Risk assessment method and system for RSV infection

Abstract

The invention relates to the technical field of medical data processing, in particular to a risk assessment method and system for RSV infection. A risk assessment method for RSV infection comprises the following steps: S1, constructing a PM2.5 land utilization regression model, and obtaining the real-time concentration of PM2.5 in a target area by using the PM2.5 land utilization regression model; s2, obtaining related influence data, and obtaining the correlation between the PM2.5 exposure and the related influence data of the children with respiratory diseases caused by RSV infection according to the related influence data; and S3, according to the correlation, determining the mediation effect of the immune function change in the respiratory diseases caused by the PM2.5 exposure to the RSV infection. By prospectively researching the correlation between PM2.5 exposure and related influence data of children with respiratory diseases caused by RSV infection, the reliability and scientificity are improved.

Description

Technical Field

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

[0002] In recent years, respiratory syncytial virus infection has become one of the important pathogenic factors causing respiratory diseases in children. The lower respiratory tract infections and hospitalizations caused by it pose a serious challenge to children's health. Traditionally, risk assessment of RSV infection has relied on epidemiological statistics and analysis of single environmental factors, which cannot fully reflect the true risk of the interaction of multiple factors in a complex environment. Especially in the current context of accelerated urbanization and increasing industrialization, the concentration of suspended particulate matter in the environment shows a trend of dynamic spatiotemporal changes. PM2.5, as an important environmental pollutant, has a close correlation with the occurrence of respiratory diseases. The meteorological conditions when air pollution occurs are conducive to the survival and spread of RSV in the air, and both enter the human body mainly through the respiratory tract. The respiratory system is a common target organ for RSV and PM2.5. This high degree of consistency in space, time, and target organs indicates that it is not enough to focus on RSV alone in the study of RSV-induced respiratory infections in children. Summary of the Invention

[0003] In order to overcome the shortcomings of focusing solely on RSV without considering the role of PM2.5 and its components and inaccurate risk assessment, the present invention provides a risk assessment method and system for RSV infection.

[0004] The technical solution is as follows: A risk assessment method for RSV infection, comprising the following steps: S1: Constructing a PM2.5 land use regression model, and using the PM2.5 land use regression model to obtain the real-time concentration of PM2.5 in the target area; S2: Obtain relevant impact data, and obtain the correlation between PM2.5 exposure and relevant impact data of children with respiratory diseases caused by RSV infection based on the relevant impact data; S3: Determine the mediating role of altered immune function in the relationship between PM2.5 exposure and RSV-induced respiratory disease based on correlations; S4: Obtain comprehensive data of the target person, and use a risk assessment formula based on the comprehensive data to obtain a risk assessment value of the target person; S5: Providing risk reminders to the target person according to the risk assessment value of the target person.

[0005] Preferably, the construction of a PM2.5 land use regression model and the use of the PM2.5 land use regression model to obtain the real-time concentration of PM2.5 in the target area include: obtaining PM2.5 concentration data, aerosol data and geographical element variables of the surrounding area in the monitoring area, the geographical element variables including road distribution, green coverage, industrial layout, population density and terrain data; obtaining the aerosol data by inverting remote sensing images, cleaning, normalizing and spatially registering the aerosol data and the geographical element variables to obtain preprocessed data, constructing a PM2.5 land use regression model based on the preprocessed data, and obtaining the real-time concentration of PM2.5 in the target area by the PM2.5 land use regression model, wherein the target area is a part of the monitoring area.

[0006] Preferably, constructing a PM2.5 land use regression model based on the preprocessed data includes: the PM2.5 land use regression model includes prediction variable selection, buffer zone analysis, bivariate correlation analysis, multivariate regression modeling and model accuracy evaluation.

[0007] Preferably, the obtaining of relevant impact data and obtaining the correlation between relevant impact data of PM2.5 exposure and RSV infection on children with respiratory diseases based on the relevant impact data include: obtaining relevant impact data, the relevant impact data including the number of patients visiting the hospital, the number of lower respiratory tract infections, the hospitalization rate and recovery-related data, and using the relevant impact data and a correlation analysis model to obtain the correlation between relevant impact data of PM2.5 exposure and RSV infection on children with respiratory diseases; the correlation analysis model is a comprehensive model combining a multiple linear regression model and a multivariate regression model; and the regression coefficient is calculated using a generalized estimating equation to correct the non-independence between multiple measurement values ​​of children with the same respiratory disease.

[0008] Preferably, the method of determining the mediating role of changes in immune function in PM2.5 exposure and respiratory diseases caused by RSV infection based on correlation includes: when the correlation is greater than or equal to a preset correlation threshold, determining the mediating role of changes in immune function in PM2.5 exposure and respiratory diseases caused by RSV infection, dividing the samples into high and low exposure groups according to the PM2.5 exposure level, and performing pattern recognition on the immunogenomic data through an orthogonal partial least squares discriminant model after dimensionality reduction preprocessing using principal component analysis, screening out key immune factors in cellular immunity, humoral immunity and inflammatory factors based on projection importance, and using a mediation effect model to use the key immune factors as mediating variables, establishing statistical models between PM2.5 exposure and mediating variables, and statistical models between mediating variables and respiratory diseases caused by RSV infection, respectively, calculating direct effects, indirect effects and total effects, and determining the credible intervals of each effect coefficient, evaluating the credible intervals to obtain credible assessment values, and performing risk assessment on the target personnel when the credible assessment values ​​are greater than the preset assessment threshold.

[0009] Preferably, the method of obtaining comprehensive data of the target person and using a risk assessment formula based on the comprehensive data to obtain a risk assessment value of the target person includes: obtaining comprehensive data of the target person, the comprehensive data including the high-frequency activity time period of the target person, the target area where the target person is located, the real-time concentration of PM2.5 in the target area, and the family health resource index, and using a risk assessment formula based on the comprehensive data to obtain the risk assessment value of the target person, wherein the target person is a child with respiratory disease caused by RSV infection.

[0010] Preferably, the risk assessment formula is used to obtain the risk assessment value of the target person according to the comprehensive data, including: the risk assessment formula is: ; Where, Risk assessment value for target personnel; For the target person in the target area High-frequency activity time periods; For the target area The concentration of PM2.5 during the high-frequency activity period; is the Family Health Resource Index; is the immune microenvironment response coefficient; is the weight adjustment coefficient.

[0011] Preferably, the The immune microenvironment response coefficient is obtained by: obtaining the immune tolerance critical value of the target person, the real-time concentration of PM2.5 in the target area, and using the risk impact formula to obtain the immune microenvironment response coefficient, wherein the real-time concentration of PM2.5 in the target area is obtained through the PM2.5 land use regression model, and the immune tolerance critical value of the target person is the maximum concentration of PM2.5 that the target person's body can withstand. The risk impact formula is: ; Where, is the immune microenvironment response coefficient; is the real-time concentration of PM2.5 in the target area; is the immune tolerance threshold of the target person; is the adjustment coefficient of the risk impact formula.

[0012] Preferably, the The family health resource index includes: obtaining the family protection data of the target person, the family protection data including the coverage rate of medical service resources in the family, the family economic status and the family health knowledge level, and obtaining the family health resource index after weighted summation of the family protection data.

[0013] Preferably, a risk assessment system for RSV infection further comprises: The data collection module is used to obtain relevant impact data, PM2.5 concentration data, aerosol data, and comprehensive data on geographical element variables in the surrounding area and target personnel; A data preprocessing module, configured to perform cleaning, normalization, and spatial registration preprocessing on the aerosol data and the geographic element variables; The regression model construction module is used to construct a PM2.5 land use regression model based on predictor variable selection, buffer zone analysis, bivariate correlation analysis, multivariate regression modeling, and model accuracy evaluation; A correlation analysis module, configured to obtain correlation between PM2.5 exposure and relevant impact data on children with respiratory diseases caused by RSV infection using the relevant impact data and the correlation analysis model; Immune-mediated effect analysis module, used to determine the mediating role of immune function changes in PM2.5 exposure on RSV-induced respiratory diseases based on correlation; The risk assessment module is used to obtain comprehensive data of the target person and use the risk assessment formula based on the comprehensive data to obtain the risk assessment value of the target person.

[0014] The beneficial effects are: 1. This invention uses a PM2.5 land use regression model, geographic element data, and aerosol data for data preprocessing, achieving real-time inversion and high-precision prediction of PM2.5 concentrations in the target area. This effectively compensates for the shortcomings of traditional monitoring networks in terms of temporal and spatial resolution, ensuring data accuracy and timeliness. 2. This study uses principal component analysis and orthogonal partial least squares discriminant models to perform pattern recognition on immunogenomic data. A mediation effect model is used to quantitatively calculate direct, indirect, and total effects. This study clarifies the mediating role of immune function changes in PM2.5 exposure on respiratory diseases caused by RSV infection, providing a basis for subsequent risk assessment. 3. The present invention dynamically calculates the risk assessment value by introducing the family health resource index, immune microenvironment response coefficient and comprehensive data into the risk assessment formula, and issues risk reminders to target personnel based on the risk assessment value, thereby achieving individualized and precise health risk management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Flow chart of the risk assessment method for RSV infection of the present invention; Figure 2 This is a flow chart of the risk assessment system for RSV infection according to the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0017] Example 1: A method for risk assessment of RSV infection, such as Figure 1 As shown, the following steps are included: S1: Constructing a PM2.5 land use regression model, and using the PM2.5 land use regression model to obtain the real-time concentration of PM2.5 in the target area; Acquire PM2.5 concentration data, aerosol data and geographic element variables of the surrounding area within the monitoring area, wherein the geographic element variables include road distribution, green coverage, industrial layout, population density and terrain data; obtain the aerosol data by inverting remote sensing images, perform cleaning, normalization and spatial registration preprocessing on the aerosol data and the geographic element variables to obtain preprocessed data, construct a PM2.5 land use regression model based on the preprocessed data, and obtain the real-time concentration of PM2.5 in the target area through the PM2.5 land use regression model, wherein the target area is a part of the monitoring area.

[0018] It should be noted that PM2.5 concentration data in the monitoring area are obtained through fixed monitoring stations, mobile monitoring equipment or relevant authoritative departments, aerosol data in the target area are collected through remote sensing image inversion, and geographic element variable data in the surrounding area are collected at the same time, where geographic element variables include road distribution, green coverage, industrial layout, population density and terrain data. Data cleaning, normalization and spatial alignment are performed on aerosol data and geographic element variables in the surrounding area. The purpose of data cleaning is to eliminate outliers, noise data or missing data to ensure that the data input to the model has high credibility; normalization is used to eliminate the imbalance between different data caused by different dimensions and value ranges; spatial alignment ensures that the data can accurately correspond to each other in spatial position, that is, to ensure that the data from different sources are strictly aligned in geographic coordinates; based on the preprocessed data, a PM2.5 land use regression model is further constructed.

[0019] The PM2.5 land use regression model includes prediction variable selection, buffer zone analysis, bivariate correlation analysis, multivariate regression modeling and model accuracy evaluation.

[0020] It should be noted that the prediction variables are selected based on the pre-processed data, and variables that have a significant impact on PM2.5 concentration are selected from the geographical element variables, such as road distribution reflecting traffic emissions, industrial layout reflecting industrial pollution, green coverage and population density. These variables are preliminarily screened to ensure that the variables entering the subsequent analysis can represent the comprehensive impact of environmental and human factors; buffer zone analysis: for each measurement point in the monitoring area, the buffer zone analysis technology is used to divide the different geographical element variables into regions, and the road density, industrial layout and green coverage within the preset radius around each measurement point are counted, so as to more finely reflect the environmental influencing factors of each point; bivariate correlation analysis: after determining the candidate prediction variables, a bivariate correlation analysis is performed on each prediction variable and the monitored PM2.5 concentration data. Analysis, statistics of the correlation coefficients between variables, elimination of variables with weak correlation, to ensure that the variables entering the multiple regression modeling stage have high explanatory power; Multiple regression modeling: using the prediction variables screened out after buffer zone analysis and bivariate correlation analysis, a multiple regression model is constructed. The model takes PM2.5 concentration as the dependent variable and the screened geographic element variables as the independent variables. The regression coefficient is determined by fitting method to achieve accurate prediction of PM2.5 concentration in the monitoring area; Model accuracy evaluation: after the model is constructed, the model is evaluated using cross-validation, residual analysis and statistical indicators of determination coefficient to ensure that the constructed PM2.5 land use regression model can truly reflect the spatiotemporal distribution characteristics of PM2.5 in the monitoring area and has a high prediction accuracy. The accuracy evaluation results will serve as the basis for subsequent real-time concentration calculations.

[0021] S2: Obtain relevant impact data, and obtain the correlation between PM2.5 exposure and relevant impact data of children with respiratory diseases caused by RSV infection based on the relevant impact data; Relevant impact data were obtained, including the number of patients visiting the hospital, the number of lower respiratory tract infections, the hospitalization rate, and recovery-related data. The relevant impact data and the correlation analysis model were used to obtain the correlation between the relevant impact data of PM2.5 exposure and RSV infection-induced respiratory diseases in children. The correlation analysis model was a comprehensive model that combined a multiple linear regression model and a multivariate regression model. The regression coefficients were calculated using generalized estimating equations to correct for the non-independence of multiple measurements of children with the same respiratory disease.

[0022] It should be noted that the relevant impact data reflecting the clinical manifestations of children with respiratory diseases caused by RSV infection were obtained through hospitals, public health departments or relevant medical institutions; the correlation analysis model is a comprehensive model combining the multiple linear regression model and the multivariate regression model, wherein the multiple linear regression model establishes a preliminary regression relationship by taking the PM2.5 exposure level as the independent variable and the relevant impact data (number of patients, number of lower respiratory tract infections, hospitalization rate and recovery-related data) as the dependent variable; the multivariate regression model, on the basis of the multiple linear regression, further introduces other variables that affect the risk of RSV infection, such as environmental temperature and humidity, to form a comprehensive impact regression model. , thereby more comprehensively describing the impact of PM2.5 exposure on clinical indicators related to RSV infection; since the collected data involve multiple measurements in the same body and there is a problem of non-independence between data, in order to ensure the accuracy of the regression coefficients and the robustness of the model, the regression coefficients were calculated and corrected using generalized estimating equations, among which generalized estimating equations can effectively solve the correlation problem in repeated measurement data, improve the reliability of the model estimation results and ensure that the true statistical relationship between the variables is objectively reflected; through the above steps, the relevant impact data and the constructed correlation analysis model were comprehensively utilized to finally obtain the correlation between PM2.5 exposure and the relevant impact data of children with respiratory diseases caused by RSV infection.

[0023] S3: Determine the mediating role of altered immune function in the relationship between PM2.5 exposure and RSV-induced respiratory disease based on correlations; When the correlation is greater than or equal to the preset correlation threshold, the mediating role of immune function changes in PM2.5 exposure on respiratory diseases caused by RSV infection is determined. The samples are divided into high and low exposure groups according to the PM2.5 exposure level. After dimensionality reduction preprocessing using principal component analysis, the immunogenomic data are pattern recognized using the orthogonal partial least squares discriminant model. The key immune factors in cellular immunity, humoral immunity and inflammatory factors are screened out based on projection importance, and the mediation effect model is used to use the key immune factors as mediating variables. Statistical models between PM2.5 exposure and mediating variables, and statistical models between mediating variables and respiratory diseases caused by RSV infection are established respectively. The direct effect, indirect effect and total effect are calculated, and the credible interval of each effect coefficient is determined. The credible interval is evaluated to obtain a credible assessment value. When the credible assessment value is greater than the preset assessment threshold, a risk assessment is performed on the target person.

[0024] It should be noted that after obtaining the correlation of the above-mentioned relevant influencing data, the correlation is compared with the preset correlation threshold. When the correlation is greater than or equal to the preset correlation threshold, it is considered that there is sufficient statistical correlation between the data, and it is determined that changes in immune function play a mediating role in PM2.5 exposure to RSV infection-induced respiratory diseases. The preset correlation threshold is determined based on the statistical results of historical data or pre-set standards to ensure the scientificity and rationality of the judgment; according to the PM2.5 exposure level, the collected samples are divided into high exposure group and low exposure group, and the principal component analysis is used to perform dimensionality reduction preprocessing on the sample data. The dimensionality reduction process retains the most representative main components in the data to reduce data redundancy and noise interference, laying the foundation for the subsequent pattern recognition of the orthogonal partial least squares discriminant model. The orthogonal partial least squares discriminant model is used to perform pattern recognition on the immunogenomics data after dimensionality reduction by principal component analysis. This model can be used to identify the immunogenomics data from massive immune genomics data. Representative patterns were screened out from the biological indicators, and key immune factors in cellular immunity, humoral immunity and inflammatory factors were further screened out based on projection importance; after the key immune factors were selected, they were used as mediating variables to establish two groups of statistical models: one group of models described the relationship between PM2.5 exposure and mediating variables; the other group of models described the relationship between mediating variables and respiratory diseases caused by RSV infection. Through the mediation effect model, the direct effect, indirect effect and total effect were calculated to clarify the mediating role of changes in immune function in PM2.5 exposure on respiratory diseases caused by RSV infection. A credible interval was established for each calculated effect coefficient, and the credible interval was evaluated to finally obtain a credible assessment value. When the credible assessment value was greater than the preset assessment threshold, it was considered that the mediating role of changes in immune function in PM2.5 exposure on respiratory diseases caused by RSV infection was fully verified, thereby conducting a risk assessment on the target personnel.

[0025] S4: Obtain comprehensive data of the target person, and use a risk assessment formula based on the comprehensive data to obtain a risk assessment value of the target person; Obtain comprehensive data of the target person, which includes the target person's high-frequency activity time period, the target area where the target person is located, the real-time concentration of PM2.5 in the target area, and the family health resource index. Use a risk assessment formula based on the comprehensive data to obtain a risk assessment value of the target person, where the target person is a child with respiratory disease caused by RSV infection.

[0026] It should be noted that the target persons are children with respiratory diseases caused by RSV infection. The comprehensive data mainly include the following parts: high-frequency activity time period: record the activities of the target persons in various time periods within the target area, obtain them through questionnaires, mobile device positioning data or on-site observations, and take the time periods with strong activity of the target persons as high-frequency activity time periods; target area: determine the specific area where the target persons are located, which is a part of the monitoring area and can accurately reflect the environmental quality status in the area; the real-time concentration of PM2.5 in the target area, use the PM2.5 land use regression model constructed above to obtain the real-time concentration data of PM2.5 in the target area, and ensure that the spatiotemporal resolution of the data meets the real-time monitoring requirements; family health resource index: collect relevant protection data of the target person's family, including the coverage rate of medical service resources in the family, family economic status and family health knowledge level.

[0027] The risk assessment formula is: ; Where, Risk assessment value for target personnel; For the target person in the target area High-frequency activity time periods; For the target area The concentration of PM2.5 during the high-frequency activity period; is the Family Health Resource Index; is the immune microenvironment response coefficient; is the weight adjustment coefficient.

[0028] It should be noted that the collected data are sorted to ensure that the target area where the target person is located during the high-frequency activity time period and the real-time concentration data of PM2.5 in the corresponding period, as well as the family health resource index, can form corresponding records. In the process of data matching, the time synchronization and the precise correspondence of spatial position are ensured to ensure the accuracy of the input data of the risk assessment formula; the formula uses the summation method to cumulatively calculate the environmental exposure risk of the target person in multiple high-frequency activity time periods, and uses the logistic function to make nonlinear adjustments to the impact of the family health resource index, so as to more reasonably reflect the risk mitigation effect of family health resources.

[0029] S5: Providing risk reminders to the target person according to the risk assessment value of the target person.

[0030] The immune tolerance critical value of the target person and the real-time concentration of PM2.5 in the target area are obtained, and the immune microenvironment response coefficient is obtained using the risk impact formula, wherein the real-time concentration of PM2.5 in the target area is obtained through the PM2.5 land use regression model. The immune tolerance critical value of the target person is the maximum concentration of PM2.5 that the target person's body can withstand. The risk impact formula is: ; Where, is the immune microenvironment response coefficient; is the real-time concentration of PM2.5 in the target area; is the immune tolerance threshold of the target person; is the adjustment coefficient of the risk impact formula.

[0031] It should be noted that the target individual's immune tolerance threshold, which represents the maximum PM2.5 concentration that the target individual's body can withstand, is typically obtained through the following methods: clinical testing and historical data analysis: immune function and respiratory tolerance tests are conducted on the target individual, and a relatively stable immune tolerance upper limit is determined based on their previous health status and exposure history; expert evaluation and standard setting: with reference to relevant medical research and standard specifications, the target individual's immune tolerance threshold is determined through expert review and used as the individual's safety limit under environmental exposure; the real-time PM2.5 concentration in the target area is obtained through a PM2.5 land use regression model. Specifically, data collection involves obtaining real-time PM2.5 concentration data from the monitoring area, and simultaneously obtaining corresponding aerosol data through remote sensing image inversion. This data is then integrated with geographic element variables (such as road distribution, industrial layout, green coverage, population density, and terrain data); model calculation: the pre-processed data that has been cleaned, normalized, and spatially aligned is substituted into the constructed PM2.5 land use regression model to calculate the real-time PM2.5 concentration in the target area.

[0032] The family protection data of the target person is obtained, wherein the family protection data includes the coverage rate of medical service resources in the family, the family economic status and the family health knowledge level, and the family health resource index is obtained by weighted summation of the family protection data.

[0033] It should be noted that the coverage rate of medical service resources within the family includes the quality of medical services that family members can obtain, the distance from medical institutions, the richness of medical resources and the use of air purification devices in the family; family economic status: through the data of family income, asset status and family economic expenditure, the family's economic ability in health protection and disease intervention is assessed; family health knowledge level: through questionnaire surveys or health education assessments, the family members' mastery of health protection knowledge, including the knowledge level of disease prevention and health management, is obtained.

[0034] Example 2: Based on Example 1, a risk assessment system for RSV infection, such as Figure 2 As shown, it also includes: The data collection module is used to obtain relevant impact data, PM2.5 concentration data, aerosol data, and comprehensive data on geographical element variables in the surrounding area and target personnel; A data preprocessing module, configured to perform cleaning, normalization, and spatial registration preprocessing on the aerosol data and the geographic element variables; The regression model construction module is used to construct a PM2.5 land use regression model based on predictor variable selection, buffer zone analysis, bivariate correlation analysis, multivariate regression modeling, and model accuracy evaluation; A correlation analysis module, configured to obtain correlation between PM2.5 exposure and relevant impact data on children with respiratory diseases caused by RSV infection using the relevant impact data and the correlation analysis model; Immune-mediated effect analysis module, used to determine the mediating role of immune function changes in PM2.5 exposure on RSV-induced respiratory diseases based on correlation; The risk assessment module is configured to obtain comprehensive data of a target person and, based on the comprehensive data, use a risk assessment formula to obtain a risk assessment value for the target person. Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that variations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for risk assessment of RSV infection, characterized in that: The following steps are involved: S1: Constructing a PM2.5 land use regression model, and using the PM2.5 land use regression model to obtain the real-time concentration of PM2.5 in the target area; S2: Obtain relevant impact data, and obtain the correlation between PM2.5 exposure and relevant impact data of children with respiratory diseases caused by RSV infection based on the relevant impact data; S3: Determine the mediating role of altered immune function in the relationship between PM2.5 exposure and RSV-induced respiratory disease based on correlations; S4: Obtain comprehensive data of the target person, and use a risk assessment formula based on the comprehensive data to obtain a risk assessment value of the target person; S5: Providing risk reminders to the target person according to the risk assessment value of the target person.

2. A risk assessment method for RSV infection according to claim 1, characterized in that: The method of constructing a PM2.5 land use regression model and using the PM2.5 land use regression model to obtain the real-time concentration of PM2.5 in the target area includes: obtaining PM2.5 concentration data, aerosol data and geographical element variables of the surrounding area in the monitoring area, wherein the geographical element variables include road distribution, green coverage, industrial layout, population density and terrain data; obtaining the aerosol data by inverting remote sensing images, cleaning, normalizing and spatially registering the aerosol data and the geographical element variables to obtain preprocessed data, constructing a PM2.5 land use regression model based on the preprocessed data, and obtaining the real-time concentration of PM2.5 in the target area by using the PM2.5 land use regression model, wherein the target area is a part of the monitoring area.

3. A risk assessment method for RSV infection according to claim 2, characterized in that: The PM2.5 land use regression model is constructed based on the preprocessed data, including: the PM2.5 land use regression model includes prediction variable selection, buffer zone analysis, bivariate correlation analysis, multivariate regression modeling and model accuracy evaluation.

4. A risk assessment method for RSV infection according to claim 1, characterized in that: The method of obtaining relevant impact data and obtaining the correlation between relevant impact data of PM2.5 exposure and RSV infection-induced respiratory diseases in children based on the relevant impact data includes: obtaining relevant impact data, wherein the relevant impact data include the number of patients visiting the hospital, the number of lower respiratory tract infections, the hospitalization rate and recovery-related data, and using the relevant impact data and a correlation analysis model to obtain the correlation between relevant impact data of PM2.5 exposure and RSV infection-induced respiratory diseases in children; the correlation analysis model is a comprehensive model that combines a multiple linear regression model and a multivariate regression model; and using a generalized estimating equation to calculate the regression coefficient and then correct the non-independence between multiple measurement values ​​of children with the same respiratory disease.

5. A risk assessment method for RSV infection according to claim 1, characterized in that: The method of determining the mediating effect of immune function changes on respiratory diseases caused by PM2.5 exposure due to RSV infection based on correlation includes: when the correlation is greater than or equal to a preset correlation threshold, determining the mediating effect of immune function changes on respiratory diseases caused by PM2.5 exposure due to RSV infection, dividing the samples into high and low exposure groups according to the PM2.5 exposure level, performing pattern recognition on the immunogenomics data through an orthogonal partial least squares discriminant model after dimensionality reduction preprocessing using principal component analysis, screening out key immune factors in cellular immunity, humoral immunity and inflammatory factors based on projection importance, using a mediation effect model to use the key immune factors as mediating variables, establishing statistical models between PM2.5 exposure and mediating variables, and between mediating variables and respiratory diseases caused by RSV infection, respectively, calculating direct effects, indirect effects and total effects, and determining the credible intervals of each effect coefficient, evaluating the credible intervals to obtain credible assessment values, and performing risk assessment on the target personnel when the credible assessment values ​​are greater than the preset assessment threshold.

6. A risk assessment method for RSV infection according to claim 1, characterized in that: The method of obtaining comprehensive data of the target person and using a risk assessment formula based on the comprehensive data to obtain a risk assessment value of the target person includes: obtaining comprehensive data of the target person, the comprehensive data including the high-frequency activity time period of the target person, the target area where the target person is located, the real-time concentration of PM2.5 in the target area, and the family health resource index; and using a risk assessment formula based on the comprehensive data to obtain the risk assessment value of the target person, wherein the target person is a child with a respiratory disease caused by RSV infection.

7. A risk assessment method for RSV infection according to claim 6, characterized in that: The risk assessment formula is used to obtain the risk assessment value of the target person according to the comprehensive data, including: the risk assessment formula is: ； Where, Risk assessment value for target personnel; For the target person in the target area High-frequency activity time periods; For the target area The concentration of PM2.5 during the high-frequency activity period; is the Family Health Resource Index; is the immune microenvironment response coefficient; is the weight adjustment coefficient.

8. A risk assessment method for RSV infection according to claim 7, characterized in that: described The immune microenvironment response coefficient is obtained by: obtaining the immune tolerance critical value of the target person, the real-time concentration of PM2.5 in the target area, and using the risk impact formula to obtain the immune microenvironment response coefficient, wherein the real-time concentration of PM2.5 in the target area is obtained through the PM2.5 land use regression model, and the immune tolerance critical value of the target person is the maximum concentration of PM2.5 that the target person's body can withstand. The risk impact formula is: ； Where, is the immune microenvironment response coefficient; is the real-time concentration of PM2.5 in the target area; is the immune tolerance threshold of the target person; is the adjustment coefficient of the risk impact formula.

9. A risk assessment method for RSV infection according to claim 7, characterized in that: described The family health resource index includes: obtaining the family protection data of the target person, the family protection data including the coverage rate of medical service resources in the family, the family economic status and the family health knowledge level, and obtaining the family health resource index after weighted summation of the family protection data.

10. A risk assessment system for RSV infection, according to a risk assessment method for RSV infection according to any one of claims 1 to 9, characterized in that: include: The data collection module is used to obtain relevant impact data, PM2.5 concentration data, aerosol data, and comprehensive data on geographical element variables in the surrounding area and target personnel; A data preprocessing module, configured to perform cleaning, normalization, and spatial registration preprocessing on the aerosol data and the geographic element variables; The regression model construction module is used to construct a PM2.5 land use regression model based on predictor variable selection, buffer zone analysis, bivariate correlation analysis, multivariate regression modeling, and model accuracy evaluation; A correlation analysis module, configured to obtain correlation between PM2.5 exposure and relevant impact data on children with respiratory diseases caused by RSV infection using the relevant impact data and the correlation analysis model; Immune-mediated effect analysis module, used to determine the mediating role of immune function changes in PM2.5 exposure on RSV-induced respiratory diseases based on correlation; The risk assessment module is used to obtain comprehensive data of the target person and use the risk assessment formula based on the comprehensive data to obtain the risk assessment value of the target person.

Images