts of the subject. In the case of subjects suffering from diseases associated with peripheral airway obstruction such as asthma, it is generally said that V50 and V25 tend to show a more remarkable decrease than the decrease in PEF when compared with healthy subjects. ..

In addition, although it does not appear in the flow volume curve L, in spirometry, the amount of 1 second (FEV1: Forced Expiratory Volume 1 sec) and the forced expiratory volume in 1 second (FEV 1%: Forced Expiratory Volume 1 sec%) are also measured. FEV1 indicates the amount of air exhaled in 1 second from the moment when exhalation is started. FEV1% is sometimes expressed as FEV1 / FVC and indicates the ratio of FEV1 to FVC.

As shown in FIG. 3, the subject's spiral SG SG that draws the flow volume curve L has a point P1 corresponding to the effort inspiration start point, a point P2 corresponding to the effort inspiration end point, and an effort inspiration start point in chronological order. , The point P3 corresponding to the peak of the PEF of the effort exhalation, and the point P4 corresponding to the end point of the effort expiration are formed in this order.

The spirogram SG obtained as a result of the subject performing a respiratory function test using the measuring unit 10 is the health condition of the subject, whether the subject handled the measuring unit 10 correctly, or an event that should not occur during the respiratory function test ( It takes various forms depending on various circumstances such as whether the subject's cough etc. has occurred. Hereinafter, various forms and related matters of the spirogram SG will be described with reference to FIGS. 4 to 11. First, a spirogram SG including a flow volume curve when a healthy subject performs measurement by a correct measurement method will be described with reference to FIG. Then, the spirogram SG treated as an error due to the failure to comply with the correct measurement method between the start and the end of the respiratory function test will be described with reference to FIGS. 5 to 9.

FIG. 4 is a schematic diagram showing an example of a spirogram SG including a flow volume curve when a healthy subject performs measurement by a correct measurement method. In FIG. 4, a reference line W is attached to the air flow rate (L / sec) corresponding to the PEF of the flow volume curve. In FIGS. 5 to 9 described later, the PEF of the flow volume curve is illustrated so as to be comparable to that of FIG. 4 by similarly attaching the reference line W attached in FIG.

FIG. 5 is a schematic diagram showing an example of a spirogram SG when an exhalation start failure occurs. In the example shown in FIG. 5, the PEF of the flow volume curve is lower than that in the example shown in FIG. 4, and the expiratory volume up to the PEF is large.

FIG. 6 is a schematic diagram showing another example of the spirogram SG when a poor exhalation start occurs. The example shown in FIG. 6 is treated as an exhalation start failure because it includes an error pattern E1 indicating that exhalation is occurring from the start of exhalation to the PEF of the flow volume curve. The exhaled breath is, for example, an unintended small amount, but the pros and cons of the determination as the error pattern E1 are based on the generation of exhaled breath, not the amount of exhaled breath.

FIG. 7 is a schematic diagram showing an example of a spirogram SG when the exhalation is weak and there is no PEF. The example shown in FIG. 7 is treated as having no PEF to appear because the PEF of the flow volume curve is clearly lower than that of the example shown in FIG.

FIG. 8 is a schematic diagram showing an example of a spirogram SG when cough is included in exhaled breath. In the example shown in FIG. 8, an error pattern E2 in which the amount of exhaled breath repeatedly decreases and increases due to the subject coughing during exhalation occurs in the flow volume curve.

FIG. 9 is a schematic diagram showing an example of a spyogram SG in the case where glottis closure is included in exhalation. In the example shown in FIG. 9, the exhaled volume does not gradually decrease due to the subject closing the glottis during exhalation, and the error pattern E3 in which the expiratory volume suddenly drops to the baseline at the end of exhalation occurs in the flow volume curve.

Whether or not there is a failure to start exhalation can be determined not only based on the shape of the spirogram SG, but also based on the extrapolated air volume EV (see Fig. 10) that can be derived from the effort expiratory curve, the effort expiratory time, the plateau at the end of exhalation, etc. is there. Hereinafter, the effort expiratory curve and the extrapolated air volume EV will be described with reference to FIG.

FIG. 10 is a schematic diagram showing an example of an effort exhalation curve. The effort expiratory curve shown in FIG. 10 shows the change in lung air volume from the point P1 to the point P4 shown in FIG. 3 along the time axis. In other words, both the spirogram SG and the effort expiratory curve can be derived from one additional data AD (and measured data 210) obtained from a single respiratory function test. In the effort exhalation curve, the horizontal axis is the time axis and the vertical axis is the air volume axis. The right end side in FIG. 10 is the start point side corresponding to the point P1, and the left end side is the end point side corresponding to the point P4. The distance between the left end in FIG. 10 and the horizontal axis MAX indicating the maximum inspiratory capacity of the subject represents FVC.

The line EVL shown in FIG. 10 is an extension of the straight line of the portion of the effort expiratory curve where the slope with respect to the horizontal axis MAX (the slope of the degree of decrease in inspiratory volume due to exhalation) is maximum. The intersection of the line EVL and the horizontal axis MAX is treated as the expiratory start point TZ of the forced vital capacity. Further, the interval between the horizontal axis MAX and the effort expiratory curve at the time of the expiratory start point TZ is treated as an extrapolated air amount EV indicating the expiratory amount at the expiratory start point TZ.

If at least one of the condition that the extrapolated air volume EV is 5% or more of FVC and the condition that the extrapolated air volume EV is 150 ml or more is satisfied, the exhaled breath in the respiratory function test including the extrapolated air volume EV is satisfied. The start is determined to be bad. For example, one of the reasons why the example shown in FIG. 4 is not a poor exhalation start and the example shown in FIG. 5 is treated as a poor exhalation start is based on the condition regarding the extrapolated air volume EV.

Further, in FIGS. 4 to 9, the curves PL1, PL2, PL3 showing the relationship between the passage of the expiratory time and the increase in the expiratory volume (presence or absence of plateau) in the respiratory function test in which each flow volume curve was obtained. PL4, PL5, PL6 are shown. In the curves PL1 to PL6, the origin side (lower side) is set to 0 seconds (sec), the passage of time from the start of exhalation is indicated by an upward vertical axis, and the origin side (left side) is set to 0 (L) to end from the start of exhalation. The expiratory volume up to is shown on the horizontal axis toward the right side. Further, the upper ends of the curves PL1 to PL6 indicate the elapsed time (effort exhalation time) from the start of exhalation to the end of exhalation. For example, in the example shown in FIG. 4, the upper end of the curve PL1 reaches the upper end of the graph. The upper end of the graph corresponds to a time of 6 seconds or more in effort expiratory time. This indicates that the effort exhalation time is sufficient. Further, on the curve PL1, a plateau in which the expiratory amount does not substantially change is generated before the end of exhalation. Such expiratory effort time and plateau generation also indicate that the respiratory function test for which the spiral shown in FIG. 4 was obtained was due to correct measurements without defects. More specifically, if the effort exhalation curve reaches the plateau for 2 seconds (sec) or more or does not become a plateau, the effort expiration time of at least 6 seconds (sec) or more is measured (effort expiration time). Until the subject is unable to sustain exhalation in 15 seconds (sec) or longer or 6 seconds (sec) or longer). On the other hand, in the example shown in FIG. 5, the upper end of the curve PL2 does not reach the upper end of the graph. This indicates that the effort exhalation time is less than 6 seconds and the effort expiration time is insufficient. Further, on the curve PL2, the expiratory volume continues to increase with the passage of time until the end of exhalation, and no plateau is generated. Such expiratory effort time and non-occurrence of plateaus also indicate that the respiratory function test for which the spiral shown in FIG. 5 was obtained was due to an incorrect measurement with defects. Although the effort exhalation curve is shown vertically in FIGS. 4 to 9, the effort exhalation curve is oriented horizontally (horizontally on the time axis) when the measurement result is displayed on the display unit 23 or when the print is output (on the report). , The air volume axis may be expressed vertically), and the flow volume curve and the effort expiratory curve may be displayed as separate graphs without overlapping.

The specific example of the error in the spirogram SG has been explained above, but the factor that determines the flow volume curve of the spirogram SG is not limited to the presence or absence of the error. Different flow volume curves can be obtained depending on the presence or absence of respiratory disease and the type of respiratory disease of the subject.

FIG. 11 is a schematic diagram showing an example of the relationship between the presence or absence of a disease, the type of disease, and the flow volume curve. In FIG. 11, the flow volume of a subject suffering from respiratory diseases of asthma, COPD, ACO, and pulmonary fibrosis is used as a guideline when the subject is a healthy person who does not have respiratory diseases. An example of the tendency of the curve is shown.

As shown in FIG. 11, a flow volume curve (for example, a flow volume curve) in which the expiratory air flow rate (L / sec) is relatively lower than that of a healthy subject from a subject suffering from a respiratory disease. L1, L2, L3, L4) are obtained.

To give an example of the tendency of each respiratory disease, the flow volume curve L2 of a subject suffering from COPD is any of PEF, V50, V25, and FVC as compared with the flow volume curve L1 of a subject suffering from asthma. Also tends to be low. Further, the flow volume curve L4 of the subject suffering from pulmonary fibrosis tends to have a relatively high V50 but a low FVC as compared with the flow volume curve L1 of the subject suffering from asthma.

In the embodiment, the measurement data 210, which is the data obtained by performing the respiratory function test with the measurement unit 10 or the configuration equivalent to that of the measurement unit 10 before the additional data AD is obtained, is the case where the respiratory function is normal. The second data 211 showing the measurement result and other data (first data 213 and third data 219 shown in FIG. 1) showing the measurement result when there is an abnormality are discriminated from each other. For example, the measurement data 210 from which the spirogram SG shown in FIG. 4 is obtained is treated as the second data 211. Further, the measurement data 210 from which the spiralogram SG shown in FIGS. 5 to 9 and 11 is obtained is treated as the first data 213.

Further, the first data 213 is classified based on the characteristics of what kind of abnormality did not make the second data 211.

For example, the data obtained by obtaining the spyloggram SG described with reference to FIGS. 5 to 9 is the data that was not regarded as the second data 211 because the respiratory function test was not performed correctly, and was NG (No Good). ) It is treated as data 213.

Further, even in the first data 213, discrimination may be performed based on a specific feature that is NG. In FIG. 1, as the first data 213, the first NG data 213a, the second NG data 213b, the third NG data 213c, the fourth NG data 213d, and the fifth NG data 213e are provided. The first NG data 213a is data obtained from which a spirogram SG as shown in FIG. 5 is obtained, which is determined by the extrapolated air volume EV described with reference to FIG. The second NG data 213b is data obtained from which a spirogram SG as shown in FIG. 6 is obtained, which is considered to be a respiratory start failure due to inspiration occurring after the start of exhalation until reaching the PEF of the flow volume curve. The first NG data 213a and the second NG data 213b may be integrated as respiratory start failure NG data. The third NG data 213c is data obtained by obtaining a spyogram SG as shown in FIG. 7, which is NG due to weak exhalation and no PEF. The fourth NG data 213d is data obtained by obtaining a spyogram SG as shown in FIG. 8 which was regarded as NG due to repeated decrease and increase of the expiratory volume due to coughing. The fifth NG data 213e is data obtained by obtaining a spyogram SG as shown in FIG. 9, which is regarded as NG due to repeated decrease and increase of the expiratory volume due to glottis closure.

Further, the data obtained from the Spylogram SG described with reference to FIG. 11 is the data that was not used as the second data 211 due to the respiratory disease of the subject, and is the data according to the type of the disease that can be discriminated. 3 Handled within data 219.

For example, the data for which the spiral SG including the flow volume curve L2 shown in FIG. 11 is obtained is treated as COPD data 214. In addition, the data obtained by obtaining the spiral SG including the flow volume curve L4 shown in FIG. 11 is treated as pulmonary fibrosis data 215.

It is difficult to discriminate respiratory diseases by itself from the data obtained by obtaining the spirogram SG including the flow volume curves L1 and L3 shown in FIG. Therefore, such data is treated as, for example, difficult-to-discriminate data 218. On the other hand, in the embodiment, among the data that can be treated as the difficult-to-discriminate data 218, the processing flow for discriminating the data having a high possibility of asthma as the asthma data 216 is provided.

It is known to perform an airway reversibility test to verify that the subject has asthma. Hereinafter, the term "reversibility test" refers to an airway reversibility test. The reversibility test is a test to confirm whether inhalation of a bronchodilator improves the function of the respiratory system. In the case of asthma, it is known that inhalation of bronchodilators significantly improves the function of the respiratory system.

Explaining with reference to FIG. 11, it is obtained when a reversibility test is performed on a subject whose flow volume curve L1 is obtained in the respiratory function test before the reversibility test, and a respiratory function test is performed after the reversibility test. The flow volume curve tends to correspond to the flow volume curve L of a subject who is a healthy subject.

On the other hand, in the case of diseases different from asthma such as COPD, it is said that inhalation of bronchodilators does not significantly improve the function of the respiratory system. Therefore, by managing the additional data AD (and measurement data 210) showing the results of both respiratory function tests before and after the reversibility test of the same subject in association with each subject, the subject based on the results of the reversibility test can be managed. It becomes possible to grasp the tendency.

It should be noted that the flow volume curve L3 of the subject suffering from ACO is unlikely to have a clear difference from the flow volume curve L1 of the subject suffering from asthma, and even a medical worker is based only on the flow volume curve. It tends to be difficult to distinguish. On the other hand, the degree of improvement of the flow volume curve by the reversibility test tends to be less apparent than that of asthma, which makes it possible to distinguish. In addition, the option of conducting a reversibility test is not excluded for subjects such as COPD who can be distinguished from asthma by the flow volume curve. In FIG. 11, ACO is illustrated as a respiratory disease whose flow volume curve is similar to asthma, but even for other respiratory diseases, a process for determining the flow volume curve according to the degree of improvement of the flow volume curve by a reversibility test or the like. A flow can be prepared separately.

The relationship between asthma and ACO flow volume curves L1 and L3 shown in FIG. 11 is merely schematic, and does not definitively indicate that asthma and ACO cannot be discriminated without a reversibility test. It is also possible to determine asthma or ACO without a reversibility test by the similarity determination described later.

In the embodiment, for each of the additional data AD newly obtained by using the measurement unit 10 and the past measurement data 210, the relationship between the data and the other data, the physical characteristics of the subject, and other information are shown. Additional data is given as the data.

FIG. 12 is a diagram showing an example when the additional data of the measurement data 210 is expressed in the table data format. The diagnosis result of FIG. 12 is set to the data of each time included in the measurement data 210 by the input performed by the user of the respiratory function test device 1 using the input unit 24 or the determination by the storage unit 21 that executes the determination program 230. It is a diagnosis result. The "normal" diagnosis result indicates that the data corresponds to the second data 211 shown in FIG. The diagnosis result of "COPD" indicates that the data corresponds to the COPD data 214 shown in FIG. The diagnosis result of "pulmonary fibrosis" indicates that the data corresponds to the pulmonary fibrosis data 215 shown in FIG. The diagnosis result of "asthma" indicates that the data corresponds to the asthma data 216 shown in FIG. The diagnosis result of "unknown" indicates that the data corresponds to the difficult-to-discriminate data 218 shown in FIG. The diagnosis result of "NG" indicates that the data corresponds to the first data 213 shown in FIG. The diagnosis result of "ACO" indicates that the data corresponds to the ACO data 217 shown in FIG. The diagnosis result of "other" indicates that the data corresponds to the third data 219 shown in FIG. 1, but is not classified internally.

The presence or absence of the test in the reversibility test column of FIG. 12 indicates whether or not it is related to the measurement result in which the reversibility test was performed. Data with or without the test "absent" indicate that it has nothing to do with the measurement results in which the reversibility test was performed. Data with or without the test "Yes" indicate that it is related to the measurement results in which the reversibility test was performed.

For the pre-test, post-test, pre-test data and post-test data in the reversibility test column of FIG. 12, parameters are set in the fields only for the data in which the presence or absence of the test is "Yes". In the example of FIG. 12, when the data corresponds to the data before the reversibility test, a “circle (○)” is set before the test, and the identification number of the data after the same subject as the data performs the reversibility test is set. Set in post-test data. Taking a record given an identification number of "00000004" as an example, the data corresponding to the record is the data before the reversibility test, and was obtained after the subject who obtained the data performed the reversibility test. It indicates that the data is the data given the identification number of "00000005". If the data corresponds to the data after the reversibility test, a "circle (○)" is set after the test, and the identification number of the data before the same subject performs the reversibility test is set in the pre-test data. To. Taking a record given an identification number of "00000005" as an example, the data corresponding to the record is the data after the reversibility test, and the subject who obtained the data obtained the data before the reversibility test. It indicates that the data is the data given the identification number of "00000004". Various parameters included in the reversibility test column are set by the user, for example, via input using the input unit 24.

Further, as illustrated by the parameters set in the columns of age [year], gender, height [cm], and weight [kg] included in the subject attributes of FIG. 12, various data included in the measurement data 210 May be further set with parameters indicating the subject's physical characteristics and other information, such as the subject's age [years], gender, height [cm], weight [kg], and the like. The parameters of the reversibility test and the subject attribute are set by the user, for example, via input using the input unit 24. The specific content of the additional data illustrated in FIG. 12 is merely an example and is not limited to this, and other expressions having the same meaning may be used.

The calculation unit 22 determines the additional data AD based on the comparison result between the additional data AD and the measurement data 210 by executing the determination program 230. Specifically, the calculation unit 22 first determines whether the additional data AD corresponds to the first data 213. When it is determined that the additional data AD does not correspond to the first data 213, the calculation unit 22 determines which respiratory disease data corresponds to.

More specifically, the calculation unit 22 determines whether at least one of the condition that the extrapolated air amount EV is 5% or more of the FVC and the condition that the extrapolated air amount EV is 150 ml or more is satisfied, for example. If the condition is satisfied, the additional data AD satisfying the condition is added to the first NG data 213a. Further, the calculation unit 22 determines whether or not a pattern (for example, error patterns E1, E2, E3) that occurs so that the increase and decrease of the expiratory amount alternate with each other in the flow volume curve is generated. If so, the additional data AD is added to the second NG data 213b, the fourth NG data 213d, or the fifth NG data 213e. A more detailed determination as to which of the second NG data 213b, the fourth NG data 213d, and the fifth NG data 213e corresponds is, for example, as described with reference to FIGS. 6, 8 and 9, as an increase in the expiratory volume. It is determined based on the period during which the descent occurs, the degree of repetition of the rise and descent, the difference between the degree of the rise and the degree of the descent, and the like. Further, the calculation unit 22 determines whether the change is in the expiratory amount that draws the flow volume curve L indicating the clear PEF, and if there is no clear PEF, the additional data AD is added to the third NG data 213c. The criteria for determining "there is no clear PEF" is the same as the threshold value of PEF in the second data 211, and the threshold value of the dedicated expiratory volume for determining "there is no clear PEF". May be set. Based on these determinations, it is determined whether the additional data AD corresponds to the first data 213.

When it is determined that the additional data AD does not correspond to the first data 213, the calculation unit 22 performs the diagnosis support process based on the additional data AD. The diagnostic support process is a process related to the provision of information that supports the diagnosis of the presence or absence and type of respiratory disease in a subject based on a spiral. Specifically, the calculation unit 22 determines, for example, whether the additional data AD corresponds to the second data 211. More specifically, the calculation unit 22 may be, for example, a change in the expiratory volume that draws a flow volume curve L indicating a clear PEF, or a decrease in the level of the flow volume curve due to a respiratory disease (PEF, V50, V25, FVC). Etc.) is not generated, and it is determined whether the additional data AD is the second data 211 based on various conditions. In order to determine "clear PEF", "flow volume curve level (PEF, V50, V25, FVC, etc.)", etc., various values of the flow volume curve such as PEF, V50, V25, FVC are normal. A criterion (for example, a calculation formula or a threshold value) for determining whether or not the value is a value is set. The calculation formula is for obtaining various values such as PEF, V50, V25, and FVC of a healthy person based on numerical values such as age [year], gender, height [cm], and weight [kg] among the subject attributes. It is an expression. The threshold value may be a value predetermined by a preliminary measurement or the like, a value derived by a calculation unit 22 executing the determination program 230 by machine learning described later, or the above-mentioned calculation. It may be a threshold value derived in advance by an equation. Further, as in the calculation formula, a plurality of types of the threshold values may be set according to the tendency of the parameter of the subject attribute (age [year], gender, height [cm], weight [kg], etc.). For example, different threshold values may be adopted for men and women, or different threshold values may be adopted depending on the physique required from height, weight, and the like. When the calculation unit 22 determines that the additional data AD corresponds to the second data 211, the calculation unit 22 adds the additional data AD to the second data 211.

As described above, the subject attributes (age [year], gender, height [cm], weight [kg], etc.) included in the additional data described with reference to FIG. 12 are combined with the additional data AD (and measurement data 210). By being associated and stored in the storage unit 21, the calculation unit 22 can determine whether the additional data AD (and the measurement data 210) corresponds to the second data 211. Since it does not correspond to the second data 211 means that it corresponds to the third data 219, the calculation unit 22 can determine whether the additional data AD corresponds to the third data 219 based on the subject attribute. The additional data may be stored in the same data structure as the data handled by, for example, a relational data base management system (RDBMS), or as data having another structure that functions in the same manner, not limited to RDBMS. It may be stored and the specific data structure is arbitrary. Further, the measurement data 210 (and the additional data AD) and the additional data correspond to, for example, an identification number individually added to the measurement data 210 (and the additional data AD) and an identification number included in the additional data shown in FIG. Can be attached.

Further, the calculation unit 22 includes data for each type of respiratory disease (for example, COPD data) included in the measurement data 210 based on a decrease in the level of the flow volume curve due to respiratory disease (PEF, V50, V25, FVC, etc.). A similarity determination with 214, pulmonary fibrosis data 215, asthma data 216, ACO data 217 and difficult-to-discriminate data 218) is performed. The calculation unit 22 adds the additional data AD to the type of data that is most similar to the additional data AD in the similarity determination.

When "circle (○)" is set for the additional data AD after the test to obtain the tested data, the calculation unit 22 performs the flow of the untested data 218a associated with the tested data. It may be determined whether the flow volume curve of the tested data is improved as compared with the volume curve. In this case, specifically, the calculation unit 22 determines the degree of improvement of the flow volume curve based on, for example, PEF, V50, V25, FVC, etc. of the flow volume curve of the untested data 218a and the tested data. .. For example, if the flow volume curve L1 shown in FIG. 11 is for untested data 218a and the flow volume curve L is for the tested data, the tested data was subjected to a reversibility test in asthma patients. It is judged that it corresponds to the improvement of the flow volume curve in the case. When such a determination result is obtained, the calculation unit 22 adds the tested data to the tested data 216a of the asthma data 216. On the other hand, when it is determined that the degree of improvement does not correspond to the improvement of the flow volume curve when the reversibility test is performed on the asthma patient, the calculation unit 22 is reversible to the subject suffering from other respiratory diseases. Further determination of the relationship with the degree of improvement of the flow volume curve when the test is carried out may be performed. Regarding the relationship between the change (improvement, etc.) of the flow volume curve and the type of respiratory disease when the reversibility test is performed, a threshold value for determination may be set for each type of respiratory disease. In this case, the threshold value may be predetermined or may be derived by machine learning described later.

Further, based on the explanation with reference to FIGS. 11 and 12, the calculation unit 22 may determine whether the additional data AD is similar to the untested data 218a associated with the tested data 216a. This similarity determination is made, for example, by correlating the untested data 218a with the tested data 216a included in the asthma data 216 and the additional data AD, and among the untested data 218a, the ACO data 217. It is performed based on the relative height of the correlation between the data associated with the tested data 217a included in the data and the additional data AD. As a result of performing this similarity determination, when it is determined that the additional data AD is similar to the untested data 218a associated with the tested data 216a included in the asthma data 216, the calculation unit 22 displays the spirogram SG. At the same time (see FIG. 15), a notice prompting the reversibility test may be included in the display. This makes it possible to provide information on the validity of conducting a reversibility test.

Further, the respiratory function test device 1 of the embodiment can further improve the determination accuracy of the additional data AD by so-called machine learning. For example, the input in the so-called neural network is the additional data AD, the output is the determination result of the additional data AD, and the teacher data is various data included in the measurement data 210. Here, the arithmetic unit 22 executing the determination program 230 generates the neural network, intervenes between the input and the output, performs the above-mentioned processing (particularly, see FIG. 10), and derives the output from the input. It functions as a hidden layer for weighting. The calculation unit 22 as the hidden layer provides additional data based on the trajectory of the spirogram SG indicated by the additional data AD, the air flow rate of FVC and PEF, V50, V25, FEV1, FEV1%, the external air volume EV, and other features. By outputting a value indicating the degree of weighting based on AD, the determination result of the additional data AD is determined.

More specifically, for example, a neuron that outputs a high value when the additional data AD is likely to be the second data 211, and a high value is output when the additional data AD is likely to be the COPD data 214. A neuron that outputs a high value when the additional data AD is likely to be asthma data 216, and a neuron that outputs a high value when the additional data AD is likely to be the first data 213. , ..., The determination program 230 in which the arithmetic unit 22 functions as a neuron corresponding to each type of data included in the measurement data 210 is adopted. Thereby, in the embodiment, it is possible to determine the additional data AD by machine learning. That is, the determination program 230 functions as a machine learning program. Further, the configuration including the arithmetic unit 22 executing the determination program 230 functions as a so-called machine learning system.

Further, a neuron for performing weighting based on FVC, a neuron for performing weighting based on the air flow rate of PEF, a neuron for performing weighting based on V50, and a neuron for performing weighting based on V25. Inputs such as neurons, neurons for weighting based on FEV1, neurons for weighting based on FEV1%, neurons for weighting based on external air volume EV, and so on. Higher accuracy can be expected by adopting the determination program 230 including an algorithm for layering the neurons constituting the hidden layer intervening between the output and the output. These may be further developed to determine the additional data AD by so-called deep learning.

When the additional data AD is classified into any of the data included in the measurement data 210 according to the determination result in the above-described embodiment, the measurement data 210 including the additional data AD subsequently functions as the teacher data. That is, as the additional data AD occurs, the measurement data 210 includes more diverse data and functions as "teacher data after learning" for obtaining a correct determination result. Here, even if there is an error in the determination result, for example, the user corrects the error by manual input via the input unit 24 and sets the correct determination result, so that the calculation unit 22 causes the determination program 230. You will have the opportunity to correct the weighting of the hidden layer by. That is, in the embodiment, the user can make the teacher data more accurate data as needed. As a result, the calculation unit 22 executing the determination program 230 can derive the determination result of the additional data AD based on the weighting that can obtain the determination result closer to the correct answer. It is desirable that the determination program 230 be provided in an updatable manner in consideration of the possibility of such an opportunity for matching the teacher data and the output.

FIG. 13 is a flowchart showing an example of the processing flow by the calculation unit 22. Unless otherwise specified, the process shown in FIG. 13 is a process performed by the calculation unit 22 running the determination program 230. When the additional data AD newly measured by the measuring unit 10 is output from the measuring unit 10 to the data management unit 20, the calculation unit 22 acquires the additional data AD (step S1) to obtain the flow volume. Obtain data that can draw a spiral SG including a curve.

The calculation unit 22 determines whether the spiralgram SG of the additional data AD obtained in the process of step S1 corresponds to the first data 213 (step S2). Specifically, the calculation unit 22 satisfies at least one of the condition that the external air volume EV is 5% or more of the FVC and the condition that the external air volume EV is 150 ml or more, or the flow volume curve L. Breathing using the measuring unit 10 based on whether an error pattern (for example, error patterns E1, E2, E3) occurs between the start and end of exhalation, and whether PEF occurs in the flow volume curve L. Determine if there are any abnormalities that would result in loss of validity of the functional test.

When it is determined in the process of step S2 that the data corresponds to the first data 213 (step S2; Yes), the calculation unit 22 determines the type of the first data 213 (step S3), and uses the additional data AD as the first data. It is added to the corresponding type of data among 213 (step S4), and additional data is given with the diagnosis result of the additional data AD as “NG”. The types of the first data 213 in the process of step S4 are, for example, the above-mentioned first NG data 213a, second NG data 213b, third NG data 213c, fourth NG data 213d, fifth NG data 213e, and the like. After the processing of step S4, the calculation unit 22 executes the display program 220 to perform display based on the additional data AD. Here, the calculation unit 22 includes a notification prompting remeasurement in the display content (step S5). The display mode by executing the display program 220 will be described later. After the process of step S5, the process related to the additional data AD ends once. If the additional data AD is acquired again using the measuring unit 10 after the remeasurement is prompted, the process is restarted from step S1.

On the other hand, when it is determined in the process of step S2 that the first data 213 does not correspond (step S2; No), that is, when it is determined that valid additional data AD has been obtained, the calculation unit 22 causes the calculation unit 22 to perform the operation. Perform diagnostic support processing (step S6).

FIG. 14 is a flowchart showing an example of the flow of the diagnosis support process. The calculation unit 22 acquires additional data input by the user of the respiratory function test device 1 regarding the additional data AD in step S1 indicating the presence or absence of the reversibility test and the context when the reversibility test is performed (step). S11). The process of step S11 may be performed before the process of step S2.

The calculation unit 22 determines whether the additional data AD obtained in the process of step S1 corresponds to the tested data based on the additional data obtained in the process of step S11 (step S12). Specifically, the calculation unit 22 determines whether or not the “circle (◯)” is set after the test of the additional data. Hereinafter, the case where it is determined in the process of step S12 that it does not correspond (step S12; No) will be described first.

The calculation unit 22 determines whether the spiralgram SG of the additional data AD obtained in the process of step S1 corresponds to the second data 211 (step S13). When it is determined that the second data 211 corresponds to (step S13; Yes), the calculation unit 22 adds the additional data AD to the second data 211 (step S14), and sets the diagnosis result of the additional data AD to "normal". The additional data is given. Further, the calculation unit 22 executes the display program 220 to perform display based on the additional data AD (step S15). The display mode by executing the display program 220 will be described later. After the process of step S15, the process related to the additional data AD ends.

When it is determined in the process of step S13 that the second data 211 does not correspond (step S13; No), the calculation unit 22 determines that the flow volume curve of the additional data AD obtained in the process of step S1 is difficult to determine data 218. Is determined (step S16). When it is determined that the data is not difficult to discriminate 218 (step S16; No), the calculation unit 22 determines which respiratory disease data the additional data AD is. In FIG. 14, as the process of step S17, the calculation unit 22 determines whether the additional data AD corresponds to the asthma data 216. When it is determined that the additional data AD obtained in the process of step S1 corresponds to the asthma data 216 (step S17; Yes), the calculation unit 22 adds the additional data AD to the asthma data 216 (step S18). Additional data Provide additional data with the diagnosis result of AD as "asthma". On the other hand, if this is not the case (step S17; No), the calculation unit 22 adds the additional data AD to the data according to the type of respiratory disease other than asthma (step S19). The types of respiratory diseases other than asthma are, for example, COPD, ACO, pulmonary fibrosis and the like described above. In the explanation with reference to FIG. 14, asthma is first determined as an example of determination according to the type of respiratory disease, but the calculation unit 22 determines whether the data is for other respiratory diseases. It may be done earlier, and the types of respiratory illnesses and the order of determination are in no particular order. Further, the calculation unit 22 does not individually determine whether or not it corresponds to each respiratory disease, but determines which disease corresponds to it based on PEF, V50, V25, FVC, etc. of the flow volume curve. You may do so.

When it is determined in the process of step S16 that the data is difficult to discriminate 218 (step S16; Yes), the calculation unit 22 adds the additional data AD to the difficult data 218 (step S20), and the additional data AD Gives additional data that makes the diagnosis result of "Unknown". The calculation unit 22 determines whether the additional data AD is similar to the untested data 218a associated with the tested data 216a of the asthma data 216 (step S21).

When it is determined that the additional data AD obtained in the process of step S1 is similar to the untested data 218a associated with the tested data 216a of the asthma data 216 (step S21; Yes), the calculation unit 22 displays the display program 220. Is executed to display based on the additional data AD, and a notification prompting the reversibility test is included in the display (step S22). After the process of step S22, the process related to the additional data AD ends. On the other hand, when it is determined that the additional data AD is not similar to the untested data 218a associated with the tested data 216a of the asthma data 216 (step S21; No), the process proceeds to step S15.

Next, a case where it is determined in the process of step S12 that the additional data AD corresponds to the tested data (step S12; Yes) will be described. The calculation unit 22 acquires the untested data 218a associated with the additional data given in the process of step S11 (step S23). The calculation unit 22 determines whether the flow volume curve of the additional data AD is improved as compared with the flow volume curve of the untested data 218a (step S24). If it is determined that the improvement has been made (step S24; Yes), the process proceeds to step S18. However, in this case, in the process of step S18, the calculation unit 22 adds the additional data AD to the tested data 216a of the asthma data 216. On the other hand, when it is determined in the process of step S24 that the flow volume curve of the additional data AD is not improved as compared with the flow volume curve of the untested data 218a (step S24; No), the process of step S19. Move to. In this case, in the process of step S19, the calculation unit 22 sets the additional data AD as the tested data (for example, the tested data 217a of the ACO data 217) included in the data for each type of respiratory disease. It may be.

FIG. 15 is a diagram showing an example of a display mode of the display unit 23. The calculation unit 22 causes the display unit 23 to perform display output based on the additional data AD and the measurement data 210 by executing the display program 220. The display mode by the display program 220 is not limited to the example shown in FIG. 15, and may be any form as long as the spyogram SG can be grasped. In the display mode shown in FIG. 15, the display unit 23 on which the spyogram SG based on the additional data AD obtained by using the measurement unit 10 is drawn is illustrated.

Further, in FIG. 15, a highlighting unit CP indicating the reason why the displayed spyloggram SG is determined to be the first data 213 is further displayed. The highlighting section CP is displayed as a frame surrounding a portion corresponding to the cause of the error that occurred during the respiratory function test, as in the error pattern E2 in FIG. 8, which is a specific highlighting section CP. It is an example of a display mode and is not limited to this. The highlighting section CP may be a highlighting by color-coding the line or background of the spyloggram SG that caused the error, an arrow for the part that caused the error, and a character string that explains the cause of the error. It may be any other mode in which the cause of the error can be grasped.

Further, when the additional data AD including the notification prompting the remeasurement is displayed as in the process of step S5 described with reference to FIG. 13, for example, "Please remeasure" as in the notification ME of FIG. Display content including a character string such as "." Is added. In addition, the notification ME may further notify the cause of the need for remeasurement. In the spirogram SG shown in FIG. 15, an error pattern E2 occurs in which the subject coughs during exhalation and the exhalation volume repeatedly decreases and increases. For this reason, since the cause of the need for remeasurement is "cough", the notification ME shows "There is a possibility of coughing during measurement" as a character string indicating the cause of the need for remeasurement. Is added before the "Please remeasure" string that prompts you to remeasure. The character string indicating the cause is not limited to this, and is set individually for each cause of the defect described with reference to FIGS. 5 to 10.

In the process of step 15 described with reference to FIG. 14, since the notification prompting the remeasurement is not performed, the highlighting section CP and the notification ME of FIG. 15 are not displayed, and the spyloggram SG is displayed. ..

FIG. 16 is a diagram showing an example of a display mode including a notification prompting a reversibility test. When the additional data AD including the notification prompting the reversibility test is displayed as in the process of step 22 described with reference to FIG. 14, the notification ME in FIG. 15 is replaced with the notification C shown in FIG. Display content including a character string such as "We recommend conducting an airway reversibility test." Is added. Further, the accompanying information M may be displayed. In the accompanying information M of FIG. 16, as the diagnosis result of the subject based on the spyloggram SG obtained from the additional data AD, the possibility of corresponding to each of various respiratory diseases including asthma is determined from percentage (0 [%] to]. It is quantified by 100 [%]). The numerical value of the percentage is derived by a process of quantifying the strength of the relationship between the additional data AD and various respiratory diseases by, for example, the weighting process by forming the neural network described above. FIG. 16 illustrates the accompanying information M displayed with the notification C, and the possibility of being diagnosed with asthma is relatively high as compared with other respiratory diseases.

The information related to the additional data AD derived by the weighting process by forming the neural network, such as the accompanying information M, is not limited to the case where the additional data AD is displayed by the process of step S22, but is based on the process of step S15. It may be displayed when the additional data AD is displayed. Of course, depending on the content of the additional data AD, it may be more likely to be diagnosed as a respiratory disease other than asthma. In that case, notification C is not displayed.

In addition, respiratory diseases that can be diagnosed and supported based on the third data 219 are not limited to asthma, COPD, ACO, and pulmonary fibrosis. For example, CPFE and other respiratory diseases can be dealt with by storing past data corresponding to combined pulmonary fibrosis (CPFE: Combined Pulmonary Fibrosis and Emphysema) and other respiratory diseases in the storage unit 21. Is. As the order of determination by the calculation unit 22, for example, the processing when asthma, COPD, ACO, and pulmonary fibrosis are not applicable and are treated as difficult-to-identify data 218 is further subdivided, and CPFE and other respiratory diseases are individually applicable. May be determined, or may be expressed as a percentage (0 [%] to 100 [%]) based on the weighting process by the formation of the neural network as in the accompanying information M.

Further, in the accompanying information M illustrated in FIG. 16, the severity of each respiratory disease when the additional data AD corresponds to each respiratory disease is attached to the horizontal axis between “mild” and “severe”. It is indicated by the position of "○". When determining the severity of a respiratory disease in this way, it is preset as in the case of "mild" or "severe" in the data for each respiratory disease included in the third data 219. Data for each stage of severity is prepared. The calculation unit 22 determines the severity based on the degree of similarity between the graded data of the severity included in the data of each respiratory disease and the additional data AD, and determines the position of “○” in the accompanying information M. To do.

17 and 18 are schematic views showing an example of a flow volume curve of additional data AD of a subject suffering from COPD. Note that FIG. 17 shows a flow volume curve when the degree of the disease is milder than that of the example of FIG. 18, and “○” is added to the mild side of the midpoint of the severity in the above-mentioned incidental information M. Degree. Further, FIG. 18 shows a flow volume curve when the degree of the disease is more severe than that of the example of FIG. 17, and in the above-mentioned incidental information M, “○” is added to the more severe side than the midpoint of the severity. Degree. According to GOLD (Global initiative for chronic Obstructive Lung Disease), which is used internationally as a COPD guideline, the example shown in FIG. 17 belongs to stage 1, and the example shown in FIG. 18 belongs to stage 3.

The flow volume curves L21 and L22 shown in FIGS. 17 and 18 are flow volume curves L1, L2, L3, L4, etc. of each respiratory disease with respect to the flow volume curve L in the case of a healthy person described with reference to FIG. It is a flow volume curve that is determined to have a high possibility of COPD based on the tendency of. Further, as illustrated by the difference between the flow volume curve L21 and the flow volume curve L22, the flow volume curve varies depending on the severity of the respiratory disease of the subject even when it is determined that there is a high possibility of the same disease. It can be different. In general, the more severe the respiratory illness, the lower the PEF, V50, V25, and FVC tend to be. When illustrated as in the examples of FIGS. 17 and 18, the decrease in PEF and FVC is particularly noticeable visually.

To give an example of diagnosing the severity, the storage unit 21 stores the data classified in advance for each severity (in the case of COPD data 214, for each stage) in the data of each respiratory disease. When it is determined that the additional data AD corresponds to the new third data 219, the calculation unit 22 determines which respiratory disease is likely to be applicable and the seriousness of the respiratory disease that is likely to be applicable. Is determined based on the existing third data 219 that has been classified in the storage unit 21. The determination may be based on the above-mentioned processing using the neural network, or may be other processing (for example, brute force comparison and collation processing). The calculation unit 22 outputs the possibility and severity corresponding to each respiratory disease as in the above-mentioned incidental information M according to the determination result.

To give another example of diagnosing the severity, the flow volume curve L in the case of a healthy person corresponding to the subject attribute based on the subject attribute (for example, the subject's age, gender, height, weight, etc.) is obtained. The arithmetic expression to be derived may be stored in the storage unit 21 in advance. In this case, the data indicating the calculation formula is included in the second data 211. Further, the relationship between various parameters (for example, PEF, V50, V25, FVC, etc.) based on the flow volume curve L derived by the calculation formula and the various parameters for each severity of each respiratory disease (for example, for example). Data indicating a percentage, etc.) is included in the third data 219. The calculation unit 22 determines whether the additional data AD corresponds to the new third data 219 based on the flow volume curve L derived based on the calculation formula and the flow volume curve derived from the additional data AD. 3 When the data 219 is applicable, it may be determined which respiratory disease corresponds to which severity.

In the explanation with reference to FIGS. 17 and 18, the diagnosis of severity is described using COPD as an example, but the diagnosis of severity is not limited to COPD, and asthma, ACO, pulmonary fibrosis, CPFE, etc. It is also applicable to the pathological condition of.

Explaining CPFE, subjects suffering from CPFE have a relatively lower oxygen saturation (SpO2) that can be measured with a pulse oximeter (95 [%]) than healthy subjects, and a lung diffusion ability test. The measurement result of (DLCO: Diffusing capacity of Lung for Carbon monOxide) tends to appear relatively lower than that of healthy subjects. However, SpO2 and DLCO are not intended to be derived from spirogram SG, and CPFE may offset the characteristics of COPD obstructive ventilatory impairment and pulmonary fibrosis restrictive ventilatory impairment. Yes, the characteristics of the waveform of the flow volume curve L are not clear. Therefore, it tends to be difficult to distinguish it from other respiratory diseases such as asthma only by the spirogram SG. On the other hand, when additional data AD and other measurement data are continuously acquired for one subject, the convex portion below the flow volume curve L that appears between the points P3 and P4 (see FIG. 3) is almost the same as that of a healthy subject. Although it has improved to the same level, SpO2 and DLCO have not improved, and diagnostic results suspected of CPFE may be obtained by diagnostic imaging such as high resolution computed tomography (High Resolution Computed Tomography). ..

When the diagnosis result regarding CPFE is performed in the embodiment, the subject who has been diagnosed as suffering from CPFE in advance is asked to perform the measurement using the measuring unit 10, and the third data 219 of CPFE is obtained. The training data is weighted by a neural network. Even if it is difficult for the inspector to determine whether the person is a healthy person or a CPFE just by looking at one Spyloggram SG, by storing more data of the healthy person and the CPFE in the storage unit 21. It is possible to support the diagnosis of healthy subjects and CPFE at a percentage (0 [%] to 100 [%]) level based on the spirogram SG by weighting processing by a neural network. This is not limited to the relationship between healthy subjects and CPFE, but also for other respiratory diseases that are difficult to diagnose by looking at one Spylogogram SG. For example, the same applies to the above-mentioned distinction between asthma and ACO.

Although not shown, when the spirogram SG shows a tendency of respiratory disease, a notification indicating the type of respiratory disease may be displayed on the display unit 23. Further, as the process of step S16 described above, a notification prompting the reversibility test may be displayed on the display unit 23. These notifications are performed by images such as character strings or symbols, but the present invention is not limited to this, and the content of the notification may be in any form that can be transmitted to the user.

Further, in response to the input operation from the input unit 24, the calculation unit 22 is not limited to the additional data AD, and displays the display based on the data included in the past measurement data 210 in the same display mode as the additional data AD. It may be displayed on 23.

As described above, the respiratory function test device 1 of the embodiment is based on data (measurement data 210) that can derive the spirogram SG and indicates the measurement result of the respiratory function of the subject performed in the past. Additional data indicating the measurement result of the new respiratory function A memory for storing the first data 213 which is a respiratory function test device for processing AD and shows the measurement result when an abnormality occurs in which the validity of the respiratory function test is lost. A unit 21 and a control unit (calculation unit 22) for determining the validity of the respiratory function test for which additional data AD has been obtained based on the first data 213 are provided.

According to such an embodiment, conventionally, an examiner who guides a subject to a respiratory function test using the measurement unit 10 before performing a pathological diagnosis of the subject based on the additional data AD is a numerical value or a flow volume of the additional data AD. It is possible to automate the determination of whether remeasurement, which was performed based on the curve, is necessary. In addition, it is possible to standardize the accuracy of determining whether remeasurement is necessary, which varies depending on the inspector. Therefore, information processing that supports judgment is possible.

Further, the calculation unit 22 of the embodiment issues a notification (for example, the notification ME in FIG. 15) prompting the reacquisition of the additional data AD when it is determined that the respiratory function test for which the additional data AD has been obtained is not valid. A display unit 23 for displaying including the display is provided.

This can provide information that encourages another respiratory function test.

Further, the storage unit 21 of the embodiment stores the second data 211 showing the measurement result of the respiratory function of a healthy person and the third data 219 showing the measurement result of the respiratory function of the subject suffering from the respiratory disease. To do. The control unit (calculation unit 22) further determines whether the additional data AD corresponds to the second data 211 or the third data 219 when it is determined that the additional data AD is appropriate for the obtained respiratory function test. judge.

This enables information processing that supports the diagnosis of the pathological condition of the subject.

Further, the measurement data 210 of the embodiment includes the tested data 216a determined to be asthma based on the measurement result again after the reversibility test. Further, the difficult-to-discriminate data 218 of the embodiment includes untested data 218a. The tested data 216a and the untested data 218a are associated with each other. The calculation unit 22 of the embodiment further determines the validity of performing the reversibility test on the subject in which the additional data AD is measured, based on the collation result of the additional data AD and the untested data 218a.

This will increase the accuracy of the diagnosis of asthma by performing a reversible test. Therefore, information processing that supports diagnosis is possible.

Further, when the additional data AD corresponds to the third data 219, the control unit (calculation unit 22) is a subject based on the third data 219 provided in the storage unit 21 according to the severity of the respiratory disease. Determine the severity of respiratory illness.

This can support the diagnosis of the severity of respiratory diseases.

Further, the calculation unit 22 executing the determination program 230 generates a neural network in which the additional data AD is input, the second data 211 and the third data 219 are used as teacher data, and the determination result of the additional data AD is output. ..

This makes it possible to support judgment using machine learning.

Furthermore, since the validity of the inspection can be confirmed from various angles using so-called AI-like processing using a neural network (or judgment by ordinary arithmetic processing without using a neural network), the validity of the additional data AD is appropriate. You can make sexual judgment speedily. Further, by displaying the error of the additional data AD determined by the respiratory function test device 1 (specific points that are regarded as defects), the effect of shortening the waiting time of the subject during the test is expected.

When the reversibility test is performed, the data before and after the reversibility test may be displayed in parallel or superimposed on the display content of the display unit 23. As a result, the effect of the reversibility test can be shown more clearly.

Further, with respect to the additional data AD in which the storage unit 21 determines the data type (diagnosis result) by executing the determination program 230, the user of the respiratory function test device 1 inputs the diagnosis result using the input unit 24. When updated, the additional data AD may be treated as data corresponding to the updated diagnostic result. As a result, even if an error occurs in the determination result of the calculation unit 22, it can be corrected after the fact. Further, by this correction, the accuracy of the subsequent determination by the calculation unit 22 can be further improved.

Further, in the configuration of the embodiment described with reference to FIG. 1, the data management unit 20 is included in the respiratory function test device 1, but the configuration of the data management unit 20 is the respiratory function test device including the measurement unit 10. It may be included in a separate information processing device. In this case, the respiratory function test device and the information processing device are communicably connected. The data management unit 20 of the information processing device acquires the additional data AD output from the respiratory function test device including the measurement unit 10, and makes a determination with reference to the measurement data 210 stored in advance. The respiratory function test device includes a display device similar to the display unit 23, and outputs a display based on the determination result of the information processing device (see FIG. 15).

1 Respiratory function test device 10 Measurement unit 20 Data management unit 21 Storage unit 22 Calculation unit 23 Display unit 24 Input unit 210 Measurement data 211 2nd data 213 1st data 213a 1st NG data 213b 2nd NG data 213c 3rd NG data 213d 4th NG Data 213e 5th NG data 214 COPD data 215 Pulmonary fibrosis data 216 Asthma data 216a, 217a Tested data 217 ACO data 218 Difficult to discriminate data 218a Untested data 219 Third data AD Additional data

Claims (10)

Pulmonary function testing device that processes additional data that indicates new respiratory function measurement results based on past data that can be derived from a spiral and that indicates the results of past measurements of the subject's respiratory function. ,
A storage unit that stores data showing the measurement result when the respiratory function is normal and data showing the measurement result when there is an abnormality as the past data, and
A respiratory function testing device including a control unit that determines at least one of the correlations between the additional data and the past data. The past data includes the first data showing the measurement result in the case of an abnormality in which the validity of the respiratory function test is lost.
The respiratory function test apparatus according to claim 1, wherein the control unit determines the validity of the respiratory function test for which the additional data is obtained based on the first data. The respiratory function test apparatus according to claim 2, further comprising a display unit that displays a notification including a notification prompting the reacquisition of the additional data when it is determined that the respiratory function test for which the additional data has been obtained is not valid. The past data includes a second data showing the measurement result of the respiratory function of a healthy person and a third data showing the measurement result of the respiratory function of a subject suffering from a respiratory disease.
Claim that the control unit further determines whether the additional data corresponds to the second data or the third data when it is determined that the respiratory function test for which the additional data is obtained is appropriate. The respiratory function test apparatus according to 2 or 3. The third data includes asthma data of a subject suffering from asthma and difficult-to-determine data which makes it difficult to determine whether it is asthma or other respiratory diseases.
The asthma data includes tested data determined to be asthma based on the results of remeasurement after undergoing an airway reversibility test.
The difficult-to-discriminate data includes untested data before the subject from whom the tested data was obtained undergoes the airway reversibility test.
The tested data and the untested data are associated with each other.
The fourth aspect of claim 4, wherein the control unit further determines the validity of performing the airway reversibility test on a subject whose additional data has been measured, based on the collation result of the additional data and the untested data. Pulmonary function test device. The historical data includes subject attribute information including at least one of the age, gender, height, and weight of each of the plurality of subjects.
The respiratory function test device according to claim 4 or 5, wherein the control unit determines whether the additional data corresponds to the second data or the third data based on the subject attribute information. When the additional data corresponds to the third data, the control unit determines the respiratory disease of the subject based on the third data provided according to the severity of the respiratory disease stored in the storage unit. The respiratory function test apparatus according to any one of claims 4 to 6, which determines the severity. The control unit receives the additional data as input, uses the data stored in the storage unit as teacher data, and generates a neural network that outputs the determination result of the additional data. Any one of claims 1 to 7. The respiratory function test device described in the section. The first data showing the measurement results of the subjects performed in the past by the information processing device using the respiratory function test device, and showing the measurement results when an abnormality occurs in which the validity of the respiratory function test is lost. A data processing method that processes additional data that indicates new measurement results based on data that includes.
A data processing method comprising the step of determining the validity of a respiratory function test from which the additional data was obtained based on the first data. A respiratory function tester equipped with a measuring unit that measures the flow volume curve of the subject,
A respiratory function test system including an information processing device that processes additional data indicating new measurement results based on data indicating the measurement results of subjects performed in the past.
The information processing device
A storage unit that stores the first data showing the measurement results when an abnormality occurs that makes the respiratory function test invalid.
A respiratory function test system including a control unit for determining the validity of a respiratory function test for which the additional data has been obtained based on the first data.

Images