Arrhythmia occurrence risk prediction system, method, storage medium and electronic device based on core proteomics

Abstract

The present application relates to the technical field of digital medical treatment, in particular to a system and method for predicting the risk of arrhythmia based on core proteomics, a storage medium and an electronic device. The system comprises a data acquisition module for acquiring plasma core protein level data of an individual, a model acquisition module for acquiring a preset arrhythmia protein risk scoring model, a risk scoring module for inputting the plasma core protein level data into the arrhythmia protein risk scoring model to obtain a risk score result of arrhythmia-related proteins, and a risk prediction module for predicting the risk of arrhythmia of the individual based on the risk score result. The present application reduces the dimensionality of high-dimensional protein data with a simplified core protein, reduces the detection cost and data operation load while ensuring the prediction accuracy, and can unify the risk prediction of various arrhythmia subtypes.

Description

Technical Field

[0001] This invention relates to the field of digital medical technology, specifically to a system, method, storage medium, and electronic device for predicting the risk of arrhythmia based on core proteomics. Background Technology

[0002] Cardiac arrhythmias are a common group of cardiovascular diseases, including various types such as atrial fibrillation, cardiac conduction disorders, and ventricular arrhythmias. Their global incidence and prevalence are continuously rising, and they have become a significant factor contributing to increased disease burden, mortality, and healthcare expenditure. Because arrhythmias can cause further changes in cardiac structure and electrical remodeling, thereby exacerbating the condition, early risk identification and intervention for arrhythmias are of great clinical significance.

[0003] Abdominal obesity, a core component of metabolic syndrome, has been proven to be closely related to the occurrence of arrhythmias. It can increase the risk of arrhythmias by inducing pathological processes such as inflammatory responses, oxidative stress, myocardial fibrosis, and atrial remodeling. However, the specific molecular mechanisms by which abdominal obesity leads to arrhythmias have not been fully elucidated, and there is currently a lack of effective biomarkers to identify high-risk individuals with arrhythmias in the abdominal obesity population.

[0004] Proteins participate in regulating numerous biochemical processes such as metabolism, signal transduction, and inflammatory responses. Detecting protein levels in the body can accurately reflect an individual's health status and disease risk. However, existing protein-based disease risk prediction schemes typically require the detection of numerous protein biomarkers, resulting in high detection costs and complex data processing. Moreover, most models are built for single outcomes, lacking a unified prediction scheme that can simultaneously cover multiple arrhythmia subtypes such as atrial fibrillation, cardiac conduction disorders, and ventricular arrhythmias. Furthermore, many of these models are built in specific populations, lacking sufficient adaptability and generalization ability for high-risk groups such as those with hypertension.

[0005] In summary, how to achieve unified risk prediction for multiple arrhythmia subtypes with the most concise protein biomarkers while ensuring prediction accuracy, and taking into account the applicability to people with different blood pressure characteristics, has become an urgent technical problem to be solved. Summary of the Invention

[0006] To overcome the above shortcomings, this invention provides a system, method, storage medium, and electronic device for predicting the risk of arrhythmia based on core proteomics. It can predict the risk of multiple arrhythmia subtypes with a simplified core protein, reducing detection costs and computational load while taking into account the applicability to people with different blood pressure characteristics.

[0007] A first aspect of this invention provides a cardiac arrhythmia risk prediction system based on core proteomics, comprising: The data acquisition module is used to acquire plasma core protein level data of an individual, the plasma core protein level being associated with the risk of arrhythmia. The model acquisition module is used to acquire a preset arrhythmia protein risk scoring model, which includes the influence weights of different plasma core protein levels on the risk of arrhythmia. The risk scoring module is used to input the plasma core protein level data into the arrhythmia protein risk scoring model to obtain the risk score results of arrhythmia-related proteins. The risk prediction module is used to predict an individual's risk of developing arrhythmia based on the risk score results.

[0008] Furthermore, the plasma core protein levels data include the following four core proteins: ectoderm dysplasia protein A2 receptor, growth differentiation factor 15, leucine-rich repeat neuronal protein 1, and N-terminal pro-B-type natriuretic peptide.

[0009] Furthermore, the arrhythmias include atrial fibrillation, cardiac conduction disorders, and ventricular arrhythmias; the risk prediction module is used to predict an individual's risk of developing atrial fibrillation, cardiac conduction disorders, and ventricular arrhythmias, respectively or simultaneously, based on the risk score results.

[0010] Furthermore, the arrhythmia protein risk scoring model is a weighted combination model based on the four core proteins.

[0011] Furthermore, the weighted combination model satisfies the following relationship: Where S represents the individual's overall risk score; Ci represents the relative expression level of the i-th core protein after logarithmic transformation and standardization; and δi represents the risk coefficient of the i-th core protein.

[0012] Furthermore, the plasma core protein level data are standardized protein expression values ​​measured by a detection platform based on close-range extension analysis technology, or protein expression level data that are relatively consistent with the numerical range and distribution characteristics of the standardized protein expression values ​​after logarithmic transformation and standardization calibration.

[0013] Furthermore, the arrhythmia protein risk scoring model is constructed in the following manner: In the training set of the population in which the model is established, the expression level data of the four core proteins are used as independent variables, and whether an individual experiences arrhythmia is used as the endpoint. A multivariate Cox proportional hazards regression model is used for survival analysis to obtain the risk coefficients of the four core proteins corresponding to arrhythmia; the arrhythmia protein risk scoring model is established based on the risk coefficients.

[0014] Furthermore, the model is established for a population with normal blood pressure; the arrhythmia protein risk scoring model is also used to predict the risk of arrhythmia in a hypertensive population.

[0015] A second aspect of this invention provides a method for predicting the risk of arrhythmia based on core proteomics, comprising: Obtain individual plasma core protein level data, which are associated with the risk of cardiac arrhythmia; A preset arrhythmia protein risk scoring model is obtained, wherein the arrhythmia protein risk scoring model includes the influence weights of different plasma core protein levels on the risk of arrhythmia. The plasma core protein level data is input into the arrhythmia protein risk scoring model to obtain the risk score results of arrhythmia-related proteins. The risk score results are used to predict an individual's risk of developing arrhythmia.

[0016] Furthermore, the plasma core protein level data includes the following four core proteins: ectodermal dysplasia protein A2 receptor, growth differentiation factor 15, leucine-rich repeat neuronal protein 1, and N-terminal pro-B-type natriuretic peptide; the cardiac arrhythmias include atrial fibrillation, cardiac conduction disorders, and ventricular arrhythmias.

[0017] Furthermore, the arrhythmia protein risk scoring model is a weighted combination model based on the four core proteins, and the weighted combination model satisfies the following relationship: Where S represents the individual's overall risk score; Ci represents the relative expression level of the i-th core protein after logarithmic transformation and standardization; and δi represents the risk coefficient of the i-th core protein.

[0018] A third aspect of the present invention provides an electronic device including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device enables the electronic device to implement the core proteomics-based arrhythmia risk prediction method as described in the second aspect of the present invention.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the arrhythmia risk prediction method based on core proteomics as described in the second aspect of the present invention.

[0020] A fifth aspect of the present invention provides a computer program product, including a computer program that, when run, causes the method for predicting the risk of arrhythmia based on core proteomics as described in the second aspect of the present invention to be executed.

[0021] Compared with the prior art, the present invention has the following advantages: Firstly, the arrhythmia protein risk scoring model of this invention replaces the numerous protein biomarkers in existing schemes with four core proteins: ectodermal dysplasia protein A2 receptor, growth differentiation factor 15, leucine-rich repeat sequence neuronal protein 1, and N-terminal pro-B-type natriuretic peptide. By weighting and summing the relative expression levels of each core protein after logarithmic transformation and standardization with their corresponding risk coefficients, high-dimensional protein information is compressed into a single comprehensive risk score. This reduces the dimensionality of high-dimensional protein data while retaining key predictive information. As a result, risk scoring can be completed by detecting only a few core proteins, avoiding the detection and complex calculations of a large number of protein biomarkers, and significantly reducing detection costs and data processing load.

[0022] Secondly, the arrhythmia protein risk scoring model of this invention assigns corresponding risk coefficients to three arrhythmia subtypes: atrial fibrillation, cardiac conduction disorders, and ventricular arrhythmias. This allows the same set of core protein level data to be substituted into the model to calculate comprehensive risk scores corresponding to different subtypes. Thus, a single set of simplified core protein combinations can be used to predict multiple arrhythmia subtypes separately or simultaneously. This overcomes the shortcomings of existing protein prediction schemes, which mostly build models for a single outcome and are difficult to uniformly cover multiple arrhythmia subtypes, thus broadening the scope of application of risk prediction.

[0023] Third, the arrhythmia protein risk scoring model of the present invention selects the normotensive population as the model building population for construction and internal validation, and directly applies the model coefficients obtained from training on the normotensive population to the hypertensive population cohort for independent cross-population generalization validation. The model shows good prediction accuracy in both normotensive and hypertensive populations. Thus, while ensuring the predictive efficacy of the modeled population, it also takes into account the applicability of different blood pressure characteristics, overcoming the shortcomings of existing models that are mostly built in specific populations and have insufficient adaptability and generalization ability to high-risk populations such as hypertension.

[0024] Fourth, the four core proteins of this invention were determined through multiple rigorous screening processes, including being significantly associated with both abdominal obesity and arrhythmia, having a significant mediating effect in the pathogenesis pathway from abdominal obesity to arrhythmia, being consistently selected through cross-validation using four machine learning algorithms (LASSO regression, Boruta algorithm, random forest, and extreme gradient boosting) in the training set, and being jointly identified as characteristic proteins in at least two arrhythmia subtypes. Furthermore, each core protein has clear biological mechanism support in areas such as inflammatory response and myocardial fibrosis, stress and energy metabolism regulation and cardiac remodeling, maintenance of cardiac electrical conduction system function, and changes in atrial and ventricular wall tension. Therefore, the selected core proteins possess both statistical robustness and biological interpretability, further ensuring the accuracy and reliability of the arrhythmia risk prediction results. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart illustrating a method for predicting the risk of arrhythmia based on core proteomics, provided in an embodiment of the present invention. Figure 2 This is a Venn diagram of the core protein extracted using four machine learning algorithms in this embodiment of the invention; Figure 3 This is a schematic diagram comparing the predictive efficacy of the core protein risk scoring model and the full model for arrhythmias in a normal blood pressure population in this embodiment of the invention. Figure 4 This is a schematic diagram illustrating the efficacy of the core protein risk scoring model for predicting arrhythmias in hypertensive individuals in this embodiment of the invention. Figure 5 This is a schematic diagram of the structure of the cardiac arrhythmia risk prediction system based on core proteomics provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0027] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0028] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0029] It should also be understood that the term “and / or” as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0030] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of the invention include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0031] Please see Figure 1 The method for predicting the risk of arrhythmia based on core proteomics provided in this invention includes the following steps S101 to S104: S101. Obtain plasma core protein level data for an individual, wherein the plasma core protein level is associated with the risk of arrhythmia.

[0032] In this application, the plasma core protein level data refers to data characterizing the expression level of target core proteins obtained from peripheral blood samples collected from an individual. Target core proteins may include, for example, four core proteins: ectodermal dysplasia protein A2 receptor, growth differentiation factor 15, leucine-rich repeat neuronal protein 1, and N-terminal pro-B-type natriuretic peptide. In this application, the plasma core protein level data can be standardized protein expression values ​​measured by a proximal extension analysis platform. When using other protein quantification techniques such as enzyme-linked immunosorbent assay (ELISA) or mass spectrometry to obtain the absolute mass concentration or molar concentration of the core protein, the absolute concentration can be logarithmically transformed and standardized to align its numerical range and distribution characteristics with the standardized protein expression values ​​before being used as the plasma core protein level data. This embodiment of the invention uses plasma core protein level data associated with the risk of arrhythmia as input, providing a data foundation for subsequent risk prediction using simplified protein biomarkers.

[0033] S102. Obtain a preset arrhythmia protein risk scoring model, wherein the arrhythmia protein risk scoring model includes the influence weights of different plasma core protein levels on the risk of arrhythmia.

[0034] In application, the arrhythmia protein risk scoring model can be a weighted combination model based on the four core proteins, where different core proteins correspond to different influence weights, and the influence weights characterize the degree to which the level of the core protein contributes to the risk of arrhythmia. The arrhythmia protein risk scoring model and its influence weights can be pre-built and stored, and directly retrieved during prediction. This embodiment of the invention, by pre-setting an arrhythmia protein risk scoring model containing influence weights, enables risk scoring to be completed using only a few core proteins, reducing the data computation load.

[0035] S103. Input the plasma core protein level data into the arrhythmia protein risk scoring model to obtain the risk score results of arrhythmia-related proteins.

[0036] In application, the plasma core protein level data obtained in step S101 is substituted into the arrhythmia protein risk scoring model. The relative expression level of each core protein is multiplied by its corresponding influence weight and summed to obtain the comprehensive risk score for the individual. In application, the weighted combination model can satisfy the following relationship: Where S represents the individual's comprehensive risk score; Ci represents the relative expression level of the i-th core protein after logarithmic transformation and standardization; and δi represents the risk coefficient of the i-th core protein. In application, δi can be taken from the risk coefficients pre-calibrated for different arrhythmia subtypes, thus enabling the calculation of comprehensive risk scores corresponding to different arrhythmia subtypes from the same set of core protein level data. This embodiment of the invention compresses high-dimensional protein information into a comprehensive risk score through weighted summation, achieving dimensionality reduction of high-dimensional data while retaining predictive information.

[0037] S104. Based on the risk score results, predict the individual's risk of developing arrhythmia.

[0038] In this application, the risk score is a continuous numerical value; the higher the risk score, the higher the predicted risk of an individual developing arrhythmia. The arrhythmia can include atrial fibrillation, cardiac conduction disorders, and ventricular arrhythmias. The risk score can be used to predict an individual's risk of developing these three arrhythmia subtypes individually or simultaneously, and the corresponding risk prediction results can be output for clinicians' reference. This invention, by predicting an individual's risk of developing arrhythmias based on a comprehensive risk score, achieves unified risk prediction for multiple arrhythmia subtypes.

[0039] In application, the arrhythmia protein risk scoring model can be pre-constructed as follows: Based on a large-scale prospective cohort study, the study population is divided into normotensive and hypertensive groups according to the subjects' blood pressure status. The normotensive group is selected as the model building population to construct and internally validate the arrhythmia protein risk scoring model; the hypertensive group is selected as the cross-population generalization validation population to independently validate the external generalization predictive efficacy of the arrhythmia protein risk scoring model in different blood pressure characteristic populations.

[0040] In application, the basic information of participants in the two population groups mentioned above is supplemented and improved by using a medical database. This basic information includes, but is not limited to, participants' age, gender, education level, lifestyle habits, body mass index, blood pressure level, medical history, and new-onset arrhythmic events. Please refer to Table 1, which shows the descriptive statistical characteristics of participants in the general population, the normotensive group, and the hypertensive group.

[0041] Table 1 Baseline characteristics of the participants In the application, 70% of the data from both normotensive and hypertensive populations were randomly selected as the training set, and the remaining 30% was used as the validation set. Based on systematic statistical analysis and machine learning methods, four core proteins closely related to the risk of arrhythmia were identified from a large number of plasma proteins: ectodermal dysplasia protein A2 receptor, growth differentiation factor 15, leucine-rich repeat neuron protein 1, and N-terminal pro-B-type natriuretic peptide.

[0042] In application, the screening of the four core proteins can simultaneously meet the following conditions: First, they are significantly correlated with both abdominal obesity and arrhythmia; second, they demonstrate a significant mediating effect in the pathogenesis pathway from abdominal obesity to core proteins to arrhythmia, as confirmed by mediation effect analysis; third, four machine learning algorithms—LASSO regression, Boruta algorithm, random forest, and extreme gradient boosting—are run in parallel on the training set for feature screening, and Venn diagrams for each arrhythmia subtype are plotted through intersection analysis. Please refer to [link to relevant documentation]. Figure 2 The core candidate proteins were cross-validated by the four machine learning algorithms and were consistently selected; fourth, in at least two of the three arrhythmia subtypes—atrial fibrillation, cardiac conduction disorder, and ventricular arrhythmia—they were identified as characteristic proteins.

[0043] In applications, the biological significance of the four core proteins mentioned above is as follows: Ectodermal dysplasia protein A2 receptor is a member of the tumor necrosis factor receptor superfamily, involved in inflammatory signal transduction and apoptosis regulation; elevated levels are closely related to obesity-related systemic inflammatory responses and myocardial fibrosis. Growth differentiation factor 15 is a member of the transforming growth factor β superfamily, involved in stress responses, energy metabolism regulation, and inflammatory processes, and closely related to myocardial injury and cardiac remodeling. Leucine-rich repeat-sequence neuronal protein 1 participates in cell adhesion and neural development, playing a role in the development and functional maintenance of the cardiac electrical conduction system. N-terminal pro-B-type natriuretic peptide is secreted by ventricular myocytes when cardiac volume and pressure load increase; elevated levels reflect increased atrial and ventricular wall tension and are closely related to the occurrence and progression of arrhythmias.

[0044] In the application, based on the identified four core proteins, the expression levels of these four core proteins are used as independent variables in the training set. The endpoint is determined by whether the individual experiences atrial fibrillation, cardiac conduction disorders, or ventricular arrhythmias. A multivariate Cox proportional hazards regression model is used for survival analysis, allowing the four core proteins to participate in the modeling as a whole and adjust for each other. The risk coefficients for each of the four core proteins corresponding to the three arrhythmia subtypes are calculated, as shown in Table 2. Based on these risk coefficients, a risk scoring model for the arrhythmia proteins can be established.

[0045] Table 2. Risk coefficients (δi) of core proteins for three arrhythmia subtypes. In application, the established arrhythmia protein risk scoring model is evaluated for efficacy on a validation set of normotensive individuals. Predictive efficacy is assessed by calculating the area under the time-related receiver operating characteristic (ROC) curve. Please refer to [link to relevant documentation]. Figure 3 The risk scoring model, which only includes the four core proteins, demonstrates predictive efficacy comparable to the full-feature protein models for each outcome, significantly reducing detection costs and data computation load while retaining predictive power. Furthermore, the model coefficients obtained from the training set of a normotensive population were directly applied to a hypertensive cohort for independent validation; please refer to [link to relevant documentation]. Figure 4 The arrhythmia protein risk scoring model also demonstrated good predictive accuracy and cross-population generalization ability in the hypertensive population.

[0046] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0047] This invention also provides a system for predicting the risk of arrhythmia based on core proteomics, used to perform the steps described in the embodiments of the method for predicting the risk of arrhythmia based on core proteomics. Please refer to... Figure 5 The arrhythmia risk prediction system based on core proteomics provided in this embodiment of the invention includes a data acquisition module 100, a model acquisition module 200, a risk scoring module 300, and a risk prediction module 400.

[0048] In application, the data acquisition module 100 functions as step S101 in the above method embodiment, acquiring individual plasma core protein level data, which is associated with the risk of arrhythmia. The model acquisition module 200 functions as step S102 in the above method embodiment, acquiring a preset arrhythmia protein risk scoring model, which includes the influence weights of different plasma core protein levels on the risk of arrhythmia. The risk scoring module 300 functions as step S103 in the above method embodiment, inputting the plasma core protein level data into the arrhythmia protein risk scoring model to obtain a risk score result for arrhythmia-related proteins. The risk prediction module 400 functions as step S104 in the above method embodiment, predicting the individual's risk of developing arrhythmia based on the risk score result.

[0049] It should be noted that the information interaction and execution process between the above systems / modules are based on the same concept as the method embodiments of the present invention. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0050] Please see Figure 6 The present invention also provides an electronic device, including an input device, an output device, a processor 201, a memory 202, and a computer program 203 stored in the memory 202 and executable on the processor 201. The input device, the processor 201, the memory 202, and the output device are interconnected. When the processor 201 executes the computer program 203, it implements the steps in the above-described method embodiments.

[0051] In the application, the input device is used to provide relevant data or instructions to the electronic device, and may include human-computer interaction interface devices such as keyboards, mice, and touch screens, for inputting plasma core protein level data, relevant clinical information, or other input parameters of the individual to be evaluated. The processor 201 is used to execute computer program instructions, perform data processing and analysis, and may be a central processing unit, graphics processing unit, or other dedicated processing unit. The memory 202 is used to store the computer programs, data, and parameters required by the electronic device, and may include random access memory and persistent memory, for storing the arrhythmia protein risk scoring model, the influence weights of each core protein, and plasma core protein level data of the individual to be evaluated. The output device is used to present the processing and analysis results to the user or external device, and may be a monitor, printer, etc., for displaying the arrhythmia risk prediction results.

[0052] In applications, electronic devices may include, but are not limited to, processors and memory. Those skilled in the art will understand that... Figure 6 This is merely an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than shown, or a combination of certain components, or different components.

[0053] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this invention. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0054] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps described in the various method embodiments above.

[0055] This invention provides a computer program product, including a computer program, which, when run on an electronic device, causes the electronic device to execute the steps described in the various method embodiments above.

[0056] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0057] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A cardiac arrhythmia risk prediction system based on core proteomics, characterized in that, include: The data acquisition module is used to acquire plasma core protein level data of an individual, the plasma core protein level being associated with the risk of arrhythmia. The model acquisition module is used to acquire a preset arrhythmia protein risk scoring model, which includes the influence weights of different plasma core protein levels on the risk of arrhythmia. The risk scoring module is used to input the plasma core protein level data into the arrhythmia protein risk scoring model to obtain the risk score results of arrhythmia-related proteins. The risk prediction module is used to predict an individual's risk of developing arrhythmia based on the risk score results.

2. The cardiac arrhythmia risk prediction system based on core proteomics according to claim 1, characterized in that, The plasma core protein levels data include the following four core proteins: ectoderm dysplasia protein A2 receptor, growth differentiation factor 15, leucine-rich repeat neuron protein 1, and N-terminal pro-B-type natriuretic peptide.

3. The cardiac arrhythmia risk prediction system based on core proteomics according to claim 2, characterized in that, The arrhythmias include atrial fibrillation, cardiac conduction disorders, and ventricular arrhythmias; the risk prediction module is used to predict an individual's risk of developing atrial fibrillation, cardiac conduction disorders, and ventricular arrhythmias, respectively or simultaneously, based on the risk score results; the arrhythmia protein risk scoring model is a weighted combination model based on the four core proteins.

4. The cardiac arrhythmia risk prediction system based on core proteomics according to claim 3, characterized in that, The weighted combination model satisfies the following relationship: Where S represents the individual's overall risk score; Ci represents the relative expression level of the i-th core protein after logarithmic transformation and standardization; and δi represents the risk coefficient of the i-th core protein.

5. The cardiac arrhythmia risk prediction system based on core proteomics according to claim 1, characterized in that, The plasma core protein level data are standardized protein expression values ​​measured by a detection platform based on close-range extension analysis technology, or protein expression level data that are relatively consistent with the numerical range and distribution characteristics of the standardized protein expression values ​​after logarithmic transformation and standardization calibration.

6. The cardiac arrhythmia risk prediction system based on core proteomics according to claim 3, characterized in that, The arrhythmia protein risk scoring model was constructed in the following manner: In the training set of the population in which the model was established, the expression level data of the four core proteins were used as independent variables, and whether an individual experienced arrhythmia was used as the endpoint. A multivariate Cox proportional hazards regression model was used for survival analysis to obtain the risk coefficients of the four core proteins corresponding to arrhythmia. A risk scoring model for the arrhythmia protein is established based on the risk coefficient.

7. A method for predicting the risk of cardiac arrhythmia based on core proteomics, characterized in that, include: Obtain individual plasma core protein level data, which are associated with the risk of cardiac arrhythmia; A preset arrhythmia protein risk scoring model is obtained, wherein the arrhythmia protein risk scoring model includes the influence weights of different plasma core protein levels on the risk of arrhythmia. The plasma core protein level data are input into the arrhythmia protein risk scoring model to obtain the risk score results of arrhythmia-related proteins. The risk score results are used to predict an individual's risk of developing arrhythmia.

8. The method for predicting the risk of cardiac arrhythmia based on core proteomics according to claim 7, characterized in that, The plasma core protein level data includes the following four core proteins: ectoderm dysplasia protein A2 receptor, growth differentiation factor 15, leucine-rich repeat neuron protein 1, and N-terminal pro-B-type natriuretic peptide; the cardiac arrhythmias include atrial fibrillation, cardiac conduction disorders, and ventricular arrhythmias.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the arrhythmia risk prediction method based on core proteomics as described in claim 7 or 8.

10. An electronic device, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it causes the electronic device to implement the core proteomics-based arrhythmia risk prediction method as described in claim 7 or 8.

Images