Method and system for predicting progress of rheumatoid arthritis joint destruction by immune repertoire

Abstract

The invention relates to the technical field of biomedicine, in particular to a method and system for predicting the progress of rheumatoid arthritis joint destruction by an immune repertoire, and the method comprises the following steps: collecting cell activity data in the immune repertoire of a rheumatoid arthritis patient, carrying out time point alignment, standardizing time sequence data, and obtaining standardized time sequence data. According to the method, through dynamic network simulation, pathological reaction path selection is further optimized, the simulation capability of potential clinical results is enhanced, more accurate recovery suggestions are provided for patients, real-time clinical data and trend analysis of key indexes are integrated, and real-time adjustment of a joint destruction progress prediction model is allowed; the adaptability and the application range of the joint destruction progress prediction model are improved, the flexibility of the joint destruction progress prediction model is enhanced through the refined and dynamic processing logic, the effect of the recovery suggestion is also improved, and the recovery reliability and the life quality of a patient are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of biomedical technology, in particular to a method and system for predicting the progression of joint destruction in rheumatoid arthritis by immune repertoire. Background Art

[0002] The field of biomedical technology encompasses interdisciplinary subjects of biology, medicine, and engineering, aiming to study and solve various biological and medical problems through scientific methods and engineering techniques. The core content of this technical field covers a wide range of technologies from molecular biology to clinical applications, including biomaterials, biomechanics, bioinformatics, physiological measurement techniques, and medical imaging, etc. The development of biomedical technology promotes the emergence of disease prevention measures and has an important impact on improving the accuracy of disease diagnosis and the effect of recovery.

[0003] Among them, immune repertoire refers to the technology of identifying disease-related immune markers by collecting and analyzing the immune cell repertoire of an individual, including using immune repertoire to predict the progression of joint destruction in rheumatoid arthritis. By analyzing the specific composition and activities of a patient's immune cells, a model is established to predict the probability of disease progression. Mainly by means of biological specimen collection, immune cell analysis, and data modeling, through quantitative and functional analysis of immune cells, to judge the activity of rheumatoid arthritis and the estimated progression of joint destruction.

[0004] Existing technologies usually lack the ability to dynamically simulate complex pathological processes and the flexibility to adjust real-time data in actual operation. This results in that when dealing with rapidly changing clinical situations, the joint destruction progression prediction model cannot accurately reflect the real-time progression of the disease condition, affecting the timely adjustment and optimization of the recovery plan. Traditional methods cannot effectively predict complex immune responses and joint destruction processes without integrating dynamic network simulation and genetic algorithms to optimize the pathological reaction path. This limitation leads to insufficient prediction, further affecting the patient recovery efficiency and cost. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, such as the lack of the ability to dynamically simulate complex pathological processes and the flexibility to adjust real-time data, which results in that when dealing with rapidly changing clinical situations, the joint destruction progression prediction model cannot accurately reflect the real-time progression of the disease condition, affecting the timely adjustment and optimization of the recovery plan. Traditional methods cannot effectively predict complex immune responses and joint destruction processes without integrating dynamic network simulation and genetic algorithms to optimize the pathological reaction path. This limitation leads to insufficient prediction, further affecting the patient recovery efficiency and cost, the embodiments of the present invention provide a method and system for predicting the progression of joint destruction in rheumatoid arthritis by immune repertoire. The technical solutions are as follows: On the one hand, a method for predicting the progression of joint destruction in rheumatoid arthritis by immune repertoire is provided, and the method includes: S1: Collect the cell activity data in the immune repertoire of patients with rheumatoid arthritis, align the time points, standardize the time series data, and obtain the standardized time series data; S2: Analyze the standardized time series data, identify the frequencies and patterns of cell behaviors in the immune repertoire, and analyze the matching degree between the cell behavior patterns in the immune repertoire and the progression of joint destruction in rheumatoid arthritis to obtain the behavior pattern recognition result; S3: Use the behavior pattern recognition result to perform a dynamic network simulation of cell responses in the immune repertoire. By simulating natural selection and genetic variation of the genetic algorithm, select the predicted pathological response path to obtain the optimized response path; S4: According to the optimized path, collect the real-time clinical data of patients with rheumatoid arthritis, extract the key indicators, and combine time series analysis to analyze the change trends of the key indicators. Adjust the numerical range of the model parameters and the weights of the adjusted parameters according to the trend changes to construct a joint destruction progression prediction model; S5: Based on the joint destruction progression prediction model, perform clinical verification, compare the predicted rheumatoid arthritis joint destruction process of the model with the real-time clinical verification result, evaluate the consistency between the joint destruction progression prediction model and the clinical verification result, and obtain the model prediction verification result.

[0006] As a further solution of the present invention, the standardized time series data includes the activity types of cells in the immune repertoire, the activity intensity indicators of each type, and the time when the activity occurs. The behavior pattern recognition result includes cell behavior patterns, key behavior triggering factors, and pattern features highly correlated with disease progression. The optimized response path includes the change trends of key biomarkers, the predicted critical period of joint destruction, and the estimated disease control nodes. The joint destruction progression prediction model includes key time points for trend analysis, dynamically adjusted parameter ranges, influence weights, and sensitivity indicators of the model to disease progression. The model prediction verification result includes the prediction consistency of the model, the deviation between the prediction of key clinical indicators and real-time monitoring, and the prediction ability of the model for the disease development in the future time period.

[0007] As a further solution of the present invention, the steps of collecting the cell activity data in the immune repertoire of patients with rheumatoid arthritis, aligning the time points, and standardizing the time series data to obtain the standardized time series data are specifically as follows: S101: Collect the cell activity data in the immune repertoire of patients with rheumatoid arthritis, screen the qualified sample data, including cell types, activity frequencies, and timestamps, to obtain the original cell activity data set; S102: Based on the original cell activity dataset, use time synchronization technology to sort the cell activity data in the differential samples according to the collection time, correct the timestamps to avoid time errors, and obtain time-aligned data; S103: Use the time-aligned data to perform standardization processing on the measurement data of cell activities in the immune repertoire, adjust and scale the measurement data, and perform linear transformation on the cell activity intensity to obtain standardized time series data.

[0008] As a further solution of the present invention, the steps of analyzing the standardized time series data to identify the frequency and pattern of cell behaviors in the immune repertoire, and analyzing the matching degree between the cell behavior pattern in the immune repertoire and the progression of joint destruction in rheumatoid arthritis to obtain the behavior pattern recognition result are specifically as follows: S201: Use the standardized time series data to divide the data in the sample into multiple time windows, calculate the frequency of cell behaviors within the time windows, identify the occurrence times of each cell behavior, and obtain the cell behavior frequency record; S202: Use the cell behavior frequency record to identify the cell behavior patterns in the immune repertoire, compare the occurrence frequencies and distributions of multiple patterns through statistical analysis, and screen the key cell behavior patterns in rheumatoid arthritis patients to obtain the behavior pattern classification record; S203: Based on the behavior pattern classification record, perform a correlation analysis of the cell behavior patterns in the immune repertoire and the progression of joint destruction in rheumatoid arthritis, evaluate the matching degree between the cell behavior pattern and the progression of joint destruction in rheumatoid arthritis, and obtain the behavior pattern recognition result.

[0009] As a further solution of the present invention, the steps of using the behavior pattern recognition result to perform a dynamic network simulation of cell reactions in the immune repertoire, and selecting the estimated pathological reaction path through simulating natural selection and genetic variation of the genetic algorithm to obtain the optimized reaction path are specifically as follows: S301: Use the behavior pattern recognition result to transform the identified cell behavior patterns into network nodes and connections through data mapping technology, define the association effects and connection strengths between the nodes, and construct a dynamic network model; S302: According to the dynamic network model, perform a natural evolution simulation of cell behaviors, calculate the adaptability scores of different paths, and obtain the path simulation result; S303: According to the path simulation result, perform priority sorting according to the scores of different candidate paths, identify the reaction path representing the progression of joint destruction in rheumatoid arthritis, and obtain the optimized reaction path.

[0010] As a further solution of the present invention, the formula for calculating the adaptability score of the different paths is: ; Among them, is the adaptability score of the path, represents the Euclidean distance of the pathological feature vector, represents the gene expression stability, represents the natural selection pressure, , and are weight coefficients.

[0011] As a further solution of the present invention, according to the optimized path, collect the real-time clinical data of rheumatoid arthritis patients, extract the key indicators, and combine time series analysis to analyze the change trend of the key indicators. The steps of constructing a joint destruction progression prediction model by adjusting the numerical range of the model parameters and the weights of the adjustment parameters are specifically as follows: S401: Based on the optimized reaction path, collect the real-time clinical data of rheumatoid arthritis patients, extract the key clinical indicators of the patients, including the inflammation level, joint damage degree, and biochemical markers, to obtain a real-time clinical data set; S402: Use the real-time clinical data set, apply time series analysis method, conduct long-term tracking on the key indicators of joint destruction progression of rheumatoid arthritis patients, analyze the change trend and periodic fluctuation, calculate the dynamic characteristic value of joint destruction progression of rheumatoid arthritis, and obtain the key indicator trend analysis result; S403: Based on the key indicator trend analysis result, adjust the numerical range and weights of the parameters in the model, evaluate the impact of real-time clinical data on the model, verify the matching degree between the joint destruction progression prediction model and the real-time progression of rheumatoid arthritis, and construct a joint destruction progression prediction model.

[0012] As a further solution of the present invention, the formula for calculating the dynamic characteristic value of the joint destruction progression of rheumatoid arthritis is: ; Among them, represents the difference between the key indicators at the current moment and the previous moment, represents the influence coefficient of the indicator change, represents the absolute value of the key indicator at the previous moment, represents the adjustment coefficient that decreases as the key indicator increases, is a fixed weight, represents the weighted influence of taking the square root of the key indicator at the previous moment, is the square root weight coefficient.

[0013] As a further solution of the present invention, based on the joint destruction progression prediction model, clinical verification is performed, and the predicted rheumatoid arthritis joint destruction process of the model is compared with the real-time clinical verification results to evaluate the consistency between the joint destruction progression prediction model and the clinical verification results. The steps for obtaining the model prediction verification results are specifically as follows: S501: Use the joint destruction progression prediction model to conduct a clinical verification experiment, combine the joint inflammation status and changes in biochemical markers of rheumatoid arthritis patients, verify the integrity of the experimental data, and obtain a clinical verification data set; S502: According to the clinical verification data set, identify the rheumatoid arthritis joint destruction process output by the joint destruction progression prediction model, compare the model prediction result with the real-time clinical trial result, and evaluate the matching degree and deviation between the two to obtain a deviation analysis result; S503: Based on the deviation analysis result, evaluate the consistency between the joint destruction progression prediction model and the real-time clinical result, and evaluate the reliability of the model by calculating consistency indicators, including the correlation coefficient and mean square error, to obtain the model prediction verification result.

[0014] On the other hand, an immune repertoire-based rheumatoid arthritis joint destruction progression prediction system is provided. The immune repertoire-based rheumatoid arthritis joint destruction progression prediction system is used to execute the above-mentioned immune repertoire-based rheumatoid arthritis joint destruction progression prediction method. The system includes: The data alignment module collects the immune repertoire data of rheumatoid arthritis patients, performs time point alignment and data standardization processing to obtain standardized time series data; The data analysis module analyzes the standardized time series data, and obtains a behavior pattern recognition result by matching the behavior pattern with the degree of rheumatoid arthritis joint destruction progression; The dynamic network simulation module uses the behavior pattern recognition result to perform a dynamic network simulation of cell reactions in the immune repertoire, selects the optimal pathological reaction path through a simulated genetic algorithm, and obtains an optimized reaction path; The prediction model construction module uses the optimized reaction path, collects real-time clinical data, analyzes the changes in key indicators, adjusts the model parameters and weights, and constructs a joint destruction progression prediction model; The clinical verification and comparison module performs clinical verification based on the joint destruction progression prediction model, and obtains the model prediction verification result by comparing the consistency between the model prediction result and the real-time clinical result.

[0015] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include: By refining the standardization and analysis of time series data, it is possible to accurately match the cell behavior patterns in the immune repertoire with the progression of rheumatoid arthritis, improve the accuracy of disease progression prediction, further optimize the selection of pathological reaction paths through dynamic network simulation, enhance the simulation ability of potential clinical outcomes, and provide more precise recovery suggestions for patients. Integrating real-time clinical data and trend analysis of key indicators allows for real-time adjustment of the joint destruction progression prediction model, improving the adaptability and application scope of the joint destruction progression prediction model. This refined and dynamic processing logic not only enhances the flexibility of the joint destruction progression prediction model but also improves the effectiveness of recovery suggestions, significantly enhancing the reliability of recovery and the quality of life of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic diagram of the work flow of the present invention; Figure 2 is a detailed flowchart of S1 of the present invention; Figure 3 is a detailed flowchart of S2 of the present invention; Figure 4 is a detailed flowchart of S3 of the present invention; Figure 5 is a detailed flowchart of S4 of the present invention; Figure 6 is a detailed flowchart of S5 of the present invention; Figure 7 is a system flowchart of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0017] The technical solutions in the present invention will be described below with reference to the accompanying drawings.

[0018] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0019] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0020] Please refer to Figure 1 , the embodiments of the present invention provide a method for predicting the joint destruction progression of rheumatoid arthritis by the immune repertoire. The processing flow of this method can include the following steps: S1: Collect the cell activity data in the immune repertoire of patients with rheumatoid arthritis, align the time points, standardize the time series data, and obtain the standardized time series data; S2: Analyze the standardized time series data, identify the frequencies and patterns of cell behaviors in the immune repertoire, and analyze the matching degree between the cell behavior patterns in the immune repertoire and the progression of joint destruction in rheumatoid arthritis to obtain the behavior pattern recognition results; S3: Use the behavior pattern recognition results to perform dynamic network simulation of cell responses in the immune repertoire. By simulating natural selection and genetic variation of the genetic algorithm, select the predicted pathological response path to obtain the optimized response path; S4: According to the optimized path, collect the real-time clinical data of patients with rheumatoid arthritis, extract the key indicators, including pathological features and joint destruction response data, and combine time series analysis to analyze the change trends of the key indicators. Adjust the numerical range of the model parameters and the weights of the adjusted parameters according to the trend changes to construct a joint destruction progression prediction model; S5: Based on the joint destruction progression prediction model, perform clinical verification, compare the predicted joint destruction process of rheumatoid arthritis by the model with the real-time clinical verification results, evaluate the consistency between the joint destruction progression prediction model and the clinical verification results, and obtain the model prediction verification results.

[0021] The standardized time series data includes the activity types of cells in the immune repertoire, the activity intensity indicators of each type, and the time when the activity occurs. The behavior pattern recognition results include cell behavior patterns, key behavior triggering factors, and pattern features highly correlated with disease progression. The optimized response path includes the change trends of key biomarkers, the predicted critical period of joint destruction, and the estimated disease control nodes. The joint destruction progression prediction model includes the key time points for trend analysis, the dynamically adjusted parameter range, the influence weights, and the sensitivity indicators of the model to disease progression. The model prediction verification results include the prediction consistency of the model, the deviation between the prediction of key clinical indicators and real-time monitoring, and the prediction ability of the model for the disease development in the future time period.

[0022] Please refer to Figure 2 , the steps for collecting the cell activity data in the immune repertoire of patients with rheumatoid arthritis, aligning the time points, and standardizing the time series data to obtain the standardized time series data are specifically as follows: S101: Collect the cell activity data in the immune repertoire of patients with rheumatoid arthritis, screen the eligible sample data, including cell types, activity frequencies, and timestamps. The execution process of obtaining the original cell activity data set is as follows; Identify and record different cell types, activity frequencies, and specific timestamps. By using high-precision biological sampling techniques, immune cell samples are obtained from patients. The samples are classified and labeled according to specific biomarkers, and then the data is initially analyzed through dedicated software to verify the integrity and accuracy of the data. The data collection tool is equipped with a time synchronization system to ensure that the timestamps of each data point are accurate. The data is uploaded to a central database for further processing. After preliminary cleaning and formatting, the data will provide a basis for the next stage of data analysis. The classification of cell types and the recording of activity frequencies are crucial for understanding the pathological mechanisms of rheumatoid arthritis, and an original dataset of cell activities is obtained.

[0023] S102: Based on the original dataset of cell activities, using time synchronization technology, the cell activity data in the differential samples is sorted according to the collection time, and the timestamps are corrected to avoid time errors. The execution process for obtaining time-aligned data is as follows; Sort the cell activity data in the differential samples according to the collection time, according to the formula: ; In the formula, represents the corrected timestamp of the th sample, represents the timestamp of the previous sample, represents the time interval; Consider a specific scenario. Set the timestamp of sample 1 to , and the timestamp of sample 2 should be after sample 1. Set seconds, so seconds; Continuing this calculation, an exact timestamp can be determined for each sample to ensure that all sample times are correctly aligned. The actual detected time interval is required in this process, and the timestamps are adjusted accordingly. This time alignment technology is crucial for subsequent data analysis because only time-aligned data can ensure the accuracy and reliability of the analysis, enabling researchers to correctly analyze the cell activity data and make scientific judgments and research based on it.

[0024] S103: Using the time-aligned data, standardize the measurement data of cell activities in the immune repertoire. Adjust the range and scale of the measurement data, and perform a linear transformation on the cell activity intensity. The execution process for obtaining standardized time series data is as follows; Standardize the measurement data of cell activities in the immune repertoire. This process includes range adjustment and scaling operations on the original measurement data. Specialized data processing software is used to analyze the statistical characteristics of the data, such as mean, variance, and standard deviation. Based on the statistical parameters, each data point will be transformed into a standardized score, also known as Z-score, that is, each measurement value minus the mean and then divided by the standard deviation. This ensures that data from different time points and different patients can be compared under the same standard, increasing the reliability and accuracy of data analysis. The linear transformation of cell activity intensity makes the data more suitable for further statistical analysis and pattern recognition, providing high-quality input for subsequent biostatistical analysis and disease pattern recognition, which is a key step in understanding the dynamics of immune cells in rheumatoid arthritis and obtaining standardized time series data.

[0025] Please refer to Figure 3 , analyze the standardized time series data to identify the frequencies and patterns of cell behaviors in the immune repertoire, and analyze the matching degree between the cell behavior patterns in the immune repertoire and the progression of joint destruction in rheumatoid arthritis. The specific steps to obtain the behavior pattern recognition results are as follows: S201: Use the standardized time series data to divide the data in the sample into multiple time windows, calculate the frequencies of cell behaviors within the time windows, and identify the occurrence times of each cell behavior. The execution process for obtaining the cell behavior frequency record is as follows; Divide the data in the sample into multiple time windows, which involves setting a fixed-length time interval in the dataset as the window to capture the dynamic changes of cell behaviors. For each time window, the system automatically counts the occurrence times of each cell behavior within the window. Through advanced data processing software, automatic counting and frequency calculation are realized, ensuring the accuracy and processing efficiency of the data. The frequency record of cell behaviors involves quantifying the activity frequencies of different cell types, such as the specific frequencies of behaviors such as cell proliferation, movement, or death, providing basic data for the next step of pattern recognition and analysis, reflecting the activities of different cells in different time windows, and having important scientific research value for understanding how cells respond to the progression of the disease, and obtaining the cell behavior frequency record.

[0026] S202: Use the cell behavior frequency record to identify the cell behavior patterns in the immune repertoire. By statistically analyzing and comparing the occurrence frequencies and distributions of multiple patterns, screen the key cell behavior patterns in rheumatoid arthritis patients. The execution process for obtaining the behavior pattern classification record is as follows; Identify the cell behavior patterns in the immune repertoire according to the formula: ; Calculate the frequency value of the pattern occurrence. In the formula, represents the occurrence frequency of pattern , Representative pattern The number of occurrences within the target time window, represents the total number of time windows during the observation period; It is set that there are 100 time windows in total during the observation period, and a certain cell behavior pattern appears in 30 of these time windows. Therefore, the occurrence frequency of this behavior pattern can be calculated as follows: ; This calculation method is not only simple and clear, but also easy to verify the scientificity and practicality through batch data, enabling researchers to quickly identify frequently occurring cell behavior patterns and further analyze their roles in rheumatoid arthritis based on this.

[0027] S203: Based on the classification record of behavior patterns, conduct a correlation analysis between the cell behavior patterns in the immune repertoire and the progression of joint destruction in rheumatoid arthritis, evaluate the matching degree between the cell behavior patterns and the progression of joint destruction in rheumatoid arthritis, and the execution process of obtaining the behavior pattern recognition result is as follows; Conduct a correlation analysis between the cell behavior patterns in the immune repertoire and the progression of joint destruction in rheumatoid arthritis. This analysis mainly compares the previously determined cell behavior patterns with the known disease progression data, evaluates the relationship between various cell behavior patterns and disease progression by using statistical models and machine learning techniques, determines the significant matching degree between the cell behavior patterns and disease progression by calculating the correlation between the occurrence frequency of each behavior pattern and the joint destruction data. The analysis results will provide valuable insights for clinicians to help better understand the biological mechanism of the disease, be used to guide the recovery strategy of rheumatoid arthritis, and provide more accurate recovery suggestions for patients to obtain the behavior pattern recognition result.

[0028] Please refer to Figure 4 , adopt the behavior pattern recognition result, conduct a dynamic network simulation of cell responses in the immune repertoire, and select the estimated pathological response path by simulating natural selection and genetic variation of the genetic algorithm. The specific steps to obtain the optimized response path are as follows: S301: Adopt the behavior pattern recognition result, transform the recognized cell behavior patterns into network nodes and connections through data mapping technology, define the association effects and connection strengths between the nodes, and the execution process of constructing a dynamic network model is as follows; Through data mapping technology, the identified cell behavior patterns are transformed into network nodes and connections. This process involves advanced computational models and algorithms, and the main purpose is to convert biological data into a format that can be used in network analysis. Nodes represent specific cell behaviors, such as cell proliferation, apoptosis, etc., while connections represent the biological associations and interaction strengths between behaviors. By using specialized software tools and programming languages (such as Python or R), the association effects and connection strengths between nodes are defined, and the weights of the connections are adjusted according to the frequency and biological importance of cell behaviors. This can not only visualize the complex relationships between cell behaviors but also simulate how behaviors act together to affect the progression of rheumatoid arthritis, thus constructing a dynamic network model.

[0029] S302: According to the dynamic network model, perform a simulation of the natural evolution of cell behaviors, calculate the adaptability scores of different paths, and the execution process of obtaining the path simulation results is as follows; The formula for calculating the adaptability scores of different paths is: ; Where, is the adaptability score of the path, represents the Euclidean distance of the pathological feature vector, represents the gene expression stability, represents the natural selection pressure, 、 and are weight coefficients; Parameter meanings and setting values: F is the Euclidean distance of the pathological feature vector, with a value of 15, reflecting the differences between different pathological states; G is the gene expression stability, with a value of 0.8, reflecting the impact of genetic variation on cell behaviors; H is the natural selection pressure, with a value of 0.5, simulating the impact of the environment on cell selection; 、 and are weight coefficients, which are set to 2, 1.5, and 1 respectively, and are adjusted according to experimental data and expected analysis; Substitute the parameters into the formula for calculation: Calculate the weighted sum of weights: ; Calculate the numerator: ; Calculate the denominator: ; Calculate the score: ; The results show that the cells have high adaptability in the current environment. A higher score indicates that the path is a key turning point in disease progression. The level of this value provides a basis for ranking the pathological states, assisting in identifying the most probable lesion path and guiding clinical decision-making.

[0030] S303: According to the path simulation results, prioritize based on the scores of the differential candidate paths, identify the reaction paths representing the progression of joint destruction in rheumatoid arthritis, and the execution process of the optimized reaction path is as follows; Prioritize through the scores of the differential candidate paths. This process involves complex data analysis and algorithm processing, using statistical models and machine learning techniques to evaluate the biological significance and potential efficacy of each candidate path. The candidate paths represent different disease mechanisms or recovery targets. By calculating the scores of the paths, based on the biomarkers, clinical data, and knowledge base of previous studies included in the path, identify the key reaction paths representing the progression of joint destruction in rheumatoid arthritis. The priority of the path in the model reflects its importance in disease progression, providing goals and directions for clinical research and drug development, enabling researchers to more precisely locate and regulate disease-related biological processes, and bringing new hope for the recovery and management of rheumatoid arthritis, thus obtaining the optimized reaction path.

[0031] Please refer to Figure 5 , according to the optimized path, collect the real-time clinical data of rheumatoid arthritis patients, extract the key indicators, and combine time series analysis to analyze the changing trends of the key indicators. The specific steps for constructing a prediction model for the progression of joint destruction are as follows: S401: Based on the optimized reaction path, collect the real-time clinical data of rheumatoid arthritis patients, and extract the key clinical indicators of the patients, including the inflammation level, joint damage degree, and biochemical markers. The execution process of obtaining the real-time clinical dataset is as follows; Collect the real-time clinical data of rheumatoid arthritis patients. This process involves detailed clinical examinations of the patients and regular measurements of relevant biomarkers. The key clinical indicators include the inflammation level, joint damage degree, and biochemical markers such as C-reactive protein and anti-CCP antibody, etc. By adopting advanced biological detection techniques and high-precision instruments, collect data regularly, and conduct detailed analysis by a professional medical team to ensure the accuracy and real-time nature of the data. It not only depends on the frequency and scope of clinical sampling but also involves the immediate upload and processing of data. Conduct preliminary analysis and formatting of the collected data through specific software tools to ensure that the dataset can reflect the current health status of the patients, thus obtaining the real-time clinical dataset.

[0032] S402: Using the real-time clinical dataset, apply time series analysis method to conduct long-term tracking on the key indicators of the joint destruction progression of rheumatoid arthritis patients, analyze the change trend and periodic fluctuations, calculate the dynamic characteristic values of the joint destruction progression of rheumatoid arthritis, and the execution process of obtaining the trend analysis results of the key indicators is as follows; The formula for calculating the dynamic characteristic values of the joint destruction progression of rheumatoid arthritis is: ; Among them, represents the difference in key indicators between the current moment and the previous moment, represents the influence coefficient of the indicator change, represents the absolute value of the key indicator at the previous moment, represents the adjustment coefficient that decreases as the key indicator increases, is the fixed weight, represents the weighted influence after taking the square root of the key indicator at the previous moment, is the square root weight coefficient; Parameter meanings and setting values: represents the influence coefficient, and the setting value is 0.3. This value is obtained based on historical data analysis and reflects how the key indicator at the previous time point affects the current change in the absence of significant external changes; represents the absolute value of the key indicator at the previous time point, which is obtained in real time from the dataset and is set to 50 at a specific moment; represents the adjustment coefficient, and the setting value is 0.05. This value is determined based on the historical change rate and fluctuation range of the key indicator and is used to balance the decrease in influence caused by the increase in the indicator; represents the square root weight coefficient, and the setting value is 0.2. This coefficient reflects the role of the non-linear influence in the dynamic change of the key indicator; Substitute the parameters into the formula for calculation: ; The calculation steps are: ; ; ; ; The result shows the expected increase value of the key indicator after considering the key indicator and influence at the previous time point. This result reflects the dynamic characteristics of the joint destruction progression of rheumatoid arthritis and provides a quantitative basis for further clinical decision-making.

[0033] S403: Based on the results of the key indicator trend analysis, adjust the parameter value ranges and weights in the model, evaluate the impact of real-time clinical data on the model, verify the matching degree between the joint destruction progression prediction model and the real-time progression of rheumatoid arthritis. The execution process of constructing the joint destruction progression prediction model is as follows; Adjust the parameter value ranges and weights in the model. This process is a key step in model optimization, involving statistical analysis and computer simulation. Trends discovered through real-time clinical data analysis, such as increases or decreases in inflammation levels, the development speed of joint damage, etc., provide a basis for model adjustment, especially for fine-tuning in terms of the model's sensitivity and specificity to ensure a high degree of consistency between the model output and actual clinical results. The adjustment process includes re-evaluating and setting multiple parameters in the model, such as adjusting weight allocation and parameter thresholds. The adjustment is based on detailed data analysis and cutting-edge biostatistical methods to improve the accuracy and reliability of predictions and construct the joint destruction progression prediction model.

[0034] Please refer to Figure 6 , based on the joint destruction progression prediction model, perform clinical verification. Compare the predicted rheumatoid arthritis joint destruction process of the model with the real-time clinical verification results, and evaluate the consistency between the joint destruction progression prediction model and the clinical verification results. The steps to obtain the model prediction verification results are specifically as follows: S501: Use the joint destruction progression prediction model to conduct a clinical verification experiment. Combine the joint inflammation status and changes in biochemical markers of rheumatoid arthritis patients to verify the integrity of the experimental data. The execution process of obtaining the clinical verification dataset is as follows; Conduct a clinical verification experiment. This process covers the recording of the joint inflammation status and changes in biochemical markers of rheumatoid arthritis patients. Through high-precision biochemical analysis equipment and software processing technology, ensure the integrity and accuracy of the experimental data. The clinical verification experiment design includes multiple stages. The sample collection involves patients' blood, urine, and biological samples. The samples are processed and analyzed according to strict laboratory standards to measure key biochemical markers such as C-reactive protein and anti-CCP antibody, etc. The changes in the markers are closely related to the process of joint destruction. The data undergoes a strict review process to confirm the integrity of the data and ensure that all data can reflect the true health status of the patients, thus obtaining the clinical verification dataset.

[0035] S502: According to the clinical verification dataset, identify the rheumatoid arthritis joint destruction process output by the joint destruction progression prediction model. Compare the model prediction results with the real-time clinical trial results, and evaluate the matching degree and deviation between the two. The execution process of obtaining the deviation analysis result is as follows; Compare the model prediction results with the real-time clinical trial results according to the formula: ; Calculate the deviation between the two. In the formula, represents the deviation between the prediction and the actual result, represents the prediction result of the model, represents the actual clinical result; Consider a specific example. Set the progress of joint destruction predicted by the model to 0.8 (normalized score), and the result obtained through actual clinical trials is 0.75. According to the deviation calculation formula, we get: ; This deviation analysis process provides an important basis for the adjustment and optimization of the model, helping researchers identify aspects of the model that need improvement and improving the accuracy of prediction.

[0036] S503: Based on the deviation analysis results, evaluate the consistency between the joint destruction progression prediction model and the real-time clinical results. By calculating consistency indicators, including the correlation coefficient and the mean square error, evaluate the reliability of the model. The execution process for obtaining the model prediction verification results is as follows; Evaluate the consistency between the joint destruction progression prediction model and the real-time clinical results. By calculating consistency indicators, which include statistical measures such as the correlation coefficient and the mean square error. The correlation coefficient reflects the linear relationship between the model prediction value and the actual clinical result, while the mean square error provides a quantitative measure of the difference between the two. Use specialized statistical software for calculation to ensure the accuracy and scientific nature of the calculation. By calculating the consistency indicators, the reliability and practicality of the model can be comprehensively evaluated. Making necessary adjustments and optimizations to the model will directly affect the wide adoption of the model in future clinical applications, providing a more accurate prediction tool for the recovery of rheumatoid arthritis and obtaining the model prediction verification results.

[0037] Please refer to Figure 7 , on the other hand, provides an immune repertoire-based system for predicting the progression of joint destruction in rheumatoid arthritis. The immune repertoire-based system for predicting the progression of joint destruction in rheumatoid arthritis is used to execute the above-mentioned immune repertoire-based method for predicting the progression of joint destruction in rheumatoid arthritis. The system includes: The data alignment module collects the immune repertoire data of rheumatoid arthritis patients, performs time point alignment and data normalization processing, and obtains normalized time series data; The data analysis module analyzes the normalized time series data, and obtains the behavior pattern recognition result by matching the behavior pattern with the degree of joint destruction progression in rheumatoid arthritis; The dynamic network simulation module uses the behavior pattern recognition result to perform a dynamic network simulation of the cellular response in the immune repertoire, and selects the optimal pathological response path through simulating the genetic algorithm to obtain the optimized response path; The prediction model construction module uses the optimized reaction path, collects real-time clinical data, analyzes the changes in key indicators, adjusts the model parameters and weights, and constructs a prediction model for joint destruction progression; The clinical verification and comparison module performs clinical verification based on the prediction model for joint destruction progression, and obtains the model prediction verification result by comparing the consistency between the model prediction result and the real-time clinical result.

[0038] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for predicting the progression of joint destruction in rheumatoid arthritis using an immune repertoire, characterized in that: The following steps are involved: S1: Collect cell activity data from the immune repertoire of patients with rheumatoid arthritis, align time points, standardize time series data, and obtain standardized time series data; S2: Analyze the standardized time series data, identify the frequency and pattern of cell behavior in the immune repertoire, analyze the degree of match between the cell behavior pattern in the immune repertoire and the progression of rheumatoid arthritis joint destruction, and obtain behavior pattern recognition results; S3: using the behavioral pattern recognition results to perform dynamic network simulation of cell responses in the immune repertoire, and selecting the estimated pathological response path by simulating natural selection and genetic variation of the genetic algorithm to obtain an optimized response path; S4: According to the optimized pathway, real-time clinical data of patients with rheumatoid arthritis are collected, key indicators are extracted, and the changing trends of the key indicators are analyzed in combination with time series. The numerical range of the model parameters and the weight of the parameters are adjusted according to the trend changes, and a joint destruction progression prediction model is constructed; S5: Based on the joint destruction progression prediction model, clinical verification is performed to compare the rheumatoid arthritis joint destruction process predicted by the model with the real-time clinical verification results, evaluate the consistency between the joint destruction progression prediction model and the clinical verification results, and obtain the model prediction verification results.

2. The method for predicting the progression of rheumatoid arthritis joint destruction by the immune repertoire according to claim 1, characterized in that: The standardized time series data include the activity types of cells in the immune repertoire, the activity intensity index of each type, and the time when the activity occurs. The behavior pattern recognition results include cell behavior patterns, key behavior triggering factors, and pattern features that are highly correlated with disease progression. The optimized reaction pathways include changing trends of key biomarkers, predicted critical periods of joint destruction, and estimated disease control nodes. The joint destruction progression prediction model includes key time points for trend analysis, dynamically adjusted parameter ranges, impact weights, and model sensitivity indicators to disease progression. The model prediction verification results include the model's prediction consistency, deviations between the prediction of key clinical indicators and real-time monitoring, and the model's ability to predict the progression of the disease in future time periods.

3. The method for predicting the progression of rheumatoid arthritis joint destruction by the immune repertoire according to claim 1, characterized in that: The steps for collecting cell activity data from the immune repertoire of patients with rheumatoid arthritis, aligning time points, and standardizing time series data are as follows: S101: Collect cell activity data from the immune repertoire of patients with rheumatoid arthritis, screen qualified sample data, including cell type, activity frequency and timestamp, and obtain the original cell activity data set; S102: Based on the original cell activity data set, using time synchronization technology, sorting the cell activity data in the differentiated samples according to the collection time, calibrating the timestamp to avoid time error, and obtaining time-aligned data; S103: Using the time-aligned data, standardize the measurement data of cell activities in the immune repertoire, adjust the range and scale the measurement data, perform linear transformation on the intensity of cell activities, and obtain standardized time series data.

4. The method for predicting the progression of rheumatoid arthritis joint destruction by the immune repertoire according to claim 1, characterized in that: The steps of analyzing the standardized time series data, identifying the frequency and pattern of cell behavior in the immune repertoire, analyzing the degree of matching between the cell behavior pattern in the immune repertoire and the progression of rheumatoid arthritis joint destruction, and obtaining the behavior pattern recognition results are specifically as follows: S201: using the standardized time series data, dividing the data in the sample into multiple time windows, calculating the frequency of cell behaviors in the time windows, identifying the number of occurrences of each cell behavior, and obtaining a cell behavior frequency record; S202: using the cell behavior frequency record, identifying the cell behavior pattern in the immune repertoire, and screening the key cell behavior patterns in rheumatoid arthritis patients by comparing the occurrence frequency and distribution of multiple patterns through statistical analysis, and obtaining a behavior pattern classification record; S203: Based on the behavioral pattern classification records, a correlation analysis is performed between the cell behavior patterns in the immune repertoire and the progression of rheumatoid arthritis joint destruction, the degree of match between the cell behavior patterns and the progression of rheumatoid arthritis joint destruction is evaluated, and a behavioral pattern recognition result is obtained.

5. The method for predicting the progression of rheumatoid arthritis joint destruction using the immune repertoire according to claim 1, characterized in that: The behavior pattern recognition results are used to perform dynamic network simulation of cell responses in the immune repertoire, and the steps of selecting the estimated pathological response path by simulating natural selection and genetic variation of the genetic algorithm to obtain the optimized response path are as follows: S301: using the behavior pattern recognition result, converting the recognized cell behavior pattern into network nodes and connections through data mapping technology, defining the association and connection strength between nodes, and constructing a dynamic network model; S302: performing a natural evolution simulation of cell behavior according to the dynamic network model, calculating the fitness score of the differentiated path, and obtaining a path simulation result; S303: According to the pathway simulation results, the differentiated candidate pathways are prioritized according to their scores, a reaction pathway representing the progression of rheumatoid arthritis joint destruction is identified, and an optimized reaction pathway is obtained.

6. The method for predicting the progression of joint destruction in rheumatoid arthritis using the immune repertoire according to claim 5, characterized in that: The formula for calculating the fitness score of the differentiated path is: ； in, is the fitness score of the path, represents the Euclidean distance of the pathological feature vector, Represents gene expression stability, represents natural selection pressure, , and is the weight coefficient.

7. The method for predicting the progression of rheumatoid arthritis joint destruction using the immune repertoire according to claim 1, characterized in that: According to the optimized path, real-time clinical data of patients with rheumatoid arthritis are collected, key indicators are extracted, and the changing trends of key indicators are analyzed in combination with time series. The numerical range of model parameters and the weight of adjustment parameters are adjusted according to the trend changes. The specific steps of constructing a joint destruction progression prediction model are as follows: S401: Based on the optimized reaction pathway, real-time clinical data of patients with rheumatoid arthritis are collected, and key clinical indicators of the patients are extracted, including inflammation level, degree of joint damage and biochemical markers, to obtain a real-time clinical data set; S402: Using the real-time clinical data set, applying a time series analysis method, long-term tracking of key indicators of joint destruction progression in patients with rheumatoid arthritis, analyzing the change trend and periodic fluctuation, calculating the dynamic characteristic value of joint destruction progression in rheumatoid arthritis, and obtaining key indicator trend analysis results; S403: Based on the key indicator trend analysis results, adjust the parameter value range and weight in the model, evaluate the impact of real-time clinical data on the model, verify the matching degree between the joint destruction progression prediction model and the real-time progression of rheumatoid arthritis, and construct a joint destruction progression prediction model.

8. The method for predicting the progression of joint destruction in rheumatoid arthritis using the immune repertoire according to claim 7, characterized in that: The formula for calculating the dynamic characteristic value of the progression of rheumatoid arthritis joint destruction is: ； in, Represents the difference between the key indicators at the current moment and the previous moment. Represents the impact coefficient of indicator change, Represents the absolute value of the key indicator at the previous moment, Represents the adjustment coefficient that decreases as the key indicator increases. is a fixed weight, Represents the weighted impact of the key indicator at the previous moment after taking the square root. is the square root weight coefficient.

9. The method for predicting the progression of rheumatoid arthritis joint destruction using the immune repertoire according to claim 1, characterized in that: Based on the joint destruction progression prediction model, clinical verification is performed to compare the rheumatoid arthritis joint destruction process predicted by the model with the real-time clinical verification results, and the consistency between the joint destruction progression prediction model and the clinical verification results is evaluated. The specific steps for obtaining the model prediction verification results are as follows: S501: using the joint destruction progression prediction model to conduct clinical validation experiments, combining the joint inflammation status and changes in biochemical markers of rheumatoid arthritis patients to verify the integrity of the experimental data, and obtaining a clinical validation data set; S502: identifying the rheumatoid arthritis joint destruction process output by the joint destruction progression prediction model according to the clinical validation data set, comparing the model prediction results with the real-time clinical trial results, evaluating the matching degree and deviation between the two, and obtaining the deviation analysis results; S503: Based on the deviation analysis results, the consistency between the joint destruction progression prediction model and the real-time clinical results is evaluated, and the reliability of the model is evaluated by calculating consistency indicators, including correlation coefficients and mean square errors, to obtain model prediction verification results.

10. An immune repertoire prediction system for the progression of rheumatoid arthritis joint destruction, characterized in that: The method for predicting the progression of rheumatoid arthritis joint destruction by the immune repertoire according to any one of claims 1 to 9, the system comprising: The data alignment module collects immune repertoire data of patients with rheumatoid arthritis, performs time point alignment and data standardization, and obtains standardized time series data; The data analysis module analyzes the standardized time series data and obtains a behavior pattern recognition result by matching the behavior pattern with the degree of progression of rheumatoid arthritis joint destruction; The dynamic network simulation module uses the behavioral pattern recognition results to perform dynamic network simulation of cell responses in the immune repertoire, and selects the optimal pathological response path by simulating the genetic algorithm to obtain the optimized response path; The prediction model building module utilizes the optimized reaction pathway, collects real-time clinical data, analyzes changes in key indicators, adjusts model parameters and weights, and builds a joint destruction progression prediction model; The clinical verification comparison module performs clinical verification based on the joint destruction progression prediction model, and obtains the model prediction verification results by comparing the consistency between the model prediction results and the real-time clinical results.

Images