Plateau pulmonary edema early disease data collection system based on polygene mutation characteristics
Through a data collection system with multigene mutation characteristics, combined with PRS standardization and LASSO regression model, key data characteristics and historical periods were screened, and the parameter selection problem in the collection of early disease data of plateau pulmonary edema was solved, achieving accurate prediction and systematic optimization.
Patent Information
- Application Number
- CN202410926942.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-11
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-07-11
AI Technical Summary
When collecting data on early plateau pulmonary edema, the existing prediction system cannot take into account all parameters as reference basis, which makes it difficult to collect data and affects the accuracy of the prediction results.
Design a data collection system for early disease of plateau pulmonary edema based on multigene mutation characteristics, including data acquisition module, user distinction module, data screening module and optimization matching module. Through PRS standardized processing, LASSO regression model and fuzzy logic analysis, key screening is selected. Data characteristics and historical periods, optimized data volume and importance analysis.
Ensure the accuracy of prediction results and system fluency, while alleviating system memory pressure, optimizing data importance parameters, and improving data collection efficiency.
Smart Images

Figure CN118899033A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of bioinformatics, and more specifically, to an early stage disease data collection system for high altitude pulmonary edema based on multi-gene mutation characteristics. Background Art
[0002] High-Altitude Pulmonary Edema (HAPE) is an acute disease common in high-altitude environments, characterized by pulmonary effusion, which can be life-threatening in severe cases. Early detection and intervention are essential for the prevention and treatment of HAPE. In recent years, the development of genomics has made it possible to predict individual disease risk through multi-gene mutation characteristics.
[0003] The prior art has the following deficiencies:
[0004] At present, the common prediction system SiGCD network system uses gene prediction to evaluate the possibility of early high-altitude pulmonary edema. Relatively speaking, in the early stage of the experiment, all subjects need to collect all parameters comprehensively to ensure the integrity of the data and the accuracy of the analysis. This strategy is suitable for the research stage and scenarios that require high-precision collection; but when the database information has reached its peak, it is impossible to collect all parameters as a reference. Some data must be screened out, but it cannot affect the user's prediction results. Obviously, the trade-offs in data collection for various users are an urgent problem that needs to be solved. Therefore, a high-altitude pulmonary edema early disease data collection system based on multi-gene mutation characteristics is proposed.
[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention
[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an early-stage high altitude pulmonary edema disease data collection system based on multi-gene mutation characteristics, which solves the problems raised in the above-mentioned background technology by using different product inspection methods.
[0007] To achieve the above object, the present invention provides the following technical solution: an early stage high altitude pulmonary edema disease data collection system based on multi-gene mutation characteristics, comprising a data acquisition module, a user differentiation module, a data screening module and an optimization matching module; signal connections between the modules;
[0008] The data collection module is used to collect user gene data and user average altitude, and send them to the user differentiation module. It also collects the number of occurrences of historical data and the upload speed of historical data and sends them to the data screening module.
[0009] The user differentiation module is used to receive user genetic data and user average altitude, establish PRS standardization processing to make it comparable between different individuals, and divide users into risk groups based on the results, and send the user division results to the data screening module;
[0010] The data screening module is used to obtain the user segmentation results and the most characteristic historical time periods, and divide the historical data occurrence times and historical data upload speeds into multiple categories according to the user segmentation results, and determine their importance in predicting the early risk of high-altitude pulmonary edema for various users through the LASSO regression model, obtain the retained data information, and send the importance of each data to the optimization matching module;
[0011] The optimization matching module is used to receive the importance of each data, obtain the data event density and calculate the limit data volume, and use fuzzy logic to determine the most characteristic historical period through comprehensive analysis, and send it to the data screening module.
[0012] In a preferred embodiment, the user gene data is obtained by calculating the PRS; step A1, after selecting the target gene associated with high altitude pulmonary edema, the mutation site of each target gene is determined; gene sequencing is performed on each user to obtain the gene fragment containing the target gene in the gene data;
[0013] Step A2: Obtain the risk effect value of each mutation site through large-scale population research; then calculate the contribution of each mutation site to the disease risk, usually expressed as a logarithmic odds ratio;
[0014] Step A3: For each mutation site, the risk score of a single mutation site is calculated based on the user's genotype and the corresponding weight, according to the following formula:
[0015] Risk Score i =β i ×G i
[0016] In the formula, β i is the weight of the ith mutation site, G i is the user’s genotype at the i-th mutation site, where i is the i-th mutation site;
[0017] Step A4: add the single gene risk scores of all mutation sites to obtain the polygenic risk score PRS, PRS = ∑ i β i ×G i .
[0018] In a preferred embodiment, the average altitude of the user is obtained by averaging the altitudes of the users at the time of measurement.
[0019] In a preferred embodiment, the comprehensive risk score is a comprehensive evaluation index combining the standardized polygenic risk score and the user's average altitude, and its calculation formula is as follows:
[0020]
[0021] In the formula, Rs t is the comprehensive risk score, α1 and α2 are the preset proportional coefficients of the standardized PRS and the average altitude of the user, and both α1 and α2 are greater than 0; where t represents the t-th user;
[0022] Risk stratification is set based on the comprehensive risk score of each user. After sorting the comprehensive risk score values from large to small, the user risk level is defined.
[0023] In a preferred embodiment, the user classification result value is preferentially defined as x, where x represents the xth user category; the number of occurrences of the early disease characteristics of high altitude pulmonary edema of the user is obtained by using each historical data to predict the occurrence of the early disease characteristics of high altitude pulmonary edema of the user. Get the historical data upload speed of each data through the network monitoring tool
[0024] In a preferred embodiment, the number of occurrences of historical data of multiple categories and the speed of uploading historical data are obtained, and their importance in predicting the early risk of high altitude pulmonary edema of various types of users is determined by LASSO regression model;
[0025] Step B1: construct a data set X containing the number of occurrences and upload speeds of historical data of each category and the response variable z. X is set as a feature matrix, including and
[0026] Step B2: Standardize the data to eliminate the impact of different dimensions: In the formula, μ j is the mean of the jth feature, σ j is the standard deviation of the jth feature;
[0027] Step B2, select the optimal λ value through cross-validation: λ * = arg min λ C(λ), where CV(λ) is the cross-validation error, and the optimal value is the value with the minimum average validation error during the validation process;
[0028] Step B3, use the optimal λ value to train the LASSO regression model: In the formula, z pis the response variable of the pth sample, X' pj is the jth standardized characteristic variable of the pth sample, β0 is the intercept term, β j is the regression coefficient of the jth eigenvector;
[0029] Step B4: The LASSO regression model will reduce the coefficients of some features to zero, and select features with non-zero coefficients as important features. The important feature set F is: F = {j|β j ≠0}, filter out the data whose characteristic coefficients are reduced to zero.
[0030] In a preferred embodiment, the calculation limit data volume Qu is obtained by the maximum amount of calculation data that the current system's computing power and storage capacity can bear at one time. t ; where t represents the tth time period, and the data event density ρ is obtained by the frequency of events that are consistent with the prediction of high altitude pulmonary edema in various types of data among various types of users t .
[0031] In a preferred embodiment, the data event density and the amount of computational restriction data are defined as input variables, and are divided into different fuzzy sets respectively;
[0032] Each historical period is defined as an output variable and divided into fuzzy sets;
[0033] Formulate fuzzy rules to describe the density of data events and calculate the impact of limiting the amount of data on various historical periods;
[0034] Fuzzy reasoning is performed based on fuzzy rules to determine each historical period.
[0035] In a preferred embodiment, the historical time periods marked as "High" are obtained, and their numerical values are collected and sorted in order from large to small. The first historical time period result is marked as the most characteristic historical time period and sent to the data screening module for calculation.
[0036] Technical effects and advantages of the present invention:
[0037] 1. The present invention classifies users through comprehensive analysis of user gene data and user average altitude, and then divides the historical data occurrence times and historical data upload speed of multiple categories according to user categories and user classification results. The important features of each data in each type of user are obtained through the LASSO regression model, and the data with characteristic coefficients reduced to zero are screened out based on them to ensure that the prediction result deviation is small and the system runs smoothly.
[0038] 2. The present invention formulates a set of fuzzy rules for fuzzy reasoning through comprehensive analysis of data event density and calculation of limited data volume, determines the most characteristic historical period, and divides the historical time span according to the calculation of limited data volume. It not only ensures that the system can collect the target parameters at one time, but also optimizes the parameters for verifying the importance of data, so that the parameters for calculating the importance of data can be further precise, which is convenient for alleviating the system memory pressure. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] Figure 1 The module diagram of the high altitude pulmonary edema early stage disease data collection system based on multi-gene mutation characteristics of the present invention. DETAILED DESCRIPTION
[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.
[0041] Based on siGCD: a network server is used to collect gene predictions to evaluate the possibility of early high-altitude pulmonary edema. When used in the research stage and scenarios requiring high-precision collection, the data that needs to be collected usually include but are not limited to genomic data, physiological parameters and environmental parameters; among them, genomic data includes the frequency of target gene mutations; physiological parameters include heart rate, blood oxygen saturation, respiratory rate, blood pressure and body temperature; environmental parameters include altitude, air pressure, ambient temperature and humidity, but obviously, not all scenarios can collect or use the above parameters. The selection of data has not been discussed, and it should be evaluated from the correlation, jump and difficulty of individual parameters. Therefore, a high-altitude pulmonary edema early disease data collection system based on multi-gene mutation characteristics is proposed;
[0042] Example 1, the present invention discloses a system for collecting early-stage high altitude pulmonary edema data based on multi-gene mutation characteristics, such as Figure 1 As shown, it includes a data acquisition module, a user differentiation module, a data screening module and an optimization matching module;
[0043] The data collection module is used to collect user gene data and user average altitude, and send them to the user differentiation module. It also collects the number of occurrences of historical data and the upload speed of historical data and sends them to the data screening module.
[0044] Among them, user genetic data refers to polygenic risk scores, which are used to estimate the overall impact of multiple gene variants in an individual's genome on a disease or specific trait. In the risk assessment of high-altitude pulmonary edema, the individual's genetic risk can be more accurately predicted by calculating PRS;
[0045] Step A1, after selecting the target gene associated with high altitude pulmonary edema, determine the mutation site of each target gene; perform gene sequencing on each user to obtain the gene fragment containing the target gene in the gene data;
[0046] Step A2: Obtain the risk effect value of each mutation site through large-scale population research; then calculate the contribution of each mutation site to the disease risk, usually expressed as a logarithmic odds ratio;
[0047] Step A3: For each mutation site, the risk score of a single mutation site is calculated based on the user's genotype and the corresponding weight, according to the following formula:
[0048] RiskScore i =β i ×G i
[0049] In the formula, β i is the weight of the ith mutation site, G i is the user’s genotype at the i-th mutation site, where i is the i-th mutation site;
[0050] Step A4: add the single gene risk scores of all mutation sites to obtain the polygenic risk score PRS, PRS = ∑ i β i ×G i ;
[0051] The average altitude of the user refers to the average altitude of the user at the time of measurement. It is understandable that the user may use the system multiple times. In this case, the average altitude can reduce the uncertainty caused by the larger value and can also intuitively express the altitude of the user for a long time. The formula is: Where k is the number of times the user uses it, k=1, 2, 3, 4...n; and n is the total number of times the user uses it;
[0052] The user differentiation module is used to receive user genetic data and user average altitude, establish PRS standardization processing to make it comparable between different individuals, and divide users into risk groups based on the results, and send the user division results to the data screening module;
[0053] In order to make the calculated PRS comparable among different individuals, it is standardized; the standardized PRS is combined with the average altitude of the user, and the formula is as follows:
[0054]
[0055] Where μ is the mean PRS of all individuals in the group, and σ is the standard deviation of PRS in the group;
[0056] The purpose of standardizing PRS is to eliminate the incomparability problem caused by different absolute values of genetic scores between different individuals. The standardized PRS represents the degree of deviation of the individual's PRS from the group mean (in units of standard deviation). For example, a standardized PRS of 1 means that the individual's PRS is one standard deviation higher than the group mean;
[0057] The comprehensive risk score is a comprehensive evaluation indicator that combines the standardized polygenic risk score and the user's average altitude. The calculation formula is as follows:
[0058]
[0059] In the formula, Rs t is the comprehensive risk score, α1 and α2 are the preset proportional coefficients of the standardized PRS and the average altitude of the user, and both α1 and α2 are greater than 0; where t represents the t-th user;
[0060] Furthermore, risk stratification is set based on the comprehensive risk score of each user, and the comprehensive risk score values are sorted from large to small. For low risk: Rs t The risk is defined as low if it is below the lower quartile (25%) of the population distribution; the risk is defined as high if it is between the middle two quartiles (25% to 75%) of the population distribution; and high if it is above the upper quartile (75%) of the population distribution;
[0061] It should be noted that the division of user risk levels can be adjusted according to actual conditions. For example, although the present embodiment defines user risk levels with three levels of risk, in fact, more than three levels of division can be performed based on the standardized PRS and the values of the average altitude of the user, so as to better filter out the data that needs to be screened out from each category of users;
[0062] The data screening module is used to obtain the user segmentation results and the most characteristic historical time periods, and divide the historical data occurrence times and historical data upload speeds into multiple categories according to the user segmentation results, and determine their importance in predicting the early risk of high-altitude pulmonary edema for various users through the LASSO regression model, obtain the retained data information, and send the importance of each data to the optimization matching module;
[0063] The user classification result value is preferably defined as x, where x represents the x-th user category, and the number of occurrences of historical data of x categories corresponding to the number of user categories and the historical data upload speed are obtained;
[0064] The logic of obtaining the number of occurrences of historical data refers to the number of occurrences of each historical data used to predict the early symptoms of high altitude pulmonary edema in the current classification category. The number of predicted data is set to y, where y represents the yth predicted data. The number of occurrences of each historical data is obtained through the built-in counter of the system.
[0065] The logic of obtaining the historical data upload speed refers to the upload speed of each historical data used to predict the early characteristics of high-altitude pulmonary edema in the current classification category. The faster the upload speed, the more attention the system will pay to the data size or the importance of the data, and the faster the system can collect the data. The historical data upload speed of each data can be obtained through the network monitoring tool.
[0066] Obtain the number of occurrences of historical data of multiple categories and the speed of historical data upload, and determine their importance in predicting the early risk of high-altitude pulmonary edema for various types of users through the LASSO regression model;
[0067] Step B1: construct a data set X containing the number of occurrences and upload speeds of historical data of each category and the response variable z. X is set as a feature matrix, including and
[0068] Step B2: Standardize the data to eliminate the impact of different dimensions: In the formula, μ j is the mean of the jth feature, σ j is the standard deviation of the jth feature;
[0069] Step B2, select the optimal λ value through cross-validation: λ * = arg min λ CV(λ), where CV(λ) is the cross-validation error, and the optimal value is the value with the minimum average validation error during the validation process;
[0070] Step B3, use the optimal λ value to train the LASSO regression model: In the formula, z p is the response variable of the pth sample, X' pj is the jth standardized characteristic variable of the pth sample, β0 is the intercept term, β jis the regression coefficient of the jth eigenvector;
[0071] Step B4: The LASSO regression model will reduce the coefficients of some features to zero, and select features with non-zero coefficients as important features. The important feature set F is: F = {j|β j ≠0}, filter out the data whose characteristic coefficient is reduced to zero, so as to ensure the accuracy of the prediction results and the smooth operation of the system;
[0072] The present invention classifies users through comprehensive analysis of user gene data and user average altitude, and then divides the historical data occurrence times and historical data upload speed of multiple categories into different categories according to the user categories and the user classification results, and obtains the important features of each data in each category of users through the LASSO regression model, and screens out data with characteristic coefficients reduced to zero based on them, so as to ensure that the prediction result deviation is small and the system runs smoothly.
[0073] Example 2
[0074] In Example 1 of the present invention, an example is given to illustrate the operation strategy of using LASSO regression model to screen out data with feature coefficients reduced to zero for important features of data in each category after dividing the user categories. However, in Example 1, all historical data are considered as the basis for evaluating data. Obviously, although this operation strategy can ensure the reliability of the data screening operation, in actual situations, the system cannot take into account all historical data. The most representative historical period should be selected for evaluation to avoid the situation where the system runs stuck. In view of the above problems, Example 2 of the present invention is further refined.
[0075] The optimization matching module is used to receive the importance of each data, obtain the data event density and calculate the limit data volume, and use fuzzy logic to determine the most characteristic historical period through comprehensive analysis, and send it to the data screening module;
[0076] The amount of data to be calculated is the maximum amount of data that the current system's computing power and storage capacity can bear at one time. In order to avoid system stalls due to processing too much data, the historical time span is divided according to the amount of data to be calculated at one time, that is, time period t, where t represents the tth time period. Time period t is the amount of data that can be calculated at one time. t changes with the changes of
[0077] It is understandable that the amount of data calculated at one time has a certain historical period. For example, if the amount of data calculated at one time is 25.6GB, and there are 64,000 data points in an average calculation day, then the data it contains is about 256,000 data points, and the historical time span is 4 days;
[0078] The data event density refers to the frequency of events that are consistent with the prediction of high altitude pulmonary edema in various types of data among various types of users. Time periods with high event density are usually more representative. The ratio of the number of events consistent with the prediction of high altitude pulmonary edema in time period t to time period t gives the data event density ρ t ;
[0079] Specifically, fuzzy logic is used to determine each historical period based on the density of data events and the amount of computationally limited data;
[0080] For example, "High", "Low", "Medium" for data event density, "Much", "Moderate", "Less" for computationally limited data volume;
[0081] Formulate a set of fuzzy rules to describe the impact of different input variables on output variables. The definition of rules can be based on professional knowledge or obtained through data analysis and experiments. For example:
[0082] The data event density is marked as X, the calculation limit data volume is marked as U, and each historical period is marked as C_results;
[0083] Then we can define:
[0084] Rule1:IF(XisHigh)AND(UisMuch)THEN(C_resultsisHigh)
[0085] Rule2:IF(UisLow)AND(UisLess)THEN(C_resultsisLow) ...
[0087] Specifically, fuzzy reasoning is performed based on fuzzy rules to determine the most characteristic historical period among various historical periods;
[0088] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, although this embodiment takes three fuzzy sets as examples, the data event density and the amount of computationally restricted data can actually be divided into more than three sets to facilitate better precise adjustment based on different similarities.
[0089] Furthermore, for the determination of the values of data event density and the amount of data to be calculated as high, medium or low, a threshold value may be set according to the actual situation for determination. For example, when the data event density exceeds 75% of the set threshold value, it is marked as "High", and when the amount of data to be calculated as being higher than 70% of the set threshold value, it is marked as "Much", etc., which will not be elaborated here.
[0090] Specifically, obtain the historical period marked as "High", collect its numerical values, sort them in order from large to small, mark the first historical period result as the most characteristic historical period and bring it into the parameter calculation in the data screening of Example 1 to accurately calculate the importance of the data;
[0091] The present invention formulates a set of fuzzy rules for fuzzy reasoning through comprehensive analysis of data event density and calculation of limited data volume, determines the most characteristic historical time period, and divides the historical time span according to the calculation of limited data volume. This not only ensures that the system can collect the target parameters at one time, but also optimizes the parameters for verifying the importance of data, making the parameters for calculating the importance of data more precise, thereby alleviating the system memory pressure.
[0092] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0093] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0094] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0095] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0097] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0098] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0099] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0100] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.
[0101] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. An early stage data collection system for high altitude pulmonary edema based on multi-gene mutation characteristics, characterized by: It includes data acquisition module, user differentiation module, data screening module and optimization matching module; signal connection between each module; The data collection module is used to collect user gene data and user average altitude, and send them to the user differentiation module. It also collects the number of occurrences of historical data and the upload speed of historical data and sends them to the data screening module. The user differentiation module is used to receive user genetic data and user average altitude, establish PRS standardization processing to make it comparable between different individuals, and divide users into risk groups based on the results, and send the user division results to the data screening module; The data screening module is used to obtain the user segmentation results and the most characteristic historical time periods, and divide the historical data occurrence times and historical data upload speeds into multiple categories according to the user segmentation results, and determine their importance in predicting the early risk of high-altitude pulmonary edema for various users through the LASSO regression model, obtain the retained data information, and send the importance of each data to the optimization matching module; The optimization matching module is used to receive the importance of each data, obtain the data event density and calculate the limit data volume, and use fuzzy logic to determine the most characteristic historical period through comprehensive analysis, and send it to the data screening module.
2. The high altitude pulmonary edema early stage disease data collection system based on multi-gene mutation characteristics according to claim 1 is characterized by: Obtain user gene data by calculating PRS; Step A1, after selecting the target gene associated with high altitude pulmonary edema, determine the mutation site of each target gene; perform gene sequencing on each user to obtain the gene fragment containing the target gene in the gene data; Step A2: Obtain the risk effect value of each mutation site through large-scale population research; then calculate the contribution of each mutation site to the disease risk, usually expressed as a logarithmic odds ratio; Step A3: For each mutation site, the risk score of a single mutation site is calculated based on the user's genotype and the corresponding weight, according to the following formula: Risk Score i =β i ×G i In the formula, β i is the weight of the ith mutation site, G i is the user’s genotype at the i-th mutation site, where i is the i-th mutation site; Step A4: add the single gene risk scores of all mutation sites to obtain the polygenic risk score PRS, PRS = ∑ i (β i ×G i ).
3. The high altitude pulmonary edema early stage disease data collection system based on multi-gene mutation characteristics according to claim 2 is characterized by: The average altitude of the user is obtained by averaging the altitudes at which the user is measuring.
4. The high altitude pulmonary edema early stage disease data collection system based on multi-gene mutation characteristics according to claim 3 is characterized by: The comprehensive risk score is a comprehensive evaluation indicator that combines the standardized polygenic risk score and the user's average altitude. The calculation formula is as follows: In the formula, Rs t is the comprehensive risk score, α1 and α2 are the preset proportional coefficients of the standardized PRS and the average altitude of the user, and both α1 and α2 are greater than 0; where t represents the t-th user; Risk stratification is set based on the comprehensive risk score of each user. After sorting the comprehensive risk score values from large to small, the user risk level is defined.
5. The high altitude pulmonary edema early stage disease data collection system based on multi-gene mutation characteristics according to claim 4 is characterized by: The user classification result value is defined as x, where x represents the xth user category; the number of occurrences of the early symptoms of high altitude pulmonary edema in users is obtained by using various historical data to predict the occurrence of the early symptoms of high altitude pulmonary edema in users. Get the historical data upload speed of each data through the network monitoring tool 6. The high altitude pulmonary edema early stage disease data collection system based on multi-gene mutation characteristics according to claim 5 is characterized by: Obtain the number of occurrences of historical data of multiple categories and the speed of historical data upload, and determine their importance in predicting the early risk of high-altitude pulmonary edema for various types of users through the LASS0 regression model; Step B1: construct a data set X containing the number of occurrences and upload speeds of historical data of each category and the response variable z. X is set as a feature matrix, including and Step B2: Standardize the data to eliminate the impact of different dimensions: In the formula, μ j is the mean of the jth feature, σ j is the standard deviation of the jth feature; Step B2, select the optimal λ value through cross-validation: λ * =argmin λ CV(λ), where CV(λ) is the cross-validation error, and the optimal value is the value with the minimum average validation error during the validation process; Step B3, use the optimal λ value to train the LASSO regression model: In the formula, z p is the response variable of the pth sample, X′ pj is the jth standardized characteristic variable of the pth sample, β0 is the intercept term, β j is the regression coefficient of the jth eigenvector; Step B4: The LASSO regression model will reduce the coefficients of some features to zero, and select features with non-zero coefficients as important features. The important feature set F is: F = {j|β j ≠0}, filter out the data whose characteristic coefficients are reduced to zero.
7. The high altitude pulmonary edema early stage disease data collection system based on multi-gene mutation characteristics according to claim 1 is characterized by: The computational limit data volume Qu is obtained by using the current system's computing power and storage capacity to bear the maximum amount of computational data at one time. t ; where t represents the tth time period, and the data event density ρ is obtained by the frequency of events that are consistent with the prediction of high altitude pulmonary edema in various types of data among various types of users t .
8. The high altitude pulmonary edema early stage disease data collection system based on multi-gene mutation characteristics according to claim 7 is characterized by: The data event density and the amount of computational limit data are defined as input variables, and they are divided into different fuzzy sets respectively; Each historical period is defined as an output variable and divided into fuzzy sets; Formulate fuzzy rules to describe the density of data events and calculate the impact of limiting the amount of data on various historical periods; Fuzzy reasoning is performed based on fuzzy rules to determine each historical period.
9. The high altitude pulmonary edema early stage disease data collection system based on multi-gene mutation characteristics according to claim 8, characterized in that: Get the historical period marked as "High", collect its numerical values, sort them in order from large to small, mark the first historical period result as the most characteristic historical period and send it to the data screening module for calculation.
Citation Information
Patent Citations
Risk event early screening system and method
CN109978396A
Plateau pulmonary edema disease risk self-assessment method and system
CN117153406A
Use Of Historic And Contemporary Tracking Data To Improve Healthcare Facility Operations
US20190304596A1
