Data processing method, device, system, equipment, medium and program product

Abstract

The invention discloses a data processing method, device, system and equipment, a medium and a program product, and is applied to the technical field of data processing. The method comprises: acquiring a plasma sample of a user; the plasma sample is detected, expression data of biomarkers are obtained, the biomarkers comprise markers related to carotid plaque occurrence, and the expression data of the biomarkers comprise the expression quantity of the biomarkers in the plasma sample; and based on the expression data of the biomarker, determining a risk score value of the user, the risk score value being used for representing a risk probability of occurrence of the carotid plaque of the user within a preset time period. According to the method, the risk probability of carotid plaque occurrence of the user within the preset time can be judged.

Description

Technical Field

[0001] This application belongs to the technical field of data processing, and particularly relates to a data processing method, apparatus, system, device, medium and program product. Background Art

[0002] Carotid plaque refers to the deposition of fat and calcium substances on the inner wall of the carotid artery, resulting in the thickening and hardening of the carotid artery blood vessel, and finally forming a plaque that appears yellow on the outside and is similar to porridge inside the carotid artery blood vessel. Carotid plaque can cause the inner diameter of the carotid artery blood vessel to become narrower, thereby blocking blood flow and affecting blood circulation in the user's body.

[0003] In the related art, observing the maximum thickness of the carotid artery intima-media locally through carotid ultrasound examination is a common method for judging carotid plaque. When the maximum thickness of the carotid artery intima-media locally is greater than 1.5 mm, it is judged that carotid plaque has occurred. However, in the initial stage of atherosclerosis, patients usually do not have obvious discomfort symptoms and generally do not go for examinations or treatments. When patients feel unwell, atherosclerosis has often progressed to a relatively serious stage, and cardiovascular diseases may have occurred. Therefore, how to early identify high-risk patients with carotid plaque occurrence is a technical problem that needs to be solved urgently at present. Summary of the Invention

[0004] Embodiments of this application provide a data processing method, apparatus, system, device, medium and program product, which can determine the risk probability of carotid plaque occurrence in a user within a preset time.

[0005] In a first aspect, embodiments of this application provide a data processing method, and the data processing method includes:

[0006] Obtain a plasma sample of a user;

[0007] Detect the plasma sample to obtain the expression data of biomarkers, where the biomarkers include markers related to carotid plaque occurrence, and the expression data of the biomarkers includes the expression levels of the biomarkers in the plasma sample;

[0008] Based on the expression data of the biomarkers, determine a risk score value of the user, and the risk score value is used to characterize the risk probability of carotid plaque occurrence in the user within a preset time period.

[0009] In a second aspect, embodiments of this application provide a data processing system, and the data processing system includes:

[0010] A biomarker extraction device, configured to extract the expression data of biomarkers from a plasma sample of a user, where the biomarkers include markers related to carotid plaque occurrence, and the expression data of the biomarkers includes the expression levels of the biomarkers in the plasma sample;

[0011] A scoring device for determining a risk score value of a user based on biomarker expression data, where the risk score value is used to characterize the risk probability of the occurrence of carotid artery plaques in the user within a preset time period;

[0012] A display device connected to the scoring device for displaying the scoring result of the user, where the scoring result includes the risk score value.

[0013] In a third aspect, an embodiment of the present application provides a data processing device, which includes:

[0014] A first acquisition module for acquiring a plasma sample of the user;

[0015] A first determination module for detecting the plasma sample to obtain biomarker expression data, where the biomarkers include markers related to the occurrence of carotid artery plaques, and the biomarker expression data includes the expression levels of the biomarkers in the plasma sample;

[0016] A second determination module for determining a risk score value of the user based on the biomarker expression data, where the risk score value is used to characterize the risk probability of the occurrence of carotid artery plaques in the user within a preset time period.

[0017] In a fourth aspect, an embodiment of the present application provides an electronic device, which includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the data processing method according to any item in the first aspect is implemented.

[0018] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the data processing method according to any item in the first aspect is implemented.

[0019] In a sixth aspect, an embodiment of the present application provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the data processing method according to any item in the first aspect is implemented.

[0020] The data processing method, device, system, device, medium, and program product in the embodiments of the present application, through the biomarker expression data obtained by detecting the plasma sample, accurately reflect the concentration level of the biomarkers related to the occurrence of carotid artery plaques in the plasma. Since the biomarkers are correlated with the occurrence of carotid artery plaques, the comprehensive analysis of their expression data can more comprehensively reflect the potential trend of the occurrence of carotid artery plaques in the user's body. Therefore, through the risk score value converted from the expression data of these biomarkers, the risk probability of the occurrence of carotid artery plaques in the user within a preset time period can be accurately predicted. Brief Description of the Drawings

[0021] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0022] Figure 1 A flowchart showing the data processing method provided by some embodiments of the present application;

[0023] Figure 2 A schematic diagram showing the fold change in the expression of metabolic markers in the discovery set and the validation set provided by some embodiments of the present application;

[0024] Figure 3 A schematic diagram showing the odds ratio (OR) and P values of the first risk model provided by some embodiments of the present application in the discovery set and the validation set;

[0025] Figure 4 A schematic diagram showing the AUC values of the first risk model provided by some embodiments of the present application in the discovery set and the validation set;

[0026] Figure 5A A curve graph showing the coefficient profile generated according to the logarithm λ provided by some embodiments of the present application;

[0027] Figure 5B A curve graph showing that the LASSO model uses ten-fold cross-validation to determine the optimal λ value provided by some embodiments of the present application;

[0028] Figure 5C A calibration curve graph of the logistic regression model for predicting the risk of carotid plaque provided by some embodiments of the present application;

[0029] Figure 5D A bootstrap receiver operating characteristic curve graph of the logistic regression model for predicting the risk of carotid plaque provided by some embodiments of the present application;

[0030] Figure 6A A receiver operating characteristic curve between the traditional prediction model and the new prediction model provided by some embodiments of the present application;

[0031] Figure 6B A calibration curve graph of the new prediction model provided by some embodiments of the present application;

[0032] Figure 7 A flowchart showing a specific implementation manner for determining a risk prevention and control strategy for a user in the data processing method provided by some embodiments of the present application;

[0033] Figure 8 Shows a schematic structural diagram of a data processing system provided by some embodiments of the present application;

[0034] Figure 9 Shows a schematic structural diagram of a data processing device provided by some embodiments of the present application;

[0035] Figure 10 Shows a schematic structural diagram of an electronic device provided by some embodiments of the present application. Detailed implementation manners

[0036] The features and exemplary embodiments of various aspects of the present application will be described in detail below. To make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The following description of the embodiments is only intended to provide a better understanding of the present application by showing examples of the present application.

[0037] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or device including a series of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, elements defined by the statement "including..." do not exclude the existence of additional identical elements in the process, method, article or device including the elements.

[0038] It should be noted that the acquisition, storage, use, processing, etc. of data in the embodiments of the present application all comply with the relevant regulations of national laws and regulations.

[0039] It should be noted that, in the embodiments of the present application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned, and they should be considered as exemplary. The purpose is only to illustrate the feasibility in the implementation of the technical solution of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0040] To solve the problems in the foregoing related technologies, the embodiments of the present application provide a data processing method, device, system, equipment, medium and program product. The following in conjunction with the attached Figure 1 to the attachedFigure 7 , the data processing method provided by the embodiments of the present application will be described in detail through specific embodiments.

[0041] Figure 1 The flowchart of the data processing method provided by some embodiments of the present application is shown. As Figure 1 shown, the data processing method may include step 110 to step 130.

[0042] Step 110, obtain the plasma sample of the user.

[0043] Step 120, detect the plasma sample to obtain the expression data of biomarkers. The biomarkers include markers related to the occurrence of carotid plaques, and the expression data of biomarkers include the expression levels of biomarkers in the plasma sample.

[0044] Step 130, based on the expression data of biomarkers, determine the risk score value of the user. The risk score value is used to characterize the risk probability of the occurrence of carotid plaques in the user within a preset time period.

[0045] Thus, the expression data of biomarkers obtained by detecting the plasma sample accurately reflects the concentration level of biomarkers related to the occurrence of carotid plaques in the plasma. Since the biomarkers are correlated with the occurrence of carotid plaques, the comprehensive analysis of their expression data can more comprehensively reflect the potential risk of the occurrence of carotid plaques in the user. Therefore, the risk score value converted from the expression data of these biomarkers can accurately predict the risk probability of the occurrence of carotid plaques in the user within a preset time period.

[0046] It should be noted here that the occurrence of carotid plaques is an early sign of atherosclerosis in patients. As atherosclerosis progresses, if not controlled, it will eventually lead to serious cardiovascular diseases and even death. Therefore, by studying the markers related to the prediction of the occurrence of carotid plaques, high-risk patients can be identified at the early stage of atherosclerosis. Through strict management and drug intervention, the occurrence of atherosclerosis and atherosclerotic cardiovascular diseases can be prevented or delayed.

[0047] The above steps will be described in detail below, as follows.

[0048] First, regarding step 110, exemplarily, obtaining the plasma sample of the user may include first collecting the whole blood sample of the user using an anticoagulant vacuum blood collection tube, and then centrifuging the whole blood sample by centrifugation to separate the plasma, thereby obtaining the plasma sample.

[0049] Secondly, regarding step 120, the biomarker involved in the embodiments of the present application refers to a specific substance related to the occurrence of carotid plaques, and the expression level of these substances in plasma can reflect the potential risk of carotid plaque occurrence. For example, certain proteins, lipid molecules, nucleic acid fragments, etc. that are closely related to the formation process of carotid plaques, such as carotid intima injury, lipid deposition, and inflammatory response.

[0050] In some embodiments of the present application, the biomarker includes metabolic biomarkers, and the metabolic biomarkers include lipoxin A4, ethyl 3-indoleacetate, N-(3-indolylacetyl)-L-alanine, phosphatidylserine PS(19:0_18:2), phosphatidic acid PA(20:0_21:0), cholesteryl ester CE(19:0), lysophosphatidylcholine LPC(O-22:1), and phosphatidylethanolamine PE(P-17:0_18:1).

[0051] Next, the above-mentioned various metabolic biomarkers will be specifically described.

[0052] Lipoxin A4 (LXA4) is a metabolite belonging to arachidonic acid (ARA) formed through a transcellular biosynthetic pathway during the inflammatory process. Here, ARA, also known as eicosanoic acid, is a major ω-6 polyunsaturated fatty acid (ω-6PUFA) and is involved in the process of cardiovascular disease (CVD), especially atherosclerosis. In addition, as an important anti-inflammatory and pro-resolution lipid mediator, LXA4 will be activated during the resolution stage of the inflammatory response and play the role of a "braking signal" in the inflammatory process, effectively regulating the intensity and process of the inflammatory response.

[0053] Ethyl 3-Indoleacetate is a derivative of indole-3-acetic acid (IAA), consisting of an indole ring and an ethyl acetate group. Its production pathway may be related to the metabolism of gut microbiota. Specifically, gut microbiota can metabolize tryptophan (Trp) into various indole derivatives, and Ethyl 3-Indoleacetate is one of the various indole derivatives. In addition, the CYP450 enzyme system in the liver, especially the CYP2E1 isoenzyme, can oxidize indole derivatives to generate other metabolites.

[0054] The English full name of N-(3-indolylacetyl)-L-alanine is "N-(3-Indolylacetyl)-L-alanine", which is a derivative formed by the combination of IAA and L-alanine. Its structure includes an indole ring and an acetylated aspartic acid residue. In chronic kidney disease, IAA is associated with the inflammation and fibrosis of cardiovascular diseases, and may also be an independent predictor of the mortality of patients with chronic kidney disease (CKD) and cardiovascular events. Therefore, IAA plays an important role in the progression of cardiovascular diseases, especially in patients with CKD.

[0055] In "Phosphatidylserine (Phosphatidylserine, PS)(19:0_18:2)", "19:0" means that the carbon chain of one of the fatty acids contains 19 carbon atoms and is a saturated fatty acid, that is, there is no double bond. "18:2" means that the carbon chain of another fatty acid has 18 carbon atoms and is an unsaturated fatty acid with 2 double bonds. In the phosphatidylserine molecule, these two fatty acids are respectively connected to different positions of the glycerol backbone. The types and structures of these two fatty acids have important effects on the physicochemical properties of phosphatidylserine, such as fluidity, hydrophilicity and hydrophobicity, and its functions in the organism, such as participating in the structure composition of cell membranes and cell signal transduction. As one of the components of cell membranes, phosphatidylserine can affect the fluidity and permeability of cell membranes, and can activate the metabolic and synthetic processes of various enzymes. Phosphatidylserine has been proven to play an important role in physiological processes such as apoptosis, inflammation and blood coagulation, and has the functions of preventing atherosclerosis, inhibiting inflammation, regulating blood coagulation and enhancing high-density lipoprotein (HDL). In addition, the properties of phosphatidylserine are related to the development of lipid-based drug delivery and the reconstruction of HDL.

[0056] In "Phosphatidic Acid (PA) (20:0_21:0)", "20:0" indicates that one of the fatty acid carbon chains contains 20 carbon atoms and is a saturated fatty acid; "21:0" indicates that the other fatty acid carbon chain has 21 carbon atoms and is also a saturated fatty acid. Among them, phosphatidic acid belongs to the lipid category and can be generated through the de novo synthesis pathway by phosphatidylcholine (PC), diacylglycerol, lysophosphatidic acid (LPA), or glycerol 3-phosphate and dihydroxyacetone phosphate. PA is present in almost all cell membrane structures, and PA and its derivative lysophosphatidic acid (LPA) are associated with various diseases. Among them, the LPA signal plays a key role in the pathophysiological processes of a series of cardiovascular diseases such as atherosclerosis, myocardial ischemia injury, myocardial remodeling, hypertension, and aortic valve stenosis. LPA participates in numerous biological effects through G protein-coupled receptors, specifically covering aspects such as cell proliferation, migration, cytokine secretion, and cytoskeleton rearrangement, thus playing an important role in both the physiological and pathological processes of the body.

[0057] In "Cholesterol Ester (CE) (19:0)", "19:0" indicates that the fatty acid carbon chain contains 19 carbon atoms and is a saturated fatty acid. Cholesterol ester is formed by the esterification reaction of a cholesterol molecule and a fatty acid molecule. The unique chemical properties of cholesterol ester make it play an important role in the lipid metabolism and transportation processes in the body. In the body, cholesterol ester is used for the transportation and storage of cholesterol and exists in the hydrophobic core of lipoproteins such as low-density lipoprotein (LDL) and high-density lipoprotein (HDL), and these lipoproteins are used to transport cholesterol in the blood circulation system. Abnormal levels of cholesterol ester and its metabolic processes are related to various diseases, especially cardiovascular diseases. For example, when the cholesterol ester level in LDL increases, the risk of developing atherosclerosis also increases. In addition, oxidized cholesterol ester (OxCE) also has pro-inflammatory and atherogenic properties.

[0058] In "Lysophosphatidylcholine (LPC) (O-22:1)", "O" represents an ether bond, and "22:1" indicates that one of the fatty acids in lysophosphatidylcholine has a fatty acid chain with 22 carbon atoms and 1 double bond. Lysophosphatidylcholine is a major component of oxidized low-density lipoprotein (oxLDL) and is associated with functional alterations in various cell types such as endothelial cells, smooth muscle cells, monocytes, macrophages, and T cells. LPC is derived from the cleavage of phosphatidylcholine by phospholipase A2 (PLA2) and can be converted to phosphatidylcholine (PC) under the action of lysophosphatidylcholine acyltransferase (LPCAT). LPC is associated with metabolic diseases and cardiovascular diseases such as diabetes, atherosclerosis, and dyslipidemia. In modified LDL and oxidized LDL, the content of LPC shows an upward trend, and it plays an important role in the formation process of atherosclerotic plaques and endothelial dysfunction. LPC is recognized as an effective pro-inflammatory and harmful mediator. In diabetic conditions, specific types of LPC can induce insulin resistance but also have a blood glucose-lowering effect. Thus, LPC plays an important role in the occurrence and development of various diseases such as cardiovascular diseases, inflammation, liver diseases, diabetes, and tumors, and is an important target in disease research and treatment.

[0059] In "Phosphatidylethanolamine (PE) (P-17:0_18:1)", "P" represents phospholipid, "17:0" indicates that the carbon chain of one fatty acid in phosphatidylethanolamine contains 17 carbon atoms and is a saturated fatty acid, and "18:1" indicates that the carbon chain of another fatty acid in phosphatidylethanolamine contains 18 carbon atoms and is an unsaturated fatty acid with 1 double bond. Glycerophospholipids include various types, such as Phosphatidylcholine (PC), Phosphatidylserine (PS), PE, etc. Among them, PE is the second most abundant phospholipid in the cell membrane, accounting for 15-25% of the total phospholipids in mammalian cells. PE plays a crucial role in a series of physiological processes, such as ensuring the integrity of the membrane structure, the process of lipid droplet formation, and the formation of autophagosomes. Changes in PE metabolism are associated with many metabolic diseases, such as atherosclerosis, insulin resistance, and obesity. The relative content of PC and PE can regulate the size and kinetic characteristics of lipid droplets, and in mitochondria, changes in the molar ratio of PC and PE will affect the energy generation process.

[0060] Based on this, step 120 above may specifically include using ultra-high performance liquid chromatography technology to analyze the plasma sample to obtain the expression data of metabolic markers. Exemplarily, using ultra-high performance liquid chromatography technology to analyze the plasma sample, according to the characteristic information of the metabolic markers, the expression data of the metabolic markers is obtained.

[0061] Among them, the characteristic information of the metabolic markers includes the molecular weight range of the substances involved in the metabolic markers, chemical structure characteristics, known chromatographic behavior characteristics such as specific retention time intervals, peak shape characteristics, etc.

[0062] Thus, the expression data of these metabolic markers can more effectively reflect the changes in the metabolic characteristics of the markers related to the occurrence of carotid plaques in the plasma sample, and determine the risk probability of the user developing carotid plaques within a preset time period.

[0063] In some embodiments of the present application, the expression data of the metabolic markers includes: the expression level of LXA4, the expression level of ethyl 3-indoleacetate, the expression level of N-(3-indolylacetyl)-L-alanine, the expression level of PS(19:0_18:2), the expression level of PA(20:0_21:0), the expression level of CE(19:0), the expression level of LPC(O-22:1), and the expression level of PE(P-17:0_18:1).

[0064] Based on this, step 130 above may specifically include inputting the expression data of metabolic markers into the first risk prediction model to obtain the risk score value of the user; wherein, the first risk prediction model is constructed based on the logistic regression algorithm.

[0065] Among them, the logistic regression algorithm can establish a mathematical relationship model between the biomarker expression level and the risk probability of carotid plaque occurrence, that is, the first risk prediction model, based on a large amount of known sample data, including the biomarker expression data of people with different carotid plaque conditions.

[0066] Exemplarily, after inputting the expression data of the metabolic markers of the new user into the first risk prediction model, the first risk prediction model will calculate a risk score value according to the mathematical relationship between the biomarker expression level and the risk probability of carotid plaque occurrence constructed internally, and comprehensively consider the weights of each biomarker and their expression levels. Among them, the weights corresponding to each biomarker are obtained based on this model, and the calculated risk score value can effectively quantify the relative possibility of the user having carotid plaque within a preset time period. For example, if the risk score value is relatively high, it means that the risk probability of the user having carotid plaque within the preset time period is relatively large; on the contrary, the risk probability of the user having carotid plaque within the preset time period is relatively small.

[0067] Thus, the risk score value obtained based on the first risk prediction model provides an intuitive, quantifiable and relatively accurate evaluation index for medical staff, which helps medical staff identify high-risk populations at an early stage, so as to be able to take targeted preventive measures in advance, such as adjusting lifestyle including diet, exercise, smoking cessation and alcohol restriction, etc., conducting more intensive medical monitoring such as regular carotid ultrasound examination, etc. or initiating appropriate drug intervention to reduce the risk of carotid plaque occurrence.

[0068] In some embodiments of the present application, the first risk prediction model can use the following formula (1) to obtain the risk score value:

[0069] P=(0.997×marker 1 )+(-2.169×marker 2 )+(0.734×marker 3 )+(0.999×marker 4 )

[0070] +(1.131×marker 5 )+(0.179×marker 6 )+(-1.232×marker 7 )+(2.083×marker 8 )…(1)

[0071] Among them, P is the risk score value, and marker 1 is the expression level of PS(19:0_18:2), and marker 2 is the expression level of PA(20:0_21:0), and marker 3 is the expression level of LPC(O-22:1), and marker 4 is the expression level of PE(P-17:0_18:1), and marker 5 is the expression level of CE(19:0), and marker 6 is the expression level of LXA4, and marker 7 is the expression level of N-(3-indolylacetyl)-L-alanine, and marker 8 is the expression level of ethyl 3-indoleacetate.

[0072] By constructing the first risk prediction model, integrating the expression levels of multiple metabolic markers related to the occurrence of carotid plaques into a formula, the risk status of an individual can be comprehensively evaluated. Multiply the expression level of each metabolic marker by the corresponding coefficient, and these coefficients reflect the weight of the corresponding marker in the overall risk assessment. For example, multiplying the expression level of PS(19:0_18:2) by 0.997 indicates that PS(19:0_18:2) has a positive contribution to the risk score and the degree of influence is reflected by the corresponding coefficient 0.997; while multiplying the expression level of PA(20:0_21:0) by -2.169 indicates that PA(20:0_21:0) has a negative impact on the risk score and the degree of influence is reflected by the corresponding coefficient 2.169.

[0073] Thus, the first risk prediction model converts the expression levels of multiple metabolic markers related to the occurrence of carotid plaques into a risk score value P. Compared with analyzing a single metabolic marker alone, the first risk prediction model can more comprehensively reflect the overall biological characteristic changes related to the occurrence of carotid plaques and their corresponding risk association degrees, thereby providing a basis and reference for the assessment and prevention of carotid plaque-related diseases.

[0074] Next, it will be combined with Figures 2 to 4 to specifically illustrate the construction method of the above first risk model. The construction method of the first risk model includes the following steps:

[0075] Step 201, Select the study population: Given that the occurrence of carotid plaque is an early sign of atherosclerosis, a nested case-control study was conducted. The study subjects were participants from the ChinaHEART cohort (Health Evaluation Andrisk Reduction through nationwide Teamwork) who underwent carotid ultrasound examinations at both baseline and two-year follow-up. Three hundred and fifty patients who developed carotid plaque during the two-year follow-up were selected as cases, and 350 subjects who did not develop carotid plaque during the two-year follow-up and were 1:1 matched with the cases in terms of project site, age, gender, body mass index (BMI), current smoking status, blood pressure, blood lipids, and diabetes mellitus history (DM) at baseline were selected as controls. Therefore, this study included a total of 700 cases (350 pairs) of samples. Subsequently, the 350 pairs were randomly divided into a discovery set and a validation set. The final discovery set included 200 cases of patients who developed carotid plaque during the subsequent two-year follow-up and 200 matched controls who still did not develop carotid plaque; the validation set included 150 cases of patients who developed carotid plaque and 150 matched controls who developed carotid plaque.

[0076] Step 202, Metabolomics analysis: Untargeted ultra-high performance liquid chromatography-tandem mass spectrometry (UPLC-MS / MS) metabolomics analysis was used for all 700 subjects participating in the study. This analysis method can comprehensively detect the situation of various metabolic markers in the subjects' bodies.

[0077] Step 203, Determine metabolic markers: In the discovery set, eight metabolic markers related to the development of carotid plaque were determined through univariate logistic regression analysis and stepwise screening statistical analysis methods, including four glycerophospholipids, namely PS(19:0_18:2), PA(20:0_21:0), LPC(O-22:1), and PE(P-17:0_18:1), one fatty acyl, namely lipoxin A4, one cholesterol ester, namely CE(19:0), and two indole derivatives, namely N-(3-indolylacetyl)-L-alanine and 3-indole acetate.

[0078] Step 204, Construct the first risk model: Using the eight metabolic markers determined in the above step 203 as independent variables and whether carotid plaque occurred within two years as the dependent variable, a logistic regression algorithm was used for modeling. At the same time, by comparing the relative contents of the eight metabolic markers in the case group and the control group, the correlation between these eight metabolic markers and the occurrence of carotid plaque was further verified. Specifically, as Figure 2 shown, Figure 2 shows the comparison of the fold change in the expression of the eight metabolic markers in the discovery set and the validation set. Figure 2The column heights therein represent the average log2-fold changes (log2FC) of each compound, where the fold change is the ratio of the case group to the control group. Among them, the metabolite marker corresponding to LIPID-N-1296 is PS(19:0_18:2); the metabolite marker corresponding to LIPID-N-1451 is PA(20:0_21:0); the metabolite marker corresponding to LIPID-P-0058 is CE(19:0); the metabolite marker corresponding to LIPID-P-0402 is LPC(O-22:1); the metabolite marker corresponding to LIPID-P-1317 is PE(P-17:0_18:1); the metabolite marker corresponding to MEDN037 is lipoxin A4; the metabolite marker corresponding to MEDP1962 is N-(3-indolylacetyl)-L-alanine; the metabolite marker corresponding to MEDP2033 is ethyl 3-indoleacetate. See Figure 2 It can be found that 6 compounds were significantly up-regulated in the case group and 2 compounds were significantly down-regulated in the case group in both the discovery set and the validation set. The risk score of each subject for carotid plaque was calculated by the above formula (1).

[0079] Step 205, verification and evaluation of the first risk model: Use the validation set (150 cases and 150 controls) determined in the above step 202 to verify the first risk model. By comparing the prediction results of the first risk model with the actual occurrence of carotid plaque in the validation set, evaluate the performance indicators of the first risk model, such as odds ratio (OR) and Area under the ROC Curve (AUC). As Figure 3 and Figure 4 shown, the first risk model showed a strong association with the risk of carotid plaque within two years in both the discovery set (OR = 2.72, 95% confidence interval (CI) = 2.24 - 3.43; P < 0.001) and the validation set (OR = 1.73, 95% CI = 1.55 - 1.97; P < 0.001), and the AUCs in the discovery set and the validation set were 0.970 (95% CI = 0.956 - 0.984) and 0.900 (95% CI = 0.864 - 0.936), respectively. These results indicate that the first risk model constructed based on the logistic regression algorithm, using 8 metabolite markers, can effectively predict the risk of an individual developing carotid plaque within two years and has good performance on different data sets, verifying the effectiveness and practicality of the first risk model.

[0080] It should be noted here that the ROC curve is used to evaluate the performance of a classification model. The higher the AUC (area under the curve) value, the stronger the prediction ability of the model. As Figure 4 shown, the AUC values of Model 1 in the two sets are relatively low, indicating that the model constructed only based on risk factors such as age, gender, BMI, smoking status, hypertension, dyslipidemia, and diabetes has poor performance in predicting carotid plaques (these factors have been matched). The AUC values of Model 2 and Model 3 in the discovery set and the validation set are relatively high, indicating that the first risk model constructed based on the 8 metabolic markers determined in step 203 above has high accuracy in predicting carotid plaques.

[0081] In some embodiments of the present application, the above-mentioned biomarker may further include protein markers, and the protein markers include thrombomodulin, intercellular adhesion molecule ICAM-3, P-selectin, growth differentiation factor-15 GDF-15, adiponectin, monocyte chemoattractant protein-1 MCP-1, interleukin-10 IL-10, placental growth factor PlGF, epidermal growth factor-like tyrosine kinase receptor 2 Tie-2, vascular endothelial growth factor D VEGF-D, and vascular cell adhesion molecule 1 VCAM-1. The expression data of the biomarker includes the expression data of the protein marker, and the expression data of the protein marker includes: the expression level of thrombomodulin, the expression level of ICAM-3, the expression level of P-selectin, the expression level of GDF-15, the expression level of adiponectin, the expression level of MCP-1, the expression level of IL-10, the expression level of PlGF, the expression level of Tie-2, the expression level of VEGF-D, and the expression level of VCAM-1.

[0082] Based on this, step 120 above may specifically include detecting the plasma sample by electrochemiluminescence technology to obtain the expression data of the protein marker.

[0083] Exemplarily, the electrochemiluminescence technology platform of Meso Scale Diagnostics (MSD) of Meso Scale Diagnostics LLC can be used to detect the plasma sample. When detecting the plasma sample, this electrochemiluminescence technology platform can accurately identify and quantify the content of various protein markers in the sample.

[0084] Next, the above-mentioned various protein markers will be specifically described.

[0085] Protein markers associated with carotid plaque development involve multiple mechanisms, including vascular injury, inflammation, and angiogenesis. These protein markers are mainly involved in two key pathways during the development of carotid plaque and atherosclerotic cardiovascular disease (ASCVD).

[0086] The first pathway is the vascular endothelial growth factor receptor pathway, which plays an essential role in promoting angiogenesis and lymphangiogenesis. Among the vascular endothelial growth factor receptor family, placental growth factor (PlGF) plays an important role. Specifically, PlGF is involved in the repair process of endothelial cells and smooth muscle cells, and it can provide certain protective effects for patients with carotid plaque and ASCVD.

[0087] The second pathway is related to the angiopoietin (Ang) and tyrosine-kinase with Ig and EGF-homology (Tie) system. Under inflammatory and hypoxic conditions, the level of Ang-2 in the Ang family will increase significantly, and then it will activate Tie-2 in the Tie family, leading to a substantial increase in the expression of monocyte chemoattractant protein-1 (MCP-1). A significant feature of atherosclerosis is the infiltration of leukocytes into the inflammatory area. During this process, monocytes are activated by chemokines such as MCP-1, enabling monocytes to adhere to endothelial cell adhesion molecules, including VCAM-1 and inter-cellular adhesion molecule-1 (ICAM-1), thereby promoting the stable adhesion of monocytes to the endothelium and subsequent migration to the arterial intima. The movement of the above monocytes is mediated by selectins, especially P-selectin. The upregulation of the expression of ICAM-3, another member of the cell adhesion factor family, will further enhance the inflammatory response of macrophages.

[0088] Adiponectin and interleukin-10 (IL-10) can promote the progression of carotid plaque by promoting lipid reduction and exerting anti-inflammatory effects.

[0089] Growth Differentiation Factor-15 (GDF-15) has a relatively low expression level in the cardiovascular tissues of healthy individuals. However, its expression significantly increases in cases of cardiovascular injury caused by atherosclerosis and other cardiovascular diseases. Excessive GDF-15 can increase angiogenesis and inflammatory responses, thereby making atherosclerotic plaques more likely to occur. In terms of the predictive ability of individual biomarkers, both GDF-15 and PlGF can significantly improve the predictive ability in the prediction model. GDF-15 can be used to predict major adverse cardiovascular events and thrombosis, while PlGF can be used to predict cardiovascular events in patients with Chronic Kidney Disease (CKD).

[0090] Thrombomodulin is a glycoprotein present on the surface of vascular endothelial cells and plays an important role in the coagulation process. By binding to thrombin and activating the protein C system, it exerts an anticoagulant effect, which is of great significance for maintaining the balance between intravascular coagulation and fibrinolysis.

[0091] Vascular endothelial growth factor receptor 1 (fms-related tyrosine kinase 1, Flt1) is one of the members of the vascular endothelial growth factor (VEGF) receptor family and is mainly involved in the regulation of angiogenesis. Under normal physiological conditions, its expression and function are strictly regulated.

[0092] In some embodiments of the present application, based on the ChinaHEART cohort (Health Evaluation And riskReduction through nationwide Teamwork), the above protein biomarkers were detected through the MSD platform, and an early carotid plaque prediction model independent of traditional cardiovascular disease risk factors, namely the second risk prediction model, was established based on the above protein biomarkers. In addition, in the UK Biobank cohort, adding the above protein biomarkers to the risk model of traditional atherosclerotic cardiovascular disease (ASCVD) can strongly increase the additional predictive value of ASCVD.

[0093] Based on this, step 130 may further include inputting the expression data of the protein biomarker into the second risk prediction model to obtain the risk score value of the user; wherein, the second risk prediction model is constructed based on the logistic regression algorithm.

[0094] Therefore, different protein markers may be involved in different links of carotid plaque formation, such as inflammatory response, cell proliferation, lipid metabolism, etc. The second risk prediction model combines 11 protein markers and can capture information related to the occurrence of carotid plaque from more perspectives, thereby improving the accuracy and reliability of the risk score value.

[0095] Next, the process of constructing the second risk prediction model based on the logistic regression algorithm will be specifically described.

[0096] In some embodiments of the present application, among the protein markers related to ASCVD reported in previous studies, there may be many protein markers related to cardiovascular diseases available for selection. However, there may be correlations among these protein markers, that is, there is redundant information. Based on this, before constructing the second risk prediction model, the above data processing method may further include screening out protein markers from the preset protein markers through the least absolute shrinkage and selection operator algorithm (LASSO regression algorithm).

[0097] For example, some protein markers may highly overlap in biological functions or be highly correlated in expression patterns. The LASSO regression algorithm can shrink some coefficients to zero by imposing a penalty term, thereby accurately screening out the most representative protein markers, which can remove variables that contribute little to the model or are highly redundant with other markers and simplify the model structure. Then, the screened protein markers are used to construct the second risk prediction model through the logistic regression algorithm. Among them, the model parameters of the second risk prediction model can be estimated through the training data set, where the training data set includes whether the known user has the risk of carotid plaque and the corresponding protein marker expression data.

[0098] Next, the construction method of the above second risk model will be specifically described. The construction method of the second risk model includes the following steps:

[0099] Step 301: Preliminary screening of protein biomarkers: Screen out 28 protein biomarkers from biomarkers related to vascular injury, inflammation, angiogenesis, and metabolism, specifically including adiponectin, fms-like tyrosine kinase-1 (Flt-1), placental growth factor (PlGF), vascular endothelial growth factor A (VEGF-A), vascular endothelial growth factor C (VEGF-C), vascular endothelial growth factor D (VEGF-D), basic fibroblast growth factor (bFGF), cystatin C, growth differentiation factor-15 (GDF-15), fibroblast growth factor 23 (FGF-23), interferon-γ (IFN-γ), interleukin 10 (IL-10), interleukin 6 (IL-6), interleukin 8 (IL-8), E-selectin, P-selectin, intercellular adhesion molecule-1 (ICAM-1), intercellular adhesion molecule-3 (ICAM-3), thrombomodulin, vascular cell adhesion molecule-1 (VCAM-1), tumor necrosis factor α (TNF-α), serum amyloid A (SAA), C-reactive protein (CRP), endothelial cell-specific tyrosine kinase receptor-2 (Tie-2), C-peptide, insulin, human proinsulin, and monocyte chemoattractant protein-1 (MCP-1).

[0100] Step 302: Determine the study population and grouping: With the help of ChinaHEART Chinese Heart Cohort, screen 145 subjects with newly developed carotid plaques during the two-year follow-up as the case group. At the same time, select another 147 subjects who did not develop carotid plaques during the two-year follow-up and were matched with the cases in terms of project site, age, gender, body mass index (BMI), current smoking status, blood pressure, blood lipids, and diabetes mellitus history (DM) at baseline as the control group. Finally, 292 participants without protein data missing were included in the discovery set.

[0101] Step 303: Construction and validation of the second risk prediction model: As Figures 5A to 5D The four subgraphs of Figure 5A collectively show the complete process of a prediction model from variable selection ( Figure 5B ) to model bias analysis ( Figure 5C ), then to variable prediction performance evaluation ( Figure 5D ), and finally to overall model prediction ability evaluation ( Figure 5AAs shown, when the logarithm (λ) reaches the minimum mean square error (λ = 0.028), this model is determined to be the optimal model, and 11 variables with non-zero coefficients, namely 11 protein markers, are screened out from numerous variables, which may specifically include thrombomodulin, ICAM-3, P-selectin, GDF-15, adiponectin, MCP-1, IL-10, PlGF, Tie-2, VEGF-D, and VCAM-1. Using these 11 protein markers to construct a second risk prediction model, as Figure 5C and Figure 5D shown, the area under the receiver operating characteristic curve (AUC) is 0.778, the Brier score is 0.192, and the result of the Hosmer-Lemeshow goodness-of-fit test (HLtest) is not statistically significant (P = 0.467), indicating that the second risk prediction model has a good fit. For the results of internal validation, after bootstrap correction with 1000 repeated samplings, the AUC is 0.778 (95% CI is 0.726 - 0.828), showing that the second risk prediction model has stable performance.

[0102] Step 304: Use the data of the UK Biobank to validate the 11 protein markers and evaluate the incremental value provided by these 11 protein markers in the risk prediction of atherosclerotic cardiovascular disease (ASCVD). Since the overlapping biomarkers are different, only the proteins measured in both the China Heart Project and the UK Biobank are used to construct the model.

[0103] Among the 30,800 participants in the UK Biobank, 3,465 people (11.25%) were determined to have developed new atherosclerotic cardiovascular disease (ASCVD), and the median time for the onset diagnosis was 7.74 years. Compared with the control group, the participants in the case group were older, more likely to be male, had a higher body mass index (BMI), higher systolic blood pressure (SBP), higher smoking rate, and more family history.

[0104] Figure 6A shows the receiver operating characteristic curves between the traditional prediction model and the new prediction model provided by some embodiments of the present application. First, a traditional prediction model is constructed based on traditional predictors, and these traditional predictors include factors closely related to ASCVD risk, such as age, gender, race, family history, BMI, blood pressure, ratio of total cholesterol to high-density lipoprotein cholesterol, etc. See Figure 6AIt can be seen that the AUC of the traditional prediction model can reach 0.700. Then, 10 protein markers are added to the traditional model to construct a new prediction model, and the AUC of the new prediction model can reach 0.721. Among them, these 10 protein markers include thrombomodulin, ICAM-3, P-selectin, GDF-15, adiponectin, MCP-1, IL-10, PlGF, VEGF-D, and VCAM-1. See Figure 6B It can be seen that the Brier score is 0.093, which proves that these 10 protein markers have a good effect on predicting the risk probability of carotid plaque occurrence in users within a preset time period.

[0105] In some embodiments of the present application, such as Figure 7 As shown, the above data processing method may further include steps 410 to 430.

[0106] Step 410: Determine a target score range that matches the risk score value from multiple preset score ranges according to the risk score value.

[0107] Exemplarily, the multiple preset score ranges refer to a series of intervals set in advance according to statistical analysis, expert experience, or medical standards, and each interval corresponds to a specific risk level or health status. After obtaining the risk score value, this risk score value is compared with the multiple preset score ranges. During the comparison process, a score range that includes this risk score value is determined as the target score range.

[0108] Step 420: Determine the target risk level corresponding to the target score range as the target risk level of the user, and the target risk level is used to characterize the risk probability of carotid plaque occurrence in the user within a preset time period.

[0109] Among them, the risk level aims to hierarchically divide and characterize the high or low risk probability of carotid plaque occurrence in the user within a preset time period, so as to intuitively reflect the degree difference of the risk of carotid plaque faced by different users.

[0110] Exemplarily, the risk levels are predefined and there are multiple of them. There is a one-to-one correspondence between the multiple risk levels and the multiple score ranges. After determining the target score range according to step 210, it can be directly and accurately mapped to the risk level corresponding to the target score range, so as to intuitively and clearly reflect the risk probability of carotid plaque occurrence in the user within a preset time period. For example, a low risk level indicates a lower probability of carotid plaque occurrence in the user within a preset time period; while a high risk level indicates a higher probability of carotid plaque occurrence in the user within a preset time period.

[0111] Step 430: Determine a risk prevention and control strategy for the user according to the target risk level.

[0112] In this way, a risk prevention and control strategy for the user is formulated according to the determined target risk level, realizing the effective combination of medical treatment and personalized health management. Exemplarily, for low-risk users, the risk prevention and control strategy focuses on advocating a healthy lifestyle, such as reasonable diet, moderate exercise, smoking cessation and alcohol restriction, etc., to prevent the formation of carotid plaques; for medium-risk users, the frequency of regular physical examinations can be increased, and the reexamination and monitoring of specific biomarkers can be carried out, etc.; for high-risk users, a comprehensive treatment plan needs to be formulated, including drug treatment to regulate cardiovascular risk factors such as blood lipid, blood pressure, and blood sugar, as well as the evaluation of possible surgical interventions, etc.

[0113] Thus, it is possible to systematically, comprehensively and accurately evaluate and grade the risk of carotid plaque occurrence in users based on biomarker expression data, so as to realize the formulation of personalized risk prevention and control strategies, tailor appropriate intervention measures according to the risk levels of different users, avoid the situations of over-medical treatment and medical insufficiency, and improve the utilization efficiency of medical resources. In this way, it helps to improve the prevention and control level of atherosclerosis in the overall population. Moreover, by early identifying high-risk individuals and strictly managing and drug-intervening high-risk users, the occurrence of atherosclerotic cardiovascular diseases in these users can be effectively prevented or delayed.

[0114] Based on the data processing method provided in the above embodiments, correspondingly, the present application also provides a data processing system. Please refer to the following embodiments.

[0115] Figure 8 The structural schematic diagram of a data processing system provided in some embodiments of the present application is shown.

[0116] As Figure 8 shown, the data processing system includes: a biomarker extraction device 510, a scoring device 520, and a display device 530.

[0117] The biomarker extraction device 510 is used to extract the expression data of biomarkers from the plasma sample of the user. The biomarkers include the markers related to the occurrence of carotid plaques, and the expression data of the biomarkers includes the expression levels of the biomarkers in the plasma sample.

[0118] The scoring device 520 is used to determine the risk score value of the user based on the expression data of the biomarkers. The risk score value is used to characterize the risk probability of carotid plaque occurrence in the user within a preset time period.

[0119] The display device 530 is connected to the scoring device and is used to display the scoring result of the user. The scoring result includes the risk score value.

[0120] Exemplarily, the biomarker extraction device 510 can be a set of bioanalysis devices, specifically including an ultra-high performance liquid chromatograph, a mass spectrometer, and related electronic devices using an electrochemiluminescence technology platform. Among them, the ultra-high performance liquid chromatograph is used to separate metabolites in the plasma sample, and the mass spectrometer is used to detect the metabolites separated by the ultra-high performance liquid chromatograph to extract the concentration of metabolite biomarkers. The related electronic devices using an electrochemiluminescence technology platform are used to extract the concentration of protein biomarkers.

[0121] The scoring device 520 is used to receive the expression data of biomarkers extracted by the biomarker extraction device 510, and analyze and process the expression data of these biomarkers based on a preset algorithm or model, and finally calculate the risk score value of the user. This risk score value is a quantitative indicator used to characterize the probability of the user having carotid plaque within a preset time period. Specifically, the scoring device can be a computer or a server running a specially designed software program to implement the data processing method in the first aspect above.

[0122] The display device 530 is a window for the user to interact with the data processing system, and is used to present the scoring result obtained by the scoring device to the user in a visual manner. The display device 530 can be any electronic device capable of displaying text and images, such as a computer monitor, a tablet computer, or a smart phone, etc. Through the display device 530, the user can intuitively understand the scoring result and take corresponding preventive measures as needed. Exemplarily, the display device 530 can be a terminal of an electronic medical record system in a hospital or the user's personal smart phone. In a hospital scenario, a doctor can view the user's scoring result on the terminal of the electronic medical record system and use it as a reference for formulating a treatment plan. In a home scenario, the user can receive their risk scoring report through a third-party application on the smart phone and adjust their living habits or receive treatment based on the risk prevention and control strategy.

[0123] Through the biomarker extraction device 510, the expression data of biomarkers related to the occurrence of carotid plaque can be accurately extracted from the user's plasma sample. These biomarkers, as early warning signals of disease occurrence, the change in their expression levels can reflect the risk of carotid plaque that the user may face within a preset time period. The scoring device 520 uses the expression data of these biomarkers and can calculate the risk score value of the user through a specific algorithm or model. This risk score value is a quantitative indicator that can intuitively and accurately reflect the risk probability of carotid plaque occurrence in the user within a preset time period, thereby providing a precise risk assessment for the user. Then, the scoring device 520 transmits the calculated risk score value to the display device 530, and the display device 530 can convert it into a format suitable for display, such as a digital format or a visual chart format, to intuitively display the carotid plaque risk status of the user.

[0124] In some embodiments of the present application, the biomarker includes a metabolic biomarker, and the metabolic biomarker includes lipoxin A4, ethyl indole-3-acetate, N-(3-indolylacetyl)-L-alanine, phosphatidylserine PS(19:0_18:2), phosphatidic acid PA(20:0_21:0), cholesteryl ester CE(19:0), lysophosphatidylcholine LPC(O-22:1), and phosphatidylethanolamine PE(P-17:0_18:1). Based on this, the above-mentioned scoring device is used to analyze a plasma sample by using ultra-high performance liquid chromatography technology to obtain the expression data of the metabolic biomarker.

[0125] In some embodiments of the present application, the expression data of the metabolic biomarker includes the expression level of lipoxin A4, the expression level of ethyl indole-3-acetate, the expression level of N-(3-indolylacetyl)-L-alanine, the expression level of PS(19:0_18:2), the expression level of PA(20:0_21:0), the expression level of CE(19:0), the expression level of LPC(O-22:1), and the expression level of PE(P-17:0_18:1); based on this, the above-mentioned scoring device is used to input the expression data of the metabolic biomarker into the first risk prediction model to obtain the risk score value of the user; wherein, the first risk prediction model is constructed based on the logistic regression algorithm.

[0126] In some embodiments of the present application, the above-mentioned scoring device is specifically used to obtain the risk score value by using the following formula:

[0127] P = (0.997 × marker 1 ) + (-2.169 × marker 2 ) + (0.734 × marker 3 ) + (0.999 × marker 4 )

[0128] + (1.131 × marker 5 ) + (0.179 × marker 6 ) + (-1.232 × marker 7 ) + (2.083 × marker 8 )

[0129] wherein, P is the risk score value, marker 1 is the expression level of PS(19:0_18:2), marker 2 is the expression level of PA(20:0_21:0), marker 3 is the expression level of LPC(O-22:1), marker 4is the expression level of PE (P-17:0_18:1), marker 5 is the expression level of CE (19:0), marker 6 is the expression level of lipoxin A4, marker 7 is the expression level of N-(3-indolylacetyl)-L-alanine, marker 8 is the expression level of ethyl 3-indoleacetate.

[0130] In some embodiments of the present application, the biomarker includes a protein biomarker, and the protein biomarker includes thrombomodulin, intercellular adhesion molecule ICAM-3, P-selectin, growth differentiation factor-15 GDF-15, adiponectin, monocyte chemoattractant protein-1 MCP-1, interleukin-10 IL-10, placental growth factor PlGF, epithelial growth factor-like tyrosine kinase receptor 2 Tie-2, vascular endothelial growth factor D VEGF-D, and vascular cell adhesion molecule 1 VCAM-1; the expression data of the biomarker includes the expression data of the protein biomarker, and the expression data of the protein biomarker includes the expression level of thrombomodulin, the expression level of ICAM-3, the expression level of P-selectin, the expression level of GDF-15, the expression level of adiponectin, the expression level of MCP-1, the expression level of IL-10, the expression level of PlGF, the expression level of Tie-2, the expression level of VEGF-D, and the expression level of VCAM-1; based on this, the above scoring device is used to detect a plasma sample by electrochemiluminescence technology to obtain the expression data of the protein biomarker.

[0131] In some embodiments of the present application, the above scoring device is used to input the expression data of the protein biomarker into a second risk prediction model to obtain the risk score value of the user; wherein, the second risk prediction model is constructed based on a logistic regression algorithm.

[0132] In some embodiments of the present application, the above scoring device is used to determine a target scoring range that matches the risk score value from a plurality of preset scoring ranges according to the risk score value; determine the risk level corresponding to the target scoring range as the target risk level of the user, and the target risk level is used to characterize the risk probability of the user's carotid plaque occurrence within a preset time period; determine a risk prevention and control strategy for the user according to the target risk level.

[0133] In some embodiments of the present application, the above display device is used to display the risk score value, the target risk level, and the risk prevention and control strategy for the user.

[0134] Based on the data processing method provided in the above embodiments, correspondingly, the present application also provides a specific implementation manner of the data processing device. Please refer to the following embodiments.

[0135] See Figure 9, the data processing device provided by the embodiments of the present application includes:

[0136] A first acquisition module 610, configured to acquire a plasma sample of a user;

[0137] A first determination module 620, configured to detect the plasma sample to obtain expression data of biomarkers, where the biomarkers include markers related to the occurrence of carotid plaques, and the expression data of the biomarkers includes the expression levels of the biomarkers in the plasma sample;

[0138] A second determination module 630, configured to determine a risk score value of the user based on the expression data of the biomarkers, where the risk score value is used to characterize the risk probability of the occurrence of carotid plaques in the user within a preset time period.

[0139] Thus, the expression data of the biomarkers obtained by the first determination module 620 through detecting the plasma sample acquired by the first acquisition module 610 accurately reflects the concentration level of the biomarkers related to the occurrence of carotid plaques in the plasma. Since the biomarkers are correlated with the occurrence of carotid plaques, the comprehensive analysis of their expression data can more comprehensively reflect the potential risk of the occurrence of carotid plaques in the user. Therefore, the risk score value converted from the expression data of these biomarkers by the second determination module 630 can accurately predict the risk probability of the occurrence of carotid plaques in the user within a preset time period.

[0140] In some embodiments of the present application, when the biomarkers include metabolic markers, and the metabolic markers include lipoxin A4, ethyl indole-3-acetate, N-(3-indolylacetyl)-L-alanine, phosphatidylserine PS(19:0_18:2), phosphatidic acid PA(20:0_21:0), cholesteryl ester CE(19:0), lysophosphatidylcholine LPC(O-22:1), and phosphatidylethanolamine PE(P-17:0_18:1), the above-mentioned first determination module 620 can be used to analyze the plasma sample by using ultra-high performance liquid chromatography technology to obtain the expression data of the metabolic markers.

[0141] In some embodiments of the present application, the expression data of the metabolic markers includes the expression level of lipoxin A4, the expression level of ethyl indole-3-acetate, the expression level of N-(3-indolylacetyl)-L-alanine, the expression level of PS(19:0_18:2), the expression level of PA(20:0_21:0), the expression level of CE(19:0), the expression level of LPC(O-22:1), and the expression level of PE(P-17:0_18:1); based on this, the above-mentioned second determination module 530 can be used to input the expression data of the metabolic markers into a first risk prediction model to obtain the risk score value of the user; where the first risk prediction model is constructed based on a logistic regression algorithm.

[0142] In some embodiments of the present application, the first risk prediction model in the second determination module 630 uses the following formula to obtain a risk score value:

[0143] P = (0.997 × marker 1 ) + (-2.169 × marker 2 ) + (0.734 × marker 3 ) + (0.999 × marker 4 )

[0144] + (1.131 × marker 5 ) + (0.179 × marker 6 ) + (-1.232 × marker 7 ) + (2.083 × marker 8 )

[0145] where P is the risk score value, marker 1 is the expression level of PS(19:0_18:2), marker 2 is the expression level of PA(20:0_21:0), marker 3 is the expression level of LPC(O-22:1), marker 4 is the expression level of PE(P-17:0_18:1), marker 5 is the expression level of CE(19:0), marker 6 is the expression level of lipoxin A4, marker 7 is the expression level of N-(3-indolylacetyl)-L-alanine, marker 8 is the expression level of ethyl 3-indoleacetate.

[0146] In some embodiments of the present application, when the biomarker includes a protein biomarker, the protein biomarker includes thrombomodulin, intercellular adhesion molecule ICAM-3, P-selectin, growth differentiation factor-15 GDF-15, adiponectin, monocyte chemoattractant protein-1 MCP-1, interleukin-10 IL-10, placental growth factor PlGF, epithelial growth factor-like tyrosine kinase receptor 2 Tie-2, vascular endothelial growth factor D VEGF-D, and vascular cell adhesion molecule 1 VCAM-1; the expression data of the biomarker includes the expression data of the protein biomarker, and the expression data of the protein biomarker includes the expression levels of thrombomodulin, ICAM-3, P-selectin, GDF-15, adiponectin, MCP-1, IL-10, PlGF, Tie-2, VEGF-D, and VCAM-1, the above-mentioned first determination module 620 can specifically be used to detect the plasma sample through electrochemiluminescence technology to obtain the expression data of the protein biomarker.

[0147] In some embodiments of the present application, the above-mentioned second determination module 630 can specifically be used to input the expression data of the protein biomarker into the second risk prediction model to obtain the risk score value of the user; wherein, the second risk prediction model is constructed based on the logistic regression algorithm.

[0148] In some embodiments of the present application, the above-mentioned data processing device may further include:

[0149] A third determination module, configured to determine a target score range that matches the risk score value from a plurality of preset score ranges according to the risk score value;

[0150] A fourth determination module, configured to determine the risk level corresponding to the target score range as the target risk level of the user, and the target risk level is used to characterize the risk level of the user having carotid plaque within a preset time period;

[0151] A fifth determination module, configured to determine a risk prevention and control strategy for the user according to the target risk level.

[0152] Each module of the data processing device provided in the embodiments of the present application can implement Figures 1 to 3 the functions of each step of the provided data processing method and can achieve its corresponding technical effects. For the sake of brevity of description, it will not be elaborated here.

[0153] Figure 10 The hardware structure diagram of an electronic device provided in some embodiments of the present application is shown.

[0154] As Figure 10As shown, the electronic device may include a processor 701 and a memory 702 storing computer program instructions.

[0155] Specifically, the above-mentioned processor 701 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured as one or more integrated circuits for implementing the embodiments of the present application.

[0156] The memory 702 may include a mass storage for data or instructions. By way of example and not limitation, the memory 702 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory 702 may include a removable or non-removable (or fixed) medium. In a suitable case, the memory 702 may be internal or external to the integrated gateway disaster recovery device. In a specific embodiment, the memory 702 is a non-volatile solid-state memory.

[0157] In a specific embodiment, the memory 702 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory 702 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the data processing method according to the first aspect of the present application.

[0158] The processor 701 reads and executes the computer program instructions stored in the memory 702 to implement any one of the data processing methods in the above embodiments.

[0159] In one example, the electronic device 700 may further include a communication interface 703 and a bus 710. Among them, as Figure 7 shown, the processor 701, the memory 702, and the communication interface 703 are connected through the bus 710 to complete communication with each other.

[0160] The communication interface 703 is mainly used to implement communication between each module, device, unit, and / or device in the embodiments of the present application.

[0161] The bus 710 includes hardware, software, or both, and couples components of the electronic device together. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, the bus 710 may include one or more buses. Although embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0162] The electronic device 700 can execute the data processing method in the embodiments of the present application, thereby implementing the Figures 1 to 9 data processing method and apparatus described in conjunction with

[0163] In addition, in combination with the data processing method in the above embodiments, embodiments of the present application can provide a computer-readable storage medium to implement. Computer program instructions are stored on the computer-readable storage medium; when the computer program instructions are executed by a processor, any one of the data processing methods in the above embodiments is implemented. Examples of computer-readable storage media include non-transitory computer-readable storage media, such as a portable disk, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM or Flash Memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, etc.

[0164] In addition, in combination with the data processing method in the above embodiments, embodiments of the present application can provide a computer program product to implement. The program product is stored in a storage medium and specifically may include a computer program or instructions. When the computer program or instructions are executed by a processor, any one of the data processing methods in the above embodiments is implemented. The program product is executed by at least one processor to implement each process of the data processing method embodiment as described above and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0165] It should be clear that the present application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0166] The functional blocks shown in the above structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted via a data signal carried in a carrier wave over a transmission medium or a communication link. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0167] It should also be noted that the exemplary embodiments mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0168] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block in the flowcharts and / or block diagrams, and the combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing devices to generate a machine such that these instructions executed by the processor of the computer or other programmable data processing devices enable the implementation of the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each block in the block diagrams and / or flowcharts, and the combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0169] The above are only specific implementation manners of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application.

Claims

1. A data processing method, characterized in that: The method comprises: Obtaining a plasma sample from a user; Testing the plasma sample to obtain biomarker expression data, wherein the biomarker includes a marker related to the occurrence of carotid artery plaque, and the biomarker expression data includes the expression amount of the biomarker in the plasma sample; Based on the expression data of the biomarker, a risk score value of the user is determined, and the risk score value is used to characterize the risk probability of occurrence of carotid artery plaque in the user within a preset time period.

2. The method according to claim 1, characterized in that The biomarkers include metabolic markers, and the metabolic markers include lipoxin A4, 3-indoleacetic acid ethyl ester, N-(3-indoleacetyl)-L-alanine, phosphatidylserine PS (19:0_18:2), phosphatidic acid PA (20:0_21:0), cholesterol ester CE (19:0), lysophosphatidylcholine LPC (O-22:1) and phosphatidylethanolamine PE (P-17:0_18:1); The detecting of the plasma sample to obtain the expression data of the biomarker includes: The plasma samples are analyzed using ultra-high performance liquid chromatography technology to obtain expression data of metabolic markers.

3. The method according to claim 2, characterized in that The expression data of the metabolic markers include lipoxin A4 expression, 3-indoleacetate expression, N-(3-indoleacetyl)-L-alanine expression, PS (19:0_18:2) expression, PA (20:0_21:0) expression, CE (19:0) expression, LPC (O-22:1) expression and PE (P-17:0_18:1) expression; The step of determining the risk score of the user based on the expression data of the biomarker comprises: Inputting the expression data of the metabolite marker into a first risk prediction model to obtain a risk score value of the user; Among them, the first risk prediction model is constructed based on a logistic regression algorithm.

4. The method according to claim 3, characterized in that The step of inputting the expression data of the metabolite marker into a first risk prediction model to obtain a risk score value of the user includes: The first risk prediction model uses the following formula to obtain the risk score value: P=(0.997×marker1)+(-2.169×marker2)+(0.734×marker3)+(0.999×marker4)+(1.131×marker5)+(0.179×marker6)+(-1.232×marker7)+(2.083×marker8) Among them, P is the risk score value, marker1 is the expression level of PS (19:0_18:2), marker2 is the expression level of PA (20:0_21:0), marker3 is the expression level of LPC (O-22:1), marker4 is the expression level of PE (P-17:0_18:1), marker5 is the expression level of CE (19:0), marker6 is the expression level of lipoxin A4, marker7 is the expression level of N-(3-indoleacetyl)-L-alanine, and marker8 is the expression level of 3-indoleacetic acid ethyl ester.

5. The method according to claim 1, characterized in that The biomarkers include protein markers, including thrombomodulin, intercellular adhesion molecule ICAM-3, P-selectin, growth differentiation factor-15GDF-15, adiponectin, monocyte chemoattractant protein-1MCP-1, interleukin-10IL-10, placental growth factor PlGF, epithelial growth factor-like tyrosine kinase receptor 2Tie-2, vascular endothelial growth factor D VEGF-D, and vascular cell adhesion molecule 1VCAM-1; The biomarker expression data includes protein marker expression data, and the protein marker expression data includes thrombomodulin expression, ICAM-3 expression, P-selectin expression, GDF-15 expression, adiponectin expression, MCP-1 expression, IL-10 expression, PlGF expression, Tie-2 expression, VEGF-D expression and VCAM-1 expression; The detecting of the plasma sample to obtain the expression data of the biomarker includes: The plasma sample is detected by electrochemiluminescence technology to obtain the expression data of the protein marker.

6. The method according to claim 5, characterized in that The step of determining the risk score of the user based on the expression data of the biomarker comprises: Inputting the expression data of the protein marker into a second risk prediction model to obtain a risk score value of the user; Among them, the second risk prediction model is constructed based on a logistic regression algorithm.

7. The method according to claim 1, characterized in that The method further comprises: According to the risk score value, determining a target score range matching the risk score value from a plurality of preset score ranges; Determine the risk level corresponding to the target score range as the target risk level of the user, wherein the target risk level is used to characterize the risk probability of occurrence of carotid artery plaque in the user within a preset time period; A risk prevention and control strategy for the user is determined based on the target risk level.

8. A data processing system, characterized in that: The system comprises: A biomarker extraction device, used to extract biomarker expression data from a user's plasma sample, wherein the biomarker includes a marker associated with the occurrence of carotid artery plaques, and the biomarker expression data includes the expression amount of the biomarker in the plasma sample; A scoring device, used to determine a risk score value of the user based on the expression data of the biomarker, wherein the risk score value is used to characterize the risk probability of occurrence of carotid artery plaque in the user within a preset time period; A display device is connected to the scoring device and is used to display the scoring result of the user, wherein the scoring result includes the risk scoring value.

9. A data processing device, characterized in that: The device comprises: A first acquisition module is used to acquire a plasma sample of a user; A first determination module is used to detect the plasma sample to obtain biomarker expression data, wherein the biomarker includes a marker related to the occurrence of carotid plaque, and the biomarker expression data includes the expression amount of the biomarker in the plasma sample; The second determination module is used to determine the risk score value of the user based on the expression data of the biomarker, and the risk score value is used to characterize the risk probability of the occurrence of carotid artery plaque in the user within a preset time period.

10. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the data processing method according to any one of claims 1 to 7 is implemented.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the data processing method according to any one of claims 1 to 7 is implemented.

12. A computer program product, characterized in that The invention comprises a computer program, which, when executed, implements the data processing method according to any one of claims 1 to 7.

Images