Acute altitude stress early disease risk prediction method based on polygene mutation characteristics
Through data collection and model construction based on multigene mutation characteristics, combined with data characteristics of different age groups, the problem of low prediction accuracy of early risk of acute altitude sickness in the existing technology is solved, and accurate prediction of the risk of acute altitude sickness and Early intervention significantly improves the accuracy and reliability of predictions.
Patent Information
- Application Number
- CN202410940180.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-15
- Publication Date
- 2024-11-08
AI Technical Summary
The existing early risk prediction methods for acute altitude sickness rely on clinical symptoms and individual medical history, lack early prediction methods, and the prediction methods based on gene characteristics do not fully consider the characteristics of multigene mutations, resulting in low prediction accuracy.
Through data collection, model construction and optimization, an acute altitude sickness risk prediction model is constructed based on multi-gene mutation characteristics, and a systematic data processing is carried out using gene sequencing data, blood, oral swabs and saliva samples, combined with data characteristics of different age groups. and multi-stage calculations, generating predicted values and optimizing.
Accurate prediction of the risk of acute altitude sickness has been achieved, significantly improving the accuracy and reliability of the prediction, and can promptly intervene in high-risk groups, reduce the incidence of disease, and improve patients' health and quality of life.
Smart Images

Figure CN118919072A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical detection technology, and in particular to a method for predicting the early risk of acute altitude sickness based on multi-gene mutation characteristics. Background Art
[0002] Genomics is a broad and important field in biology, which mainly studies the genome and function of organisms. With the development of technology, genomic research has gradually become more detailed and formed a number of specific branches. Among them, medical genomics is an important direction. It provides a scientific basis for the diagnosis, prevention and treatment of diseases by studying the relationship between genes and diseases. In medical genomics, disease risk prediction based on multi-gene mutation characteristics has become a hot topic of research, especially for complex diseases such as acute mountain sickness, the study of prediction methods is particularly important.
[0003] At present, the early risk prediction method for acute mountain sickness mainly relies on clinical symptoms and individual medical history, which has significant limitations. Since the symptoms of acute mountain sickness often appear after arriving in the plateau area, the lack of early prediction means leads to many high-risk individuals entering the plateau environment without adequate preparation, increasing the risk of disease. At the same time, the existing prediction methods based on gene characteristics have not fully considered the comprehensive impact of multi-gene mutation characteristics, resulting in low prediction accuracy and difficulty in widespread application in practice. Summary of the invention
[0004] 1. Technical issues to be resolved
[0005] In view of the deficiencies in the prior art, the present invention provides a method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics, which solves the problems mentioned in the above background technology.
[0006] (II) Technical solution
[0007] To achieve the above objectives, the present invention is implemented by the following technical scheme: a method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics, characterized in that: the specific steps are as follows;
[0008] S1. Data collection: Collect genetic data and related phenotypic data from the target population, including gene sequencing data and personal health data, pre-process and screen the collected genetic data, and extract multi-gene mutation characteristics related to acute mountain sickness;
[0009] S2. Establish a training model to construct an acute mountain sickness risk prediction model based on the selected gene features, and use historical data for training and validation;
[0010] S3, model optimization, evaluate the trained model, use multiple indicators to measure model performance, and optimize based on the evaluation results;
[0011] S4. Put the model online for practical use.
[0012] Preferably, in step S1, the specific data collection steps are as follows:
[0013] S1.1. Determine the target population for data collection and collect genetic samples from the target population, including blood samples, oral swab samples, and saliva samples;
[0014] S1.2. Record relevant phenotypic data of the target, including gender and age.
[0015] Preferably, in step S1.1;
[0016] Blood samples include: red blood cell count, hemoglobin concentration, white blood cell count, and blood sugar level;
[0017] Oral swab samples included: DNA purity, genotype, microbial diversity index, and gene expression levels;
[0018] Saliva samples included: cortisol levels, total protein concentration, salivary pH, and amylase activity.
[0019] Preferably, in step S2, the specific model building method is as follows:
[0020] S2.1. Divide the pre-processed blood samples, oral swab samples and saliva samples into a first data set and a second data set according to the age of 18-25 and 26-55 years;
[0021] S2.2, integrating and calculating the first data set and the second data set to generate a first stage value, a second stage value, and a third stage value;
[0022] S2.3. Calculate the first stage value, the second stage value and the third stage value to generate a predicted value.
[0023] Preferably, in step S2.1, the first data set is data for the age group of 18-25 years old, specifically including: a first red blood cell count HXB1, a first hemoglobin concentration DNB1, a first white blood cell count BXB1, a first blood glucose level XTP1, a first DNA purity DNC1, a first genotype JYX1, a first microbial diversity index DYX1, a first gene expression level BDP1, a first cortisol level PZC1, a first total protein concentration ZDB1, a first saliva pH TYP1 and a first amylase activity DFM1;
[0024] The second data set is data for the age group of 26-55 years old, specifically including: a second red blood cell count HXB2, a second hemoglobin concentration DNB2, a second white blood cell count BXB2, a second blood glucose level XTP2, a second DNA purity DNC2, a second genotype JYX2, a second microbial diversity index DYX2, a second gene expression level BDP2, a second cortisol level PZC2, a second total protein concentration ZDB2, a second saliva pH TYP2 and a second amylase activity DFM2.
[0025] Preferably, the specific calculation method of the first stage value G1 is as follows:
[0026]
[0027] In the formula: A is the reference function, and 1 or 2 is selectively filled in to represent male parameters or female parameters, log is the logarithmic function, e is the base function, a1, a2, a3 and a4 are weight values, and the values of a1, a2, a3 and a4 are adjusted and set by the user, Gd1 is the data of the 18-25 age group, Gg1 is the data of the 26-55 age group, HXB1 is the first red blood cell count, DNB1 is the first hemoglobin concentration, BXB1 is the first white blood cell count, XTP1 is the first blood glucose level, HXB2 is the second red blood cell count, DNB2 is the second hemoglobin concentration, BXB2 is the second white blood cell count, and XTP2 is the second blood glucose level.
[0028] Preferably, the specific calculation method of the second stage value G2 is as follows:
[0029]
[0030]
[0031] Wherein: A is the reference function, 1 or 2 is selectively filled in to represent male parameters or female parameters, log is the logarithmic function, e is the base function, Gd2 is the data of the 18-25 age group, Gg2 is the data of the 26-55 age group, b1, b2, b3 and b4 are weight values, and the values of b1, b2, b3 and b4 are adjusted and set by the user, DNC1 is the first DNA purity, JYX1 is the first genotype, DYX1 is the first microbial diversity index, BDP1 is the first gene expression level, DNC2 is the second DNA purity, JYX2 is the second genotype, DYX2 is the second microbial diversity index, and BDP2 is the second gene expression level.
[0032] Preferably, the specific calculation method of the third stage value G3 is as follows:
[0033]
[0034] In the formula: A is the reference function, and 1 or 2 is optionally filled in to represent male parameters or female parameters, log is the logarithmic function, e is the base function, Gd2 is the data of the 18-25 age group, Gg2 is the data of the 26-55 age group, c1, c2, c3 and c4 are weight values, and the values of c1, c2, c3 and c4 are adjusted and set by the user, PZC1 is the first cortisol level, ZDB1 is the first total protein concentration, TYP1 is the first saliva pH, DFM1 is the first amylase activity, PZC2 is the second cortisol level, ZDB2 is the second total protein concentration, TYP2 is the second saliva pH, and DFM2 is the second amylase activity.
[0035] Preferably, the specific calculation method of the third stage value G3 is as follows:
[0036]
[0037] In the formula: A is the reference function, and 1 or 2 is optionally filled in to represent male parameters or female parameters, log is the logarithmic function, e is the base function, Gd2 is the data of the 18-25 age group, Gg2 is the data of the 26-55 age group, c1, c2, c3 and c4 are weight values, and the values of c1, c2, c3 and c4 are adjusted and set by the user, PZC1 is the first cortisol level, ZDB1 is the first total protein concentration, TYP1 is the first saliva pH, DFM1 is the first amylase activity, PZC2 is the second cortisol level, ZDB2 is the second total protein concentration, TYP2 is the second saliva pH, and DFM2 is the second amylase activity.
[0038] Preferably, the predicted value is calculated by the following formula:
[0039]
[0040] In the formula: d1, d2 and d3 are weight values respectively, G1 is the first stage value, G2 is the second stage value, G3 is the third stage value, e is the base function, and ln is the logarithmic function.
[0041] Preferably, in step S3, the predicted value is compared with a preset first threshold value Y to generate a comparison result, and the comparison result is compared with the hospital diagnosis result to determine whether the comparison result is successful. If it is unsuccessful, the operation is optimized. The comparison result is as follows;
[0042] When YCZ≤Y×95%, it means that the current prediction result is that there will be no altitude sickness;
[0043] When YCZ>Y×95%, it means that the current prediction result is that there will be altitude sickness;
[0044] YCZ is the predicted value, and Y is the first threshold.
[0045] (III) Beneficial effects
[0046] The present invention provides a method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics. It has the following beneficial effects:
[0047] (1) This method is based on the characteristics of multiple gene mutations to predict the early risk of acute mountain sickness. This method is based on the characteristics of multiple gene mutations. Through systematic data collection, scientific model construction, strict evaluation and optimization, and practical clinical application, it can accurately predict the risk of acute mountain sickness. Compared with existing technical means, this method has significantly improved the comprehensiveness of data processing, the scientific nature of model construction, and the accuracy of prediction results. Accurate risk prediction enables medical institutions to intervene in high-risk groups in a timely manner, significantly reduce the incidence of acute mountain sickness, and improve patients' health level and quality of life.
[0048] (2) This method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics can more comprehensively assess the risk of an individual's disease by carefully considering the data of different age groups and different sample characteristics, and combining the calculation results of each stage, providing a more accurate basis for clinical diagnosis and treatment. At the same time, users can adjust the weight value according to the specific situation, making the model more flexible and applicable, which can better adapt to the characteristics of different individuals and improve the accuracy and reliability of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] Figure 1 It is a schematic diagram of the steps of the method of the present invention. DETAILED DESCRIPTION
[0050] 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.
[0051] Example 1
[0052] See also Figure 1 , a method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics, the specific steps are as follows;
[0053] S1. Data collection: Collect genetic data and related phenotypic data from the target population, including gene sequencing data and personal health data, pre-process and screen the collected genetic data, and extract multi-gene mutation characteristics related to acute mountain sickness;
[0054] S2. Establish a training model to construct an acute mountain sickness risk prediction model based on the selected gene features, and use historical data for training and validation;
[0055] S3, model optimization, evaluate the trained model, use multiple indicators to measure model performance, and optimize based on the evaluation results;
[0056] S4. Put the model online for practical use.
[0057] In this embodiment: In step S1, by collecting genetic data and related phenotypic data from the target population, including gene sequencing data and personal health data, the collected genetic data is preprocessed and screened to extract polygenic mutation features associated with acute altitude sickness. This step ensures the accuracy and completeness of the data and provides reliable basic data for the construction of subsequent models. Systematic data collection and processing effectively captures and analyzes key gene variations associated with altitude sickness, greatly improving the prediction accuracy of the model.
[0058] In step S2, an acute mountain sickness risk prediction model is constructed based on the selected gene features, and historical data is used for training and verification. The model is trained using historical case data through a machine learning algorithm, so that the model can identify high-risk groups. This stage achieves accurate analysis of individual genetic characteristics and significantly improves the early prediction ability of acute mountain sickness. The trained model can accurately assess individual disease risks in practical applications and provide strong support for clinical intervention.
[0059] In step S3, the trained model is comprehensively evaluated, and the model performance is measured using a variety of indicators, and optimized based on the evaluation results. Through cross-validation, confusion matrix, and ROC curve evaluation methods, the advantages and disadvantages of the model are fully understood, and adjustments and improvements are made to the deficiencies. The optimized model not only significantly improves the prediction accuracy, but also excels in robustness and stability. This step ensures the applicability of the model in different populations and improves the reliability of the prediction results.
[0060] In step S4, the acute mountain sickness risk prediction model, which has been rigorously evaluated and optimized, is applied in actual clinical practice. The model can identify high-risk individuals in a timely manner, helping medical institutions to conduct early intervention and personalized treatment. The model performed well in clinical practice after it was launched, significantly reducing the incidence of acute mountain sickness and improving the quality of life of patients. Through practical applications, the effectiveness of the model in different environments and populations has been verified, laying a solid foundation for subsequent large-scale promotion and application.
[0061] This method is based on the characteristics of multi-gene mutations, and through systematic data collection, scientific model construction, strict evaluation and optimization, and practical clinical application, it has achieved accurate prediction of the risk of acute mountain sickness. Compared with existing technical means, this method has significantly improved the comprehensiveness of data processing, the scientific nature of model construction, and the accuracy of prediction results. Accurate risk prediction enables medical institutions to intervene in high-risk groups in a timely manner, significantly reduce the incidence of acute mountain sickness, and improve patients' health level and quality of life.
[0062] Example 2
[0063] See also Figure 1 In step S1, the specific data collection steps are as follows:
[0064] S1.1. Determine the target population for data collection and collect genetic samples from the target population, including blood samples, oral swab samples, and saliva samples;
[0065] S1.2. Record relevant phenotypic data of the target, including gender and age.
[0066] In this embodiment: In step S1.1, the steps of determining the target population and collecting blood samples, oral swab samples, and saliva samples ensure the systematic and representative nature of data collection. By clarifying the target population, researchers can concentrate resources to obtain sample data with high relevance. This method not only increases the diversity of the data, but also more accurately reflects the actual occurrence of acute altitude sickness in the target population. Specifically, blood samples provide physiological data related to blood components, such as red blood cell counts and blood sugar levels; oral swab samples provide genetic and microbial diversity information; and saliva samples provide indicators related to stress response and metabolism, such as cortisol levels and saliva pH. Through diversified sample collection, the comprehensiveness and multidimensionality of the data are ensured, providing a solid foundation for subsequent analysis and modeling.
[0067] In step S1.2, recording the phenotypic data (including gender and age) of the target population is an indispensable part of the data collection process. These phenotypic data provide key background information for individualized risk prediction. For example, gender and age are important factors affecting the occurrence of acute mountain sickness. By recording these data, different groups can be stratified and analyzed to improve the accuracy and pertinence of the prediction model. This step not only completes the supplement of basic data, but also provides the necessary individual difference information for subsequent model training and optimization. By combining phenotypic data with genetic sample data, we can more comprehensively understand the impact of individual differences on acute mountain sickness, thereby enhancing the practical application value of the prediction model.
[0068] This method significantly improves the integrity and multidimensionality of the data compared to existing technical means by systematically collecting multiple biological samples and recording key phenotypic data. Current technical means often focus on a single data source or lack comprehensive consideration of individual differences, resulting in low accuracy and reliability of prediction results. The new method has improved the systematicity, diversity, and representativeness of data collection, so that the prediction model can more accurately reflect the actual situation. In addition, by combining phenotypic data and genetic sample data, this method not only improves the individualized prediction ability of the model, but also provides a rich data foundation for further research on the mechanism of acute altitude sickness. These improvements effectively improve the accuracy and reliability of the prediction, thereby enhancing the scientificity and practicality of disease prevention and health management.
[0069] Example 3
[0070] See also Figure 1 , in step S1.1;
[0071] Blood samples include: red blood cell count, hemoglobin concentration, white blood cell count, and blood sugar level;
[0072] Oral swab samples included: DNA purity, genotype, microbial diversity index, and gene expression levels;
[0073] Saliva samples included: cortisol levels, total protein concentration, salivary pH, and amylase activity.
[0074] In this embodiment: through the comprehensive analysis of multiple biological samples and key biological indicators, the model can more comprehensively and accurately reflect the physiological state of individuals in a plateau environment, thereby improving the prediction accuracy of acute mountain sickness. Combining multiple indicators of blood, oral swabs and saliva samples, the model can perform more refined individualized risk assessments, taking into account the physiological and genetic differences of different individuals, and improving the individualized accuracy of prediction results. Multiple biological samples provide a comprehensive data basis, enabling the model to analyze the risk factors of acute mountain sickness from multiple dimensions, thereby gaining a deeper understanding of the mechanism of the disease and supporting subsequent scientific research and the formulation of health management strategies. Compared with traditional methods, this method has been improved in terms of the systematicity, diversity and representativeness of data collection, so that the prediction model can more accurately reflect the actual situation and improve the scientificity and practicality of the technical means.
[0075] Example 4
[0076] See also Figure 1 In step S2, the specific model building method is as follows:
[0077] S2.1. Divide the pre-processed blood samples, oral swab samples and saliva samples into a first data set and a second data set according to the age of 18-25 and 26-55 years;
[0078] S2.2, integrating and calculating the first data set and the second data set to generate a first stage value, a second stage value, and a third stage value;
[0079] S2.3. Calculate the first stage value, the second stage value and the third stage value to generate a predicted value.
[0080] In this embodiment: in step S2.1, the pre-processed blood samples, oral swab samples and saliva samples are divided into a first data set and a second data set according to different age groups (18-25 years old and 26-55 years old).
[0081] In step S2.2, the first data set and the second data set are integrated and calculated to generate first-stage values, second-stage values, and third-stage values, which reflect the characteristics of individuals of different age groups in terms of the early risk of acute mountain sickness.
[0082] In step S2.3, the first stage value, the second stage value, and the third stage value are integrated and calculated to generate a final prediction value, which is used to evaluate the probability of an individual's risk of early acute mountain sickness.
[0083] By dividing the data set according to age groups, we can more accurately consider the physiological characteristics and genetic mutations of individuals in different age groups, improve the individualization and accuracy of the prediction model, and integrate the calculation of the characteristic values of different samples to more comprehensively reflect the status of individuals at different biological levels, thereby increasing the comprehensiveness and explanatory power of the model. By comprehensively considering the characteristic values of different stages and generating the final prediction value, we can more accurately assess the probability of an individual's early risk of acute mountain sickness, thereby improving the accuracy and practicality of the prediction model.
[0084] Example 5
[0085] See also Figure 1 , in step S2.1, the first data set is data of the age group of 18-25 years old, specifically including: a first red blood cell count HXB1, a first hemoglobin concentration DNB1, a first white blood cell count BXB1, a first blood glucose level XTP1, a first DNA purity DNC1, a first genotype JYX1, a first microbial diversity index DYX1, a first gene expression level BDP1, a first cortisol level PZC1, a first total protein concentration ZDB1, a first saliva pH TYP1 and a first amylase activity DFM1;
[0086] The second data set is data for the age group of 26-55 years old, specifically including: a second red blood cell count HXB2, a second hemoglobin concentration DNB2, a second white blood cell count BXB2, a second blood glucose level XTP2, a second DNA purity DNC2, a second genotype JYX2, a second microbial diversity index DYX2, a second gene expression level BDP2, a second cortisol level PZC2, a second total protein concentration ZDB2, a second saliva pH TYP2 and a second amylase activity DFM2.
[0087] In this embodiment, the method for predicting the early risk of acute mountain sickness based on the characteristics of multiple gene mutations, in terms of data collection, carefully divides the data sets of different age groups and combines the characteristic parameters of multiple samples, and more comprehensively considers the characteristics of individuals at different biological levels. This approach makes the model more targeted and individualized, and can more accurately assess the probability of early risk of acute mountain sickness in individuals of different age groups, providing a more reliable basis for early intervention and treatment.
[0088] Example 5
[0089] See also Figure 1 , the specific calculation method of the first stage value G1 is as follows:
[0090]
[0091] In the formula: A is the reference function, and 1 or 2 is selectively filled in to represent male parameters or female parameters, log is the logarithmic function, e is the base function, a1, a2, a3 and a4 are weight values, and the values of a1, a2, a3 and a4 are adjusted and set by the user, Gd1 is the data of the 18-25 age group, Gg1 is the data of the 26-55 age group, HXB1 is the first red blood cell count, DNB1 is the first hemoglobin concentration, BXB1 is the first white blood cell count, XTP1 is the first blood glucose level, HXB2 is the second red blood cell count, DNB2 is the second hemoglobin concentration, BXB2 is the second white blood cell count, and XTP2 is the second blood glucose level.
[0092] The specific calculation method of the second stage value G2 is as follows:
[0093]
[0094]
[0095] Wherein: A is the reference function, 1 or 2 is selectively filled in to represent male parameters or female parameters, log is the logarithmic function, e is the base function, Gd2 is the data of the 18-25 age group, Gg2 is the data of the 26-55 age group, b1, b2, b3 and b4 are weight values, and the values of b1, b2, b3 and b4 are adjusted and set by the user, DNC1 is the first DNA purity, JYX1 is the first genotype, DYX1 is the first microbial diversity index, BDP1 is the first gene expression level, DNC2 is the second DNA purity, JYX2 is the second genotype, DYX2 is the second microbial diversity index, and BDP2 is the second gene expression level.
[0096] The specific calculation method of the third stage value G3 is as follows:
[0097]
[0098] In the formula: A is the reference function, and 1 or 2 is optionally filled in to represent male parameters or female parameters, log is the logarithmic function, e is the base function, Gd2 is the data of the 18-25 age group, Gg2 is the data of the 26-55 age group, c1, c2, c3 and c4 are weight values, and the values of c1, c2, c3 and c4 are adjusted and set by the user, PZC1 is the first cortisol level, ZDB1 is the first total protein concentration, TYP1 is the first saliva pH, DFM1 is the first amylase activity, PZC2 is the second cortisol level, ZDB2 is the second total protein concentration, TYP2 is the second saliva pH, and DFM2 is the second amylase activity.
[0099] The predicted value is calculated using the following formula:
[0100]
[0101] In the formula: d1, d2 and d3 are weight values respectively, G1 is the first stage value, G2 is the second stage value, G3 is the third stage value, e is the base function, and ln is the logarithmic function.
[0102] In this embodiment: In the process of establishing a specific model, this method adopts a multi-stage data processing and calculation method, including the calculation of the first stage value G1, the second stage value G2 and the third stage value G3. This method comprehensively considers the data characteristics of different stages and combines the calculation results of each stage to more accurately assess the risk probability of an individual, providing more targeted guidance for early intervention and treatment.
[0103] The calculation of the first-stage value G1 involves data from the 18-25 and 26-55 age groups, including indicators such as red blood cell count, hemoglobin concentration, white blood cell count, and blood sugar level, and a comprehensive value is obtained through comprehensive calculation. The calculation methods of the second-stage value G2 and the third-stage value G3 are similar, taking into account data from different age groups and different sample types, and calculating the comprehensive value through integration. Finally, the predicted value YCZ is calculated by comprehensively considering the weights of the values of each stage to obtain the final prediction result.
[0104] This method can more comprehensively assess the risk of an individual's disease by carefully considering data from different age groups and different sample characteristics, and combining the calculation results of each stage, providing a more accurate basis for clinical diagnosis and treatment. At the same time, users can adjust the weight value according to specific circumstances, making the model more flexible and applicable, better adapting to the characteristics of different individuals, and improving the accuracy and reliability of predictions.
[0105] Example 5
[0106] See also Figure 1 In step S3, the predicted value is compared with the preset first threshold value Y to generate a comparison result, and the comparison result is compared with the hospital diagnosis result to determine whether the comparison result is successful. If it is unsuccessful, the operation is optimized. The comparison results are as follows;
[0107] When YCZ≤Y×95%, it means that the current prediction result is that there will be no altitude sickness;
[0108] When YCZ>Y×95%, it means that the current prediction result is that there will be altitude sickness;
[0109] YCZ is the predicted value, and Y is the first threshold.
[0110] In this embodiment: This method can judge the accuracy and success rate of the prediction result by comparing the predicted value with the preset first threshold value Y, and comparing the comparison result with the hospital diagnosis result. If the comparison result is unsuccessful, the operation is optimized to improve the accuracy and reliability of the prediction result. Through the accurate judgment of the comparison result, the individual's altitude sickness risk can be more accurately predicted, providing doctors with more targeted diagnosis and treatment plans. At the same time, by optimizing the operation, the efficiency and accuracy of the prediction model can be further improved, providing a more reliable auxiliary decision-making basis for clinical work.
[0111] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics, characterized by: The specific steps are as follows; S1. Data collection: Collect genetic data and related phenotypic data from the target population, including gene sequencing data and personal health data, pre-process and screen the collected genetic data, and extract multi-gene mutation characteristics related to acute mountain sickness; S2. Establish a training model to construct an acute mountain sickness risk prediction model based on the selected gene features, and use historical data for training and validation; S3, model optimization, evaluate the trained model, use multiple indicators to measure model performance, and optimize based on the evaluation results; S4. Put the model online for practical use.
2. The method for predicting the early risk of acute mountain sickness based on polygenic mutation characteristics according to claim 1, characterized in that: In step S1, the specific data collection steps are as follows: S1.
1. Determine the target population for data collection and collect genetic samples from the target population, including blood samples, oral swab samples, and saliva samples; S1.
2. Record relevant phenotypic data of the target, including gender and age.
3. The method for predicting the early risk of acute mountain sickness based on polygenic mutation characteristics according to claim 2, characterized in that: In step S1.1; Blood samples include: red blood cell count, hemoglobin concentration, white blood cell count, and blood sugar level; Oral swab samples included: DNA purity, genotype, microbial diversity index, and gene expression levels; Saliva samples included: cortisol levels, total protein concentration, salivary pH, and amylase activity.
4. The method for predicting the early risk of acute mountain sickness based on polygenic mutation characteristics according to claim 3, characterized in that: In step S2, the specific model building method is as follows: S2.
1. Divide the pre-processed blood samples, oral swab samples and saliva samples into a first data set and a second data set according to the age of 18-25 and 26-55 years; S2.2, integrating and calculating the first data set and the second data set to generate a first stage value, a second stage value, and a third stage value; S2.
3. Calculate the first stage value, the second stage value and the third stage value to generate a predicted value.
5. The method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics according to claim 4, characterized in that: In step S2.1, the first data set is data for the age group of 18-25 years old, specifically including: a first red blood cell count HXB1, a first hemoglobin concentration DNB1, a first white blood cell count BXB1, a first blood glucose level XTP1, a first DNA purity DNC1, a first genotype JYX1, a first microbial diversity index DYX1, a first gene expression level BDP1, a first cortisol level PZC1, a first total protein concentration ZDB1, a first saliva pH TYP1, and a first amylase activity DFM1; The second data set is data for the age group of 26-55 years old, specifically including: a second red blood cell count HXB2, a second hemoglobin concentration DNB2, a second white blood cell count BXB2, a second blood glucose level XTP2, a second DNA purity DNC2, a second genotype JYX2, a second microbial diversity index DYX2, a second gene expression level BDP2, a second cortisol level PZC2, a second total protein concentration ZDB2, a second saliva pH TYP2 and a second amylase activity DFM2.
6. The method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics according to claim 5, characterized in that: The specific calculation method of the first stage value G1 is as follows: In the formula: A is the reference function, and 1 or 2 is optionally filled in to represent male parameters or female parameters, log is the logarithmic function, e is the base function, a1, a2, a3 and a4 are weight values, and the values of a1, a2, a3 and a4 are adjusted and set by the user, Gd1 is the data of the 18-25 age group, Gg1 is the data of the 26-55 age group, HXB1 is the first red blood cell count, DNB1 is the first hemoglobin concentration, BXB1 is the first white blood cell count, XTP1 is the first blood glucose level, HXB2 is the second red blood cell count, DNB2 is the second hemoglobin concentration, BXB2 is the second white blood cell count, and XTP2 is the second blood glucose level.
7. The method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics according to claim 6, characterized in that: The specific calculation method of the second stage value G2 is as follows: Wherein: A is the reference function, 1 or 2 is selectively filled in to represent male parameters or female parameters, log is the logarithmic function, e is the base function, Gd2 is the data of the 18-25 age group, Gg2 is the data of the 26-55 age group, b1, b2, b3 and b4 are weight values, and the values of b1, b2, b3 and b4 are adjusted and set by the user, DNC1 is the first DNA purity, JYX1 is the first genotype, DYX1 is the first microbial diversity index, BDP1 is the first gene expression level, DNC2 is the second DNA purity, JYX2 is the second genotype, DYX2 is the second microbial diversity index, and BDP2 is the second gene expression level.
8. The method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics according to claim 7, characterized in that: The specific calculation method of the third stage value G3 is as follows: In the formula: A is the reference function, and 1 or 2 is optionally filled in to represent male parameters or female parameters, log is the logarithmic function, e is the base function, Gd2 is the data of the 18-25 age group, Gg2 is the data of the 26-55 age group, c1, c2, c3 and c4 are weight values, and the values of c1, c2, c3 and c4 are adjusted and set by the user, PZC1 is the first cortisol level, ZDB1 is the first total protein concentration, TYP1 is the first saliva pH, DFM1 is the first amylase activity, PZC2 is the second cortisol level, ZDB2 is the second total protein concentration, TYP2 is the second saliva pH, and DFM2 is the second amylase activity.
9. The method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics according to claim 8, characterized in that: The predicted value is calculated using the following formula: In the formula: d1, d2 and d3 are weight values respectively, G1 is the first stage value, G2 is the second stage value, G3 is the third stage value, e is the base function, and ln is the logarithmic function.
10. The method for predicting the early risk of acute mountain sickness based on multi-gene mutation characteristics according to claim 9, characterized in that: In step S3, the predicted value is compared with the preset first threshold value Y to generate a comparison result, and the comparison result is compared with the hospital diagnosis result to determine whether the comparison result is successful. If it is unsuccessful, the operation is optimized. The comparison result is as follows; When YCZ≤Y×95%, it means that the current prediction result is that there will be no altitude sickness; When YCZ>Y×95%, it means that the current prediction result is that there will be altitude sickness; YCZ is the predicted value, and Y is the first threshold.
