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

Abstract

The invention discloses a data processing method, device and system, equipment, a medium and a program product, and relates to the technical field of data processing. The method comprises the following steps: acquiring micro ribonucleic acid (MicroRNA) data of a user, wherein the MicroRNA comprises at least one of the following components: let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p and miR-92a-3p; and based on the MicroRNA data, determining a target score value of the user. The method can accurately predict the probability of occurrence of all-cause death events in the first preset time period of the acute heart failure patient with the reserved ejection fraction.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to a data processing method, device, system, equipment, medium and program product. Background Art

[0002] A variety of factors that cause myocardial damage will inevitably weaken the ventricular contraction and relaxation efficiency and the heart's overall pumping capacity, eventually inducing heart failure (HF). Heart failure is characterized by a significant decline in the heart's pumping function, which is unable to meet the basic metabolic needs of various parts of the body, thereby hindering the effective exchange of oxygen, nutrients and metabolic waste between blood and tissues.

[0003] Among the many categories of heart failure, heart failure with preserved ejection fraction (HFpEF) is characterized by normal or near-normal left ventricular ejection fraction (EF) but with significant left ventricular diastolic function impairment and / or increased filling pressure. Such patients often show a series of symptoms, including dyspnea, persistent fatigue, edema, etc., and in terms of treatment response, compared with heart failure with reduced ejection fraction (HFrEF) patients, HFpEF patients often show lower sensitivity to conventional treatments, making the clinical management and prognosis assessment of HFpEF patients more difficult.

[0004] In the related art, prognostic evaluation data of heart failure patients can be generated based on the clinical characteristic data of patients through evaluation tools such as the MAGGIC scoring system for chronic heart failure and the ASCEND-HF scoring system for acute decompensated heart failure. However, for patients with acute heart failure with preserved ejection fraction, the accuracy of prognostic evaluation using the above method is low. Summary of the invention

[0005] The embodiments of the present application provide a data processing method, apparatus, system, device, medium and program product, which can more accurately predict the probability of all-cause mortality in patients with acute heart failure with preserved ejection fraction within a first preset time period by introducing the expression level of MicroRNA related to the death prognosis of heart failure patients in the user's plasma as an evaluation indicator.

[0006] In a first aspect, an embodiment of the present application provides a data processing method, the data processing method comprising:

[0007] Obtaining the user's microRNA data, the MicroRNA data including the expression level of MicroRNA related to the death prognosis of heart failure patients in the user's plasma, the MicroRNA including at least one of the following: let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, miR-92a-3p;

[0008] Based on the MicroRNA data, the user's target score value is determined. The target score value is used to characterize the probability of the user suffering from all-cause mortality within a first preset time period. The user is a patient with acute heart failure with preserved ejection fraction.

[0009] In some implementations of the embodiments of the present application, determining the target score value of the user based on the MicroRNA data includes:

[0010] Input the MicroRNA data into the risk prediction model to obtain the user's target score value;

[0011] Among them, the risk prediction model was constructed based on the Cox proportional hazard regression model and the weights of sample MicroRNA data;

[0012] The sample MicroRNA data include the expression levels of sample MicroRNA in plasma related to the prognosis of death in patients with heart failure;

[0013] The sample microRNAs included let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, and miR-92a-3p;

[0014] The weights of the sample MicroRNA data include the weight of let-7b-5p expression, the weight of let-7f-5p expression, the weight of miR-128-3p expression, the weight of miR-191-5p expression, the weight of miR-197-3p expression, the weight of miR-23b-3p expression, the weight of miR-25-3p expression, the weight of miR-26b-5p expression, the weight of miR-29a-3p expression, the weight of miR-423-5p expression, the weight of miR-485-5p expression, the weight of miR-625-3p expression, and the weight of miR-92a-3p expression.

[0015] In some implementations of the embodiments of the present application, the MicroRNA data is input into the risk prediction model to obtain the user's target score value, including:

[0016] The MicroRNA data is input into the risk prediction model, and the risk prediction model is used to perform weighted sum processing on the expression level of each MicroRNA in the user's plasma and the weight corresponding to the expression level of each MicroRNA in the MicroRNA data to obtain the user's target score value.

[0017] In some implementations of the embodiments of the present application, the microRNA data includes the expression level of let-7b-5p, the expression level of let-7f-5p, the expression level of miR-128-3p, the expression level of miR-191-5p, the expression level of miR-197-3p, the expression level of miR-23b-3p, the expression level of miR-25-3p, the expression level of miR-26b-5p, the expression level of miR-29a-3p, the expression level of miR-423-5p, the expression level of miR-485-5p, the expression level of miR-625-3p, and the expression level of miR-92a-3p;

[0018] The MicroRNA data is input into the risk prediction model, and the risk prediction model is used to perform weighted sum processing on the expression level of each MicroRNA in the user's plasma and the weight corresponding to the expression level of each MicroRNA in the MicroRNA data to obtain the user's target score value, including:

[0019] The risk prediction model uses the following formula to obtain the user's first evaluation value:

[0020] P=(5.12*10 -6 *MicroRNA 1 )+(9.45*10 -6 *MicroRNA 2 )+

[0021] (-1.35*10 -4 *MicroRNA 3 )+(8.40*10 -5 *MicroRNA 4 )+(4.94*10 -4 *MicroRNA 5 )+

[0022] (1.24*10 -3 *MicroRNA 6 )+(-5.26*10 -5 *MicroRNA 7 )+(1.23*10 -4 *MicroRNA 8 )+

[0023] (7.65*10 -5 *MicroRNA 9 )+(1.94*10 -6 *MicroRNA 10 )+(1.10*10 -3 *MicroRNA 11 )+

[0024] (2.49*10 -4 *MicroRNA 12 )+(2.03*10 -5 *MicroRNA 13 )

[0025] Among them, P is the user's target score, MicroRNA 1 Indicates the expression level of let-7b-5p, MicroRNA 2 Indicates the expression level of let-7f-5p, MicroRNA 3 Indicates the expression level of miR-128-3p, MicroRNA 4 Indicates the expression level of miR-191-5p, MicroRNA 5 Indicates the expression level of miR-197-3p, MicroRNA 6 Indicates the expression level of miR-23b-3p, MicroRNA 7 Indicates the expression level of miR-25-3p, MicroRNA 8 Indicates the expression level of miR-26b-5p, MicroRNA 9 Indicates the expression level of miR-29a-3p, MicroRNA 10Indicates the expression level of miR-423-5p, MicroRNA 11 Indicates the expression level of miR-485-5p, MicroRNA 12 Indicates the expression level of miR-625-3p, MicroRNA 13 Represents the expression level of miR-92a-3p.

[0026] In some implementations of the embodiments of the present application, determining the target score value of the user based on the MicroRNA data includes:

[0027] Based on the MicroRNA data and the user's clinical data, the user's target score value is determined.

[0028] In some implementations of the embodiments of the present application, the clinical data include an Ascend-HF score value, a gender characteristic value, a heart failure history score value, and a NT-proBNP score value;

[0029] Based on the MicroRNA data and the user's clinical data, the user's target score value is determined, including:

[0030] Use the following formula to determine the user's target score:

[0031] P = x 1 P 1 +x 2 P 2 +x 3 P 3 +x 4 P 4 +x 5 P 5

[0032] Among them, P represents the target score value, P 1 Indicates the MicroRNA data score, x 1 represents the weight of the MicroRNA data score, P 2 represents the Ascend-HF score, x 2 represents the weight of the Ascend-HF score, P 3 represents the gender feature value, x 3 Represents the weight of the gender feature value, P 4 represents the heart failure history score, x 4 represents the weight of the heart failure history score, P 5 represents the NT-proBNP score, x 5 Represents the weight of the NT-proBNP score value.

[0033] In some implementations of the embodiments of the present application, the data processing method further includes:

[0034] According to the target score value, determining a target score range matching the target score value from a plurality of preset score ranges;

[0035] The risk level corresponding to the target score range is determined as the target risk level of the user, and the target risk level is used to represent the risk level of the user incurring an all-cause death event within the first preset time period;

[0036] Based on the target risk level, a prognostic recommendation for the user is determined.

[0037] In a second aspect, an embodiment of the present application provides a data processing device, the device comprising:

[0038] An acquisition module is used to acquire the user's microRNA data, wherein the MicroRNA data includes the expression level of MicroRNA related to the death prognosis of heart failure patients in the user's plasma, and the MicroRNA includes at least one of the following: let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, and miR-92a-3p;

[0039] The first determination module is used to determine the user's target score value based on MicroRNA data. The target score value is used to characterize the probability of the user suffering from all-cause mortality within a first preset time period. The user is an acute heart failure patient with preserved ejection fraction.

[0040] In a third aspect, an embodiment of the present application provides a data processing system, the data processing system comprising:

[0041] A gene extractor, for extracting MicroRNA data from a plasma sample of a user, wherein the MicroRNA data includes the expression level of MicroRNA associated with the death prognosis of a heart failure patient in the plasma of the user, wherein the MicroRNA includes at least one of the following: let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, and miR-92a-3p;

[0042] A scoring device is used to determine a target score value of a user based on MicroRNA data extracted by a gene extractor, wherein the target score value is used to characterize the probability of an all-cause death event occurring to the user within a first preset time period, and the user is an acute heart failure patient with preserved ejection fraction.

[0043] The display device is used to display the user's rating results, which include the target rating value.

[0044] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the data processing method as any one of the first aspect.

[0045] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, a data processing method as described in any one of the first aspects is implemented.

[0046] In a sixth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device can perform a data processing method such as any one of the first aspects.

[0047] The data processing method, device, system, equipment, medium and program product of the embodiment of the present application can more accurately reflect the microscopic biological changes in the patient's body and improve the specificity of the assessment by selecting the expression of MicroRNA related to the prognosis of death in heart failure patients in the user's plasma as a biomarker for assessing the prognosis risk of acute heart failure patients with preserved ejection fraction. Furthermore, the target score value of the user determined based on the MicroRNA data can more accurately reflect the probability of all-cause death in patients with acute heart failure with preserved ejection fraction within the first preset time period. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0049] Figure 1 A schematic diagram showing a flow chart of a data processing method provided by some embodiments of the present application;

[0050] Figure 2 A schematic diagram showing a flow chart of a data processing method provided by other embodiments of the present application;

[0051] Figure 3A schematic diagram showing the structure of a data processing device provided in some embodiments of the present application is shown;

[0052] Figure 4 A schematic diagram showing the structure of a data processing system provided by some embodiments of the present application is shown;

[0053] Figure 5 A schematic diagram of the structure of an electronic device provided in some embodiments of the present application is shown. DETAILED DESCRIPTION

[0054] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, 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 the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0055] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0056] It should be noted that the acquisition, storage, use and processing of data in the embodiments of this application are in compliance with the relevant provisions of national laws and regulations. In addition, in the embodiments of this application, some existing solutions in the industry such as certain software, components, models, etc. may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0057] Heart failure, especially acute heart failure with preserved ejection fraction, is a major challenge in the current public health field. The number of patients worldwide is huge and continues to grow, especially with the aging of the population. Acute heart failure with preserved ejection fraction has become a difficult problem that needs to be solved in clinical practice due to its complex pathophysiological mechanism, high incidence and limited treatment options.

[0058] In the related art, there are MAGGIC scoring systems for patients with chronic heart failure and ASCEND-HF scoring systems for the prognosis assessment of patients with acute decompensated heart failure. Specifically, the MAGGIC scoring system consists of 13 parameters and is a tool for assessing the prognosis of patients with chronic heart failure, mainly used to predict the patient's 1, 2, and 3-year survival rate. These parameters include age, gender, whether there is diabetes, chronic obstructive pulmonary disease, smoking, heart failure course, heart failure classification, etc. The purpose of the MAGGIC risk score is to risk stratify patients, strengthen management for high-risk patients, and reduce mortality. Through the comprehensive evaluation of these parameters, the prognosis of patients can be predicted more accurately, providing a reference for clinical treatment. The ASCEND-HF scoring system covers five key clinical variables, including age, degree of dyspnea, blood urea nitrogen level, serum sodium concentration, and systolic blood pressure status, to effectively quantify the severity of acute heart failure. The purpose of this scoring system is to predict the mortality rate of patients with acute decompensated heart failure.

[0059] It can be seen that the MAGGIC scoring system mainly focuses on the prognosis prediction of patients with chronic heart failure, while the ASCEND-HF scoring system mainly focuses on the prognosis assessment of patients with acute heart failure. However, neither the MAGGIC scoring system nor the ASCEND-HF scoring system takes into account the specificity of patients with heart failure with preserved ejection fraction, which leads to the unsatisfactory application of the MAGGIC scoring system and the ASCEND-HF scoring system in HFpEF patients, and cannot fully meet the assessment needs of patients with heart failure with preserved ejection fraction.

[0060] MicroRNAs are a group of short non-protein-coding ribonucleic acids (RNAs) that are widely present in eukaryotes and are highly conserved, temporal, and tissue-specific. As an important class of non-coding RNAs, microRNAs participate in post-transcriptional regulation of gene expression. Specifically, microRNAs participate in gene regulation of almost all physiological and pathological processes by precisely binding to the 3' untranslated region of messenger RNA. MicroRNAs play an important role in cardiac differentiation, development, and myocardial response to stress and injury.

[0061] In order to evaluate the role of each MicroRNA in the prognosis assessment of HFpEF patients, 299 HFpEF patients were randomly selected in the present embodiment, including 179 HFpEF patients in the discovery set and 120 HFpEF patients in the validation set, all of whom met the inclusion criteria of LVEF>50% and NT-proBNP>300ng / L. The accuracy and completeness of the data were ensured through a rigorous data collection process, including the extraction of medical history, clinical characteristics and treatment regimens, as well as face-to-face interviews during follow-up.

[0062] The present application example uses LASSO regression analysis to screen out 20 candidate MicroRNAs that can predict the risk of all-cause mortality in HFpEF users within 4 years. As shown in Table 1 below, specifically, Table 1 below shows the fold changes (log 2 FC), statistical significance (p-value), and predictive performance (AUC value), which are parameters used to evaluate the potential and accuracy of microRNAs as predictors.

[0063] In Table 1, Discovery set (N=179) and Validation set (N=120) represent the discovery set and validation set respectively, wherein the discovery set contains 179 samples and the validation set contains 120 samples. Detailed description of Table 1 is as follows.

[0064] Probes refer to the specific microRNA species used for detection.

[0065] log 2 FC represents the ratio of the median concentration of each MicroRNA in the plasma of deceased patients and surviving patients to the base 2 logarithm, which is used to measure the difference in MicroRNA expression levels between deceased and surviving patients.

[0066] The p value represents the statistical significance value, which is used to evaluate whether the microRNA is significantly associated with the patient's death within 4 years. The smaller the p value, the more significant the difference, and p < 0.05 is defined as a significant correlation with the death outcome.

[0067] AUC (Area Under the Curve) stands for the area under the ROC curve and is used to evaluate the accuracy of the prediction model. The closer the AUC value is to 1, the better the prediction performance.

[0068] Table 1 below shows that 20 categories of candidate MicroRNAs identified by univariate Cox regression analysis have a predictive effect on the risk of all-cause mortality within 4 years in patients with heart failure with preserved ejection fraction. Specifically, Table 1 shows the specific data performance of specific MicroRNAs in predicting the prognosis of HFpEF patients. These data not only reveal the extent and direction of expression changes of these 20 MicroRNAs in the discovery set and validation set, but also show the statistical significance of these changes through p value, and intuitively reflect the predictive ability of each specific MicroRNA for the risk of death through AUC value.

[0069] Furthermore, through the least absolute shrinkage and selection operator (Lasso) regression analysis, the MicroRNA combination that contributes the most to the prediction results can be screened out from the above 20 candidate MicroRNAs, specifically, including let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, and miR-92a-3p. Then, a Cox proportional hazard regression model was established through the above-mentioned MicroRNA combination to predict the 4-year mortality risk of HFpEF patients, and the predictive ability of this model was verified in the validation group.

[0070]

[0071] Table 1

[0072] Based on this, the embodiments of the present application provide a data processing method, apparatus, system, device, medium and program product. Figure 1 To Attachment Figure 2 , the data processing method provided in the embodiment of the present application is described in detail through specific examples.

[0073] Figure 1 FIG. 1 is a flow chart showing a data processing method provided by some embodiments of the present application. Figure 1 As shown, the data processing method includes steps 110 to 120.

[0074] Step 110, obtaining the user's microRNA data, the MicroRNA data including the expression level of MicroRNA related to the death prognosis of heart failure patients in the user's plasma, the MicroRNA including at least one of the following: let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, miR-92a-3p.

[0075] Step 120, based on the MicroRNA data, determine the target score value of the user, the target score value is used to characterize the probability of the user suffering from all-cause mortality within a first preset time period, and the user is an acute heart failure patient with preserved ejection fraction.

[0076] In the embodiment of the present application, the MicroRNA associated with the prognosis of death in patients with heart failure may participate in the development of heart failure by regulating the expression of target genes, affecting the proliferation, differentiation, apoptosis and myocardial remodeling of cardiomyocytes. In view of the complex pathological process of HFpEF, the expression of multiple genes in different pathways may be dysregulated. Therefore, the expression of these MicroRNAs in the user's plasma can be used as an indicator for predicting the prognosis risk of HFpEF users. By selecting multiple MicroRNAs related to the prognosis of death in HFpEF patients to calculate the user's target score value, it is possible to capture more microscopic and specific pathological changes of the user in the acute phase of the user's onset, thereby more accurately reflecting the user's disease state and the probability of all-cause death events in the user within the first preset time period. That is, by introducing the user's target score value as an evaluation indicator, the user's clinical characteristics are fully considered, so that the target score value obtained can more accurately predict the probability of all-cause death events in patients with acute heart failure with preserved ejection fraction within the first preset time period.

[0077] First, the MicroRNA data involved in step 110 of the embodiment of the present application and the role of these MicroRNA data in the heart failure process are specifically described.

[0078] The following is a specific description of the roles of 13 MicroRNAs in the MicroRNA data: let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, and miR-92a-3p.

[0079] In the examples of the present application, the MicroRNA data includes two let-7 family members, such as let-7b-5p and let-7f-5p. Let-7b-5p and let-7f-5p are highly homologous MicroRNAs, and the lowercase letters b and f after let-7 are used to distinguish the two; 5p means that let-7b-5p and let-7f-5p are cut from the 5' end of the MicroRNA precursor. The let-7 family plays an important role in cardiovascular biological processes and cardiovascular diseases. Let-7b-5p is one of the most abundant MicroRNAs in the pericardial fluid of patients with heart failure, and its expression level in the pericardial fluid is related to the severity of heart failure. Another let-7 family member, let-7f-5p, regulates cardiac inflammation and fibrosis through the PI3K / AKT / COX2 signaling pathway, both of which are closely related to the pathology of heart failure. The effects of these let-7 families are consistent with the findings of this application in HFpEF patients.

[0080] The miR-128 family plays an important role in the proliferation of cardiomyocytes and cardiac regeneration. In mouse models, miR-128 can promote cardiac hypertrophy and heart failure by activating the Wnt / β-catenin signaling pathway, while inhibition of miR-128 can slow down this process. In addition, compared with HFrEF patients, the expression level of miR-128-3p in HFpEF patients is lower and is associated with myocardial fibrosis. Referring to Table 1 above, in the discovery set of the present application, the expression level of miR-128-3p was higher in deceased HFpEF patients than in surviving HFpEF patients. This indicates that miR-128 has a negative regulatory role in the development of heart failure.

[0081] miR-197 was also found to be closely related to myocardial fibrosis and could predict the 30-month prognosis of patients with end-stage heart failure under the age of 50. In addition, a large-scale microRNA microarray study found that miR-197-3p is one of the microRNAs regulated by hypoxia, which further supports the role of miR-197-3p in heart failure.

[0082] miR-23 is upregulated during myocardial hypertrophy and can promote the growth of hypertrophy, suggesting that the miR-23 family has a regulatory effect on myocardial hypertrophy. miR-23a-3p is a member of the miR-23 family and can accurately predict the prognosis of patients with myocardial infarction, including hospitalization for heart failure and cardiovascular death.

[0083] miR-26b plays an important regulatory role in the process of cardiac hypertrophy and fibrosis. Specifically, miR-26b expression was downregulated in the myocardial tissue of TAC mice and in AngII-induced hypertrophic cardiomyocytes. Overexpression of miR-26b could reverse this hypertrophic phenomenon, indicating that miR-26b has a potential anti-hypertrophic effect.

[0084] The miR-29 family plays an important role in the pathological process of myocardial hypertrophy and fibrosis. In particular, miR-29a is significantly associated with both hypertrophy and fibrosis, and is considered a potential biomarker for evaluating myocardial remodeling in hypertrophic cardiomyopathy. Based on the discovery set of this application, miR-29a-3p is highly expressed in HFpEF patients who died within 4 years compared with surviving patients, indicating that miR-29a also plays a role in the prognosis of death in HFpEF patients.

[0085] miR-423-5p is a specific diagnostic marker for heart failure and a potential biomarker for treatment efficacy in patients with heart failure and hypertension or with moderately reduced ejection fraction. In addition, a meta-analysis showed that low expression of miR-423-5p was significantly associated with poor overall survival in HF patients, suggesting that miR-423-5p is a strong biomarker for predicting the prognosis of heart failure.

[0086] The miR-92a family includes miR-25, miR-92a-1, miR-92a-2, and miR-363, which have the same seed region and come from three different homologous gene clusters, miR-17-92, miR-106a-363, and miR-106b-25. miR-25 is associated with the pathogenesis of multiple diseases, such as acute myocardial infarction, heart failure, diabetes, nephropathy, cerebral ischemia / reperfusion injury, etc. miR-92 (also known as miR-92a) can be used as a diagnostic biomarker for chronic and acute heart failure, and can be used as a potential biomarker to evaluate the therapeutic effect of endothelial dysfunction in patients with HFpEF and diabetes. miR-25-3p and miR-92-3p in this family are associated with the long-term mortality risk of HFpEF patients, further indicating that the miR-92a family is involved in the pathological process of multiple types of heart failure.

[0087] miR-625, including miR-625-3p, inhibits cardiac hypertrophy by targeting STAT3 and CaMKII, suggesting that miR-625 is a negative regulator of cardiac hypertrophy.

[0088] Heart failure, as a clinical syndrome triggered by multiple factors, is centered on a significant decline in cardiac systolic and / or diastolic function, which results in the inability of the heart to pump blood to meet the body's normal metabolic needs. In the progression of heart failure, the heart undergoes a series of profound pathophysiological changes in order to compensate for and maintain basic pumping function, among which abnormal regulation of gene expression plays a crucial role. Different types of heart failure, such as HFpEF and HFrEF, have different abnormally expressed genes due to different case mechanisms.

[0089] Target genes, as key molecules in these pathophysiological changes, have expression levels that directly determine the physiological state and functional characteristics of cardiomyocytes. In the context of heart failure, specific target genes will be activated or inhibited, and these changes affect core biological processes such as cardiomyocyte proliferation, differentiation, apoptosis, and myocardial remodeling. The imbalance of these processes further aggravates the decline of cardiac function and forms a vicious cycle of continued deterioration of heart failure. The expression level of target genes is regulated by MicroRNA, so studying the expression of MicroRNA in HFpEF is crucial for user risk stratification.

[0090] Exemplarily, obtaining the user's microRNA data specifically includes the following steps:

[0091] Step 1: Extract total RNA: Use a serum / plasma kit to extract total RNA from the user's plasma sample;

[0092] Step 2: Construct MicroRNA sequencing library: First, use a bioanalyzer to evaluate the quality of the extracted total RNA. Then, construct a MicroRNA sequencing library. Specifically, connect an adapter to each MicroRNA, connect the adapter to the 3' end and 5' end of the MicroRNA in turn, perform UMI (Unique Molecular Identifiers)-based cDNA (Complementary DNA) synthesis, then perform cDNA cleaning, and finally, use universal forward primers and index reverse primers for amplification to generate a MicroRNA sequencing library;

[0093] Step 3: Generate sequencing data: First, perform a quality assessment of the MicroRNA sequencing library to ensure that the MicroRNA sequencing library is suitable for high-throughput sequencing. Then, if the MicroRNA sequencing library is qualified, sequence the qualified MicroRNA sequencing library to generate a large amount of sequencing data. The sequencing data exists in the form of a large number of sequence reads, each of which represents a portion of the sequence information of the DNA or RNA in the sample;

[0094] Step 4: Process the sequencing data: remove low-quality and contaminated reads from the sequencing data to obtain cleaned sequencing data;

[0095] Step 5: Data analysis of the cleaned sequencing data: First, use the known MicroRNA sequence information in miRBase to identify the corresponding known MicroRNA in the cleaned sequencing data. Then, count the reads of each MicroRNA and standardize them by the number of tags per million fragments (TPM) to eliminate the impact of different sequencing library sizes on the results. The TPM value reflects the relative expression of each MicroRNA in the sequencing library.

[0096] It is worth noting that in the MicroRNA sequencing library, the relative expression of each MicroRNA directly reflects the expression level of the MicroRNA under specific conditions. A high relative expression means that the abundance of the MicroRNA in the MicroRNA sequencing library is high, that is, its gene expression is more active; conversely, a low relative expression indicates that the gene expression of the MicroRNA in the MicroRNA sequencing library is inhibited or the expression level is low.

[0097] Then, the meaning of the target score value and the first preset time period involved in step 120 of the embodiment of the present application is specifically described.

[0098] The target score is a quantitative indicator derived from the user's MicroRNA data, which is used to evaluate the probability of the user's all-cause death event occurring within the first preset time period. The higher the target score, the greater the probability of the user's all-cause death event occurring within the first preset time period.

[0099] The first preset time period refers to a specific time range for evaluating the risk of death from heart failure of a user, which can be several months, several years or longer. The setting of this time period depends on the evaluation requirements. As a specific example, the first preset time period refers to 4 years.

[0100] For example, through accurate prognostic risk assessment of users, that is, according to the target score value, doctors can perform risk stratification management on users to more reasonably allocate limited medical resources. For high-risk users, more active prevention and treatment measures can be taken; for low-risk users, relatively conservative treatment strategies can be adopted to ensure that high-risk patients receive timely and effective treatment to reduce mortality, while avoiding over-medicalization of low-risk patients.

[0101] In some embodiments of the present application, in order to improve the accuracy and reliability of the target score value prediction. The above step 120 may specifically include inputting the MicroRNA data into the risk prediction model to obtain the user's target score value. Among them, the risk prediction model is constructed based on the Cox proportional risk regression model using sample MicroRNA data and its corresponding weights. The sample MicroRNA data includes the expression level of sample MicroRNA in plasma that is related to the prognosis of death in patients with heart failure, and the weight of the sample MicroRNA data is used to measure the importance of different MicroRNA expression data in the prediction model. When constructing the model, weights are assigned according to the strength of the association between the expression level of the sample MicroRNA and the risk of death due to heart failure.

[0102] Exemplarily, the sample MicroRNA includes let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p and miR-92a-3p. The weights of the sample MicroRNA data include the weight of the expression level of let-7b-5p, the weight of the expression level of let-7f-5p, the weight of the expression level of miR-128-3p, the weight of the expression level of miR-191-5p, the weight of the expression level of miR-197-3p, the weight of the expression level of miR-23b-3p, the weight of the expression level of miR-25-3p, the weight of the expression level of miR-26b-5p, the weight of the expression level of miR-29a-3p, the weight of the expression level of miR-423-5p, the weight of the expression level of miR-485-5p, the weight of the expression level of miR-625-3p and the weight of the expression level of miR-92a-3p.

[0103] Next, the meaning of the Cox proportional hazard regression model and sample MicroRNA data involved in the specific steps of step 110 of the embodiment of the present application is specifically described.

[0104] The Cox proportional hazard regression model is a statistical method used to analyze survival data. The Cox proportional hazard regression model takes into account the impact of time factors on the probability of an event, and allows for the simultaneous consideration of multiple independent variables, such as the impact of the expression levels of multiple MicroRNAs in the user's plasma on survival time. In the prediction of the probability of all-cause mortality in patients with acute heart failure with preserved ejection fraction, the Cox proportional hazard regression model not only considers whether the patient dies, but also considers the early or late time of the patient's death, thus more accurately evaluating the impact of different MicroRNA expression levels on the risk of heart failure, thereby improving the accuracy and reliability of the prediction.

[0105] Sample MicroRNA data refers to gene expression data collected from a certain number of HFpEF patients, which are used to build and train risk prediction models. By collecting and analyzing a large amount of sample MicroRNA data, the association between the prognosis of death from heart failure and the expression of specific genes can be revealed, providing data support for the construction of the model. The diversity and representativeness of these data help improve the generalization ability and prediction accuracy of the risk prediction model.

[0106] In the embodiment of the present application, by integrating sample MicroRNA data, especially incorporating the expression of sample MicroRNA related to heart failure death and the weight of the expression of each sample MicroRNA into the risk prediction model, the constructed risk prediction model can accurately generate death risk prediction results for individuals, thereby meeting the personalized needs of different patients. Specifically, the risk prediction model adopts the Cox proportional hazard regression model to incorporate the time factor into the risk prediction model, ensuring that the prediction results of the risk prediction model fully consider the dynamic characteristics of the user's early or late death event, making the prediction results closer to the actual situation. In addition, the risk prediction model can evaluate the contribution of different MicroRNA expression levels in the prediction through a weight optimization strategy, ensuring that the risk prediction model fully considers the uniqueness and importance of each MicroRNA expression level when predicting, thereby further improving the accuracy and reliability of the prediction.

[0107] In some embodiments of the present application, in order to further improve the accuracy and reliability of the target score value prediction, the above-mentioned inputting the MicroRNA data into the risk prediction model to obtain the user's target score value can specifically include inputting the MicroRNA data into the risk prediction model, and performing weighted summation processing on the expression amount of each MicroRNA in the user's plasma and the weight corresponding to the expression amount of each MicroRNA in the MicroRNA data through the risk prediction model to obtain the user's target score value.

[0108] Among them, the weighted summation method is a mathematically stable and reliable processing method, which can reduce the impact of data noise and outliers on the prediction results to a certain extent. By multiplying the expression level of each MicroRNA by its weight and then summing them, a more robust target score value can be obtained, thereby enhancing the stability and reliability of the prediction results.

[0109] For example, the weight corresponding to the expression level of each MicroRNA can be determined using the Cox proportional hazard model. Specifically, the following steps may be included:

[0110] A training sample set is obtained, the training sample set includes a plurality of training samples, each training sample includes MicroRNA data of a sample user and a user label of the sample user. The MicroRNA data of the sample user includes the expression level of MicroRNA related to the death prognosis of heart failure patients in the plasma sample of the sample user, and the user label of the sample user is used to characterize whether the sample user has all-cause death within a first preset time period.

[0111] For each training sample, the MicroRNA data of the sample user is input into the Cox proportional hazard model to obtain the corresponding prediction result of the sample user.

[0112] When the Cox proportional hazard model meets the preset training conditions, the weight corresponding to the expression level of each MicroRNA is obtained, and the weight corresponding to the expression level of each MicroRNA is used to reflect the probability of the MicroRNA expression level causing the user to die from all causes within the first preset time period.

[0113] In the embodiment of the present application, in the risk prediction model, the expression level of each MicroRNA is assigned a corresponding weight, which can be obtained through the training of the Cox proportional risk regression model, reflecting the importance of different MicroRNAs in the occurrence and development of heart failure. Through weighted summation, the model can comprehensively consider the comprehensive impact of multiple MicroRNAs on the risk of heart failure, effectively avoiding the one-sidedness of single factor evaluation and improving the comprehensiveness and accuracy of risk assessment.

[0114] In some embodiments of the present application, in order to further improve the accuracy and reliability of the target score value prediction. MicroRNA data include the expression of let-7b-5p, the expression of let-7f-5p, the expression of miR-128-3p, the expression of miR-191-5p, the expression of miR-197-3p, the expression of miR-23b-3p, the expression of miR-25-3p, the expression of miR-26b-5p, the expression of miR-29a-3p, the expression of miR-423-5p, the expression of miR-485-5p, the expression of miR-625-3p, and the expression of miR-92a-3p. Based on this, the MicroRNA data is input into the risk prediction model, and the expression amount of each MicroRNA in the MicroRNA data in the user's plasma and the weight corresponding to the expression amount of each MicroRNA are weighted and summed by the risk prediction model to obtain the user's target score value. Specifically, the risk prediction model uses the following formula (1) to obtain the user's first evaluation value:

[0115] P=(5.12*10 -6 *MicroRNA 1 )+(9.45*10 -6 *MicroRNA 2 )+

[0116] (-1.35*10 -4 *MicroRNA 3 )+(8.40*10 -5 *MicroRNA 4 )+(4.94*10 -4 *MicroRNA 5 )+

[0117] (1.24*10 -3 *MicroRNA 6 )+(-5.26*10 -5 *MicroRNA 7 )+(1.23*10 -4 *MicroRNA 8 )+

[0118] (7.65*10 -5 *MicroRNA 9 )+(1.94*10 -6 *MicroRNA 10 )+(1.10*10 -3 *MicroRNA 11 )+

[0119] (2.49*10 -4 *MicroRNA 12 )+(2.03*10 -5 *MicroRNA 13 )(1)

[0120] In formula (1), P is the user's target score, MicroRNA 1 Indicates the expression level of let-7b-5p, MicroRNA 2 Indicates the expression level of let-7f-5p, MicroRNA 3 Indicates the expression level of miR-128-3p, MicroRNA 4 Indicates the expression level of miR-191-5p, MicroRNA 5 Indicates the expression level of miR-197-3p, MicroRNA 6 Indicates the expression level of miR-23b-3p, MicroRNA 7 Indicates the expression level of miR-25-3p, MicroRNA 8 Indicates the expression level of miR-26b-5p, MicroRNA 9 Indicates the expression level of miR-29a-3p, MicroRNA 10 Indicates the expression level of miR-423-5p, MicroRNA 11 Indicates the expression level of miR-485-5p, MicroRNA 12 Indicates the expression level of miR-625-3p, MicroRNA 13 Represents the expression level of miR-92a-3p.

[0121] In the present application example, by assigning a weight value to each MicroRNA, the actual role of these MicroRNAs in a specific biological process or disease can be more accurately reflected. This weighting method can take into account the importance and influence differences of different MicroRNAs, thereby improving the prediction accuracy of the overall target score value.

[0122] Based on this, in other embodiments of the present application, in order to more comprehensively integrate MicroRNA data and clinical data, thereby significantly improving the accuracy and credibility of target score prediction, the above step 120 may specifically include determining the user's target score based on the MicroRNA data and the user's clinical data.

[0123] Exemplarily, the clinical data includes Ascend-HF score value, gender characteristic value, heart failure history score value and NT-proBNP score value. Based on this, the acquisition and application of Ascend-HF score value, gender characteristic value, heart failure history score value and NT-proBNP score value are described below.

[0124] The Ascend-HF score is calculated based on a model of five common clinical variables (age, dyspnea, blood urea nitrogen, sodium, and systolic blood pressure). It has good predictive value for the mortality rate within 30 days and 180 days in patients with acute decompensated heart failure. It is one of the existing predictive models that can predict the prognosis of patients with acute heart failure in the long term.

[0125] The gender characteristic value can be calculated based on the gender of the user. For example, when the user is male, the corresponding gender characteristic value is 1; when the user is female, the corresponding gender characteristic value is 2.

[0126] The heart failure history score value can be determined based on whether the patient has suffered from heart failure in the past. For example, when the user has suffered from heart failure in the past, the corresponding heart failure history score value is 1; when the user has not suffered from heart failure in the past, the corresponding heart failure history score value is 0. This information can be derived from the patient's medical records. Thus, the heart failure history score value can reflect the user's heart failure disease burden and treatment history, which is of great reference value for formulating long-term treatment plans and evaluating prognosis.

[0127] The NT-proBNP score, or amino-terminal pro-brain natriuretic peptide score, can be obtained by measuring the NT-proBNP concentration in the user's plasma and performing a logarithmic transformation. NT-proBNP is a cardiac marker whose serum levels are significantly elevated in patients with heart failure. The NT-proBNP score is an important biomarker for diagnosing heart failure and assessing its severity. It can monitor changes in the disease during treatment and evaluate the effectiveness of treatment.

[0128] In the embodiments of the present application, by deeply integrating MicroRNA data with clinical data and conducting multi-factor interactive analysis, not only the contribution of a single factor is considered, but also the interaction and influence between the factors are deeply explored, thereby achieving a more comprehensive and accurate understanding of the user's health status, thereby significantly improving the prediction accuracy and reliability of the target score value.

[0129] Based on this, the following will explain how to determine the user's target score value based on MicroRNA data and the user's clinical data.

[0130] In some embodiments of the present application, the following formula (2) may be used to determine the target score value of the user:

[0131] P = x 1 P 1 +x 2 P 2 +x 3 P 3 +x 4 P 4 +x 5 P 5 (2)

[0132] In formula (2), P represents the target score value, P 1 Indicates the MicroRNA data score, x 1 represents the weight of the MicroRNA data score, P 2 represents the Ascend-HF score, x 2 represents the weight of the Ascend-HF score, P 3 represents the gender feature value, x 3 Represents the weight of the gender feature value, P 4 represents the heart failure history score, x 4 represents the weight of the heart failure history score, P 5 represents the NT-proBNP score, x 5 Represents the weight of the NT-proBNP score value.

[0133] In the embodiment of the present application, the score values ​​of five different dimensions, namely P 1 To P 5 , corresponding to the MicroRNA data and the corresponding clinical data, and through their respective weights, namely x 1 to x 5 A weighted sum is performed to ultimately arrive at a target score value P, which is intended to provide clinicians with a comprehensive risk assessment result.

[0134] As a specific example, the above formula (2) can be specifically expressed as:

[0135] P = (0.019 × age score) + (-0.183 × sex characteristic value) + (0.281 × Ascend-HF score) + (0.257 × heart failure history score) + (0.220 × log 2 NT-proBNP)+(0.970×MicroRNA data score value).

[0136] Among them, log 2NT-proBNP refers to the logarithm of the user's amino-terminal pro-brain natriuretic peptide (NT-proBNP) concentration to adjust the numerical range of NT-proBNP.

[0137] Therefore, by comprehensively considering multiple clinical data and setting corresponding weights, the impact of a single data on the target score can be reduced, and the accuracy and reliability of the target score can be improved. Based on a more comprehensive and accurate target score, medical personnel can formulate a more scientific and reasonable diagnosis and treatment plan to improve treatment effects and patient satisfaction. The degree of influence of different factors on the target score can be comprehensively considered to make the target score more comprehensive and accurate. Different clinical data may have different importance in reflecting the user's health status, and the weight setting can reflect this difference.

[0138] It is worth noting here that for the MicroRNA data score P representing the MicroRNA data 1 The determination method can adopt the aforementioned risk prediction model and obtain the user's first evaluation value through formula (1), which has been explained in detail in the aforementioned embodiment. Therefore, in order to avoid repetition, the specific details will not be repeated here.

[0139] In some embodiments of the present application, in order to further improve the prediction effect of the target score value on the user, such as Figure 2 As shown, the data processing method may further include steps 210 to 230.

[0140] Step 210: According to the target score value, determine a target score range that matches the target score value from a plurality of preset score ranges.

[0141] Exemplarily, the preset scoring range refers to a series of intervals set in advance based on statistical analysis, expert experience or medical standards, and each interval corresponds to a specific risk level or health status. After obtaining the target score value, this first score value is compared with the preset multiple scoring ranges. During the comparison process, the first scoring range that contains the target score value is found, which is the target scoring range. If there are four preset scoring ranges, they are: [0, 10) corresponds to low risk, [10, 20) corresponds to medium-low risk, [20, 30) corresponds to medium-high risk, and [30, +∞) corresponds to high risk. If a user's target score value is 25, the target scoring range is [20, 30), which is medium-high risk.

[0142] Step 220, determining the risk level corresponding to the target score range as the target risk level of the user, where the target risk level is used to characterize the risk level of the user experiencing an all-cause mortality event within a first preset time period.

[0143] The risk level is used to characterize the probability of death of the user within the first preset time period. According to the target score range determined in step 210, the corresponding risk level is directly searched or mapped. The risk level is pre-defined and has a one-to-one correspondence with the score range. Continuing to refer to the above example, the target score range is [20, 30), and the corresponding risk level is medium-high risk.

[0144] Step 230, determining a prognostic recommendation for the user according to the target risk level.

[0145] Among them, prognostic recommendations refer to possible future situations and measures or suggestions to be taken based on the user's health status or disease risk level. Analyze the health status or disease risk represented by the target risk level. According to the analysis results, combined with medical knowledge, expert experience or treatment guidelines, formulate targeted prognostic recommendations. Prognostic recommendations may include lifestyle adjustments, regular checkups, drug treatment, surgical treatment and other options.

[0146] Therefore, starting from data collection (covering the acquisition of MicroRNA data and clinical data), the target score is calculated by comprehensively evaluating MicroRNA data and clinical data to ensure the accuracy of the evaluation. Subsequently, risk grading is performed based on the target score. Finally, based on the user's risk level, targeted treatment management recommendations are provided to achieve accurate assessment and personalized management of the user's health status or disease risk. By providing scientific and reasonable management to patients, it helps users to understand their own health status in a timely manner and take effective measures to reduce the risk of death. At the same time, it also provides strong decision-making support for medical personnel.

[0147] The data processing method provided in the embodiment of the present application can be executed by a data processing device. In the embodiment of the present application, a data processing device executing data processing is taken as an example to illustrate the device of the data processing method provided in the embodiment of the present application.

[0148] Based on the same inventive concept, the present application also provides a data processing device. Figure 3 Provide detailed explanation.

[0149] Figure 3 A schematic diagram of the structure of a data processing device provided in some embodiments of the present application is shown.

[0150] like Figure 3 As shown, the data processing device 300 may specifically include an acquisition module 310 and a first determination module 320 .

[0151] The acquisition module 310 is used to obtain the user's microribonucleic acid MicroRNA data, and the MicroRNA data includes the expression level of MicroRNA related to the death prognosis of heart failure patients in the user's plasma, and the MicroRNA includes at least one of the following: let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, miR-92a-3p.

[0152] The first determination module 320 is used to determine the target score value of the user based on the MicroRNA data, and the target score value is used to characterize the probability of the user suffering from all-cause death within a first preset time period. The user is a patient with acute heart failure with preserved ejection fraction.

[0153] In an embodiment of the present application, the user's microribonucleic acid MicroRNA data is obtained by using the acquisition module 310, and then the user's target score value is determined based on the MicroRNA data using the first determination module 320. The MicroRNA related to the prognosis of heart failure in the user's MicroRNA data may participate in the development of heart failure by regulating the expression of target genes, affecting the proliferation, differentiation, apoptosis and myocardial remodeling of myocardial cells. In view of the complex pathological process of HFpEF, the expression of multiple genes in different pathways may be dysregulated. Therefore, the changes in the expression levels of these MicroRNAs at baseline admission can be used as a sensitive indicator for predicting the prognostic risk of HFpEF users. By selecting multiple MicroRNAs related to the long-term death of HFpEF users to calculate the user's target score value (multi-MicroRNA score value), it is possible to capture more microscopic and specific pathological changes of the user in the acute phase of the user's onset, thereby more accurately reflecting the user's disease state and the probability of all-cause death in patients with acute heart failure with preserved ejection fraction within the first preset time period. That is, by introducing the user's target score value (multi-MicroRNA score value) as an evaluation indicator, the user's clinical characteristics are fully taken into consideration, so that the obtained target score value can more accurately predict the probability of death events occurring in HFpEF patients within the first preset time period.

[0154] The data processing device 300 in the embodiment of the present application is described in detail below, as shown below.

[0155] In some embodiments of the present application, the first determination module 320 in the embodiment of the present application can be specifically used to input the MicroRNA data into the risk prediction model to obtain the user's target score value. The risk prediction model is constructed based on the Cox proportional risk regression model, and the model includes the sample MicroRNA data and its corresponding weighted MicroRNA data;

[0156] The sample MicroRNA data include the expression levels of sample MicroRNA in plasma that are related to the prognosis of death from heart failure;

[0157] The sample microRNAs included let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, and miR-92a-3p;

[0158] The weights of the sample MicroRNA data include the weight of let-7b-5p expression, the weight of let-7f-5p expression, the weight of miR-128-3p expression, the weight of miR-191-5p expression, the weight of miR-197-3p expression, the weight of miR-23b-3p expression, the weight of miR-25-3p expression, the weight of miR-26b-5p expression, the weight of miR-29a-3p expression, the weight of miR-423-5p expression, the weight of miR-485-5p expression, the weight of miR-625-3p expression, and the weight of miR-92a-3p expression.

[0159] In some embodiments of the present application, the first determination module 320 in the embodiments of the present application can be specifically used to input the MicroRNA data into a risk prediction model, and perform weighted summation processing on the expression level of each MicroRNA in the user's plasma and the weight corresponding to the expression level of each MicroRNA in the MicroRNA data through the risk prediction model to obtain the user's target score value.

[0160] In some embodiments of the present application, the first determination module 320 in the embodiments of the present application can be specifically used to obtain the first evaluation value of the user by using the risk prediction model using the following formula when the MicroRNA data includes the expression level of let-7b-5p, the expression level of let-7f-5p, the expression level of miR-128-3p, the expression level of miR-191-5p, the expression level of miR-197-3p, the expression level of miR-23b-3p, the expression level of miR-25-3p, the expression level of miR-26b-5p, the expression level of miR-29a-3p, the expression level of miR-423-5p, the expression level of miR-485-5p, the expression level of miR-625-3p, and the expression level of miR-92a-3p:

[0161] P=(5.12*10 -6 *MicroRNA 1 )+(9.45*10 -6 *MicroRNA 2 )+

[0162] (-1.35*10 -4 *MicroRNA 3 )+(8.40*10 -5 *MicroRNA 4 )+(4.94*10 -4 *MicroRNA 5 )+

[0163] (1.24*10 -3 *MicroRNA 6 )+(-5.26*10 -5 *MicroRNA 7 )+(1.23*10 -4 *MicroRNA 8 )+

[0164] (7.65*10 -5 *MicroRNA 9 )+(1.94*10 -6 *MicroRNA 10 )+(1.10*10 -3 *MicroRNA 11 )+

[0165] (2.49*10 -4 *MicroRNA 12 )+(2.03*10 -5 *MicroRNA 13 )

[0166] Among them, P is the user's target score, MicroRNA 1 Indicates the expression level of let-7b-5p, MicroRNA 2 Indicates the expression level of let-7f-5p, MicroRNA 3 Indicates the expression level of miR-128-3p, MicroRNA 4 Indicates the expression level of miR-191-5p, MicroRNA 5 Indicates the expression level of miR-197-3p, MicroRNA 6 Indicates the expression level of miR-23b-3p, MicroRNA 7 Indicates the expression level of miR-25-3p, MicroRNA 8 Indicates the expression level of miR-26b-5p, MicroRNA 9 Indicates the expression level of miR-29a-3p, MicroRNA 10 Indicates the expression level of miR-423-5p, MicroRNA 11 Indicates the expression level of miR-485-5p, MicroRNA 12 Indicates the expression level of miR-625-3p, MicroRNA 13 Represents the expression level of miR-92a-3p.

[0167] In other embodiments of the present application, the first determination module 320 in the embodiments of the present application can be specifically used to determine the target score value of the user based on the MicroRNA data and the clinical data of the user.

[0168] In other embodiments of the present application, when the clinical data includes an Ascend-HF score value, a gender characteristic value, a heart failure history score value, and a NT-proBNP score value, the following formula may be used to determine the user's target score value:

[0169] P = x 1 P 1 +x 2 P 2 +x 3 P 3 +x 4 P 4 +x 5 P 5

[0170] Among them, P represents the target score value, P 1 Indicates the MicroRNA data score, x 1represents the weight of the MicroRNA data score, P 2 represents the Ascend-HF score, x 2 represents the weight of the Ascend-HF score, P 3 represents the gender feature value, x 3 Represents the weight of the gender feature value, P 4 represents the heart failure history score, x 4 represents the weight of the heart failure history score, P 5 represents the NT-proBNP score, x 5 Represents the weight of the NT-proBNP score value.

[0171] In some embodiments of the present application, the data processing device 300 in the embodiments of the present application may further include a second determination module, a third determination module and a fourth determination module.

[0172] The second determining module is used to determine a target scoring range that matches the target scoring value from a plurality of preset scoring ranges according to the target scoring value.

[0173] The third determination module is used to determine the risk level corresponding to the target score range as the user's target risk level, and the target risk level is used to characterize the user's risk level of an all-cause death event within a first preset time period.

[0174] The fourth determination module is used to determine the prognostic recommendation for the user according to the target risk level.

[0175] The data processing device provided in the embodiment of the present application can realize Figure 1 to Figure 2 The various processes implemented in the data processing method embodiment shown achieve the same technical effect, and will not be described again here to avoid repetition.

[0176] Figure 4 A schematic diagram of the structure of a data processing system provided in some embodiments of the present application is shown.

[0177] like Figure 4 As shown, the data processing system includes a gene extractor, a scoring device and a display device.

[0178] Gene extractor 410 is used to extract MicroRNA data from the user's plasma sample, where the MicroRNA data includes the expression level of MicroRNA related to the death prognosis of heart failure patients in the user's plasma, where the MicroRNA includes at least one of the following: let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, and miR-92a-3p.

[0179] The scoring device 420 is connected to the gene extractor 410 and is used to determine the user's target score value based on the MicroRNA data extracted by the gene extractor. The target score value is used to characterize the probability of the user suffering from all-cause death within a first preset time period. The user is an acute heart failure patient with preserved ejection fraction.

[0180] The display device 430 is connected to the scoring device 420 and is used to display the user's scoring results, which include the target scoring value.

[0181] Next, the meanings of the gene extractor, scoring device and display device involved in the embodiments of the present application are specifically explained.

[0182] The gene extractor 410 is used to extract RNA from biological samples such as plasma samples. For example, gene extraction using a gene sequencer specifically involves extracting RNA from blood or other samples, and then sequencing the extracted RNA to determine the expression level of each MicroRNA in plasma, thereby obtaining MicroRNA data.

[0183] The scoring device 420 is responsible for receiving the MicroRNA data extracted by the gene extractor, and analyzing and processing the data based on a preset algorithm or model, and finally calculating the user's target score value. This target score value is a quantitative indicator used to characterize the probability of the user's all-cause death event within the first preset time period. Specifically, the scoring device can be a computer or server running a specially designed software program to implement the data processing method of the first aspect above.

[0184] The display device 430 is a window for the user to interact with the data processing system. It is responsible for presenting the scoring results calculated by the scoring device to the user in a visual manner. The display device 430 can be any electronic device that can display text and images, such as a computer monitor, a tablet computer or a smart phone. Through the display device 430, the user's scoring results can be intuitively understood, and corresponding preventive measures can be taken as needed. Exemplarily, the display device 430 can be a hospital's electronic medical record system terminal or a patient's personal smart phone. In the hospital scenario, the doctor can view the patient's scoring results on the electronic medical record system terminal and use it as a reference for formulating a treatment plan. In the home scenario, the patient can receive his or her own risk score report through a third-party application on the smart phone, and understand how to adjust his or her lifestyle according to the scoring results or follow the doctor's advice for treatment.

[0185] In the embodiment of the present application, by integrating the gene extractor, the scoring device and the display device, an efficient and accurate data processing system for the prognosis and mortality risk assessment of patients with heart failure is formed. This data processing system starts with the collection of the user's plasma sample, extracts and analyzes the MicroRNA data, and finally presents the user's scoring results to the user or medical staff in an intuitive way.

[0186] The data processing system provided in the embodiment of the present application can realize Figure 1 to Figure 2 The various processes implemented in the data processing method embodiment shown achieve the same technical effect, and will not be described again here to avoid repetition.

[0187] Figure 5 A schematic diagram of the structure of an electronic device provided in some embodiments of the present application is shown.

[0188] The electronic device may include a processor 510 and a memory 520 storing computer program instructions. Specifically, the processor 510 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0189] The memory 520 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 520 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 appropriate cases, the memory 520 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 520 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 520 is a non-volatile solid-state memory.

[0190] In a particular embodiment, the memory 520 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. Therefore, the memory 520 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) 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.

[0191] The processor 510 implements any one of the data processing methods in the above embodiments by reading and executing computer program instructions stored in the memory 520 .

[0192] In some examples, the electronic device may further include a communication interface 530 and a bus 540. Figure 5 As shown, the processor 510, the memory 520, and the communication interface 530 are connected via a bus 540 and communicate with each other.

[0193] The communication interface 530 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0194] Bus 540 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus 540 may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 540 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0195] Exemplarily, the electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA).

[0196] The electronic device can execute the data processing method in the embodiment of the present application, thereby realizing the combination Figures 1 to 3 The data processing method and device described.

[0197] In addition, in combination with the data processing method in the above embodiment, the embodiment of the present application also provides a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the data processing methods in the above embodiment is implemented. Examples of computer-readable storage media include non-transitory computer-readable storage media, such as portable disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, etc.

[0198] The embodiment of the present application also provides a computer program product, which is stored in a storage medium and may specifically include a computer program or instruction, and when the computer program or instruction is 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 the various processes of the above data processing method embodiment, and can achieve the same technical effect, so it will not be repeated here to avoid repetition.

[0199] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0200] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram 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 device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. 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 box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0201] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A data processing method, characterized in that: The method comprises: Acquire microRNA data of a user, wherein the MicroRNA data includes the expression level of MicroRNA related to the death prognosis of heart failure patients in the plasma of the user, wherein the MicroRNA includes at least one of the following: let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, and miR-92a-3p; Based on the MicroRNA data, a target score value of the user is determined, and the target score value is used to characterize the probability of the user suffering from an all-cause death event within a first preset time period, and the user is a patient with acute heart failure with preserved ejection fraction.

2. The method according to claim 1, characterized in that Determining the target score value of the user based on the MicroRNA data includes: Inputting the MicroRNA data into a risk prediction model to obtain a target score value of the user; Wherein, the risk prediction model is constructed based on the Cox proportional hazard regression model and the weights of sample MicroRNA data; The sample MicroRNA data includes the expression level of the sample MicroRNA in plasma related to the death prognosis of heart failure patients; The sample microRNAs include let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p and miR-92a-3p; The weights of the sample MicroRNA data include the weight of let-7b-5p expression level, the weight of let-7f-5p expression level, the weight of miR-128-3p expression level, the weight of miR-191-5p expression level, the weight of miR-197-3p expression level, the weight of miR-23b-3p expression level, the weight of miR-25-3p expression level, the weight of miR-26b-5p expression level, the weight of miR-29a-3p expression level, the weight of miR-423-5p expression level, the weight of miR-485-5p expression level, the weight of miR-625-3p expression level and the weight of miR-92a-3p expression level.

3. The method according to claim 2, characterized in that The step of inputting the MicroRNA data into a risk prediction model to obtain a target score value of the user includes: The MicroRNA data is input into the risk prediction model, and the risk prediction model is used to perform weighted sum processing on the expression amount of each MicroRNA in the MicroRNA data in the user's plasma and the weight corresponding to the expression amount of each MicroRNA to obtain the target score value of the user.

4. The method according to claim 3, characterized in that The microRNA data include the expression level of let-7b-5p, the expression level of let-7f-5p, the expression level of miR-128-3p, the expression level of miR-191-5p, the expression level of miR-197-3p, the expression level of miR-23b-3p, the expression level of miR-25-3p, the expression level of miR-26b-5p, the expression level of miR-29a-3p, the expression level of miR-423-5p, the expression level of miR-485-5p, the expression level of miR-625-3p, and the expression level of miR-92a-3p; The step of inputting the MicroRNA data into the risk prediction model, and performing weighted sum processing on the expression amount of each MicroRNA in the MicroRNA data in the user's plasma and the weight corresponding to the expression amount of each MicroRNA through the risk prediction model to obtain the target score value of the user includes: The risk prediction model uses the following formula to obtain the first evaluation value of the user: P=(5.12*10 -6 *MicroRNA1)+(9.45*10 -6 *MicroRNA2)+ (-1.35*10 -4 *MicroRNA3)+(8.40*10 -5 *MicroRNA4)+(4.94*10 -4 *MicroRNA5)+ (1.24*10 -3 *MicroRNA6)+(-5.26*10 -5 *MicroRNA7)+(1.23*10 -4 *MicroRNA8)+ (7.65*10 -5 *MicroRNA9)+(1.94*10 -6 *MicroRNA 10 )+(1.10*10 -3 *MicroRNA 11 )+ (2.49*10 -4 *MicroRNA 12 )+(2.03*10 -5 *MicroRNA 13 ) Wherein, P is the target score value of the user, MicroRNA1 represents the expression level of let-7b-5p, MicroRNA2 represents the expression level of let-7f-5p, MicroRNA3 represents the expression level of miR-128-3p, MicroRNA4 represents the expression level of miR-191-5p, MicroRNA5 represents the expression level of miR-197-3p, MicroRNA6 represents the expression level of miR-23b-3p, MicroRNA7 represents the expression level of miR-25-3p, MicroRNA8 represents the expression level of miR-26b-5p, MicroRNA9 represents the expression level of miR-29a-3p, MicroRNA 10 represents the expression level of miR-423-5p, MicroRNA 11 represents the expression level of miR-485-5p, MicroRNA 12 represents the expression level of miR-625-3p, MicroRNA 13 represents the expression level of the miR-92a-3p.

5. The method according to claim 1, characterized in that: Determining the target score value of the user based on the MicroRNA data includes: Based on the MicroRNA data and the clinical data of the user, a target score value of the user is determined.

6. The method according to claim 5, characterized in that The clinical data include Ascend-HF score, gender characteristic value, heart failure history score and NT-proBNP score; Determining the target score value of the user based on the MicroRNA data and the clinical data of the user includes: The target score of the user is determined using the following formula: P=x1P1+x2P2+x3P3+x4P4+x5P5 Among them, P represents the target score value, P1 represents the MicroRNA data score value, x1 represents the weight of the MicroRNA data score value, P2 represents the Ascend-HF score value, x2 represents the weight of the Ascend-HF score value, P3 represents the gender characteristic value, x3 represents the weight of the gender characteristic value, P4 represents the heart failure history score value, x4 represents the weight of the heart failure history score value, P5 represents the NT-proBNP score value, and x5 represents the weight of the NT-proBNP score value.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: According to the target score value, determining a target score range that matches the target 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, where the target risk level is used to characterize the risk level of the user experiencing an all-cause death event within a first preset time period; A prognostic recommendation for the user is determined according to the target risk level.

8. A data processing device, characterized in that: The device comprises: an acquisition module, for acquiring microRNA data of a user, wherein the MicroRNA data includes the expression level of MicroRNA related to the death prognosis of heart failure patients in the plasma of the user, wherein the MicroRNA includes at least one of the following: let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, and miR-92a-3p; The first determination module is used to determine the target score value of the user based on the MicroRNA data, and the target score value is used to characterize the probability of the user suffering from all-cause mortality within a first preset time period, and the user is a patient with acute heart failure with preserved ejection fraction.

9. A data processing system, characterized in that: The system comprises: A gene extractor, for extracting MicroRNA data from a plasma sample of a user, wherein the MicroRNA data includes the expression level of MicroRNA associated with the death prognosis of a heart failure patient in the plasma of the user, wherein the MicroRNA includes at least one of the following: let-7b-5p, let-7f-5p, miR-128-3p, miR-191-5p, miR-197-3p, miR-23b-3p, miR-25-3p, miR-26b-5p, miR-29a-3p, miR-423-5p, miR-485-5p, miR-625-3p, miR-92a-3p; A scoring device is used to determine a target score value of the user based on the MicroRNA data extracted by the gene extractor, wherein the target score value is used to characterize the probability of the user suffering from an all-cause death event within a first preset time period, and the user is a patient with acute heart failure with preserved ejection fraction. The display device is used to display the rating result of the user, wherein the rating result includes the target rating value.

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 When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute the data processing method as described in any one of claims 1 to 7.

Images