A dynamic map generation system for cross-allergen risk of children

Abstract

This invention relates to the field of map generation technology, specifically to a system for generating dynamic cross-allergen risk maps for children. First, a sensitivity index is determined based on the immune response to each type of allergen in all allergy testing processes. Then, based on the similarity of each type of allergen to other allergens in two dimensions—allergen protein structure and IgE level—combined with the sensitivity index, a comprehensive characterization of the cross-reaction risk index for each type of allergen in each allergy testing process is achieved. Furthermore, considering the dynamic changes in cross-allergic reactions that may be caused by seasonal variations, the system comprehensively determines the degree of cross-allergic risk for each type of allergen in each seasonal period based on the increasing trend of the cross-reaction risk index curve and the overall magnitude of the cross-reaction risk index. This makes the dynamic cross-allergen risk map generated in real time based on the degree of cross-allergic risk more accurate.

Description

Technical Field

[0001] This invention relates to the field of map generation technology, specifically to a dynamic map generation system for cross-allergen risk in children. Background Technology

[0002] After a child is exposed to one allergen, they may develop allergic reactions to other related substances, such as certain foods, pollen, and insect toxins. Because children's immune systems are not yet fully developed, the risk of cross-allergic reactions is increased. Therefore, it is necessary to generate a dynamic cross-allergen risk profile for each child in real time to reduce the risk of cross-allergic reactions.

[0003] Existing technologies typically only screen out cross-allergens that simultaneously cause allergic reactions based on the allergy history of target children in medical databases, and generate cross-allergen risk maps based on the screened cross-allergens; however, this method only records and analyzes static data, neither taking into account the cross-allergy associations between different allergens in essence, nor taking into account the dynamic evolution of children's immune responses to each type of allergen with seasonal factors; resulting in low accuracy in generating dynamic cross-allergen risk maps in real time. Summary of the Invention

[0004] To address the technical problem of low accuracy in generating cross-allergen risk dynamic maps in existing technologies, this application aims to provide a system for generating cross-allergen risk dynamic maps for children. The specific technical solution adopted is as follows:

[0005] The first aspect of this application provides a system for generating a dynamic map of cross-allergen risk in children, including:

[0006] The data acquisition and preprocessing module is used to collect the IgE level test values ​​of each type of allergen for the target child in each allergy test from the medical database;

[0007] The first determining module is used to determine the corresponding sensitivity index based on the overall deviation of the IgE level detection values ​​of each type of allergen from the normal range during all allergy testing; and to determine the corresponding cross-reactivity risk index based on the sensitivity index and the similarity between each type of allergen and other types of allergens in IgE level detection values ​​and protein three-dimensional structure during each allergy testing.

[0008] The second determining module is used to determine the cross-reactivity risk index curve of each type of allergen in each seasonal period based on the temporal changes of the cross-reactivity risk index corresponding to each type of allergen in all allergy testing processes; and to determine the degree of cross-allergy risk of each type of allergen in each seasonal period based on the overall magnitude of the cross-reactivity risk index curve and the similarity of the increasing trend of the cross-reactivity risk index curve in all seasonal periods.

[0009] The dynamic map generation module is used to generate a dynamic map of cross-allergen risk in real time based on the degree of cross-allergy risk.

[0010] Furthermore, the process of obtaining the sensitivity index includes:

[0011] Obtain the upper limit of normal IgE level for each type of allergen; use the difference between the IgE level of each type of allergen and the corresponding upper limit of normal IgE level for the target child in each allergy test as the corresponding normal deviation value; determine the frequency weight of each type of allergen based on the total number of times the corresponding normal deviation value is greater than 0 in all allergy tests.

[0012] The average IgE level for each type of allergen across all allergy tests is used as the degree of allergic abnormality for each type of allergen.

[0013] The product of the frequency weight and the degree of allergic abnormality is normalized to determine the sensitivity index of the target child to each type of allergen.

[0014] Furthermore, the process of obtaining the cross-reactivity risk index includes:

[0015] Cluster analysis is performed based on the similarity of normal deviations of various allergens during each allergy test to obtain at least two allergen clusters; each allergen is then used as the target allergen.

[0016] During each allergy test, when the normal deviation value of the target allergen is less than or equal to 0, the preset similarity parameter is used as the corresponding final similarity weight.

[0017] When the normal deviation value of the target allergen is greater than 0, the number of similarity weights in the allergen cluster to which the target allergen belongs is used as the allergy similarity weight; the protein structure similarity weight of the target allergen is determined based on the overall structural similarity between the protein of the target allergen and the proteins of other allergens in the allergen cluster to which it belongs; the product between the allergy similarity weight and the protein structure similarity weight is normalized to determine the final similarity weight of the target allergen.

[0018] The cross-reactivity risk index of the target allergen in each allergy test is determined by multiplying the final similarity weight of the target allergen with the corresponding sensitivity index.

[0019] Furthermore, the process of obtaining the allergen clusters includes:

[0020] The ratio between the normal deviation value of each type of allergen and the corresponding normal upper limit value of IgE level during each allergy test is used as the normal deviation rate; k-means cluster analysis is performed on the normal deviation rates of all types of allergens during each allergy test to obtain at least two allergen clusters; the K value of the k-means cluster analysis is determined by the elbow method.

[0021] Furthermore, the process of obtaining the protein structural similarity weights includes:

[0022] All allergens in the allergen cluster containing the target allergen are used as contrast allergens. The protein of the target allergen is compared with the protein of each contrast allergen using the protein structure alignment tool TM-align to determine the TM-score value between the protein of the target allergen and the protein of each contrast allergen. The mean of the TM-score values ​​between the protein of the target allergen and the proteins of all contrast allergens is used as the protein structure similarity weight of the target allergen.

[0023] Furthermore, the process of obtaining the cross-reactivity risk index curve includes:

[0024] In all allergy testing processes, allergy testing processes with a normal deviation value greater than 0 for each type of allergen are considered as the corresponding allergic reaction processes. The cross-reaction risk index of each type of allergen in all allergy reaction processes for the target child in each season is arranged in chronological order and then curve-fitted to determine the cross-reaction risk index curve of each type of allergen in each season. The season refers to the time period corresponding to the same season.

[0025] Furthermore, the process of obtaining the degree of cross-allergy risk includes:

[0026] Based on the frequency of allergic reaction processes to each type of allergen in each seasonal period and the increasing trend on the cross-reactivity risk index curve, the corresponding seasonal trend is determined.

[0027] The standard deviation of the seasonal trend of each type of allergen in all seasons is normalized to determine the corresponding central characteristic weights.

[0028] Based on the overall seasonal trend deviation between each seasonal period and other seasonal periods, determine the risk concentration characteristic value of each type of allergen in each seasonal period;

[0029] Based on the mean of the cross-reaction risk index for each type of allergen during all allergic reactions in each season, the corresponding cross-reaction risk characteristic value is determined.

[0030] The weighted cluster feature value for each type of allergen in each seasonal period is determined by multiplying the cluster feature weights with the risk cluster feature values.

[0031] The weighted risk characteristic value of each type of allergen in each seasonal period is determined by multiplying the negative correlation mapping value of the centralized feature weights with the cross-reactivity risk characteristic value.

[0032] The sum of the weighted set feature values ​​and the weighted risk feature values ​​is normalized to determine the degree of cross-allergy risk for each type of allergen in each seasonal period.

[0033] Furthermore, the process of obtaining the seasonal trend includes:

[0034] The total number of allergic reaction events for each type of allergen in the target child during each season is used as the corresponding weight of the allergic reaction occurrence; the average slope of the tangent line corresponding to all allergic reaction events on the cross-reaction risk index curve is used to determine the allergy risk growth value for each type of allergen in each season; the seasonal trend of each type of allergen in each season is determined by multiplying the allergic reaction occurrence weight by the allergy risk growth value.

[0035] Furthermore, the process of obtaining the risk set feature values ​​includes:

[0036] Each seasonal period is sequentially designated as the target period; other seasonal periods outside the target period are designated as comparison periods; the difference between the seasonal trend of each type of allergen in the target period and the seasonal trend of each comparison period is calculated to determine the trend deviation value of each comparison period; the mean of the trend deviation values ​​of all comparison periods corresponding to the target period is normalized to determine the risk concentration characteristic value of each type of allergen in the target period.

[0037] Furthermore, the process of obtaining the dynamic cross-allergen risk map based on the degree of cross-allergy risk includes:

[0038] Allergens with a cross-allergy risk level greater than a preset risk threshold in each season are identified as high-risk cross-allergens for each season. The high-risk cross-allergens for the target child in each season are highlighted in the original cross-allergen risk map, and a dynamic cross-allergen risk map for the target child is generated in real time.

[0039] Secondly, this application provides a computer device including a memory and a processor. The memory is used to store computer program code, and the processor is used to call and run the computer program code from the memory to execute a system as described in the first aspect of this application or any embodiment of the first aspect.

[0040] Thirdly, this application provides a computer program product, which includes computer program code that, when executed, performs a system as described in the first aspect of this application or any embodiment thereof.

[0041] Fourthly, this application provides a computer-readable storage medium that stores computer program code, which, when executed, performs a system as described in the first aspect of this application or any embodiment thereof.

[0042] This application has the following beneficial effects:

[0043] This application first determines the sensitivity index based on the immune response of each type of allergen in all allergy testing processes. Then, based on the similarity of each type of allergen to other types of allergens in two dimensions—allergen protein structure and IgE level—and combined with the sensitivity index, it comprehensively characterizes the cross-reactivity risk index of each type of allergen in each allergy testing process. Then, considering the dynamic changes in cross-allergic reactions that may be caused by seasonal changes, it comprehensively determines the degree of cross-allergic risk of each type of allergen in each season based on the increasing trend of the cross-reactivity risk index curve and the overall size of the cross-reactivity risk index. This makes the cross-allergen risk dynamic map generated in real time based on the degree of cross-allergic risk more accurate. Attached Figure Description

[0044] 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.

[0045] Figure 1 This is a structural diagram of a dynamic map generation system for cross-allergen risk in children provided in one embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of a computer device structure provided in one embodiment of the present invention. Detailed Implementation

[0047] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a dynamic risk map generation system for cross-allergens in children proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature.

[0048] 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.

[0049] The following description, in conjunction with the accompanying drawings, details the specific scheme of the dynamic map generation system for cross-allergen risk in children provided by this invention.

[0050] This application provides a system for generating a dynamic cross-allergen risk map for children. Please refer to [link / reference]. Figure 1 The diagram illustrates a structural diagram of a dynamic risk map generation system for cross-allergens in children according to an embodiment of the present invention. The system includes:

[0051] The data acquisition and preprocessing module 101 is used to collect the IgE level test values ​​of each type of allergen for the target child in each allergy test from the medical database.

[0052] In the target child's previous clinical allergy treatment data, the IgE level of each allergen during each allergy test is recorded and stored in a medical database. When generating a dynamic cross-allergen risk map at the current time, the IgE level of each allergen during each allergy test is extracted. Regarding IgE level detection, under normal circumstances, the body produces a specific type of IgE in response to a particular allergen. For example, a child allergic to peanuts will produce peanut-specific IgE during an allergy test. If the corresponding IgE level exceeds the upper limit of the normal range, it indicates an allergic reaction. Therefore, detecting IgE levels can reflect the immune response to various allergens. In one specific implementation of this invention, the types of allergens analyzed include, but are not limited to, dust mites, pollen, peanuts, milk, dust, animal dander, shrimp, and penicillin. The historical data collection time range in this embodiment is set to within one year prior to the current time. The types of allergens and the historical data collection time range can be adjusted according to the specific implementation environment, which will not be further elaborated here.

[0053] The first determining module 102 is used to determine the corresponding sensitivity index based on the overall deviation of the normal range of IgE level detection values ​​for each type of allergen in all allergy testing processes; and to determine the corresponding cross-reactivity risk index based on the sensitivity index and the similarity between each type of allergen and other types of allergens in IgE level detection values ​​and protein three-dimensional structure in each allergy testing process.

[0054] This invention first identifies the sensitivity of the target child to different allergens based on the allergic manifestation characteristics of the target child during allergy testing, thereby providing certain data support for subsequent cross-allergen risk assessment. Specifically, based on the overall deviation of the IgE level detection values ​​of each type of allergen from the normal range during all allergy testing, the corresponding sensitivity index is determined.

[0055] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the sensitivity index includes:

[0056] Obtain the upper limit of normal IgE levels for each type of allergen. The difference between the measured IgE level for each allergen and its corresponding upper limit of normal IgE level in each allergy test for the target child is used as the normal deviation value. The upper limit of normal IgE levels may differ for different types of allergens, so it needs to be determined based on the specific implementation environment. The upper limit of normal IgE level is the lowest IgE level measured when each type of allergen causes an allergic reaction. When the measured IgE level for each type of allergen is greater than its corresponding upper limit of normal IgE level, it indicates a possible allergic reaction. Therefore, the frequency weight of each allergen is determined based on the total number of times the normal deviation value for each type of allergen is greater than 0 in all allergy tests. A higher frequency weight indicates a higher frequency of allergic reactions to the corresponding allergen, indicating a stronger sensitivity of the target child to the corresponding allergen.

[0057] Furthermore, if the IgE level of a certain type of allergen remains high in multiple tests, it indicates that the target child's immune system has a long-term sensitivity to that allergen. Therefore, the average IgE level of each type of allergen across all allergy tests is used as the degree of allergy abnormality for each type of allergen. A higher degree of allergy abnormality indicates a stronger sensitivity of the target child to the corresponding allergen. Finally, a sensitivity index is comprehensively represented by combining correlation, frequency weights, and the degree of allergy abnormality. In one specific implementation of this invention, the product of frequency weights and the degree of allergy abnormality is normalized to determine the sensitivity index of the target child for each type of allergen.

[0058] In one specific implementation of this invention, the process of obtaining the sensitivity index is expressed by the formula: ;in, For target children's allergens Sensitivity index; Allergen The total number of times the normal deviation value is greater than 0 in all allergy tests, i.e., frequency weight; Allergen The mean value of IgE levels detected in all allergy tests, which is also the degree of allergic abnormality; It should be noted that, unless otherwise specified, all normalization methods in the embodiments of this invention adopt linear normalization, and will not be further elaborated hereafter.

[0059] For each allergy testing procedure, if a certain allergen with a high sensitivity index exhibits similar allergic reaction characteristics to several other allergens, and the protein structures of these allergens are relatively similar, then it indicates that cross-reactions may have occurred among these allergens. Therefore, during each allergy testing procedure, a cross-reaction risk index is determined based on the sensitivity index of each type of allergen and its similarity to other allergens in IgE levels and three-dimensional protein structures. A higher cross-reaction risk index indicates a higher risk of cross-reaction with the corresponding allergen during the allergy testing process.

[0060] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the cross-reactivity risk index includes:

[0061] Cluster analysis is performed based on the similarity of normal deviations of various allergens during each allergy test to obtain at least two allergen clusters. In one specific implementation of this invention, the process of obtaining allergen clusters includes:

[0062] The ratio between the normal deviation value of each allergen type and the corresponding upper limit of normal IgE level during each allergy test is used as the normal deviation rate. K-means clustering analysis is performed on the normal deviation rates of all allergen types during each allergy test to obtain at least two allergen clusters. The K value for the k-means clustering analysis is determined using the elbow method. It should be noted that the k-means clustering algorithm and the elbow method are techniques well-known to those skilled in the art and will not be elaborated further here.

[0063] Because different allergens have different upper limits of normal IgE levels, cluster analysis based solely on IgE level detection values ​​cannot accurately measure the similarity of allergic reactions among allergens within the same cluster. Therefore, the allergic reaction characteristics of each allergen are measured by the ratio between the normal deviation value of each allergen type and the corresponding upper limit of normal IgE level. This normal deviation rate is calculated to assess the allergic reaction characteristics of each allergen type. This ensures that allergens in each allergen cluster obtained through cluster analysis based on the normal deviation rate exhibit similar allergic reaction manifestations during corresponding allergy testing. For each type of allergen that causes an allergic reaction, the more allergens in its cluster, the more likely the allergens in that cluster have similar IgE level changes. The more closely they match the characteristics of cross-reaction, the higher the probability of cross-reaction, thus requiring a larger cross-reaction risk index.

[0064] Each type of allergen is sequentially designated as the target allergen. During each allergy test, when the normal deviation value of the target allergen is less than or equal to 0, a preset similarity parameter is used as the corresponding final similarity weight. In a specific implementation of this invention, the preset similarity parameter is set to 0, which can be adjusted according to the specific implementation environment. For the target allergen, a normal deviation value less than 0 indicates that no allergic reaction occurred during the corresponding allergy test, and therefore, no cross-allergy characteristics can be exhibited. Therefore, setting it to 0 makes the subsequently calculated cross-reaction risk index also take a value of 0.

[0065] When the normal deviation value of the target allergen is greater than 0, the number of similar weights in the allergen cluster to which the target allergen belongs is used as the allergy similarity weight. According to the above analysis of allergen clusters, the larger the allergy similarity weight, the more the target allergen conforms to the characteristics of cross-reactivity, and the greater the corresponding cross-reactivity risk index.

[0066] Based on the overall structural similarity between the target allergen protein and the proteins of other allergens in its allergen cluster, a protein structural similarity weight for the target allergen is determined. In one specific implementation of this invention, the process of obtaining the protein structural similarity weight includes:

[0067] All allergens within the allergen cluster containing the target allergen are used as contrast allergens. The protein structure of the target allergen is compared with that of each contrast allergen using the TM-align protein structure alignment tool to determine the TM-score value between the target allergen and each contrast allergen. The average of these TM-score values ​​is used as the protein structure similarity weight for the target allergen. The TM-score value output by TM-align characterizes the degree of three-dimensional structural overlap between two proteins; a higher value, closer to 1, indicates greater similarity between the corresponding protein structures. Therefore, for a target allergen, a higher protein structure similarity weight indicates greater similarity in protein structure between the target allergen and its contrast allergens with similar allergic manifestations during allergy testing. Since the immune system can recognize specific antigenic epitopes, greater similarity in protein structure between the target allergen and each contrast allergen means that these antigens are more likely to be recognized by the same antibodies, leading to a higher probability of cross-allergic reactions.

[0068] In one specific implementation of this invention, before alignment using the protein structure alignment tool TM-align, the three-dimensional protein data of various allergens are preprocessed. Specifically, firstly, non-main chain atoms such as heteroatoms and water molecules are removed; then, amino acid numbers are aligned to ensure one-to-one correspondence of residues during alignment; and finally, the main structural chain is selected for alignment after standardizing amino acid names and chain IDs. It should be noted that when the target allergen's cluster contains only the target allergen itself, the corresponding protein structural similarity weight is set to 0, which will not be further elaborated here.

[0069] Finally, based on the correlation, and combining the probability of cross-reaction jointly represented by the allergy similarity weight and the protein structure similarity weight, the product between the allergy similarity weight and the protein structure similarity weight is normalized to determine the final similarity weight of the target allergen. A higher final similarity weight indicates a higher risk of cross-reaction in the corresponding allergy testing process. Furthermore, considering that a higher sensitivity index for the target allergen indicates a stronger sensitivity in the target child and a higher reliability of cross-reaction, the final similarity weight, which characterizes the risk of cross-reaction, is combined with the sensitivity index to determine the cross-reaction risk index of the target allergen in each allergy testing process. A higher cross-reaction risk index indicates a higher risk of cross-reaction. Finally, based on the calculation process of the target allergen's cross-reaction risk index, the cross-reaction risk index for each type of allergen in each allergy testing process is calculated.

[0070] In one specific implementation of this invention, when allergens In the target children When the normal deviation value during the allergy testing process is greater than 0, the process of obtaining the cross-reactivity risk index is expressed by the formula: ;in, Allergen In the target children Cross-reactivity risk index during allergy testing; For target children's allergens Sensitivity index; Allergen In the target children The protein structure similarity weight in the first allergy test, that is, the target child's first allergy test. Allergens during the second allergy test The mean TM-score between the protein and the proteins of all corresponding contrast allergens. Allergen In the target children The final similarity weight in the allergy testing process.

[0071] The second determining module 103 is used to determine the cross-reactivity risk index curve of each type of allergen in each seasonal period based on the temporal changes of the cross-reactivity risk index corresponding to each type of allergen in all allergy testing processes; and to determine the degree of cross-allergy risk of each type of allergen in each seasonal period based on the overall magnitude of the cross-reactivity risk index curve and the similarity of the increasing trend of the cross-reactivity risk index curve in all seasonal periods.

[0072] The first determining module 102 determines the cross-reaction risk index of various allergens in each allergy test of the target child. The higher the cross-reaction risk index, the higher the cross-reaction risk. Furthermore, considering that the occurrence of cross-allergic reactions is usually dynamic and accompanied by seasonal changes, cross-allergic reactions are usually affected and have different characteristics. Therefore, the seasonal factor is further introduced to analyze the evolution trend of the cross-reaction risk index of each type of allergen in each season to more accurately measure the degree of cross-allergy risk. Therefore, the cross-reaction risk index curve of each type of allergen in each season is first determined.

[0073] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the cross-reactivity risk index curve includes:

[0074] In all allergy testing processes, those with a normal deviation value greater than 0 for each type of allergen were considered as the corresponding allergic reaction processes. The cross-reactivity risk indices for each type of allergen in all allergy reaction processes for the target child in each seasonal period were arranged chronologically and then curve-fitted to determine the cross-reactivity risk index curve for each type of allergen in each seasonal period. The seasonal period refers to the time interval corresponding to the same season. It should be noted that curve fitting is a technique well-known to those skilled in the art and will not be further limited or elaborated upon here.

[0075] It should be noted that, since the historical data collection time range in this embodiment of the invention is set to within one year prior to the current moment, the seasonal period in this embodiment of the invention only corresponds to the seasonal period within one year. In other implementation environments, such as when the historical data collection time range is set to two years prior to the current moment, the data from the previous year and the following year need to be merged together for curve fitting. For example, in the winter seasonal period, the allergic reaction process in the previous year was December 10th, and the allergic reaction process in the following year was December 9th. Although the allergic reaction process on December 9th of the following year is after December 10th in terms of time dimension, after merging, it is only arranged according to the time order within the year. That is, in the same year dimension, December 9th is before December 10th. Therefore, when arranging, the allergic reaction process on December 10th of the previous year should be arranged after the allergic reaction process on December 9th for curve fitting.

[0076] For each type of allergen, a higher overall cross-reactivity risk index and a more pronounced increasing trend during a certain season usually indicates that the allergen has a high concentration of cross-reactivity risk characteristics in the corresponding season. In other words, the higher the degree of cross-reactivity risk of the corresponding allergen in the corresponding season, the more necessary it is to update or perceive this information on the cross-allergen risk dynamic map. Therefore, based on the overall magnitude of the cross-reactivity risk index curve and the similarity of the increasing trend of the cross-reactivity risk index curve across all seasons, the degree of cross-reactivity risk of each type of allergen in each season can be determined.

[0077] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the degree of cross-allergy risk includes:

[0078] Based on the frequency of allergic reaction processes for each type of allergen in each seasonal period and their increasing trend on the cross-reactivity risk index curve, the corresponding seasonal trend is determined. The process of obtaining the seasonal trend includes: taking the total number of allergic reaction processes for each type of allergen in each seasonal period as the corresponding weight of allergic reaction occurrence; determining the allergy risk growth value for each type of allergen in each seasonal period based on the average slope of the tangent line corresponding to all allergic reaction processes on the cross-reactivity risk index curve; and determining the seasonal trend of each type of allergen in each seasonal period based on the product of the allergic reaction occurrence weight and the allergy risk growth value.

[0079] For each season, if the frequency of allergic reactions to a certain type of allergen is higher and the upward trend of the corresponding cross-reaction risk index curve is more obvious, it indicates that there is a more significant and concentrated allergic behavior in that season. Therefore, it is more necessary to pay attention to the risk of cross-reaction to that allergen in the corresponding season, and the degree of cross-reaction risk is also higher.

[0080] The standard deviation of the seasonal trend for each type of allergen across all seasons is normalized to determine the corresponding central tendency weight. According to the definition of standard deviation, a larger central tendency weight indicates a greater overall deviation in the seasonal trend across different seasons, suggesting a higher likelihood of a stronger seasonal trend in one or more specific seasons. This necessitates separate analysis of the seasonal trend at the local dimension to more accurately measure the degree of cross-reactivity risk across seasons. Conversely, a smaller central tendency weight indicates more similar or stable seasonal trends across different seasons. In this case, analysis based on local seasonal trends cannot reflect the degree of cross-reactivity risk across seasons. Therefore, a holistic analysis of the cross-reactivity risk characteristics across seasons is needed, considering the overall cross-reactivity risk index.

[0081] Firstly, at the local level, based on the overall seasonal trend deviation between each seasonal period and other seasonal periods, the risk concentration characteristic value of each type of allergen under each seasonal period is determined. The process of obtaining the risk concentration characteristic value includes: sequentially taking each seasonal period as the target period; taking other seasonal periods outside the target period as comparison periods; calculating the difference between the seasonal trend of each type of allergen under the target period and the seasonal trend of each comparison period to determine the trend deviation value of each comparison period; and normalizing the mean of the trend deviation values ​​of all comparison periods corresponding to the target period to determine the risk concentration characteristic value of each type of allergen under the target period. For the target period, a larger risk concentration characteristic value indicates that the seasonal trend of the target period is relatively greater than that of all seasonal periods, the concentrated allergic characteristics of the corresponding allergen under the target period are more obvious, that is, the risk of allergic reaction to the corresponding allergen is higher under the target period, and the degree of cross-allergy risk is also greater.

[0082] In terms of overall analysis, the corresponding cross-reactivity risk characteristic value is determined based on the average cross-reactivity risk index of all allergic reactions to each type of allergen during each seasonal period. Since the cross-reactivity risk index itself represents the cross-reactivity risk of each type of allergen, for each seasonal period, a larger cross-reactivity risk characteristic value indicates a higher degree of cross-reactivity risk during that season.

[0083] As described in the calculation process of the concentration feature weight, a larger concentration feature weight may indicate a stronger seasonal trend for certain allergens in a specific area. Therefore, when analyzing the degree of cross-reactivity risk, it is necessary to focus on analyzing the risk concentration characteristics of the corresponding allergen in each seasonal period at the local dimension to more accurately highlight the characteristic that cross-reactivity tends to concentrate in one or more seasonal periods. For example, if the seasonal trend of the corresponding allergen is stronger in a certain seasonal period than in other seasons when the concentration feature weight is larger, then it is necessary to pay more attention to the cross-risk characteristics of the allergen in that seasonal period, and therefore assign a greater degree of cross-reactivity risk. Conversely, a smaller concentration feature weight indicates that the seasonal trends of each season are relatively close, and the risk concentration characteristics cannot be reflected. Therefore, when specifically measuring the degree of cross-reactivity risk, it is necessary to pay more attention to the overall size of the cross-reactivity risk index, which represents the risk of cross-reactivity, in each seasonal period.

[0084] Therefore, this embodiment of the invention further determines the weighted clustered feature value for each type of allergen in each seasonal period based on the product of the clustered feature weight and the risk clustered feature value; and determines the weighted risk feature value for each type of allergen in each seasonal period based on the product of the negative correlation mapping value of the clustered feature weight and the cross-reactivity risk feature value. This ensures that the larger the weighted clustered feature value and the larger the weighted risk feature value, the higher the degree of cross-reactivity risk. Finally, based on this correlation, the sum of the weighted clustered feature value and the weighted risk feature value is normalized to determine the degree of cross-allergy risk for each type of allergen in each seasonal period.

[0085] In one specific implementation of this invention, the process of obtaining the degree of cross-allergy risk is expressed by the following formula: ;in, Allergen In the Seasonal trends within a specific seasonal period; Allergen The normalized value of the standard deviation of seasonal trends across all seasonal periods, which is also the corresponding central tendency weight; Allergen In the Cross-reactivity risk characteristics corresponding to each seasonal period, i.e., allergens In the The average of the cross-reactivity risk indices corresponding to all allergy testing processes during a given seasonal period; Allergen In the The mean of the trend deviation values ​​of all comparison periods corresponding to each seasonal period. Allergen In the Risk concentration characteristics under each seasonal period; Allergen In the Weighted risk characteristic values ​​for each seasonal period; Allergen In the Weighted concentrated feature values ​​for each seasonal period.

[0086] The dynamic map generation module 104 is used to generate a dynamic map of cross-allergen risk in real time based on the degree of cross-allergy risk.

[0087] For the target children, after determining the cross-allergy risk level of each type of allergen in each season, a dynamic cross-allergen risk map can be generated in real time based on the cross-allergy risk level. Preferably, in a specific implementation of this invention, the process of obtaining the dynamic cross-allergen risk map based on the cross-allergy risk level includes:

[0088] Allergens with a cross-allergy risk level greater than a preset risk threshold in each seasonal period are designated as high-risk cross-allergens for that season. The high-risk cross-allergens for the target child in each seasonal period are highlighted in the original cross-allergen risk map, generating a dynamic cross-allergen risk map for the target child in real time. In one specific implementation of this invention, the preset risk threshold is set to 0.6; that is, when the corresponding cross-allergy risk level is greater than 0.6, it indicates that the target child has a higher risk of cross-allergy to the corresponding allergen in the corresponding seasonal period. Therefore, the high-risk cross-allergens highlighted in the original cross-allergen risk map for each seasonal period require greater avoidance of the corresponding allergens in that season.

[0089] In one specific implementation of this invention, the target child in the original cross-allergen risk map corresponds to each seasonal period, and each seasonal period corresponds to all allergens. After highlighting the high-risk cross-allergens by magnification, highlighting, or other methods, the dynamic cross-allergen risk map of the target child at the current moment is obtained.

[0090] In summary, a dynamic cross-allergen risk map generation system for children first determines the sensitivity index by analyzing the immune response of each allergen class across all allergy testing processes. Then, based on the similarity of each allergen class to other allergen classes in terms of allergen protein structure and IgE levels, combined with the sensitivity index, it comprehensively characterizes the cross-reaction risk index of each allergen class during each allergy testing process. Furthermore, considering the dynamic changes in cross-allergic reactions that may be caused by seasonal variations, and based on the increasing trend of the cross-reaction risk index curves in each seasonal period and the overall magnitude of the cross-reaction risk index, it comprehensively determines the degree of cross-allergic risk for each type of allergen in each seasonal period. This makes the dynamic cross-allergen risk map generated in real time based on the degree of cross-allergic risk more accurate.

[0091] This application also provides a computer device; please refer to [link / reference]. Figure 2 The illustration shows a schematic diagram of a computer device structure according to an embodiment of the present invention. The computer device includes a memory 201, a processor 202, and a computer program 203 stored in the memory 201 and running on the processor 202. When the processor 202 executes the computer program 203, the computer device can execute any of the aforementioned children's cross-allergen risk dynamic map generation systems.

[0092] This application also provides a computer program product that, when run on a computer device, enables the computer device to execute any of the aforementioned dynamic map generation systems for cross-allergen risk in children.

[0093] This application also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer device, the computer device can execute any of the aforementioned children's cross-allergen risk dynamic map generation systems.

[0094] In the embodiments provided in this application, it should be understood that the computer device, computer program product and computer-readable storage medium provided are all used to execute the corresponding system provided above, and therefore the beneficial effects they can achieve can be referred to the beneficial effects of the system provided above, which will not be repeated here.

[0095] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0096] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A system for generating a dynamic cross-allergen risk map for children, characterized in that, The system includes: The data acquisition and preprocessing module is used to collect the IgE level test values ​​of each type of allergen for the target child in each allergy test from the medical database; The first determining module is used to determine the corresponding sensitivity index based on the overall deviation of the IgE level detection values ​​of each type of allergen from the normal range during all allergy testing; and to determine the corresponding cross-reactivity risk index based on the sensitivity index and the similarity between each type of allergen and other types of allergens in IgE level detection values ​​and protein three-dimensional structure during each allergy testing. The second determining module is used to determine the cross-reactivity risk index curve of each type of allergen in each seasonal period based on the temporal changes of the cross-reactivity risk index corresponding to each type of allergen in all allergy testing processes; and to determine the degree of cross-allergy risk of each type of allergen in each seasonal period based on the overall magnitude of the cross-reactivity risk index curve and the similarity of the increasing trend of the cross-reactivity risk index curve in all seasonal periods. The dynamic spectrum generation module is used to generate a dynamic spectrum of cross-allergen risk in real time based on the degree of cross-allergy risk. The process of obtaining the cross-reactivity risk index curve includes: In all allergy testing processes, allergy testing processes with normal deviation values ​​greater than 0 for each type of allergen are considered as corresponding allergic reaction processes. The cross-reactivity risk index of each type of allergen in all allergy reaction processes for the target child in each season is arranged in chronological order and then curve-fitted to determine the cross-reactivity risk index curve of each type of allergen in each season. The season refers to the time period corresponding to the same season. The process of obtaining the degree of cross-allergy risk includes: Based on the frequency of allergic reaction processes to each type of allergen in each seasonal period and the increasing trend on the cross-reactivity risk index curve, the corresponding seasonal trend is determined. The standard deviation of the seasonal trend of each type of allergen in all seasons is normalized to determine the corresponding central characteristic weights. Based on the overall seasonal trend deviation between each seasonal period and other seasonal periods, determine the risk concentration characteristic value of each type of allergen in each seasonal period; Based on the mean of the cross-reaction risk index for each type of allergen during all allergic reactions in each season, the corresponding cross-reaction risk characteristic value is determined. The weighted cluster feature value for each type of allergen in each seasonal period is determined by multiplying the cluster feature weights with the risk cluster feature values. The weighted risk characteristic value of each type of allergen in each seasonal period is determined by multiplying the negative correlation mapping value of the centralized feature weight with the cross-reactivity risk characteristic value. The sum of the weighted set feature values ​​and the weighted risk feature values ​​is normalized to determine the degree of cross-allergy risk for each type of allergen in each seasonal period.

2. The system for generating a dynamic cross-allergen risk map for children according to claim 1, characterized in that, The process of obtaining the sensitivity index includes: Obtain the upper limit of normal IgE level for each type of allergen; use the difference between the IgE level of each type of allergen and the corresponding upper limit of normal IgE level for the target child in each allergy test as the corresponding normal deviation value; determine the frequency weight of each type of allergen based on the total number of times the corresponding normal deviation value is greater than 0 in all allergy tests. The average IgE level for each type of allergen across all allergy tests is used as the degree of allergic abnormality for each type of allergen. The product of the frequency weight and the degree of allergic abnormality is normalized to determine the sensitivity index of the target child to each type of allergen.

3. The system for generating a dynamic cross-allergen risk map for children according to claim 2, characterized in that, The process of obtaining the cross-reactivity risk index includes: Cluster analysis is performed based on the similarity of normal deviations of various allergens during each allergy test to obtain at least two allergen clusters; each allergen is then used as the target allergen. During each allergy test, when the normal deviation value of the target allergen is less than or equal to 0, the preset similarity parameter is used as the corresponding final similarity weight. When the normal deviation value of the target allergen is greater than 0, the number of allergens in the allergen cluster to which the target allergen belongs is used as the allergy similarity weight; the protein structure similarity weight of the target allergen is determined based on the overall structural similarity between the protein of the target allergen and the proteins of other allergens in the allergen cluster to which it belongs; the product between the allergy similarity weight and the protein structure similarity weight is normalized to determine the final similarity weight of the target allergen. The cross-reactivity risk index of the target allergen in each allergy test is determined by multiplying the final similarity weight of the target allergen with the corresponding sensitivity index.

4. The system for generating a dynamic cross-allergen risk map for children according to claim 3, characterized in that, The process of obtaining the allergen clusters includes: The ratio between the normal deviation value of each type of allergen and the corresponding normal upper limit value of IgE level during each allergy test is used as the normal deviation rate; k-means cluster analysis is performed on the normal deviation rates of all types of allergens during each allergy test to obtain at least two allergen clusters; the K value of the k-means cluster analysis is determined by the elbow method.

5. The system for generating a dynamic cross-allergen risk map for children according to claim 3, characterized in that, The process of obtaining the protein structural similarity weights includes: All allergens in the allergen cluster containing the target allergen are used as contrast allergens. The protein of the target allergen is compared with the protein of each contrast allergen using the protein structure alignment tool TM-align to determine the TM-score value between the protein of the target allergen and the protein of each contrast allergen. The mean of the TM-score values ​​between the protein of the target allergen and the proteins of all contrast allergens is used as the protein structure similarity weight of the target allergen.

6. The system for generating a dynamic cross-allergen risk map for children according to claim 1, characterized in that, The process of obtaining the seasonal trend includes: The total number of allergic reaction events for each type of allergen in the target child during each season is used as the corresponding weight of the allergic reaction occurrence; the average slope of the tangent line corresponding to all allergic reaction events on the cross-reaction risk index curve is used to determine the allergy risk growth value for each type of allergen in each season; the seasonal trend of each type of allergen in each season is determined by multiplying the allergic reaction occurrence weight by the allergy risk growth value.

7. The system for generating a dynamic cross-allergen risk map for children according to claim 1, characterized in that, The process of obtaining the risk set characteristic values ​​includes: Each seasonal period is sequentially designated as the target period; other seasonal periods outside the target period are designated as comparison periods; the difference between the seasonal trend of each type of allergen in the target period and the seasonal trend of each comparison period is calculated to determine the trend deviation value of each comparison period; the mean of the trend deviation values ​​of all comparison periods corresponding to the target period is normalized to determine the risk concentration characteristic value of each type of allergen in the target period.

8. The system for generating a dynamic cross-allergen risk map for children according to claim 1, characterized in that, The process of generating a dynamic risk map of cross-allergens based on the degree of cross-allergy risk includes: Allergens with a cross-allergy risk level greater than a preset risk threshold in each season are identified as high-risk cross-allergens for each season. The high-risk cross-allergens for the target child in each season are highlighted in the original cross-allergen risk map, and a dynamic cross-allergen risk map for the target child is generated in real time.

Images