A system for assisting in the interpretation of pediatric lung function test data

Abstract

This invention relates to the field of medical auxiliary technology, specifically to a system for assisting in the interpretation of pediatric pulmonary function test data. This system, through the cooperation of multiple modules, can achieve the following steps: acquiring target measurement data of the child to be tested and each reference healthy child under different preset factors, and acquiring the lung volume curve corresponding to each reference healthy child; determining the local importance of each preset factor for each pair of reference healthy children; determining the overall interpretation importance corresponding to each preset factor; based on the overall interpretation importance corresponding to different preset factors, and the differences between the target measurement data of the child to be tested and each reference healthy child under the same preset factor, determining the marginal bias of the child to be tested under each preset factor, and evaluating the applicability of using the GLI equation for interpreting pulmonary function test data of the child to be tested, thereby improving the effectiveness of assisting in the interpretation of pediatric pulmonary function test data.

Description

Technical Field

[0001] This invention relates to the field of medical auxiliary technology, specifically to a system for assisting in the interpretation of pediatric lung function test data. Background Technology

[0002] When conducting pulmonary function tests on children, the GLI (Global Lung Function Initiative) equation is often used to assist in the interpretation of the data. However, when directly using the GLI equation to assist in the interpretation of pulmonary function test data on children, the following technical problems often arise:

[0003] In practice, GLI equations are often constructed using a large number of healthy individuals. They tend to work well for the central regions of the data, such as common height and age ranges. However, they are less effective for peripheral regions, such as children whose height is significantly lower than their peers due to growth and development disorders. In such cases, GLI equations are often not applicable. If GLI equations are used directly to assist in the interpretation of a child's lung function test data, the interpretation of the child's lung function test data will often be ineffective. Summary of the Invention

[0004] To address the technical problem of poor effectiveness in interpreting pediatric pulmonary function test data, this invention proposes a system for interpreting pediatric pulmonary function test data.

[0005] In a first aspect, the present invention provides a system for assisting in the interpretation of pediatric pulmonary function test data, the system comprising:

[0006] The data acquisition module is used to acquire target measurement data of the child to be tested and each reference healthy child under different preset factors, and to acquire the lung volume curve corresponding to each reference healthy child;

[0007] The local importance determination module is used to determine the local importance of each preset factor for every two reference healthy children based on the correlation between target measurement data of all reference healthy children under different preset factors;

[0008] The overall interpretation importance determination module is used to determine the overall interpretation importance of each preset factor based on the local importance of each preset factor to each pair of reference healthy children, the difference between target measurement data under the same preset factor, and the difference between lung volume curves corresponding to different reference healthy children.

[0009] The edge deviation determination module is configured to determine the edge deviation of the to-be-tested child under each preset factor according to the overall interpretation importance corresponding to different preset factors and the difference between the target measurement data of the to-be-tested child and each reference healthy child under the same preset factor.

[0010] The applicability evaluation module is configured to evaluate the applicability of the GLI equation in the lung function test interpretation of the to-be-tested child according to the edge deviation of the to-be-tested child under all preset factors.

[0011] In a possible implementation manner of the first aspect, the determination of the local importance of each preset factor for each two reference healthy children based on the correlation between the target measurement data of all reference healthy children under different preset factors comprises the following steps.

[0012] Any one of the preset factors is determined as a marker factor, and each preset factor except the marker factor is determined as a reference factor.

[0013] All reference healthy children are clustered according to the target measurement data of all reference healthy children under the marker factor, to obtain a target cluster.

[0014] The target correlation of the marker factor for each reference factor is determined according to the variance of the target measurement data of all reference healthy children under the same reference factor in the same target cluster.

[0015] The local importance of the marker factor for each two reference healthy children is determined according to the target correlation of the marker factor for different reference factors and the difference between the target measurement data of each two reference healthy children under the same reference factor.

[0016] In a possible implementation manner of the first aspect, the determination of the local importance of the marker factor for each two reference healthy children according to the target correlation of the marker factor for different reference factors and the difference between the target measurement data of each two reference healthy children under the same reference factor comprises the following steps.

[0017] The reference similarity of each two reference healthy children under each reference factor is determined according to the target correlation of the marker factor for each reference factor and the difference between the target measurement data of each two reference healthy children under the same reference factor.

[0018] The cumulative value of the reference similarity of each two reference healthy children under all reference factors is determined as the local importance of the marker factor for each two reference healthy children.

[0019] In a possible implementation manner of the first aspect, the determining of the overall interpretation importance of each preset factor based on the local importance of each preset factor for each two reference healthy children, the difference between the target measurement data of the same preset factor, and the difference between the lung volume curves corresponding to different reference healthy children comprises:

[0020] determining the factor function change difference of each preset factor for each two reference healthy children based on the difference between the target measurement data of the same preset factor of each two reference healthy children and the area between the lung volume curves corresponding to each two reference healthy children, wherein the area between the two lung volume curves represents the difference between the two lung volume curves;

[0021] determining the initial interpretation importance of each preset factor for each two reference healthy children based on the factor function change difference and the local importance of each preset factor for each two reference healthy children;

[0022] determining the overall interpretation importance of each preset factor as the cumulative value of the initial interpretation importance of each preset factor for all different reference healthy children.

[0023] In a possible implementation manner of the first aspect, the determining of the edge deviation of the to-be-detected child under each preset factor based on the overall interpretation importance of different preset factors and the difference between the target measurement data of the same preset factor of the to-be-detected child and each reference healthy child comprises:

[0024] determining any one preset factor as a marker factor and determining each preset factor except the marker factor as a reference factor;

[0025] determining the reference comparability of the marker factor for the to-be-detected child and each reference healthy child based on the overall interpretation importance of all reference factors and the difference between the target measurement data of the same reference factor of the to-be-detected child and each reference healthy child;

[0026] determining the local deviation of the to-be-detected child and each reference healthy child under the marker factor based on the reference comparability of the marker factor for the to-be-detected child and each reference healthy child, the overall interpretation importance of the marker factor, and the difference between the target measurement data of the to-be-detected child and each reference healthy child under the marker factor;

[0027] determining the edge deviation of the to-be-detected child under the marker factor based on the local deviation of the to-be-detected child and all reference healthy children under the marker factor.

[0028] In conjunction with the first aspect above, in one possible implementation, determining the reference comparability of the labeled factor for the child to be tested and each reference healthy child based on the overall interpretive importance corresponding to all reference factors and the differences between the target measurement data of the child to be tested and each reference healthy child under the same reference factor includes:

[0029] Based on the overall interpretive importance of each reference factor and the differences between the target measurement data of the child under test and each reference healthy child under that reference factor, the local comparability of each reference factor for the child under test and each reference healthy child is determined.

[0030] The reference comparability of the labeling factor for the child under test and each reference healthy child is determined by summing the local comparability of all reference factors for the child under test and the same reference healthy child.

[0031] In conjunction with the first aspect above, in one possible implementation, determining the local bias of the child under test and each reference healthy child under the labeled factor based on the reference comparability of the labeled factor for the child under test and each reference healthy child, the overall interpretive importance corresponding to the labeled factor, and the difference between the target measurement data of the child under test and each reference healthy child under the labeled factor includes:

[0032] Based on the reference comparability of the labeled factors for the child to be tested and each reference healthy child, and the overall interpretation importance corresponding to the labeled factors, the target comparability of the labeled factors for the child to be tested and each reference healthy child is determined, wherein both reference comparability and overall interpretation importance are positively correlated with target comparability;

[0033] Based on the absolute value of the difference between the target measurement data of the child under test and each reference healthy child under the labeled factor, and the comparability of the labeled factor with respect to the target of the child under test and each reference healthy child, the local bias of the child under test and each reference healthy child under the labeled factor is determined.

[0034] In conjunction with the first aspect above, in one possible implementation, determining the marginal bias of the child to be tested under the labeled factor based on the local bias of the child to be tested and all reference healthy children under the labeled factor includes:

[0035] The sum of the local biases of the child under test and all reference healthy children under the labeled factor is determined as the marginal bias of the child under test under the labeled factor.

[0036] In conjunction with the first aspect above, in one possible implementation, assessing the applicability of using the GLI equation to interpret pulmonary function tests in the child under test based on the marginal bias of the child under test under all preset factors includes:

[0037] The largest marginal deviation among the marginal deviations of the child under all preset factors is selected as the target deviation.

[0038] Based on the aforementioned target bias, the applicability of using the GLI equation to interpret pulmonary function tests in children under investigation is evaluated.

[0039] In conjunction with the first aspect above, in one possible implementation, assessing the applicability of using the GLI equation to interpret pulmonary function tests in the children to be tested, based on the target bias, includes:

[0040] The target deviation is normalized to obtain a representative value of the overall deviation;

[0041] If the overall deviation value is less than or equal to the preset applicable threshold, it is determined that it is appropriate to use the GLI equation to interpret the lung function test of the child to be tested.

[0042] If the overall deviation value is greater than the preset applicable threshold, it is determined that using the GLI equation to interpret the lung function test of the child to be tested is inappropriate.

[0043] Secondly, the present invention provides a method for assisting in the interpretation of pediatric pulmonary function test data, implemented by a pediatric pulmonary function test data assistance interpretation system, the method comprising:

[0044] Acquire target measurement data of the children to be tested and each reference healthy child under different preset factors, and obtain the lung volume curve corresponding to each reference healthy child;

[0045] Based on the correlation between target measurement data of all reference healthy children under different preset factors, determine the local importance of each preset factor for every two reference healthy children;

[0046] The overall interpretation importance of each preset factor is determined based on the local importance of each preset factor to each pair of reference healthy children, the differences between target measurement data under the same preset factor, and the differences between lung volume curves corresponding to different reference healthy children.

[0047] Based on the overall interpretation importance corresponding to different preset factors, and the difference between the target measurement data of the child to be tested and each reference healthy child under the same preset factor, the marginal bias of the child to be tested under each preset factor is determined;

[0048] The applicability of using the GLI equation to interpret pulmonary function tests in children under test was assessed based on the marginal bias of the children under test under all preset factors.

[0049] Thirdly, a server is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the device to execute the aforementioned method for assisting in the interpretation of pediatric pulmonary function test data.

[0050] Fourthly, a computer program product is provided, comprising: computer program code, which, when run on a computer, causes the computer to execute the aforementioned method for assisting in the interpretation of pediatric lung function test data.

[0051] Fifthly, a computer-readable storage medium is provided that stores computer program code, which, when executed on a computer, causes the computer to perform the aforementioned method for assisting in the interpretation of pediatric pulmonary function test data.

[0052] The present invention has the following beneficial effects:

[0053] This invention provides a system for assisting in the interpretation of pediatric pulmonary function test data, addressing the technical problem of poor effectiveness in this type of data interpretation and improving its overall effectiveness. Specifically, by analyzing target measurement data from the child being tested and a healthy reference child under different preset factors, and using the lung volume curves of the healthy reference child, this invention quantifies several indicators related to the applicability of the GLI equation for the child being tested. These indicators include local importance and overall interpretation importance. This quantifies the marginal bias of the child being tested under each preset factor. Based on the marginal bias of the child being tested under all preset factors, the system assesses the applicability of using the GLI equation for interpreting pulmonary function test data in the child being tested. This reduces the reliance on the GLI equation for interpreting inapplicable pediatric pulmonary function test data, thereby improving the overall effectiveness of the system. Attached Figure Description

[0054] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1This is a schematic diagram of the structure of a pediatric pulmonary function test data auxiliary interpretation system according to the present invention;

[0056] Figure 2 This is a flowchart of a method for assisting in the interpretation of pediatric pulmonary function test data according to the present invention;

[0057] Figure 3 This is a schematic diagram of the structure of a computer device according to the present invention. Detailed Implementation

[0058] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the specific implementation methods, structures, features, and effects of the technical solution proposed according to the present invention are described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0060] refer to Figure 1 A schematic diagram of a pediatric pulmonary function test data interpretation system according to the present invention is shown. The pediatric pulmonary function test data interpretation system includes:

[0061] The data acquisition module 101 is used to acquire target measurement data of the child to be tested and each reference healthy child under different preset factors, and to acquire the lung volume curve corresponding to each reference healthy child.

[0062] The child to be tested can be a child whose lung function test data is to be interpreted. The reference healthy child can be a healthy child of the same ethnicity as the child to be tested. In practice, when interpreting lung function test data, the operator often needs to select the appropriate GLI (Global Lung Function Initiative) equation in GLI2012 based on ethnicity. The reference healthy child and the child to be tested can be of the same ethnicity. A healthy child can be a physically healthy child with no history of muscle disease, no neurological abnormalities, and no clinical manifestations of hand dysfunction or muscle lesions. The child's age range can be 0-18 years.

[0063] Preset factors can be factors related to lung function. The number of preset factors can be pre-set, up to four. For example, preset factors can be, but are not limited to, height, weight, age, and chest circumference. Target measurement data can be normalized values ​​of measurement data under the preset factors. For example, target measurement data under the height factor can be normalized height values. Target measurement data of the child being tested under different preset factors can be collected on the same day. Target measurement data of the same healthy reference child under different preset factors, and their corresponding lung volume curves, can also be collected on the same day.

[0064] The duration corresponding to the lung volume curve can be preset and can be equal to the duration of a standard respiratory cycle. A standard respiratory cycle typically refers to a complete breathing process, including inhalation and exhalation. The duration of a standard respiratory cycle is usually 3-5 seconds. In this embodiment of the invention, the duration corresponding to the lung volume curve can be set to 5 seconds. For example, the lung volume of a reference healthy child can be collected within 5 seconds, and a curve can be constructed with the time sequence number of the lung volume within these 5 seconds as the horizontal axis and the lung volume of the reference healthy child collected within these 5 seconds as the vertical axis. This constructed curve is then recorded as the lung volume curve corresponding to the reference healthy child.

[0065] The local importance determination module 102 is used to determine the local importance of each preset factor for every two reference healthy children based on the correlation between target measurement data of all reference healthy children under different preset factors.

[0066] As an example, determining the local importance of each pre-defined factor for every two reference healthy children may include the following steps:

[0067] The first step is to designate any one preset factor as a marker factor, and to designate each preset factor other than the marker factor as a reference factor.

[0068] The second step is to cluster all reference healthy children based on their target measurement data under the above-mentioned labeled factors to obtain target clusters.

[0069] Within the target cluster, the target measurement data of the reference healthy children under the labeled factors can be the same.

[0070] The third step is to determine the target relevance of the above-mentioned labeled factors to each reference factor based on the variance of the target measurement data of all reference healthy children within the same target cluster under the same reference factor.

[0071] For example, the formula for determining the target relevance of a marker factor to different reference factors can be:

[0072] ;

[0073] in, This represents the target relevance of the marker factor to the a-th reference factor. 'a' is the index of the reference factor. It is an exponential function with the natural constant as its base. N is the number of target clusters. b is the index of the target cluster. It is the variance of the target measurement data of all reference healthy children within the b-th target cluster under the a-th reference factor.

[0074] It should be noted that in practice, if a labeled factor has a strong correlation with other factors, then within the same category of the labeled factor, other factors should generally exhibit relatively small fluctuations, because the labeled factor has a certain constraining effect on other data. For example, if there is a strong correlation between height and age, then children of the same height will often have similar ages. The smaller the value, the more similar the target measurement data of the reference healthy children within the b-th target cluster are to the target measurement data of the a-th reference factor, and the smaller the degree of fluctuation. Therefore, when The larger the value, the more relevant the marker factor is to the a-th reference factor.

[0075] The fourth step, based on the target relevance of the aforementioned marker factors to different reference factors, and the differences in target measurement data between each pair of reference healthy children under the same reference factor, determines the local importance of the aforementioned marker factors for each pair of reference healthy children, which may include the following sub-steps:

[0076] The first sub-step involves determining the reference similarity of each pair of reference healthy children under each reference factor, based on the target relevance of the aforementioned labeled factors to each reference factor and the difference between the target measurement data of each pair of reference healthy children under the same reference factor.

[0077] For example, the formula for determining the reference similarity of different reference healthy children under the same reference factor can be:

[0078] ;

[0079] in, It is the first Reference similarity between the vth reference healthy child and the vth reference healthy child under the ath reference factor. "v" represents the sequence number of the different reference healthy children. "a" represents the sequence number of the reference factor. It is an exponential function with the natural constant as its base. It is an absolute value function. It is the first Target measurement data for a reference healthy child under the a-th reference factor. This is the target measurement data of the vth reference healthy child under the ath reference factor. It is the target relevance of the marker factor to the a-th reference factor.

[0080] It should be noted that when A larger value generally indicates a stronger correlation between the marker factor and the a-th reference factor. When The smaller the size, the more likely it is to indicate the first The more similar the data of the vth reference healthy child and the vth reference healthy child are under the ath reference factor, the better. Therefore, when The larger the value, the more likely the a-th reference factor is to be correlated with the marker factor, and the... The more similar the data of the vth and vth reference healthy children are under the ath reference factor, the more likely it is that the data of the vth reference healthy child are similar; this often indicates that the data of the vth reference healthy child are similar under the ath reference factor. The more similar the data of the vth reference healthy child and the vth reference healthy child are under the reference factor a, which is highly correlated with the marker factor.

[0081] The second sub-step involves summing the reference similarities of each pair of reference healthy children across all reference factors, and determining the local importance of the aforementioned labeling factors for each pair of reference healthy children.

[0082] For example, the formula for determining the local importance of a marker factor for different reference healthy children can be:

[0083] ;

[0084] in, Is the marker factor for the first The local importance of the vth reference healthy child and the vth reference healthy child. v and are the ordinal numbers of the different reference healthy children. n is the number of reference factors. a is the ordinal number of the reference factor. It is the first Reference similarity between the vth reference healthy child and the vth reference healthy child under the ath reference factor.

[0085] It should be noted that when The larger the value, the more likely the a-th reference factor is to be correlated with the marker factor, and the... The more similar the data of the vth and vth reference healthy children are under the ath reference factor, the more likely it is that the data of the vth reference healthy child are similar; this often indicates that the data of the vth reference healthy child are similar under the ath reference factor. The more similar the data of the vth reference healthy child and the vth reference healthy child are under the reference factor a, which is highly correlated with the marker factor, the better. Therefore, when The larger the value, the more likely it is to indicate the first The more similar the data of the vth reference healthy child and the vth reference healthy child are under the reference factors, the more likely it is that the vth reference healthy child is the most likely to be ... The more similar the data of the vth reference healthy child and the vth reference healthy child are under factors other than the labeling factor.

[0086] The overall interpretation importance determination module 103 is used to determine the overall interpretation importance of each preset factor based on the local importance of each preset factor to each pair of reference healthy children, the difference between target measurement data under the same preset factor, and the difference between lung volume curves corresponding to different reference healthy children.

[0087] As an example, determining the overall interpretive importance of each preset factor may include the following steps:

[0088] The first step is to determine the difference in factor function changes for each preset factor for each pair of reference healthy children based on the difference in target measurement data between each pair of reference healthy children under the same preset factor, and the area between the corresponding lung volume curves of each pair of reference healthy children.

[0089] The area between two lung volume curves can represent the difference between them. For example, if the duration of a lung volume curve is 5 seconds, then the area between the two lung volume curves can be the net area of ​​the region enclosed by the two lung volume curves within 5 seconds.

[0090] For example, the formula for determining the differences in factor function changes of predefined factors among different reference healthy children can be:

[0091] ;

[0092] in, Is the i-th preset factor for the i-th Differences in factor function changes between the vth and vth reference healthy children. i is the sequence number of the pre-set factor. v and v are the ordinal numbers of different reference healthy children. is the absolute value function. It is a maximum and minimum value normalization function. It is the first The target measurement data of a reference healthy child under the i-th preset factor. It is the target measurement data of the vth reference healthy child under the i-th preset factor. It is the first The area between the lung volume curve corresponding to the vth reference healthy child and the lung volume curve corresponding to the vth reference healthy child.

[0093] It should be noted that, It can characterize the first The changes of the first reference healthy child and the vth reference healthy child in the i-th preset factor. To a certain extent, it can characterize the first Changes in lung function between the vth and vth reference healthy children. Therefore, when The smaller the size, the more likely it is to indicate the first The more similar the changes in the i-th presupposed factor between the v-th and v-th reference healthy children are to their changes in lung function.

[0094] The second step is to determine the initial interpretation importance of each preset factor for each pair of reference healthy children based on the differences in factor function changes and local importance of each preset factor for each pair of reference healthy children.

[0095] For example, the formula for determining the importance of pre-defined factors in the initial interpretation of different reference healthy children can be:

[0096] ;

[0097] in, Is the i-th preset factor for the i-th The importance of the initial interpretations for the vth reference healthy child and the vth reference healthy child. i is the sequence number of the presupposition factor. "v" and "v" are different reference numbers for healthy children. It is an exponential function with the natural constant as its base. Is the i-th preset factor for the i-th Differences in factor function changes between the vth reference healthy child and the vth reference healthy child. Is the i-th preset factor for the i-th The local importance of the vth reference healthy child and the vth reference healthy child.

[0098] It should be noted that when The smaller the size, the more likely it is to indicate the first The more similar the changes in the i-th presupposed factor between the v-th and v-th reference healthy children are to their changes in lung function, the better. The larger the value, the more likely it is to indicate the first The more similar the data of the first reference healthy child and the vth reference healthy child are under factors other than the i-th preset factor, the better. Can be used as The weight. Therefore, when A larger value often indicates that, while keeping the data consistent with all factors except the i-th preset factor, the i-th factor... The more likely the change in lung function between the first and vth reference healthy children is to be caused by a change in the i-th presupposed factor, the more likely it is to indicate that for the i-th reference healthy child, the change in lung function is due to a change in the i-th presupposed factor. For the first reference healthy child and the vth reference healthy child, the data under the i-th preset factor is more helpful in assisting the interpretation.

[0099] The third step is to sum the initial interpretation importance of each preset factor for all different reference healthy children, and determine the overall interpretation importance corresponding to each preset factor.

[0100] For example, the formula for determining the overall interpretive importance of a preset factor can be:

[0101] ;

[0102] in, This represents the overall interpretation importance corresponding to the i-th preset factor. i is the index of the preset factor. v and are the serial numbers of the different reference healthy children. B is the number of reference healthy children. Is the i-th preset factor for the i-th The importance of the initial interpretation of the vth reference healthy child and the vth reference healthy child.

[0103] It should be noted that when A larger value often indicates that, while keeping the data consistent with all factors except the i-th preset factor, the i-th factor... The more likely the change in lung function between the first and vth reference healthy children is to be caused by a change in the i-th presupposed factor, the more likely it is to indicate that for the i-th reference healthy child, the change in lung function is due to a change in the i-th presupposed factor. For the first and vth reference healthy children, the data under the i-th presupposed factor is more helpful in aiding interpretation. Therefore, when The larger the value, the more likely the data under the i-th preset factor is to aid interpretation for most healthy children in the reference population.

[0104] The marginal bias determination module 104 is used to determine the marginal bias of the child under test under each preset factor based on the overall interpretation importance corresponding to different preset factors, and the difference between the target measurement data of the child under test and each reference healthy child under the same preset factor.

[0105] As an example, determining the marginal bias of a child under test under each preset factor may include the following steps:

[0106] The first step is to designate any one preset factor as a marker factor, and to designate each preset factor other than the marker factor as a reference factor.

[0107] The second step, based on the overall interpretive importance of all reference factors and the differences between the target measurement data of the children to be tested and each reference healthy child under the same reference factor, determines the reference comparability of the aforementioned labeling factors for the children to be tested and each reference healthy child, which may include the following sub-steps:

[0108] The first sub-step involves determining the local comparability of each reference factor for the children under test and each reference healthy child based on the overall interpretive importance of each reference factor and the differences between the target measurement data of the children under test and each reference healthy child under that reference factor.

[0109] For example, the formula for determining the local comparability of a reference factor for the child being tested and the reference healthy child can be:

[0110] ;

[0111] in, The a-th reference factor is for the child being tested and the first reference factor. Local comparability of a reference healthy child. This refers to the serial number of the healthy child. 'a' is the serial number of the reference factor. It is an exponential function with the natural constant as its base. It is an absolute value function. It is the first Target measurement data for a reference healthy child under the a-th reference factor. These are the target measurement data for the child to be tested under the a-th reference factor. This refers to the overall interpretive importance of the a-th reference factor.

[0112] It should be noted that when A larger value generally indicates that the data under the a-th reference factor may be more helpful in interpreting the data for most reference healthy children. The larger the value, the more likely it is that the child being tested is a close relative of the first child. The greater the variation in the data for the reference healthy child under the a-th reference factor, the greater the variation. Therefore, when The larger the value, the more likely it is that the child being tested is a close relative of the first child. The more similar the data of the reference healthy children under the a-th reference factor, and the more likely the data under the a-th reference factor is to aid in interpretation for most reference healthy children, the more likely it is to indicate that the child being tested and the data under the a-th reference factor are similar. The more similar the data of the reference healthy children under reference factors with relatively good interpretation effects, the more likely it is that the data of the first reference healthy child are similar. The more reference healthy children there are, the more meaningful they are for the child being tested.

[0113] The second sub-step involves determining the reference comparability of the aforementioned marker factors for the aforementioned child under test and each reference healthy child based on the cumulative value of the local comparability of all reference factors for the aforementioned child under test and the same reference healthy child.

[0114] For example, the formula for determining the reference comparability of the marker factor for the child being tested and the reference healthy child can be:

[0115] ;

[0116] in, These are marker factors for the children being tested and the first Comparability of reference healthy children. This refers to the reference number of a healthy child. 'n' represents the number of reference factors. 'a' is the reference factor number. The a-th reference factor is for the child being tested and the first reference factor. Local comparability of a reference healthy child.

[0117] It should be noted that when The larger the value, the more likely it is that the child being tested is a close relative of the first child. The more similar the data of the reference healthy children under the a-th reference factor, and the more likely the data under the a-th reference factor is to aid in interpretation for most reference healthy children, the more likely it is to indicate that the child being tested and the data under the a-th reference factor are similar. The more similar the data of healthy children under reference factors with relatively good interpretability, the better. Therefore, when The larger the value, the more likely it is that the child being tested is a close relative of the first child. The more similar the data of the reference healthy children under factors other than the marker factor, the more likely it is that the child being tested and the first child are similar. The more significant the changes in data for the reference healthy children under the marker factors, the more valuable the data is, often indicating the relationship between the tested child and the first healthy child. Changes in lung function among reference healthy children are more likely to be due to changes in marker factors.

[0118] The third step, based on the comparability of the aforementioned labeling factors for the children under test and each reference healthy child, the overall interpretive importance of the aforementioned labeling factors, and the differences between the target measurement data of the children under test and each reference healthy child under the aforementioned labeling factors, determining the local bias of the children under test and each reference healthy child under the aforementioned labeling factors may include the following sub-steps:

[0119] The first sub-step involves determining the target comparability of the aforementioned marker factors for the children to be tested and each reference healthy child, based on the reference comparability of the marker factors for the children to be tested and each reference healthy child, and the overall interpretive importance of the aforementioned marker factors.

[0120] Among them, the importance of reference comparability and overall interpretation can both be positively correlated with the comparability of the target.

[0121] For example, the formula for determining the target comparability of marker factors for the child being tested and the reference healthy child can be:

[0122] ;

[0123] in, These are marker factors for the children being tested and the first Comparability with the target of a healthy child. It is a reference number for healthy children. These are marker factors for the children being tested and the first Comparability of reference healthy children. A represents the overall interpretive importance of the marker factors.

[0124] It should be noted that when The larger the value, the more likely it is that the child being tested is a close relative of the first child. The more similar the data of the reference healthy children under factors other than the marker factor, the more likely it is that the child being tested and the first child are similar. The more significant the changes in data for the reference healthy children under the marker factors, the more valuable the data is, often indicating the relationship between the tested child and the first healthy child. Variations in lung function among a group of healthy reference children are more likely to be due to changes in marker factors. A larger value for A generally indicates that data under the marker factors are more likely to be helpful in interpreting for most healthy reference children. Therefore, when... The larger the value, the more important the marker factor is for the child being tested and the first-degree child. The greater the reference value of a healthy child, the more likely it is that the child being tested is similar to the first healthy child. Changes in lung function among reference healthy children are more likely to be due to changes in marker factors.

[0125] The second sub-step involves determining the local bias of the child under test and each reference healthy child under the aforementioned labeling factors based on the absolute value of the difference between the target measurement data of the child under test and each reference healthy child under the aforementioned labeling factors, and the comparability of the aforementioned labeling factors with respect to the targets of the child under test and each reference healthy child under the aforementioned labeling factors.

[0126] For example, the formula for determining the local bias of the child being tested and the reference healthy child under the labeled factors can be:

[0127] ;

[0128] in, The children to be tested and the first Local bias of a reference healthy child under labeled factors. It is a reference number for healthy children. These are marker factors for the children being tested and the first Comparability with the target of a healthy child. It is a normalization function for maximum and minimum values. It is a function for taking the absolute value. It is the first F represents the target measurement data of a reference healthy child under labeled factors. F represents the target measurement data of the child to be tested under labeled factors.

[0129] It should be noted that, Can be used as The weight. When The larger the value, the more important the marker factor is for the child being tested and the first-degree child. The greater the reference value of a healthy child, the more likely it is that the child being tested is similar to the first healthy child. The more likely the changes in lung function among a group of healthy reference children are to be due to changes in marker factors, the more likely the marker factors are to be present in the child being tested and the first group of healthy reference children. Key factors among healthy children. When The larger the value, the more likely it is that the child being tested is a close relative of the first child. The greater the variation in data among reference healthy children under the labeled factors, the greater the difference. Therefore, when The larger the value, the more likely the marker factor is to be the child being tested and the first-degree child. The key factors among reference healthy children, and the greater the difference in variation under these factors.

[0130] The fourth step is to determine the marginal bias of the children to be tested under the aforementioned labeling factors, based on the local bias of the children to be tested and all reference healthy children under the aforementioned labeling factors.

[0131] For example, the sum of the local biases of the child under test and all reference healthy children under the above-mentioned labeling factors can be determined as the marginal bias of the child under test under the above-mentioned labeling factors.

[0132] For example, the formula for determining the marginal bias of a child under a labeled factor can be:

[0133] ;

[0134] Where p represents the marginal bias of the children being tested under the labeled factors. B represents the number of reference healthy children. It is a reference number for healthy children. The children to be tested and the first Local bias of a reference healthy child under labeled factors.

[0135] It should be noted that when The larger the value, the more likely the marker factor is to be the child being tested and the first-degree child. The key factor between the tested children and most of the reference healthy children, and the greater the difference in variation under that factor. Therefore, the larger the p-value, the more likely the marker factor is to be a key factor between the tested child and most of the reference healthy children, and the greater the difference in variation under that factor; it also tends to indicate that the marker factor is more likely to be a key factor, and the tested child is more likely to deviate from a healthy state under the marker factor.

[0136] The applicability assessment module 105 is used to assess the applicability of using the GLI equation to interpret pulmonary function tests in children under test based on the marginal bias of the children under test under all preset factors.

[0137] As an example, assessing the applicability of using the GLI equation for interpreting pulmonary function tests in children may include the following steps:

[0138] The first step is to select the largest marginal deviation from the marginal deviations of the children to be tested under all preset factors, and use it as the target deviation.

[0139] It's important to note that in practice, the GLI (Global Lung Function Initiative) equation is often constructed using a large number of healthy individuals. It typically performs well in the central regions of the data, such as common height and age ranges. However, its effectiveness is often poor in peripheral regions, such as children whose height is significantly below average due to growth and developmental disorders. In these cases, the GLI equation is often unsuitable, and directly using it to interpret the child's lung function test data will often result in poor interpretation. Therefore, a greater target bias indicates that the child being tested is more likely to deviate from the majority of healthy conditions under key factors, is more likely to be in the peripheral region rather than the majority of typical healthy conditions, and is less likely to be suitable for interpreting lung function test data using the GLI equation.

[0140] The second step, based on the aforementioned target bias, assessing the applicability of using the GLI equation for interpreting pulmonary function tests in the children being tested may include the following sub-steps:

[0141] The first sub-step is to normalize the above-mentioned target deviation to obtain the overall deviation representative value.

[0142] In the second sub-step, if the overall deviation value is less than or equal to the preset applicable threshold, it is determined that using the GLI equation to interpret the lung function test of the above-mentioned children to be tested is appropriate.

[0143] The preset applicable threshold can be a pre-set threshold that can be adjusted according to the actual scenario. For example, the preset applicable threshold can be 0.8.

[0144] In the third sub-step, if the overall deviation value is greater than the preset applicable threshold, it is determined that using the GLI equation to interpret the lung function test of the above-mentioned children is inappropriate, and doctors often need to conduct key observations and judgments on the above-mentioned children.

[0145] refer to Figure 2 Based on the same inventive concept as the above-described method embodiments, the present invention provides a method for assisting in the interpretation of pediatric pulmonary function test data, comprising the following steps:

[0146] Step S1: Obtain target measurement data of the child to be tested and each reference healthy child under different preset factors, and obtain the lung volume curve corresponding to each reference healthy child.

[0147] Step S2: Based on the correlation between the target measurement data of all reference healthy children under different preset factors, determine the local importance of each preset factor for every two reference healthy children.

[0148] Step S3: Determine the overall interpretation importance of each preset factor based on the local importance of each preset factor to each pair of reference healthy children, the difference between target measurement data under the same preset factor, and the difference between lung volume curves corresponding to different reference healthy children.

[0149] Step S4: Based on the overall interpretation importance corresponding to different preset factors, and the difference between the target measurement data of the child to be tested and each reference healthy child under the same preset factor, determine the marginal bias of the child to be tested under each preset factor.

[0150] Step S5: Based on the marginal bias of the child under test under all preset factors, assess the applicability of using the GLI equation to interpret the pulmonary function test results of the child under test.

[0151] Figure 3This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. For example, as shown... Figure 3 As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302. When the processor 302 executes the computer program 303, the computer device can perform the aforementioned method for assisting in the interpretation of pediatric lung function test data.

[0152] Based on the same inventive concept as the above-described method embodiments, the present invention provides a server, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the device to execute the above-described method for assisting in the interpretation of pediatric lung function test data.

[0153] Based on the same inventive concept as the above-described method embodiments, the present invention provides a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform the above-described method for assisting in the interpretation of pediatric lung function test data.

[0154] Based on the same inventive concept as the above-described method embodiments, the present invention provides a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform the above-described method for assisting in the interpretation of pediatric lung function test data.

[0155] In summary, this invention quantifies several indicators related to the applicability of the GLI equation for the children under test by analyzing target measurement data of the children under test and reference healthy children under different preset factors, as well as the lung volume curves of the reference healthy children. These indicators include local importance and overall interpretation importance. This quantifies the marginal bias of the children under test under each preset factor. Based on the marginal bias of the children under test under all preset factors, the invention assesses the applicability of the GLI equation for interpreting pulmonary function test data of the children under test. To a certain extent, this can reduce the auxiliary interpretation of pulmonary function test data of children for whom the GLI equation is not applicable, thereby improving the overall effect of auxiliary interpretation of pulmonary function test data of children.

[0156] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A system for assisting in the interpretation of pediatric pulmonary function test data, characterized in that, The system comprises: a data acquisition module configured to acquire target measurement data of the child to be detected and each reference healthy child under different preset factors, and acquire a lung volume curve corresponding to each reference healthy child; a local importance determination module configured to determine local importance of each preset factor for each two reference healthy children based on correlation between the target measurement data of all reference healthy children under different preset factors; a global interpretation importance determination module configured to determine global interpretation importance corresponding to each preset factor according to the local importance of each preset factor for each two reference healthy children, difference between the target measurement data under the same preset factor, and difference between the lung volume curves corresponding to different reference healthy children; an edge bias determination module configured to determine edge bias of the child to be detected under each preset factor according to the global interpretation importance corresponding to different preset factors, and difference between the target measurement data of the child to be detected and each reference healthy child under the same preset factor; an applicability evaluation module configured to evaluate applicability of using the GLI equation to interpret lung function examination of the child to be detected according to the edge bias of the child to be detected under all preset factors. The local importance of each preset factor for each two reference healthy children is determined based on correlation between the target measurement data of all reference healthy children under different preset factors, comprising: determining any one preset factor as a marker factor, and determining each preset factor other than the marker factor as a reference factor; clustering all reference healthy children according to the target measurement data of all reference healthy children under the marker factor to obtain a target cluster; determining target correlation of the marker factor for each reference factor according to variance of the target measurement data of all reference healthy children under the same reference factor within the same target cluster; and determining local importance of the marker factor for each two reference healthy children according to the target correlation of the marker factor for different reference factors, and difference between the target measurement data of each two reference healthy children under the same reference factor.

2. The system of claim 1, wherein, The local importance of the marker factor for each two reference healthy children is determined according to the target correlation of the marker factor for different reference factors, and difference between the target measurement data of each two reference healthy children under the same reference factor, comprising: determining reference similarity of each two reference healthy children under each reference factor according to the target correlation of the marker factor for each reference factor, and difference between the target measurement data of each two reference healthy children under the same reference factor; determining the local importance of the marker factor for each two reference healthy children as an accumulated value of the reference similarity of each two reference healthy children under all reference factors.

3. The system for assisting in the interpretation of data from a test of pulmonary function in children according to claim 1, characterized in that, The overall interpretation importance of each preset factor is determined according to the local importance of each preset factor for each two reference healthy children, the difference between the target measurement data of the same preset factor, and the difference between the lung volume curves corresponding to different reference healthy children, and includes: The factor function change difference of each preset factor for each two reference healthy children is determined according to the difference between the target measurement data of the same preset factor of each two reference healthy children and the area between the lung volume curves corresponding to each two reference healthy children, wherein the area between the two lung volume curves represents the difference between the two lung volume curves; The initial interpretation importance of each preset factor for each two reference healthy children is determined according to the factor function change difference and the local importance of each preset factor for each two reference healthy children; The overall interpretation importance of each preset factor is determined by accumulating the initial interpretation importance of each preset factor for all different reference healthy children.

4. The system for assisting in the interpretation of data from a test of pulmonary function in children according to claim 1, characterized in that, The marginal deviation of the to-be-detected child under each preset factor is determined according to the overall interpretation importance corresponding to different preset factors and the difference between the target measurement data of the same preset factor of the to-be-detected child and each reference healthy child, and includes: Any one preset factor is determined as a marker factor, and each preset factor other than the marker factor is determined as a reference factor; The reference comparability of the marker factor for the to-be-detected child and each reference healthy child is determined according to the overall interpretation importance corresponding to all reference factors and the difference between the target measurement data of the same reference factor of the to-be-detected child and each reference healthy child; The local deviation of the to-be-detected child and each reference healthy child under the marker factor is determined according to the reference comparability of the marker factor for the to-be-detected child and each reference healthy child, the overall interpretation importance corresponding to the marker factor, and the difference between the target measurement data of the marker factor of the to-be-detected child and each reference healthy child; The marginal deviation of the to-be-detected child under the marker factor is determined according to the local deviation of the to-be-detected child and all reference healthy children under the marker factor.

5. A system for assisted interpretation of a child lung function test according to claim 4, wherein The reference comparability of the marker factor for the to-be-detected child and each reference healthy child is determined according to the overall interpretation importance corresponding to all reference factors and the difference between the target measurement data of the same reference factor of the to-be-detected child and each reference healthy child, and includes: The local comparability of each reference factor for the to-be-detected child and each reference healthy child is determined according to the overall interpretation importance corresponding to each reference factor and the difference between the target measurement data of the reference factor of the to-be-detected child and each reference healthy child; The reference comparability of the marker factor for the to-be-detected child and each reference healthy child is determined according to the accumulation of the local comparability of all reference factors for the to-be-detected child and the same reference healthy child.

6. The child lung function test data aided interpretation system according to claim 4, characterized in that, The local deviation of the child to be detected and each reference healthy child under the marker factor is determined according to the reference comparability of the marker factor to the child to be detected and each reference healthy child, the overall interpretation importance corresponding to the marker factor, and the difference between the target measurement data of the child to be detected and each reference healthy child under the marker factor, including: The target comparability of the marker factor to the child to be detected and each reference healthy child is determined according to the reference comparability of the marker factor to the child to be detected and each reference healthy child, and the overall interpretation importance corresponding to the marker factor, wherein the reference comparability and the overall interpretation importance are positively correlated with the target comparability; The local deviation of the child to be detected and each reference healthy child under the marker factor is determined according to the absolute value of the difference between the target measurement data of the child to be detected and each reference healthy child under the marker factor, and the target comparability of the marker factor to the child to be detected and each reference healthy child.

7. The child lung function test data aided interpretation system according to claim 4, characterized in that, The marginal deviation of the child to be detected under the marker factor is determined according to the local deviation of the child to be detected and all reference healthy children under the marker factor, including: The marginal deviation of the child to be detected under the marker factor is determined as the cumulative value of the local deviation of the child to be detected and all reference healthy children under the marker factor.

8. The child lung function test data aided interpretation system according to claim 1, characterized in that, The applicability of the GLI equation for interpreting the lung function test of the child to be detected is evaluated according to the marginal deviation of the child to be detected under all preset factors, including: The maximum marginal deviation is selected from the marginal deviation of the child to be detected under all preset factors as a target deviation; The applicability of the GLI equation for interpreting the lung function test of the child to be detected is evaluated according to the target deviation.

9. A system for assisted interpretation of a child lung function test according to claim 8, wherein, The applicability of the GLI equation for interpreting the lung function test of the child to be detected is evaluated according to the target deviation, including: The target deviation is normalized to obtain an overall deviation representative value; If the overall deviation representative value is less than or equal to a preset applicability threshold, it is determined that the GLI equation is suitable for interpreting the lung function test of the child to be detected; If the overall deviation representative value is greater than the preset applicability threshold, it is determined that the GLI equation is not suitable for interpreting the lung function test of the child to be detected.

Images