Medical data processing method and system for inspection

Abstract

The invention relates to the technical field of medical data processing, in particular to a medical data processing method and system for inspection. The method comprises the following steps: firstly, determining a search radius of an antigen immunoreaction spectrum according to a data value and a characteristic value of each main component of each antigen immunoreaction spectrum; obtaining the radius adjustment demand degree of the to-be-analyzed chart according to the overall representative difference between the to-be-analyzed chart and all antigen immunoreaction spectrums in the local range of the to-be-analyzed chart; the search radius is adjusted according to the radius adjustment requirement degree, and the adjusted search radius of the to-be-analyzed graph is obtained; and carrying out DBSCAN clustering on all the antigen immunoreaction spectrums to obtain each antigen immunoreaction spectrum class cluster. According to the method, the adjusted search radius of the antigen immunoreaction spectrum is reasonably set, key information in the antigen immunoreaction spectrum can be better captured, and the accuracy of a clustering result of the antigen immunoreaction spectrum is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a method and system for processing medical data for inspection and examination. Background Art

[0002] Medical data from tests and examinations refers to data on various indicators of the patient's body obtained through clinical laboratory tests, medical imaging examinations, bioelectric measurements, etc., which are of great significance for auxiliary treatment plans. The antigen immune response spectrum is the result of one of the detection methods. The antigen immune response spectrum is a graph that measures the change of antigen response intensity with antigen concentration through experimental methods. The antigen immune response spectrum can intuitively display the characteristics of the immune response, including affinity, specificity, and sensitivity, which is crucial for the medical evaluation and treatment of all patients. Classifying the antigen immune response spectrum of all patients can provide a basis for doctors to formulate personalized treatment plans.

[0003] The DBSCAN algorithm is a widely used clustering algorithm and has been widely used in the task of antigen immune response spectrum classification. When using the DBSCAN algorithm to classify all antigen immune response spectra, the existing technology often uses a fixed search radius for clustering, which does not fully consider the representativeness of the characteristics of the antigen immune response spectrum and is difficult to accurately capture the key information in the antigen immune response spectrum, resulting in inaccurate clustering results of the antigen immune response spectrum. Summary of the invention

[0004] In order to solve the technical problem of inaccurate clustering of antigen immune response spectrum in the prior art, the purpose of the present invention is to provide a medical data processing method and system for inspection and examination. The technical solution adopted is as follows: A method for processing medical data of an inspection and examination, the method comprising: Obtain antigen signal data and all patient characteristic indicators for each antigen immune response profile; According to the antigen signal data of all the antigen immune response spectra, dimension reduction processing is performed to obtain the data value and characteristic value of each principal component of each antigen immune response spectrum; according to the data value and characteristic value of each principal component of each antigen immune response spectrum, the search radius of the antigen immune response spectrum is determined; Take any one of the antigen immune response spectra as the graph to be analyzed, and take any one of the patient characteristic indicators as the indicator to be analyzed; obtain the characteristic representativeness of the indicator to be analyzed of the graph to be analyzed according to the deviation of the indicator to be analyzed of the graph to be analyzed from the central trend; obtain the influence measure of the indicator to be analyzed according to the correlation between the data values ​​of the indicator to be analyzed and the principal component corresponding to all the antigen immune response spectra; obtain the overall representativeness of the graph to be analyzed according to the characteristic representativeness of all the patient characteristic indicators of the graph to be analyzed and the influence measure; obtain the radius adjustment requirement of the graph to be analyzed according to the difference between the graph to be analyzed and the overall representativeness of all the antigen immune response spectra in the local range; adjust the search radius according to the radius adjustment requirement to obtain the adjusted search radius of the graph to be analyzed; According to the adjusted search radius of each antigen immune response spectrum, DBSCAN clustering is performed on all the antigen immune response spectra to obtain each antigen immune response spectrum cluster.

[0005] Furthermore, the method for obtaining the data value and the characteristic value of the principal component includes: The PCA method is used to perform dimensionality reduction processing on the antigen signal data of all the antigen immune response spectra to obtain the data values ​​and characteristic values ​​of each principal component of each antigen immune response spectrum.

[0006] Furthermore, the method for obtaining the search radius includes: The distance metric value is obtained according to the distance metric value formula, and the distance metric value formula includes: ;in, For the The immune response spectrum of each antigen and the The distance measure between the immune response profiles of the antigens; For the The eigenvalues ​​of the principal components; For the The first antigen immune response spectrum The data values ​​of the principal components; For the The first antigen immune response spectrum The data values ​​of the principal components; is the total number of all principal components; The k-distance analysis method is used to determine the search radius of the antigen immune response spectrum according to the distance metric value between every two antigen immune response spectra.

[0007] Furthermore, the method for obtaining the representativeness of the features includes: According to the indicators to be analyzed corresponding to all antigen immune response spectra, the normal distribution mean is obtained; the absolute value of the difference between the indicator to be analyzed in the graph to be analyzed and the normal distribution mean is calculated and negative correlation mapping is performed to obtain the characteristic representativeness of the indicator to be analyzed in the graph to be analyzed.

[0008] Furthermore, the method for obtaining the impact metric includes: Labeling all the antigen immune response spectra; sequentially counting the data values ​​of the principal components corresponding to all the antigen immune response spectra in the order of the labels to obtain a data value sequence of the principal components; sequentially counting the indicators to be analyzed corresponding to all the antigen immune response spectra in the order of the labels to obtain a sequence of indicators to be analyzed; The influence metric is obtained according to an influence metric formula, wherein the influence metric formula includes: ;in, The impact measure for the indicator to be analyzed; For the The eigenvalues ​​of the principal components; is the sum of the eigenvalues ​​of all principal components; The indicator sequence to be analyzed and Pearson correlation coefficient of the data value sequence of the principal components; is the total number of all principal components; is the absolute value symbol.

[0009] Furthermore, the overall representativeness acquisition formula includes: ;in, is the overall representativeness of the graph to be analyzed; For the Each patient characteristic indicator corresponds to an impact measure; It is the cumulative value of the corresponding impact measure of all patient characteristic indicators; is the first The characteristic representativeness of each patient characteristic indicator; is the total number of all patient characteristic indicators; Adjust the value for the preset denominator.

[0010] Furthermore, the method for obtaining the radius adjustment requirement includes: In the principal component space, each antigen immune response spectrum in the search radius of the image to be analyzed is used as each neighborhood analysis graph of the image to be analyzed; The relative typicality is obtained according to a relative typicality formula, wherein the relative typicality formula includes: ;in, To be analyzed Relative to neighborhood analysis graph The relative typicality of To be analyzed No. Neighborhood analysis diagram; For the The eigenvalues ​​of the principal components; is the sum of the eigenvalues ​​of all principal components; is the total number of all principal components; For the The principal components correspond to all eigenvalues, and the No. The total number of all eigenvalues ​​with the same value for the eigenvalues ​​corresponding to the principal components; For the The principal components correspond to all eigenvalues, and the neighborhood analysis diagram No. The total number of all eigenvalues ​​with the same value for the eigenvalues ​​corresponding to the principal components; To be analyzed overall representativeness of Neighborhood analysis graph overall representativeness of Adjust the value for the preset denominator; The relative typicality of the image to be analyzed relative to all neighborhood analysis images and the overall representativeness of the image to be analyzed are forwardly integrated to obtain the radius adjustment requirement of the image to be analyzed.

[0011] Furthermore, the method for obtaining the radius adjustment requirement includes: The radius adjustment requirement is obtained according to the radius adjustment requirement formula, and the radius adjustment requirement formula includes: ;in, The graph to be analyzed The radius adjustment required; To be analyzed Relative to neighborhood analysis graph The relative typicality of To be analyzed No. Neighborhood analysis diagram; To be analyzed The total number of all neighborhood analysis graphs; To be analyzed overall representativeness of is the normalization function.

[0012] Furthermore, the method for obtaining the adjusted search radius includes: The product of the radius adjustment requirement of the image to be analyzed and a preset adjustment value is calculated as a target adjustment value of the image to be analyzed; and the product of the target adjustment value and the search radius is used as the adjusted search radius of the image to be analyzed.

[0013] The present invention proposes a medical data processing system for inspection and examination, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the medical data processing method for inspection and examination when executing the computer program.

[0014] The present invention has the following beneficial effects: Since antigen signal data is usually high-dimensional, direct analysis is relatively complicated, and dimensionality reduction processing is required to obtain the data values ​​and eigenvalues ​​of each principal component of each antigen immune response spectrum; the principal component represents the dimension with more immune response information. Further, based on the data values ​​and eigenvalues ​​of each principal component of each antigen immune response spectrum, the search radius of the antigen immune response spectrum is preliminarily determined. Reasonable determination of the search radius is a key step in the subsequent adjustment and optimization of clustering results. Select any antigen immune response spectrum as the graph to be analyzed, and select a patient characteristic index as the index to be analyzed. Analyze the trend of the index to be analyzed in the graph to be analyzed, and reflect the representativeness of the index to be analyzed in the graph to be analyzed through the representativeness of the characteristics; by analyzing the correlation between the index to be analyzed and the data values ​​of all antigen immune response spectra on the principal components, obtain the influence measure of the index to be analyzed, and the influence measure reflects the importance of the index to be analyzed to the antigen immune response spectrum. Combined with the characteristic representativeness of the graph to be analyzed on all patient characteristic indicators and the influence measure of these indicators, the overall representativeness of the graph to be analyzed is obtained, and the overall representativeness comprehensively evaluates the overall representativeness of the graph to be analyzed. The difference between the image to be analyzed and its overall representativeness of all antigen immune response spectra in the local range is compared, and the radius adjustment requirement of the image to be analyzed is calculated. The greater the difference, the higher the adjustment requirement may be, which means that a larger search radius needs to be allocated to the image to be analyzed to capture more similar points. According to the calculated radius adjustment requirement, the original search radius of the image to be analyzed is adjusted, and the adjusted search radius is reasonably set to improve the accuracy of clustering. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1A flowchart of a method for processing medical data for inspection and examination provided by one embodiment of the present invention; Figure 2 A structural diagram of a medical data processing system for inspection and examination provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the medical data processing method and system for inspection and examination proposed by the present invention, its specific implementation method, structure, characteristics and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, 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 belongs.

[0019] The specific scheme of the medical data processing method and system for inspection and examination provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] The present invention provides a method and system for processing medical data for inspection and examination. Figure 1 , which shows a flow chart of a medical data processing method for inspection and examination provided by an embodiment of the present invention, the method comprising the following steps: Step S1: Obtain antigen signal data and all patient characteristic indicators for each antigen immune response spectrum.

[0021] In order to perform accurate clustering later, the antigen signal data and all patient characteristic indicators of each antigen immune response spectrum were first obtained.

[0022] The data acquisition process must strictly follow the user authorization principle to ensure that the antigen signal data of each antigen immune response spectrum and all patient characteristic indicators are legally obtained from the database. The specific acquisition process includes: The database stores each patient's antigen immune response spectrum and all patient characteristic indicators; antigen signal data is extracted based on each patient's antigen immune response spectrum.

[0023] The antigen immune response spectrum is the result of one of the detection methods. It is a graph that shows the change of antigen reaction intensity with antigen concentration through experimental methods. The horizontal axis of the antigen immune response spectrum represents the antigen concentration, and the vertical axis represents the antigen response intensity; the antigen signal data is a sequence of antigen response intensities that are statistically analyzed in order of antigen concentration, which clearly shows the characteristics of the change of antigen response intensity with antigen concentration.

[0024] The database collects all the patient characteristic indicators of the patient, such as height, weight, age and blood pressure, etc.; all the patient characteristic indicators of the patient are counted as the patient's antigen immune response spectrum corresponding to all the patient characteristic indicators, so as to provide a deeper understanding of the patient's background information of the antigen immune response spectrum.

[0025] The data collection in the present invention is authorized by the user, does not violate relevant laws and regulations, and does not violate public order and good morals. In order to facilitate calculations, all indicator data involved in the calculations in the embodiments of the present invention are subjected to data preprocessing to eliminate the dimension effect. The specific means of removing the dimension effect are technical means well known to those skilled in the art and are not limited here. It should be noted that the present invention contains an antigen signal data for the antigen immune response spectrum, and the antigen signal data of all antigen immune response spectra contain the same number of antigen reaction intensities, and the number of all patient characteristic indicators of all antigen immune response spectra is consistent.

[0026] Step S2: Perform dimensionality reduction processing based on the antigen signal data of all antigen immune response spectra to obtain the data values ​​and eigenvalues ​​of each principal component of each antigen immune response spectrum; determine the search radius of the antigen immune response spectrum based on the data values ​​and eigenvalues ​​of each principal component of each antigen immune response spectrum.

[0027] Since antigen signal data are usually high-dimensional, direct analysis is relatively complicated and requires dimensionality reduction to obtain the data values ​​and eigenvalues ​​of each principal component of each antigen immune response spectrum. The principal component represents the dimension with more immune response information. Based on the data values ​​and eigenvalues ​​of each principal component of each antigen immune response spectrum, the search radius of the antigen immune response spectrum is preliminarily determined. Reasonable determination of the search radius is a key step in the subsequent adjustment and optimization of the clustering results.

[0028] Since antigen signal data has high dimensionality, direct analysis is complex and difficult to capture the main information. Therefore, dimensionality reduction processing is required to obtain the data values ​​and eigenvalues ​​of each principal component of each antigen immune response spectrum. Preferably, in one embodiment of the present invention, the method for obtaining the data values ​​and eigenvalues ​​of the principal components includes: The PCA method is used to perform dimensionality reduction processing on the antigen signal data of all antigen immune response spectra to obtain the data values ​​and eigenvalues ​​of each principal component of each antigen immune response spectrum.

[0029] It should be noted that the PCA method (Principal Component Analysis) is a commonly used dimensionality reduction technology. Here we only briefly describe how to use the PCA method to reduce the dimensionality of the antigen signal data of all antigen immune response spectra to obtain the data values ​​and eigenvalues ​​of each principal component of each antigen immune response spectrum: First, the antigen signal data of all antigen immune response spectra are organized into a two-dimensional data matrix. In this matrix, each row represents an antigen immune response spectrum, and each column represents the antigen response intensity corresponding to an antigen concentration. Next, the covariance matrix of this data matrix is ​​calculated to capture the correlation between the monitoring values ​​at different antigen concentration points. Subsequently, the covariance matrix is ​​subjected to eigenvalue decomposition, which will produce eigenvalues ​​and corresponding eigenvectors. The size of the eigenvalue represents the amount of variance explained by each principal component, that is, the amount of information. The eigenvector defines the direction of the principal component, that is, the projection direction of the data in the principal component space. Based on the size of the eigenvalue, the principal components with the largest variance are selected. These principal components will be used for subsequent dimensionality reduction processing. The eigenvectors corresponding to these selected principal components are used to perform a linear transformation on the original data. This transformation process projects the original data into the principal component space to obtain the reduced-dimensional data. In the reduced-dimensional data matrix, each row still represents an antigen immune response spectrum, but each column now represents the coordinate value of the antigen immune response spectrum in the principal component space, that is, the data value of the principal component. At the same time, the eigenvalues ​​of the principal components of each antigen immune response spectrum are also obtained in the eigenvalue decomposition process, and these eigenvalues ​​reflect the importance of each principal component in the data set. The preset number in the present invention is 3, that is, the total number of all principal components in the present invention is 3, and the implementer can set it according to the implementation scenario.

[0030] It should be noted that the subsequent clustering is performed in the principal component space containing all antigen immune response spectra. Here is a brief description of the principal component space: each axis of the principal component space corresponds to each principal component, and each antigen immune response spectrum is represented as a data point in the principal component space. Specifically, the data values ​​of each antigen immune response spectrum on each principal component are used as its coordinates in the principal component space, so that each antigen immune response spectrum is mapped to a multidimensional space composed of principal components to form a data point, that is, a principal component space containing all antigen immune response spectra is obtained. Among them, the principal component space is a multidimensional space, each axis of which corresponds to a principal component, and the total number of principal components in the present invention is set to 3, that is, the principal component space is a three-dimensional space.

[0031] Considering that in the DBSCAN algorithm, the search radius refers to the neighborhood range around a point, and the search radius is a core parameter that affects the clustering effect of the DBSCAN algorithm, by explicitly calculating the distance measurement value of the two antigen immune response spectra, the search radius can be set more accurately, thereby ensuring the accuracy of the preliminary determination of the search radius. Preferably, in one embodiment of the present invention, the method for obtaining the search radius includes: The distance metric value is obtained according to the distance metric value formula. The distance metric value formula includes: ;in, For the The immune response spectrum of each antigen and the The distance measure between the immune response profiles of the antigens; For the The eigenvalues ​​of the principal components; For the The first antigen immune response spectrum The data values ​​of the principal components; For the The first antigen immune response spectrum The data values ​​of the principal components; is the total number of all principal components. It should be noted that the data values ​​of different antigen immune response spectra in the principal component space are not necessarily the same, but the characteristic values ​​of the principal components used in the principal component analysis of different antigen immune response spectra are the same.

[0032] In the formula, Reflects the The importance of a principal component. The larger the eigenvalue, the more information the principal component contains, the stronger its ability to explain the data, and the higher its importance. When calculating the distance, important principal components will be given greater weights. Reflects the The immune response spectrum of each antigen and the The immune response spectrum of the antigen is The distance metric comprehensively reflects the differences between the immune response spectra of two antigens in the principal component space.

[0033] The k-distance analysis method is used to determine the search radius of the antigen immune response spectrum according to the distance measurement value between every two antigen immune response spectra.

[0034] It should be noted that the k-distance analysis method is a prior art well known to those skilled in the art, and is only briefly described here: for each antigen immune response spectrum, the distance metric between it and all other antigen immune response spectra is calculated, and the distances are sorted according to the distance metric values. Then, the distance of the kth nearest antigen immune response spectrum is selected as the search radius of the antigen immune response spectrum. Among them, k is a preset parameter, and the value of the present invention is 5, which is usually set by itself according to the characteristics of the data and the purpose of analysis.

[0035] Considering that in the DBSCAN clustering algorithm, the setting of the search radius has a crucial impact on the clustering results. If the search radius is too small, it may not be possible to effectively identify representative data points as core points, thereby hindering the correct formation of clusters. This is because a smaller search radius limits the connectivity between data points, so that some points that should belong to the same cluster cannot be classified as one class due to being too far away. On the contrary, if the search radius is set too large, although the connectivity between data points can be enhanced, it may also cause some unrepresentative data points to be mistakenly identified as core points. In this case, the clustering results may become too broad, including some points that do not belong to the cluster, thereby reducing the representativeness and accuracy of the classification results. An excessively large search radius makes the boundaries of the clusters blurred, making it difficult to accurately describe the characteristics of the clusters. In order to solve this problem, the present invention adjusts the search radius, and the core idea of ​​the adjustment method is: for data points that are more representative in the principal component space, a larger clustering search radius should be set so that similar points around them can be captured more accurately to form a more compact and representative cluster. The search radius represents the range of other antigen immune response spectra similar to the given antigen immune response spectra in the principal component space. Specifically, if the search radius of an antigen immune response spectra is small, then there are fewer antigen immune response spectra similar to it in the principal component space; conversely, if the search radius of an antigen immune response spectra is large, then there are more antigen immune response spectra similar to it in the principal component space.

[0036] Step S3: taking any antigen immune response spectrum as the graph to be analyzed, and taking any patient characteristic index as the index to be analyzed; obtaining the characteristic representativeness of the index to be analyzed of the graph to be analyzed according to the deviation of the index to be analyzed of the graph to be analyzed from the center trend; obtaining the influence measure of the index to be analyzed according to the correlation between the data values ​​of the index to be analyzed and the principal component corresponding to all antigen immune response spectra; obtaining the overall representativeness of the graph to be analyzed according to the characteristic representativeness and influence measure of all patient characteristic indicators of the graph to be analyzed; obtaining the radius adjustment requirement of the graph to be analyzed according to the difference between the graph to be analyzed and the overall representativeness of all antigen immune response spectra in the local range; adjusting the search radius according to the radius adjustment requirement to obtain the adjusted search radius of the graph to be analyzed.

[0037] Select any antigen immune response spectrum as the graph to be analyzed, and select a patient characteristic index as the index to be analyzed. Analyze the approach to the central trend of the index to be analyzed in the graph to be analyzed, and reflect the representativeness of the index to be analyzed in the graph to be analyzed by the characteristic representativeness; by analyzing the correlation between the index to be analyzed and the data values ​​of all antigen immune response spectra on the principal component, obtain the influence measure of the index to be analyzed, and the influence measure reflects the importance of the index to be analyzed to the antigen immune response spectrum. Combined with the characteristic representativeness of the graph to be analyzed on all patient characteristic indicators and the influence measure of these indicators, the overall representativeness of the graph to be analyzed is obtained, and the overall representativeness comprehensively evaluates the overall representativeness of the graph to be analyzed. Compare the difference between the graph to be analyzed and the overall representativeness of all antigen immune response spectra in the local range, and calculate the radius adjustment need of the graph to be analyzed. The greater the difference, the higher the adjustment need may be, which means that a larger search radius needs to be allocated to the graph to be analyzed to capture more similar points. According to the calculated radius adjustment need, the original search radius of the graph to be analyzed is adjusted, and the adjusted search radius is reasonably set to improve the accuracy of clustering.

[0038] In order to analyze the representativeness of the indicators to be analyzed of the graph to be analyzed, preferably, in one embodiment of the present invention, a method for obtaining the representativeness of the features includes: According to the indicators to be analyzed corresponding to all antigen immune response spectra, the normal distribution mean is obtained; the absolute value of the difference between the indicator to be analyzed and the normal distribution mean of the graph to be analyzed is calculated and negative correlation mapping is performed to obtain the characteristic representativeness of the indicator to be analyzed of the graph to be analyzed. It should be noted that negative correlation mapping is a technical means well known to those skilled in the art, and negative correlation mapping can be in the form of inverse proportion or negative exponential power without limitation.

[0039] For the above steps, since the sample size of the antigen immune response spectrum involved in the present invention is large enough, the distribution of these antigen immune response spectra on the corresponding indicators to be analyzed presents the characteristics of a normal distribution. The normal distribution mean, as the central tendency of the indicator to be analyzed, can reflect the typical values ​​of most antigen immune response spectra on the indicator to be analyzed. First, according to the numerical values ​​of all antigen immune response spectra on the indicator to be analyzed, the normal distribution mean is calculated. This normal distribution mean represents the central position of the indicator to be analyzed in all antigen immune response spectra, that is, the most typical value. Next, for the indicator value to be analyzed of each antigen immune response spectrum, the absolute value of the difference between it and the normal distribution mean is calculated. This difference reflects the degree to which the antigen immune response spectrum deviates from the central tendency on the indicator to be analyzed. In order to convert the absolute value of the difference into characteristic representativeness, a negative correlation mapping is performed. Specifically, the larger the absolute value of the difference, the more atypical the antigen immune response spectrum is on the indicator to be analyzed, that is, the more it deviates from the central tendency, so the smaller its characteristic representativeness is.

[0040] In order to quantify the importance of the index to be analyzed to the antigen immune response spectrum, preferably, in one embodiment of the present invention, the method for obtaining the impact metric includes: All antigen immune response spectra are numbered; data values ​​of principal components corresponding to all antigen immune response spectra are counted in sequence according to the order of numbers to obtain the data value sequence of principal components; indicators to be analyzed corresponding to all antigen immune response spectra are counted in sequence according to the order of numbers to obtain the sequence of indicators to be analyzed.

[0041] According to the above steps, all antigen immune response spectra are numbered one by one. This step is to ensure the orderliness and accuracy of subsequent data processing. Each antigen immune response spectrum is assigned a unique identifier for easy tracking and statistics. The data value sequence of the principal component reflects the direction of change of the main immune response information and is a direct reflection of the results of principal component analysis. The sequence of indicators to be analyzed reflects the direction of change of the patient characteristics of the antigen immune response spectrum.

[0042] The impact metric is obtained according to the impact metric formula. The impact metric formula includes: ;in, The impact measure for the indicator to be analyzed; For the The eigenvalues ​​of the principal components; is the sum of the eigenvalues ​​of all principal components; The indicator sequence to be analyzed and Pearson correlation coefficient of the data value sequence of the principal components; is the total number of all principal components; It should be noted that the Pearson correlation coefficient is a prior art well known to those skilled in the art and will not be described in detail here.

[0043] In the formula, To use for Normalize it, The larger the eigenvalue is, the greater the information content of the principal component is, and the more representative it is of the original data. When calculating the influence, the principal component with a larger eigenvalue should have a greater weight. Represents the sequence of indicators to be analyzed and the The larger the linear correlation degree of the data value sequence of the principal component, the stronger the linear relationship between the indicator to be analyzed and the principal component, and therefore the greater the influence of the principal component on the indicator to be analyzed. The influence metric can quantitatively evaluate the importance of each indicator to be analyzed to the antigen immune response spectrum.

[0044] In order to comprehensively evaluate the overall representativeness of the graph to be analyzed, preferably, in one embodiment of the present invention, the formula for obtaining the overall representativeness includes: ;in, is the overall representativeness of the graph to be analyzed; For the Each patient characteristic indicator corresponds to an impact measure; It is the cumulative value of the corresponding impact measure of all patient characteristic indicators; is the first The characteristic representativeness of each patient characteristic indicator; is the total number of all patient characteristic indicators; Adjust the value for the preset denominator.

[0045] In the formula, A normalized benchmark is provided for the cumulative value of the impact metric corresponding to all patient characteristic indicators. right Normalize it and get ;pass To measure the importance of each patient characteristic indicator in the antigen immune response spectrum, and then combine the importance of each indicator with its own characteristic representativeness to comprehensively evaluate the overall representativeness of the graph to be analyzed. The greater the overall representativeness, the more the graph to be analyzed can represent the patient's characteristics as a whole, and the more information it contains.

[0046] Preferably, in one embodiment of the present invention, the method for obtaining the radius adjustment requirement includes: In the principal component space, each antigen immune response spectrum in the search radius of the image to be analyzed is used as each neighborhood analysis graph of the image to be analyzed; In order to quantify the representativeness of the graph to be analyzed relative to its neighborhood analysis graph, the relative typicality is obtained according to the relative typicality formula, which includes: ;in, To be analyzed Relative to neighborhood analysis graph The relative typicality of To be analyzed No. Neighborhood analysis diagram; For the The eigenvalues ​​of the principal components; is the sum of the eigenvalues ​​of all principal components; is the total number of all principal components; For the The principal components correspond to all eigenvalues, and the No. The total number of all eigenvalues ​​with the same value of the corresponding eigenvalue of the principal component; For the The principal components correspond to all eigenvalues, and the neighborhood analysis diagram No. The total number of all eigenvalues ​​with the same value of the corresponding eigenvalue of the principal component; To be analyzed overall representativeness of Neighborhood analysis graph overall representativeness of The preset denominator adjustment value is 0.01, which is used to prevent the denominator from being 0. The implementer can set it according to the implementation scenario.

[0047] In the formula, The larger the eigenvalue is, the greater the information content of the principal component is, and the more representative it is of the original data. When calculating, the principal component with a larger eigenvalue should have a greater weight. It reflects the representativeness of the principal component corresponding eigenvalues ​​of the image to be analyzed relative to its neighborhood analysis image. The larger the value, the more the principal component corresponding eigenvalues ​​of the image to be analyzed relative to its neighborhood analysis image appear, which means that the representativeness of the image to be analyzed on this principal component is stronger. It reflects the representativeness of the graph to be analyzed relative to the neighborhood analysis graphs. The larger the value, the stronger the representativeness of the graph to be analyzed relative to its neighborhood analysis graphs. Relative typicality quantifies the representativeness of the graph to be analyzed relative to its neighborhood analysis graphs.

[0048] It should be noted that in other embodiments of the present invention, the relative typicality calculation formula also includes: . That is, directly through calculate .

[0049] The relative typicality of the image to be analyzed relative to all neighborhood analysis images and the overall representativeness of the image to be analyzed are forwardly integrated to obtain the radius adjustment requirement of the image to be analyzed. It should be noted that forward fusion is a prior art well known to those skilled in the art, and forward fusion can adopt simple product, arithmetic mean or other suitable fusion methods. In one embodiment of the present invention, the radius adjustment requirement formula includes: ;in, To be analyzed The radius adjustment required; To be analyzed Relative to neighborhood analysis graph The relative typicality of To be analyzed No. Neighborhood analysis diagram; To be analyzed The total number of all neighborhood analysis graphs; To be analyzed overall representativeness of is a normalization function. It should be noted that the normalization method is: using the norm normalization function for normalization, and limiting the value range to between 0 and 1. Normalization is a technical means well known to those skilled in the art, and the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0050] In the formula, It reflects the overall performance of the relative typicality of the graph to be analyzed relative to all neighborhood analysis graphs, and combines , a quantitative radius adjustment requirement is obtained, which characterizes the comprehensive representativeness of the graph to be analyzed.

[0051] Preferably, in one embodiment of the present invention, the method for obtaining the adjusted search radius includes: The product of the radius adjustment requirement of the image to be analyzed and the preset adjustment value is calculated as the target adjustment value of the image to be analyzed; the product of the target adjustment value and the search radius is used as the adjusted search radius of the image to be analyzed. In one embodiment of the present invention, the preset adjustment value is 1.4, and the implementer can set it according to the implementation scenario.

[0052] For the above steps, the radius adjustment requirement takes into account the relative typicality of the graph to be analyzed and its neighborhood analysis graphs, as well as the overall representativeness of the graph to be analyzed itself, so as to accurately reflect the importance of each graph in the clustering process. The product of the radius adjustment requirement of the graph to be analyzed and the preset adjustment value is calculated as the target adjustment value of the graph to be analyzed; the product of the target adjustment value and the search radius is used as the adjusted search radius of the graph to be analyzed. By assigning a larger adjusted search radius to more representative antigen immune response spectra, key information in the antigen immune response spectra can be more accurately captured, thereby effectively reducing the possibility of misclassification. This helps to form tighter and more clearly structured clusters, thereby improving the accuracy of clustering.

[0053] Step S4: According to the adjusted search radius of the antigen immune response spectrum, DBSCAN clustering is performed on all antigen immune response spectra to obtain clusters of each antigen immune response spectrum.

[0054] By reasonably setting the adjusted search radius of the antigen immune response spectrum, the key information in the antigen immune response spectrum can be better captured and the accuracy of the clustering results of the antigen immune response spectrum can be improved.

[0055] It should be noted that DBSCAN density clustering is a technical means well known to those skilled in the art, and will not be described in detail here. Only a brief description is given of a brief method for performing DBSCAN clustering on all antigen immune response spectra according to the adjusted search radius of the antigen immune response spectra to obtain clusters of each antigen immune response spectrum: In the principal component space, the distance metric between each two antigen immune response spectra is first calculated, which reflects the relative spatial distance between each two antigen immune response spectra. Subsequently, combined with the adjusted search radius of each antigen immune response spectrum, the adjusted search radius is set by the present invention to control the neighborhood range in the clustering process, and DBSCAN clustering is performed on all antigen immune response spectra to obtain each antigen immune response spectrum cluster. Antigen immune response spectrum clusters can better capture the key information in the antigen immune response spectrum and improve the accuracy of the clustering results of the antigen immune response spectrum.

[0056] The present invention also proposes a medical data processing system for inspection and examination, see Figure 2 , which shows a structural diagram of a medical data processing system for inspection and examination provided by an embodiment of the present invention. The system includes: a data acquisition module 101, a search radius analysis module 102, a search radius adjustment module 103 and a clustering module 104.

[0057] The data acquisition module 101 is used to acquire antigen signal data of each antigen immune response spectrum and all patient characteristic indicators.

[0058] The search radius analysis module 102 is used to perform dimensionality reduction processing based on the antigen signal data of all antigen immune response spectra to obtain the data values ​​and eigenvalues ​​of each principal component of each antigen immune response spectrum; and determine the search radius of the antigen immune response spectrum based on the data values ​​and eigenvalues ​​of each principal component of each antigen immune response spectrum.

[0059] The search radius adjustment module 103 is used to take any antigen immune response spectrum as a graph to be analyzed and any patient characteristic index as an index to be analyzed; obtain the characteristic representativeness of the index to be analyzed of the graph to be analyzed according to the deviation of the index to be analyzed of the graph to be analyzed from the center trend; obtain the influence measure of the index to be analyzed according to the correlation between the data values ​​of the index to be analyzed and the principal component corresponding to all antigen immune response spectra; obtain the overall representativeness of the graph to be analyzed according to the characteristic representativeness and influence measure of all patient characteristic indexes of the graph to be analyzed; obtain the radius adjustment requirement of the graph to be analyzed according to the difference between the graph to be analyzed and the overall representativeness of all antigen immune response spectra in the local range; adjust the search radius according to the radius adjustment requirement to obtain the adjusted search radius of the graph to be analyzed.

[0060] The clustering module 104 is used to perform DBSCAN clustering on all antigen immune response spectra according to the adjusted search radius of each antigen immune response spectrum to obtain clusters of each antigen immune response spectrum.

[0061] It should be noted that: For the system provided in the above embodiments, only the division of the above functional modules is used for illustration. In actual applications, the above functions can be assigned to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, a medical data processing system for inspection and a medical data processing method embodiment provided in the above embodiments belong to the same concept. For the specific implementation process, please refer to the method embodiment and will not be elaborated here.

[0062] In summary, the embodiments of the present invention provide a medical data processing method and system for inspection. First, according to the data values and eigenvalue of each principal component of each antigen immune response spectrum, the search radius of the antigen immune response spectrum is determined; according to the feature representativeness and influence measure of all patient characteristic indicators of the graph to be analyzed, the overall representativeness of the graph to be analyzed is obtained; according to the difference between the graph to be analyzed and the overall representativeness of all antigen immune response spectra in its local range, the need for radius adjustment of the graph to be analyzed is obtained; according to the need for radius adjustment, the search radius is adjusted to obtain the adjusted search radius of the graph to be analyzed; and then DBSCAN clustering is performed on all antigen immune response spectra to obtain each antigen immune response spectrum cluster. The present invention reasonably sets the adjusted search radius of the antigen immune response spectrum, can better capture the key information in the antigen immune response spectrum, and improves the accuracy of the clustering result of the antigen immune response spectrum.

[0063] It should be noted that: The above sequence of the embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0064] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. A method for processing medical data for inspection and examination, characterized in that: The method comprises: Obtain antigen signal data and all patient characteristic indicators for each antigen immune response profile; According to the antigen signal data of all the antigen immune response spectra, dimension reduction processing is performed to obtain the data value and characteristic value of each principal component of each antigen immune response spectrum; according to the data value and characteristic value of each principal component of each antigen immune response spectrum, the search radius of the antigen immune response spectrum is determined; Take any one of the antigen immune response spectra as the graph to be analyzed, and take any one of the patient characteristic indicators as the indicator to be analyzed; obtain the characteristic representativeness of the indicator to be analyzed of the graph to be analyzed according to the deviation of the indicator to be analyzed of the graph to be analyzed from the central trend; obtain the influence measure of the indicator to be analyzed according to the correlation between the data values ​​of the indicator to be analyzed and the principal component corresponding to all the antigen immune response spectra; obtain the overall representativeness of the graph to be analyzed according to the characteristic representativeness of all the patient characteristic indicators of the graph to be analyzed and the influence measure; obtain the radius adjustment requirement of the graph to be analyzed according to the difference between the graph to be analyzed and the overall representativeness of all the antigen immune response spectra in the local range; adjust the search radius according to the radius adjustment requirement to obtain the adjusted search radius of the graph to be analyzed; According to the adjusted search radius of each antigen immune response spectrum, DBSCAN clustering is performed on all the antigen immune response spectra to obtain each antigen immune response spectrum cluster.

2. A method for processing medical data for inspection and examination according to claim 1, characterized in that: The method for obtaining the data value and the characteristic value of the principal component includes: The PCA method is used to perform dimensionality reduction processing on the antigen signal data of all the antigen immune response spectra to obtain the data values ​​and characteristic values ​​of each principal component of each antigen immune response spectrum.

3. A method for processing medical data for inspection and examination according to claim 1, characterized in that: The method for obtaining the search radius includes: The distance metric value is obtained according to the distance metric value formula, and the distance metric value formula includes: ;in, For the The immune response spectrum of each antigen and the The distance measure between the immune response profiles of the antigens; For the The eigenvalues ​​of the principal components; For the The first antigen immune response spectrum The data values ​​of the principal components; For the The first antigen immune response spectrum The data values ​​of the principal components; is the total number of all principal components; The k-distance analysis method is used to determine the search radius of the antigen immune response spectrum according to the distance metric value between every two antigen immune response spectra.

4. A method for processing medical data for inspection and examination according to claim 1, characterized in that: The method for obtaining the representativeness of the features includes: According to the indicators to be analyzed corresponding to all antigen immune response spectra, the normal distribution mean is obtained; the absolute value of the difference between the indicator to be analyzed in the graph to be analyzed and the normal distribution mean is calculated and negative correlation mapping is performed to obtain the characteristic representativeness of the indicator to be analyzed in the graph to be analyzed.

5. The method for processing medical data of an inspection according to claim 1, characterized in that: The method for obtaining the impact metric includes: Labeling all the antigen immune response spectra; sequentially counting the data values ​​of the principal components corresponding to all the antigen immune response spectra in the order of the labels to obtain a data value sequence of the principal components; sequentially counting the indicators to be analyzed corresponding to all the antigen immune response spectra in the order of the labels to obtain a sequence of indicators to be analyzed; The influence metric is obtained according to an influence metric formula, wherein the influence metric formula includes: ;in, The impact measure for the indicator to be analyzed; For the The eigenvalues ​​of the principal components; is the sum of the eigenvalues ​​of all principal components; The indicator sequence to be analyzed and Pearson correlation coefficient of the data value sequence of the principal components; is the total number of all principal components; is the absolute value symbol.

6. A method for processing medical data for inspection and examination according to claim 1, characterized in that: The formula for obtaining the overall representativeness includes: ;in, is the overall representativeness of the graph to be analyzed; For the Each patient characteristic indicator corresponds to an impact measure; It is the cumulative value of the corresponding impact measure of all patient characteristic indicators; is the first The characteristic representativeness of each patient characteristic indicator; is the total number of all patient characteristic indicators; Adjust the value for the preset denominator.

7. A method for processing medical data for inspection and examination according to claim 1, characterized in that: The method for obtaining the radius adjustment requirement includes: In the principal component space, each antigen immune response spectrum in the search radius of the image to be analyzed is used as each neighborhood analysis graph of the image to be analyzed; The relative typicality is obtained according to a relative typicality formula, wherein the relative typicality formula includes: ;in, To be analyzed Relative to neighborhood analysis graph The relative typicality of To be analyzed No. Neighborhood analysis diagram; For the The eigenvalues ​​of the principal components; is the sum of the eigenvalues ​​of all principal components; is the total number of all principal components; For the The principal components correspond to all eigenvalues, and the No. The total number of all eigenvalues ​​with the same value of the corresponding eigenvalue of the principal component; For the The principal components correspond to all eigenvalues, and the neighborhood analysis diagram No. The total number of all eigenvalues ​​with the same value of the corresponding eigenvalue of the principal component; To be analyzed overall representativeness of Neighborhood analysis graph overall representativeness of Adjust the value for the preset denominator; The relative typicality of the image to be analyzed relative to all neighborhood analysis images and the overall representativeness of the image to be analyzed are forwardly integrated to obtain the radius adjustment requirement of the image to be analyzed.

8. A method for processing medical data for inspection and examination according to claim 7, characterized in that: The method for obtaining the radius adjustment requirement includes: The radius adjustment requirement is obtained according to the radius adjustment requirement formula, and the radius adjustment requirement formula includes: ;in, The graph to be analyzed The radius adjustment required; To be analyzed Relative to neighborhood analysis graph The relative typicality of To be analyzed No. Neighborhood analysis diagram; To be analyzed The total number of all neighborhood analysis graphs; To be analyzed overall representativeness of is the normalization function.

9. A method for processing medical data for inspection and examination according to claim 1, characterized in that: The method for obtaining the adjusted search radius includes: The product of the radius adjustment requirement of the image to be analyzed and a preset adjustment value is calculated as a target adjustment value of the image to be analyzed; and the product of the target adjustment value and the search radius is used as the adjusted search radius of the image to be analyzed.

10. A medical data processing system for inspection and examination, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the medical data processing method for inspection and examination as described in any one of claims 1 to 9 are implemented.

Images