Marker determination method and device, equipment, storage medium and program product

Abstract

The invention discloses a marker determination method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring a first expression quantity and a second expression quantity of a plurality of micro ribonucleic acids of a plurality of target objects in a perioperative period; according to the first expression quantity, the second expression quantity and the variable quantity, determining a first micro ribonucleic acid from a plurality of micro ribonucleic acids; inputting the first expression quantity and the second expression quantity into a preset screening model, and screening to obtain second micro ribonucleic acid; for each target object, according to the first expression quantity and the second expression quantity, drawing an expression quantity change track curve of each micro ribonucleic acid of the target object; determining a third micro ribonucleic acid according to the expression quantity change trajectory curve; and determining a first candidate target marker according to the first micro ribonucleic acid, the second micro ribonucleic acid and the third micro ribonucleic acid. According to the embodiment of the invention, the long-term clinical event of the coronary heart disease is accurately predicted through the change of the determined marker.

Description

Technical Field

[0001] The present application belongs to the technical field of medical clinical medicine, and in particular, relates to a marker determination method, device, equipment, storage medium and program product. Background Art

[0002] Coronary heart disease is the leading cause of death among Chinese residents. Its pathogenesis is complex and there are large individual differences in clinical manifestations. Currently, there is a lack of markers that can accurately assess its risk and prognosis. Large-scale standardized populations, tissue-specific marker identification, and accurate detection methods are the key to solving this problem.

[0003] This type of coronary heart disease is generally treated with coronary artery bypass grafting (CABG), but the operation itself is dangerous, with a high perioperative mortality and complications. In addition, after the surgical treatment, certain adverse events may occur in the long term perioperative period, affecting the patient's health. Currently, the prediction of the outcome of long-term treatment of coronary heart disease generally relies mainly on medical history information, but the long-term treatment outcomes of coronary heart disease predicted by medical history information are generally not effective. Therefore, there is an urgent need for a marker to accurately predict adverse events after long-term treatment of coronary heart disease by observing changes in the marker. Summary of the invention

[0004] The embodiments of the present application provide a marker determination method, apparatus, device, storage medium and program product, which can accurately predict long-term clinical events of coronary heart disease by determining changes in markers.

[0005] In one aspect, the present invention provides a method for determining a marker, the method comprising: Acquiring first expression amounts and second expression amounts of multiple microRNAs of multiple target subjects during the perioperative period, wherein the first expression amount represents the expression amounts of the multiple microRNAs of the target subjects at a first preset time before the operation, and the second expression amount represents the expression amounts of the multiple microRNAs of the target subjects at a second preset time after the operation, wherein the target subjects include patients who have undergone coronary artery bypass grafting; Determining, from a plurality of microRNAs, a first microRNA that is different from a preset control group according to the first expression amount, the second expression amount, and the first variation at different preset time points, wherein the first variation represents the variation between the first expression amount and the second expression amount at different preset time points; Inputting the first expression amount, the second expression amount and the first change amount into a preset screening model, so that the preset screening model screens the second microRNA according to the first expression amount, the second expression amount and the first change amount of each microRNA, wherein the second microRNA represents a microRNA associated with a cardiovascular and cerebrovascular medical event; For each of the target subjects, drawing a curve of the change trajectory of the expression level of each microRNA in the target subject during the perioperative period according to the first expression level and the second expression level; Determining a third microRNA according to the expression change trajectory curve of each target object, wherein the third microRNA represents a microRNA whose expression change trajectory is different from that of a preset control group; A first candidate target marker is determined based on the first microRNA, the second microRNA and the third microRNA, so as to predict the probability of the target subject having adverse cardiovascular and cerebrovascular events within a preset time in the future based on the first candidate target marker.

[0006] Optionally, determining a first microRNA that is different from a preset control group from a plurality of microRNAs according to the first expression amount, the second expression amount and the first change amount at different preset time points includes: The first expression amount, the second expression amount and the first change amount for each microRNA; Dividing the target subjects into different subgroups according to the type of surgery and the type of expected events, wherein the subgroups include an event group and a control group; In each subgroup, the occurrence frequency of candidate microRNAs in different subgroups is counted, wherein the candidate microRNAs include microRNAs whose difference between the change amount or state amount of each microRNA of the target object in the event group and the change amount or state amount of the microRNA corresponding to the target object in the control group is greater than a preset difference; The candidate microRNA whose appearance frequency is greater than the preset frequency is determined as the first microRNA.

[0007] Optionally, the first expression amount, the second expression amount and the first change amount are input into a preset screening model, so that the preset screening model screens the second microRNA according to the first expression amount, the second expression amount and the first change amount of each microRNA, including: For each microRNA, the first expression amount, the second expression amount and the first change amount are input into a preset screening model to obtain a correlation coefficient between each microRNA and cardiovascular and cerebrovascular medical events; Determining a plurality of second candidate microRNAs according to the correlation coefficient and a preset correlation coefficient threshold; The second candidate microRNA that meets the preset expression screening condition is determined as the second microRNA, and the preset screening condition includes that the correlation coefficient between the second candidate microRNA and cardiovascular and cerebrovascular medical events is greater than a preset threshold.

[0008] Optionally, before inputting the first expression amount, the second expression amount and the first change amount into a preset screening model so that the preset screening model screens the second microRNA according to the first expression amount, the second expression amount and the first change amount of each microRNA, the method further comprises: Acquire multiple training samples, wherein the training samples include the state expression amount of each microRNA of multiple training subjects during the perioperative period and the corresponding time point state correlation coefficient, wherein the time point state correlation coefficient represents the correlation between the state expression amount and cardiovascular and cerebrovascular medical events; Inputting the state expression into the initial regression model to obtain a prediction correlation coefficient; Determining a loss function of the initial regression model according to the predicted correlation coefficient and the historical correlation coefficient; When the loss function does not meet the convergence condition, the model parameters of the initial regression model are adjusted to optimize the initial regression model until the loss function meets the convergence condition, thereby obtaining a preset screening model.

[0009] Optionally, determining the third microRNA according to the expression level change trajectory curve of each target object includes: Obtaining the type of surgery and the type of cardiovascular and cerebrovascular medical events of each target object; Grouping the plurality of target objects according to the operation type and the cardiovascular and cerebrovascular medical event type to obtain a plurality of second groups; For each second group, comparing the expression change trajectory curves of each microRNA of each target object to obtain a differential expression change trajectory curve, wherein the differential expression change trajectory curve represents an expression change trajectory curve in which the change trend of the microRNA is inconsistent with the change trend of the microRNA of a preset control group; The microRNA corresponding to the differential expression change trajectory curve is determined as the third microRNA.

[0010] Optionally, after determining the first candidate marker according to the first microRNA, the second microRNA and the third microRNA, the method further comprises: Determining a first ratio of any two first candidate markers based on the first expression level and the second expression level, wherein the first ratio represents an expression ratio of any two first candidate markers for the same target object within a first preset time or a second preset time; Acquire first characteristic information of the target object, where the first characteristic information includes basic information and treatment method of the target object; Inputting the first characteristic information and the first ratio into a preset risk classification model to perform regression analysis on the first ratio to obtain the risk probability corresponding to each of the first characteristic information and the first ratio and the cardiovascular and cerebrovascular medical event, wherein the preset risk classification model is used to analyze the risk relationship between the first characteristic information, the first ratio and the cardiovascular and cerebrovascular medical event; When the risk probability is not a preset ratio, the first candidate target marker corresponding to the first ratio is determined as the second candidate target marker.

[0011] Optionally, the step of inputting the first characteristic information and the first ratio into a preset risk classification model to perform regression analysis on the first ratio to obtain the risk probability corresponding to each of the first characteristic information and the first ratio and the cardiovascular and cerebrovascular medical events includes: For each first characteristic information and first ratio, determine the regression coefficient of the first ratio in a preset risk classification model based on the basic information and treatment method using a maximum likelihood estimation method; Based on the regression coefficient, the risk probability corresponding to each of the first feature information and the first ratio and the cardiovascular and cerebrovascular medical event is determined.

[0012] Optionally, after determining the first candidate target marker corresponding to the first ratio as the second candidate target marker, the method further includes: Combining the plurality of the first ratios in any number to obtain a plurality of verification combinations; Inputting the first ratio into a preset binary classification model to obtain a receiver operating characteristic curve corresponding to the first ratio; Integrating the operating characteristic curve to obtain an area under the curve corresponding to the first ratio; Performing multiple cross-validations on the multiple validation combinations to obtain a weight corresponding to each first ratio in each validation, and calculating a weight variation coefficient of each validation combination; The second candidate target marker corresponding to the first ratio in the verification combination corresponding to which the area under the curve is greater than the preset area and the weight variation coefficient is lower than the preset threshold is determined as the final target marker.

[0013] Optionally, after determining the second candidate target marker corresponding to the first ratio in the verification combination corresponding to the area under the curve being greater than the preset area and the weight variation coefficient being lower than the preset threshold as the final target marker, the method further comprises: Obtaining a third expression level and a fourth expression level of the final target marker of the subject to be predicted during the perioperative period and second characteristic information; Predicting the risk probability of the subject to be predicted to have a cardiovascular and cerebrovascular medical event within a preset time period in the future according to the second feature information, the third expression value and the fourth expression value, to obtain the predicted probability of the cardiovascular and cerebrovascular medical event; Based on the predicted probability, a preventive strategy is determined.

[0014] On the other hand, the present invention also provides a kit, comprising: A microRNA reagent, wherein the microRNA reagent is obtained by the marker determination method described in the first aspect.

[0015] Optionally, the microRNAs include miR-425-5p, miR-23a-3p, miR-181a-5p, miR-22-3p, miR-122-5p, miR-99a-5p, miR-499a-5p and miR-133a-3p.

[0016] On the other hand, an embodiment of the present application provides a marker determination device, the device comprising: an acquisition module, configured to acquire first expression amounts and second expression amounts of multiple microRNAs of multiple target subjects during the perioperative period, wherein the first expression amount indicates the expression amounts of multiple microRNAs of the target subjects at a first preset time before the operation, and the second expression amount indicates the expression amounts of multiple microRNAs of the target subjects at a second preset time after the operation, wherein the target subjects include patients who have undergone coronary artery bypass grafting; a determination module, configured to determine, from a plurality of microRNAs, a first microRNA that is different from a preset control group according to the first expression amount, the second expression amount, and a first change amount at different preset time points, wherein the first change amount represents a change amount between the first expression amount and the second expression amount at different preset time points; A screening module, for inputting the first expression amount, the second expression amount and the first change amount into a preset screening model, so that the preset screening model screens the second microRNA according to the first expression amount, the second expression amount and the first change amount of each microRNA, wherein the second microRNA represents a microRNA associated with a cardiovascular and cerebrovascular medical event; A drawing module, for drawing, for each target object, a curve of expression change trajectory of each microRNA of the target object during the perioperative period according to the first expression amount and the second expression amount; The determination module is further used to determine a third microRNA according to the expression change trajectory curve of each target object, wherein the third microRNA represents a microRNA whose expression change trajectory is different from that of a preset control group; The determination module is also used to determine a first candidate target marker based on the first microRNA, the second microRNA and the third microRNA, so as to predict the probability of the target object experiencing adverse cardiovascular and cerebrovascular events within a preset time in the future based on the first candidate target marker.

[0017] In another aspect, an embodiment of the present application provides an electronic device, the device comprising: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the marker determination method as described in the first aspect is implemented.

[0018] On the other hand, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the marker determination method as described in the first aspect is implemented.

[0019] On the other hand, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the marker determination method as described in the first aspect.

[0020] The marker determination method, device, equipment, storage medium and program product of the embodiments of the present application can screen a large number of types of microRNAs by analyzing the first expression levels and the second expression levels of multiple microRNAs of multiple target objects at different times during the perioperative period and the first change between each preset time point, respectively through the difference change amount, the preset screening model and the expression amount change trajectory curve, to obtain the first microRNA, the second microRNA and the third microRNA, and then determine the first candidate target marker based on the first microRNA, the second microRNA and the third microRNA, which can not only reduce the amount of calculation, but also accurately predict the probability of adverse cardiovascular and cerebrovascular events occurring in the target object within a preset time in the future through the first candidate target marker, so as to prevent the adverse consequences of adverse cardiovascular and cerebrovascular events occurring in the target object in advance and ensure the safety of the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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.

[0022] Figure 1 is a schematic diagram of a flow chart of a marker determination method provided in one embodiment of the present application; Figure 2is a flow chart of a marker determination method provided in yet another embodiment of the present application; Figure 3 is a flow chart of a marker determination method provided in yet another embodiment of the present application; Figure 4 is a flow chart of a marker determination method provided in yet another embodiment of the present application; Figure 5 is a flow chart of a marker determination method provided in yet another embodiment of the present application; Figure 6 is a flow chart of a marker determination method provided in yet another embodiment of the present application; Figure 7 is a flow chart of a marker determination method provided in another embodiment of the present application; Figure 8 is a flow chart of a marker determination method provided in another embodiment of the present application; Fig. 9 is a schematic structural diagram of a marker determination device provided in another embodiment of the present application; Fig.10 It is a structural schematic diagram of an electronic device provided in yet another embodiment of the present application. DETAILED DESCRIPTION

[0023] 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.

[0024] 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.

[0025] In order to understand the innovation process of this application, the background introduction is introduced in detail below.

[0026] Coronary heart disease is the leading cause of death among Chinese residents. Its pathogenesis is complex and there are large individual differences in clinical manifestations. Currently, there is a lack of markers that can accurately assess its risk and prognosis. Large-scale standardized populations, tissue-specific marker identification, and accurate detection methods are the key to solving this problem.

[0027] This type of coronary heart disease is generally treated with coronary artery bypass grafting (CABG), but the operation itself is dangerous, with a high perioperative mortality and complications. In addition, after the surgical treatment, certain adverse events may occur in the long term perioperative period, affecting the patient's health. Currently, the prediction of the outcome of long-term treatment of coronary heart disease generally relies mainly on medical history information, but the long-term treatment outcomes of coronary heart disease predicted by medical history information are generally not effective. Therefore, there is an urgent need for a marker to accurately predict adverse events after long-term treatment of coronary heart disease by observing changes in the marker.

[0028] Among related technologies, circulating microRNA (miRNA) has shown unique advantages in the prognosis assessment of cardiovascular diseases due to its high stability, tissue specificity and relevance to pathological processes. For example, miR-1 is positively correlated with the risk of atrial fibrillation after CABG surgery, miR-208a can reflect the degree of myocardial damage, and inflammation-related miRNA (such as miR-155) can characterize the level of systemic inflammation. However, there are still the following technical obstacles in miRNA research in the field of CABG: 1) Insufficient dynamic monitoring: Existing studies mostly use miRNA detection at a single time point or from a specific tissue source, which fails to systematically reveal the dynamic changes of the full spectrum of plasma miRNA during the perioperative period; 2) Blind spots in marker screening: The key miRNAs associated with long-term adverse events (such as 10-year mortality) and their optimal detection time windows have not yet been clearly identified, and there is a lack of long-term follow-up data support; 3) Quantitative technology bottleneck: The traditional qPCR method has poor repeatability in detecting low-abundance miRNA due to differences in reverse transcription efficiency and insufficient stability of internal references; 4) Lack of data standardization: The comparability of test results across platforms is low, and there is a lack of effective correction methods for the interference of individual baseline differences (such as age and renal function) on miRNA expression.

[0029] In order to solve the problems of the prior art, the embodiments of the present application provide a marker determination method, device, equipment, storage medium and program product. By analyzing the first expression and second expression of multiple microRNAs of multiple target objects at different times during the perioperative period, a large number of types of microRNAs are screened by preset differential expression, preset screening model and expression change trajectory curve, and the first microRNA, the second microRNA and the third microRNA are obtained. Then, the first candidate target marker is determined according to the first microRNA, the second microRNA and the third microRNA, which can not only reduce the amount of calculation, but also accurately predict the probability of cardiovascular and cerebrovascular adverse events in the target object within a preset time in the future through the first candidate target marker, so as to prevent the adverse consequences of cardiovascular and cerebrovascular adverse events on the target object in advance and ensure the safety of the target object. The marker determination method provided in the embodiments of the present application is first introduced below.

[0030] Figure 1 FIG. 1 is a flow chart of a marker determination method provided in one embodiment of the present application. Figure 1 As shown, the marker determination method may include S101-S106: S101, obtaining first expression levels and second expression levels of multiple microRNAs of multiple target subjects during the perioperative period.

[0031] In this embodiment, the first expression level can represent the expression levels of multiple microRNAs in the target object at a first preset time before surgery, and the second expression level can represent the expression levels of multiple microRNAs in the target object at a second preset time after surgery. The target object includes patients who have undergone coronary heart disease surgery.

[0032] As an example, the following steps may be used to determine when constructing a target object's queue and collecting samples.

[0033] Specifically, when selecting a target subject, a cohort standard may be preset, for example, at least three indicators may be set to screen the target subject, wherein the three indicators may include: adult patients receiving elective simple coronary artery bypass grafting, patients who sign an informed consent form and provide a perioperative plasma oxygen pump, and patients who do not have other concurrent cardiac surgeries, and other cardiac surgeries may be valve replacements; A large number of patients are screened by the above criteria. After the screening, further exclusion can be performed. Exclusion indicators may include: preoperative serum creatinine ≥ 200 μM, obstructive hepatobiliary disease or hereditary myopathy, and perioperative use of drugs that affect miRNA expression, which may be high-dose glucocorticoids. Patients are screened by the above method to obtain a large number of target objects, and cohort construction, sample collection and processing are realized according to the target objects, and the samples are sequenced.

[0034] As an example, it is worth noting that for human patients, there are a large number of types of micro RNA (micro Ribonucleic Acid, miRNA) in the patient's body, and the expression of these miRNAs can be obtained through the patient's cardiomyocytes and vascular endothelial cells. In this embodiment, the perioperative period can refer to the time period between the patient's decision to undergo surgery and the end of the surgery and entering the recovery stage. Specifically, in this embodiment, the first preset time can be any time point within 48 hours before the start of the surgery, the second preset time can be 6 hours after the surgery, the third preset time is 24 hours after the surgery, and the fourth preset time is 48 hours after the surgery. In some embodiments, preferably, after a large amount of data shows, the first preset time is 6 hours before the surgery and the second preset time is 6 hours after the surgery.

[0035] S102, determining a first microRNA that is different from a preset control group from a plurality of microRNAs according to the first expression amount, the second expression amount, and the first change amount at different preset time points; In this embodiment, as an example, the first variation represents the variation between the first expression amount and the second expression amount at different preset time points; In this embodiment, in S102, the target object can be divided into an event group and a control group based on whether it has coronary heart disease-related adverse events after surgery. Among them, adverse events can be further divided into cardiogenic events and cerebral events. In addition, the methods of CABG surgery are mainly divided into two surgical methods: on-pump CABG (ONCAB) and off-pump CABG. First, the discovery cohort can be divided into different subgroups through the above grouping, and the expression level of each microRNA can be compared to see whether there is a significant difference between the event group and the control group in the subgroup; secondly, after each target object undergoes coronary heart disease surgery, the expression level of each microRNA will change, so the expression level between any two time points can be compared to obtain different changes, and then it can be determined whether the change amount of each microRNA is significantly different between the event group and the control group in the subgroup patients. The occurrence frequency of each microRNA in the above-mentioned surgical subgroups, outcome subgroups, time point subgroups, and change amount subgroups is counted, and the microRNA with a frequency exceeding a predetermined threshold is determined as the first microRNA to reduce the types of microRNAs that are not related to coronary heart disease surgery, thereby reducing the amount of calculation.

[0036] In this embodiment, the cardiovascular and cerebrovascular medical events may be some complications after coronary heart disease surgery, which may include death caused by cardiovascular and cerebrovascular reasons, non-fatal myocardial infarction and non-fatal ischemic stroke.

[0037] S103, inputting the first expression amount, the second expression amount and the first change amount into a preset screening model, so that the preset screening model screens the second microRNA according to the first expression amount, the second expression amount and the first change amount of each microRNA.

[0038] In some embodiments, in S103, the second microRNA represents a microRNA associated with cardiovascular and cerebrovascular medical events.

[0039] In some embodiments, in S103, multiple microRNAs can also be screened through a preset screening model. In this embodiment, the preset screening model can be screened according to the correlation between microRNAs and adverse cardiovascular and cerebrovascular events to reduce the calculation amount of microRNAs, and accurately predict adverse cardiovascular and cerebrovascular events through a second microRNA.

[0040] As an example, the preset screening model may be an unconstrained nonlinear optimization model, and the second microRNA represents microRNA associated with adverse cardiovascular and cerebrovascular events.

[0041] S104, for each target subject, draw a curve of the change trajectory of the expression level of each microRNA of the target subject during the perioperative period.

[0042] In some embodiments, in S104, as time changes, each target object will change for each microRNA during the perioperative period, and the expression change trajectory curve can be fitted by the first expression amount, the second expression amount and the first change amount, that is, the expression change trajectory curve can show the changes of each microRNA during the perioperative period.

[0043] S105, determining a third microRNA according to the expression level change trajectory curve of each target object.

[0044] As an example, the third microRNA represents a microRNA whose expression level change trajectory is different from that of a preset control group.

[0045] In some embodiments, in S105, although there are individual differences between each target object, the expression change trends of different microRNAs in different populations during the perioperative period may be similar, so the microRNAs with different change trends between the event group and the control group can be determined through the expression change trajectory curve, and the microRNAs with different change trends are determined as the third microRNAs.

[0046] As an example, a non-linear change trajectory of RNA marker expression over time can be fitted by a non-parametric smoothing algorithm (such as spline regression or Gaussian process). The third microRNA can represent a microRNA whose change trajectory is significantly different between the control group and the event group; the microRNA can be determined as the third microRNA, and the probability of adverse cardiovascular and cerebrovascular events can be predicted by the third microRNA.

[0047] S106, determining a first candidate target marker based on the first microRNA, the second microRNA and the third microRNA, so as to predict the probability of the target subject having adverse cardiovascular and cerebrovascular events within a preset time in the future based on the marker.

[0048] In some embodiments, in S106, the first candidate target marker determined by the first microRNA, the second microRNA and the third microRNA determined by the above three methods can predict the probability of adverse cardiovascular and cerebrovascular events in the target object in the future through the first candidate target marker, that is, the change of the first candidate target marker in the perioperative period can reflect the probability of adverse cardiovascular and cerebrovascular events in the future preset time, thereby improving the accuracy of accurate prediction of adverse cardiovascular and cerebrovascular events.

[0049] In this embodiment, by analyzing the first expression levels and the second expression levels of multiple microRNAs of multiple target objects at different times during the perioperative period, a large number of types of microRNAs are screened through direct comparison of the state amount or change amount between groups of expression amounts, a preset screening model and an expression amount change trajectory curve, to obtain the first microRNA, the second microRNA and the third microRNA, and then determine the first candidate marker based on the first microRNA, the second microRNA and the third microRNA, which can not only reduce the amount of calculation, but also accurately predict the probability of adverse cardiovascular and cerebrovascular events occurring in the target object within a preset time in the future through the first candidate target marker, so as to prevent the adverse consequences of adverse cardiovascular and cerebrovascular events occurring in the target object in advance and ensure the safety of the target object.

[0050] Reference Figure 2 In some other embodiments, in order to screen a variety of microRNAs and reduce the amount of calculation while ensuring that the screened microRNAs can more accurately predict cardiovascular and cerebrovascular adverse events, S102 may include: S1021, for each microRNA's first expression amount, second expression amount, and first change amount, divide the target subject into different subgroups according to the surgery type and the expected event type, the subgroups including an event group and a control group; S1022, in each subgroup, counting the frequency of candidate microRNAs in different subgroups; S1023, determining the candidate microRNA corresponding to a frequency greater than a preset frequency as the first microRNA.

[0051] In this embodiment, as an example, the candidate microRNAs include microRNAs whose change amount or state amount of each microRNA of the target object in the event group differs from the change amount or state amount of the microRNA corresponding to the target object in the control group by more than a preset difference.

[0052] In this embodiment, when screening is performed using the preset control change amount, it is first necessary to collect the first expression amount of each RNA within 48 hours before the target subject undergoes CABG surgery, and then collect the second, third, and fourth expression amounts of each RNA 6 hours, 24 hours, and 48 hours after the surgery. After that, the various changes in the micro RNA of the target patient before and after the surgery are determined, and then the four expression amounts (before surgery, 6 hours after surgery, 24 hours after surgery, and 48 hours after surgery) and six changes (6 hours vs. before surgery, 24 hours vs. before surgery, 48 hours vs. before surgery, 24 hours vs. 6 hours, 48 ​​hours vs. 24 hours, and 48 hours vs. 24 hours) are screened simultaneously.

[0053] Specifically, in this embodiment, in order to ensure the accuracy of screening, patients who have undergone coronary heart disease surgery and have not experienced adverse cardiovascular and cerebrovascular events are determined as preset controls, and then the first candidate microRNA is determined by comparing whether there are significant differences in the above expression levels and changes, that is, the one that is significantly greater than or less than the control group is determined as the first candidate microRNA.

[0054] Then, the occurrence frequency of the first candidate microRNA is determined according to the selection frequency of the first candidate microRNA in the comparison of different subgroups; Specifically, S1022 may include: Dividing multiple target subjects into groups according to surgery type (all patients, ONCAB patients, and OPCAB patients) and coronary heart disease event type (all event types, cardiac events, and cerebral events), to obtain multiple first groups; Obtaining microRNAs that vary significantly in each first group; According to the summary results of different first groups, the occurrence frequency of the first candidate microRNA of the expression amount and the change amount at each preset time point is determined.

[0055] In this example, the overall predictive efficacy of expression and change at different time points is compared to further reduce the detection time window required for subsequent verification, which is convenient for clinical promotion. In this example, the predictive efficacy of different microRNAs is evaluated by comparing the AUC values ​​at different time points. The results suggest that the two time points with the strongest predictive efficacy are before surgery and 6 hours after surgery.

[0056] It is worth noting that the patients included are those who have completed coronary heart disease surgery for five years or more. The first microRNA screened in this way can predict the probability of adverse cardiovascular and cerebrovascular events within a preset time in the future.

[0057] Reference Figure 3 In some other embodiments, in order to improve the accuracy of the probability of predicting adverse cardiovascular and cerebrovascular events by microRNA, S103 may include: S1031, for each microRNA, inputting the first expression amount, the second expression amount and the first change amount into a preset screening model to obtain a correlation coefficient between each microRNA and cardiovascular and cerebrovascular medical events; S1032, determining a plurality of second candidate microRNAs according to the correlation coefficient and a preset correlation coefficient threshold; S1033, determining the second candidate microRNA that meets the preset expression amount screening condition as the second microRNA.

[0058] In this embodiment, the preset screening condition includes that the correlation coefficient between the second candidate microRNA and the cardiovascular and cerebrovascular medical events is greater than a preset threshold.

[0059] In some embodiments, in S1031, the preset screening model can be an unconstrained nonlinear optimization model. By inputting the expression change into the preset screening model, the classification model in the preset screening model can continuously perform classification optimization to obtain the correlation coefficient between each microRNA and adverse cardiovascular and cerebrovascular events. It is worth noting that the preset screening model is a nonlinear optimization model based on the correlation between the expression change and adverse cardiovascular and cerebrovascular events.

[0060] Reference Figure 4 Specifically, the method for training the preset screening model may include: S401, obtaining multiple training samples; S402, inputting the state expression into the initial regression model to obtain a prediction correlation coefficient; S403, determining a loss function of an initial regression model according to the predicted correlation coefficient and the historical correlation coefficient; S404, when the loss function does not meet the convergence condition, adjust the model parameters of the initial regression model to optimize the initial regression model until the loss function meets the convergence condition, thereby obtaining a preset screening model.

[0061] In some embodiments, in S401, the training samples may include the state expression levels of each microRNA of multiple training subjects at multiple time points during the perioperative period and the corresponding time point-specific correlation coefficients, and the correlation coefficients represent the correlation between the historical expression levels and cardiovascular and cerebrovascular medical events.

[0062] It is worth mentioning that the training subjects can be patients who have undergone coronary heart disease surgery, and the training subjects can be patients of all ages, all genders and all comorbidities, that is, patients involved in all aspects of coronary heart disease surgery.

[0063] In some other embodiments, in S402 and S403, the initial regression model may be a logistic regression model or a support vector machine, which is not limited here, as long as it can achieve unconstrained nonlinear optimization.

[0064] Specifically, in order to ensure that the initial regression model can perform classification more accurately, the initial regression model can be initialized, that is, the objective function of the initial regression model can be defined by formula (1):

[0065] Where ω is the weight vector of microRNA, is the loss function value, and m is the number of training samples.

[0066] In some other embodiments, the initial regression model may be trained by a regularization algorithm to quickly train the initial regression model to obtain a preset screening model.

[0067] As an example, when ω=0, it means that the training sample is not selected, and when ω>0, it means that the training sample is selected to achieve the screening of microRNAs.

[0068] In some other embodiments, in S404, the loss function may be a cross entropy loss function or a mean square error function.

[0069] In some other embodiments, the model performance index can also be used to determine whether the initial regression model meets the convergence condition, that is, the convergence condition can indicate that the initial training model has been trained or converged. The specific adjustment method is consistent with the relevant technology and will not be elaborated here.

[0070] In some other embodiments, in S1033, after the expression change is input into the preset screening model, the preset screening model can output a correlation coefficient based on the expression change, and then determine multiple second candidate micro RNAs through the correlation coefficient and the preset correlation coefficient threshold. Specifically, for example, the correlation coefficient of a certain micro RNA is 0.5, and the preset correlation coefficient threshold is 0.3, which indicates that the micro RNA is the second candidate micro RNA.

[0071] In addition, in order to make the screened microRNA representative, it is necessary to further screen the second candidate microRNA through preset expression screening conditions. As an example, the preset expression screening conditions include that the third expression level corresponding to the second candidate microRNA is greater than the preset expression level threshold. For example, the correlation coefficient of a certain microRNA is 0.5. At this time, the third expression level of the microRNA is 500, and the preset expression level threshold is 200. Then the microRNA can be determined as the second microRNA.

[0072] Reference Figure 5 In some other embodiments, in order to screen microRNAs, S105 may include: S1051, obtaining the surgery type and cardiovascular and cerebrovascular medical event type of each target object; S1052, grouping the multiple target objects according to the operation type and the cardiovascular and cerebrovascular event type to obtain multiple second groups; S1053, for each second group, comparing the expression change trajectory curves of each microRNA of each target object to obtain a differential expression change trajectory curve; S1054, determining the microRNA corresponding to the differential expression change trajectory curve as the third microRNA.

[0073] In some embodiments, the implementation of S1051 is consistent with the implementation of S1022 described above, and will not be further elaborated here.

[0074] In some other embodiments, the implementation method of S1052 is consistent with the implementation method of S1022 described above, and will not be further elaborated here.

[0075] In some other embodiments, in S1053, when the expression change trajectory curve is used to determine the third microRNA, an expression change trajectory curve is first drawn for all the microRNAs of each target object in each second group, and then the expression change trajectory curves of different target objects are compared for each microRNA, and the differential expression change curve is determined by the expression change curves of different target objects in each microRNA.

[0076] For example, for a certain microRNA, the expression change trajectory curve of the target object in the event group first increases and then decreases, but the expression change trajectory curve of the target object in the control group first decreases and then increases, then the expression change trajectory curve can be determined as a differential expression change trajectory curve.

[0077] In this embodiment, the third microRNA determined by the above method can represent microRNAs with different expression change patterns between the second groups, and can more accurately predict cardiovascular and cerebrovascular adverse events from the changes in the same microRNAs between different target objects.

[0078] Reference Figure 6 In some other embodiments, in some embodiments, the first microRNA, the second microRNA and the third microRNA determined by the above method greatly reduce the types of microRNAs, but there are still many types of the first microRNA, the second microRNA and the third microRNA. In order to further reduce the amount of calculation, it is also necessary to narrow the candidate range of the target marker from the first microRNA, the second microRNA and the third microRNA to obtain the second candidate marker. At the same time, in order to facilitate clinical application, it is necessary to replace the detection platform with a low-throughput, widely used platform (RT-qPCR) for targeted detection. And, according to the above content, the detection time point is further narrowed to two time points before and 6 hours after surgery. Specifically, after S106, the method also includes: S601, determining a first ratio of any two first candidate markers based on the first expression level and the second expression level, where the first ratio represents the expression ratio of any two first candidate markers for the same target object within a first preset time or a second preset time; S602, obtaining first characteristic information of the target object, where the first characteristic information includes basic information and treatment method of the target object; S603, inputting the first characteristic information and the first ratio into a preset risk classification model to perform regression analysis on the first ratio to obtain the risk probability corresponding to each first characteristic information and the first ratio and the cardiovascular and cerebrovascular medical event; S604: When the risk probability is not the preset ratio, determine the first candidate target marker corresponding to the first ratio as the second candidate target marker.

[0079] In this embodiment, in S602, first characteristic information of the target object is obtained; the first candidate target marker is detected using an RT-qPCR platform in a cohort with an expanded sample size, and the RT-qPCR detection data is standardized using a suitable method.

[0080] In some embodiments, in S602, the first characteristic information of the target object can be obtained through the hospital's information storage system. The first characteristic information may include basic information and treatment methods of the target object, wherein the basic information may include age, gender, comorbidities and heart function, and the treatment method may be a treatment method for the cause of coronary heart disease surgery.

[0081] In some embodiments, in S602, the RT-qPCR platform for detecting the first candidate marker is not unique, and a commercially available or self-developed RT-qPCR platform based on a dye method or a probe method can be used. However, there are differences in the detection efficiency, specificity, and sensitivity between the above-mentioned different platforms, which can be selected as appropriate according to specific needs. In this example, the RT-qPCR detection is performed using a miRXES RT-qPCR platform using three specific primers (specific reverse transcription stem-loop primer, specific PCR forward primer, and specific PCR reverse primer). Preferably, the platform can better achieve accurate and stable detection of microRNAs of different abundances.

[0082] In some embodiments, there are differences in the abundance of background RNA in different target objects, but these differences are less correlated with long-term coronary heart disease events. Therefore, it is necessary to correct for such inherent differences between individuals. In some instances, correction is often performed using fixed internal reference RNA widely used in previous studies, such as hsa-miR-16-5p, etc. In this example, our samples showed that the internal reference used in previous studies was not applicable because its expression level changed significantly with the time point of surgery and was not a reference for stable expression. Therefore, preferably, we use the ratio method to standardize the detection data of RT-qPCR. That is, for the 24 first candidate markers, all micro RNAs are standardized by combining them in pairs and calculating their ratios.

[0083] In this embodiment, 276 preoperative ratios, 276 postoperative 6-hour ratios, and 276 ratio change ranges were obtained for all target subjects in the expanded verification internal cohort.

[0084] In order to avoid including too many ratios with low correlation with long-term coronary heart disease, we compared the above three ratios in the event group and the control group respectively, and finally verified that the ratios with a P value less than 0.05 entered the next step of evaluation.

[0085] In order to avoid including highly correlated ratios, which would result in the model being unable to fit effectively, correlation analysis was performed on the ratios after the above screening, and ratios with correlations less than 0.75 were included in the subsequent analysis.

[0086] Then, the first characteristic information and the expression and change of the ratio of the first microRNA, the second microRNA and the third microRNA are input into the preset risk classification model, and the corresponding risk probability is obtained through the preset risk classification model, wherein the preset risk classification model is used to analyze the risk relationship between the first characteristic information, the first candidate target marker and adverse cardiovascular and cerebrovascular events.

[0087] In this embodiment, the preset risk classification model can be a proportional hazard model (Cox Proportional-Hazards Model, referred to as CoxPH model). The proportional hazard model is a commonly used statistical model used to analyze the relationship between time-related events and multiple covariates to allow the relative impact of the first characteristic information on the risk to be evaluated.

[0088] Specifically, in some embodiments, S603 may include: For each first characteristic information and first ratio, a regression coefficient of the first ratio in a preset risk classification model is determined by using a maximum likelihood estimation method based on basic information and treatment methods; Based on the regression coefficient, the risk probability corresponding to each first characteristic information and the first ratio and the cardiovascular and cerebrovascular medical event is determined.

[0089] In this embodiment, when calculating the risk probability, the first feature information can be used as a covariate, that is, the first feature information is converted into a covariate vector to represent factors that may affect the risk, and then the regression coefficient is determined by the maximum likelihood estimation method. Then, the risk probability corresponding to the first feature information and the first candidate target marker and the cardiovascular and cerebrovascular adverse event is determined based on the regression coefficient. The specific calculation formula (2) is as follows:

[0090] Among them, HR is the risk probability and βi is the regression coefficient.

[0091] In some other embodiments, in S603, as an example, the preset ratio is 1. If HR>1, it means that the covariate increases the risk, that is, increases the probability of adverse cardiovascular and cerebrovascular events. If HR<1, it means that the covariate reduces the risk, that is, reduces the probability of adverse cardiovascular and cerebrovascular events. If HR=1, it means that the covariate has no effect on the risk, that is, it is irrelevant to the probability of adverse cardiovascular and cerebrovascular events. The comparison result of the risk probability and the preset ratio can be used to determine whether the first candidate target marker is the second candidate marker ratio. In this example, 13 miRNA ratios were finally screened and confirmed as the second candidate markers (Table 1).

[0092] Table 1. Results of univariate Cox proportional hazards regression analysis of miRNA ratios

[0093] Through the preset risk model, the first candidate marker can be screened again according to the first characteristic information. The obtained second candidate marker ratio can not only reduce the amount of calculation, but also reduce the cost of clinical application detection, thereby achieving accurate prediction of adverse cardiovascular and cerebrovascular events.

[0094] Reference Figure 7 In some other embodiments, in order to determine the marker combination with the best predictive efficacy and perform double verification, after S106, the method may further include: S701, performing any number of combinations of the multiple first ratios to obtain multiple verification combinations; S702, inputting the first ratio into a preset binary classification model to obtain a receiver operating characteristic curve corresponding to the first ratio; S703, integrating the operating characteristic curve to obtain an area under the curve corresponding to the first ratio; S704, performing multiple cross-validations on the multiple validation combinations to obtain a weight corresponding to each first ratio in each validation, and calculating a weight variation coefficient of each validation combination; S705, determining the second candidate target marker corresponding to the first ratio in the verification combination corresponding to which the area under the curve is greater than the preset area and the weight variation coefficient is lower than the preset threshold as the final target marker.

[0095] In this embodiment, if 13 groups of expression ratios are taken as an example, if the 13 groups of expression ratios are combined in any number, the obtained validation combinations are 8191 combinations. By repeating the two-fold cross validation 10 times, it is determined that when the number of marker ratios included in the model is 4-6, the prediction efficiency can reach a high level, and the stability of the model is also acceptable. Finally, the marker combination with the top 30% cross-validation AUC mean and the smallest average coefficient of variation of the model weight is screened out, that is, a combination consisting of 5 miRNA ratios (5-miRatio), including preoperative miR-425-5p / miR-23a-3p and 6 hours after surgery miR-181a-5p / miR-22-3p, miR-181a-5p / miR-122-5p, miR-99a-5p / miR-122-5p, miR-499a-5p / miR-133a-3p as the final target marker. In the internal validation cohort, the above five expression ratios were used for validation. That is, the five expression ratios were input as a set of input data into the preset binary classification model to obtain the receiver operating characteristic curve (ROC curve) corresponding to the expression ratio. Then, the area under the curve (Area Under the Curve AUC value) corresponding to the expression ratio was obtained by integrating the ROC curve.

[0096] In some embodiments, the ROC curve is displayed by plotting the True Positive Rate (TPR, also called recall rate or sensitivity) against the False Positive Rate (FPR, also called 1-specificity) at different thresholds.

[0097] True positive rate (TPR) = TP / (TP + FN), which indicates the proportion of all positive samples that are correctly predicted as positive samples.

[0098] False positive rate (FPR) = FP / (FP + TN), which indicates the proportion of all negative samples that are incorrectly predicted as positive samples.

[0099] Among them, TP (True Positives) represents true positives, FP (False Positives) represents false positives, FN (False Negatives) represents false negatives, and TN (True Negatives) represents true negatives.

[0100] The AUC value is the area under the ROC curve. The AUC value ranges from 0 to 1, and its meaning is as follows: AUC = 1: It indicates that the model perfectly distinguishes between positive and negative samples.

[0101] AUC = 0.5: It indicates that the model has no discrimination ability and is equivalent to random guessing.

[0102] AUC < 0.5: It indicates that the model performance is worse than random guessing. This situation is rare in practical applications because the model can be improved by reversing the prediction results.

[0103] 0.5 < AUC < 1: It indicates that the model has discrimination ability. The larger the AUC value, the stronger the model's discrimination ability.

[0104] In this set of embodiments, AUC has the following advantages: (1) Not affected by the threshold: AUC evaluates the performance of the entire model rather than the performance under a specific threshold.

[0105] (2) Robustness: AUC is not sensitive to the change of the positive and negative sample ratio, so it has better robustness on different data sets.

[0106] (3) Intuitive and easy to understand: The AUC value is a numerical value between 0 and 1. The larger the value, the better the model performance, which is easy to understand and compare.

[0107] By using the area under the curve and the weight coefficient to re-screen the final biomarker, it can ensure that the new final biomarker can accurately predict the cardiovascular and cerebrovascular adverse events in the future preset time.

[0108] After internal validation: The AUC of 5-miRatio = 0.663 (95% CI: 0.605–0.721), which is 0.112 higher than NYScore (P = 0.006). External validation: AUC = 0.684 (95% CI: 0.564–0.805), and after combination with NYScore, NRI = 0.213 (P = 0.042).

[0109] Refer to Figure 8 , in some other embodiments, after S106, the method may further include: S801, obtaining the third expression level and the fourth expression level of the final biomarker of the object to be predicted during the perioperative period and the second characteristic information; S802, predicting the probability of the object to be predicted having cardiovascular and cerebrovascular adverse events within the future preset time period according to the second characteristic information, the third expression level and the fourth expression level, to obtain the prediction probability of the cardiovascular and cerebrovascular adverse events; S803, determining a prevention strategy based on the prediction probability.

[0110] In this embodiment, after the final marker is determined in the above manner, the final marker can be used to estimate the probability that the predicted object will experience adverse cardiovascular and cerebrovascular events within a preset time period in the future (such as the perioperative period five years after surgery). If the predicted probability is greater than a preset threshold, it means that the predicted object will experience adverse cardiovascular and cerebrovascular events within the preset time period in the future. Prevention strategies can be prepared in advance for adverse cardiovascular and cerebrovascular events that may occur in the future, thereby ensuring the life safety of the predicted object.

[0111] In an embodiment of the present application, a kit is also provided, the kit comprising a microRNA reagent, wherein the microRNA reagent is obtained by the above-mentioned marker determination method.

[0112] Preferably, the microRNA may include miR-425-5p, miR-23a-3p, miR-181a-5p, miR-22-3p, miR-122-5p, miR-99a-5p, miR-499a-5p and miR-133a-3p.

[0113] In the embodiments of the present application, the steps for making the kit are similar to those of the related art, except that the microRNA is different, so the preparation process of the kit will not be described in detail here.

[0114] Based on the marker determination method provided in the above embodiment, the present application also provides a specific implementation of the marker determination device 900. Please refer to the following embodiment.

[0115] Reference Fig. 9 , the marker determination device 900 provided in the embodiment of the present application may include: An acquisition module 901 is used to acquire first expression amounts and second expression amounts of multiple microRNAs of multiple target subjects during the perioperative period, wherein the first expression amount represents the expression amounts of the multiple microRNAs of the target subjects at a first preset time before the operation, and the second expression amount represents the expression amounts of the multiple microRNAs of the target subjects at a second preset time after the operation, and the target subjects include patients who have undergone coronary artery bypass grafting; A determination module 902 is used to determine a first microRNA that is different from a preset control group from a plurality of microRNAs according to the first expression amount, the second expression amount, and the first variation at different preset time points, wherein the first variation represents the variation between the first expression amount and the second expression amount at different preset time points; A screening module 903 is used to input the first expression amount, the second expression amount and the first change amount into a preset screening model, so that the preset screening model screens the second microRNA according to the first expression amount, the second expression amount and the first change amount of each microRNA, wherein the second microRNA represents a microRNA related to a cardiovascular and cerebrovascular medical event; A drawing module 904 is used to draw, for each target object, a curve of the change trajectory of the expression level of each microRNA in the perioperative period according to the first expression level and the second expression level; The determination module 902 is further used to determine a third microRNA according to the expression change trajectory curve of each target object, where the third microRNA represents a microRNA whose expression change trajectory is different from that of a preset control group; The determination module 902 is also used to determine a first candidate target marker based on the first microRNA, the second microRNA and the third microRNA, so as to predict the probability of a target subject experiencing a cardiovascular or cerebrovascular adverse event within a preset time in the future based on the first candidate target marker.

[0116] As an optional implementation, the determination module 902 may also be used to: a first expression amount, a second expression amount, and a first change amount for each microRNA; The target subjects were divided into different subgroups according to the type of surgery and the type of expected events, including the event group and the control group; In each subgroup, the occurrence frequency of candidate microRNAs in different subgroups is counted, wherein the candidate microRNAs include microRNAs whose difference between the change amount or state amount of each microRNA of the target object in the event group and the change amount or state amount of the microRNA corresponding to the target object in the control group is greater than a preset difference; The candidate microRNA whose appearance frequency is greater than the preset frequency is determined as the first microRNA.

[0117] As an optional implementation, the determination module 902 may also be used to: For each microRNA, the first expression amount, the second expression amount and the first change amount are input into a preset screening model to obtain a correlation coefficient between each microRNA and cardiovascular and cerebrovascular medical events; Determining a plurality of second candidate microRNAs according to the correlation coefficient and a preset correlation coefficient threshold; The second candidate microRNA that meets the preset expression screening condition is determined as the second microRNA. The preset screening condition includes that the correlation coefficient between the second candidate microRNA and cardiovascular and cerebrovascular medical events is greater than a preset threshold.

[0118] As an optional implementation, the determination module 902 may also be used to: Acquire multiple training samples, the training samples include historical expression of each microRNA of multiple training subjects during the perioperative period and corresponding historical correlation coefficients, the historical correlation coefficients indicating the correlation between the historical expression and the preset medical events; The historical expression levels were input into the initial regression model to obtain the predicted correlation coefficient; Determine the loss function of the initial regression model based on the predicted correlation coefficient and the historical correlation coefficient; When the loss function does not meet the convergence condition, the model parameters of the initial regression model are adjusted to optimize the initial regression model until the loss function meets the convergence condition to obtain the preset screening model.

[0119] As an optional implementation, the determination module 902 may also be used to: Obtain the type of surgery and cardiovascular and cerebrovascular medical events for each target subject; Grouping multiple target objects according to the types of surgery and the types of cardiovascular and cerebrovascular medical events to obtain multiple second groups; For each second group, the expression change trajectory curves of each microRNA of each target object are compared to obtain a differential expression change trajectory curve, wherein the differential expression change trajectory curve represents an expression change trajectory curve in which the change trend of the microRNA is inconsistent with the change trend of the microRNA of the preset control group; The microRNA corresponding to the differential expression change trajectory curve is determined as the third microRNA.

[0120] As an optional implementation, the determination module 902 may also be used to: Determine a first ratio of any two first candidate markers based on the first expression level and the second expression level, wherein the first ratio represents an expression ratio of any two first candidate markers within a first preset time or a second preset time for the same target object; Acquire first characteristic information of the target object, where the first characteristic information includes basic information and treatment method of the target object; Inputting the first characteristic information and the first ratio into a preset risk classification model to perform regression analysis on the first ratio to obtain the risk probability corresponding to each first characteristic information and the first ratio and the cardiovascular and cerebrovascular medical event, wherein the preset risk classification model is used to analyze the risk relationship between the first characteristic information, the first ratio and the cardiovascular and cerebrovascular medical event; When the risk probability is not the preset ratio, the first candidate target marker corresponding to the first ratio is determined as the second candidate target marker.

[0121] As an optional implementation, the determination module 902 may also be used to: For each first characteristic information and first ratio, a regression coefficient of the first ratio in a preset risk classification model is determined by using a maximum likelihood estimation method based on basic information and treatment methods; Based on the regression coefficient, the risk probability corresponding to each first characteristic information and the first ratio and the cardiovascular and cerebrovascular medical event is determined.

[0122] As an optional implementation, the determination module 902 may also be used to: Combining the multiple first ratios in any number to obtain multiple verification combinations; Inputting the first ratio into a preset binary classification model to obtain a receiver operating characteristic curve corresponding to the first ratio; Integrating the operating characteristic curve to obtain an area under the curve corresponding to the first ratio; Perform multiple cross-validations on multiple validation combinations to obtain the weight corresponding to each first ratio in each validation, and calculate the weight variation coefficient of each validation combination; The second candidate target marker corresponding to the first ratio in the verification combination corresponding to which the area under the curve is greater than the preset area and the weight variation coefficient is lower than the preset threshold is determined as the final target marker.

[0123] As an optional implementation, the determination module 902 may also be used to: Obtaining the third expression level and the fourth expression level of the final target marker of the subject to be predicted during the perioperative period and the second characteristic information; Predicting the risk probability of a cardiovascular and cerebrovascular medical event occurring in the predicted object within a preset future time period according to the second feature information, the third expression value, and the fourth expression value, to obtain a predicted probability of the cardiovascular and cerebrovascular medical event; Based on the predicted probability, prevention strategies are determined.

[0124] Fig.10 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0125] The electronic device may include a processor 1001 and a memory 1002 storing computer program instructions.

[0126] Specifically, the processor 1001 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.

[0127] The memory 1002 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 1002 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 one example, the memory 1002 may include a removable or non-removable (or fixed) medium, or the memory 1002 is a non-volatile solid-state memory. The memory 1002 may be inside or outside the integrated gateway disaster recovery device.

[0128] In one example, the memory 1002 may be a read-only memory (ROM). In one example, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0129] The memory 1002 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, typically, the memory 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 marker determination method according to the first aspect of the present disclosure.

[0130] The processor 1001 reads and executes the computer program instructions stored in the memory 1002 to implement Figure 1 A marker determination method in the illustrated embodiment.

[0131] In one example, the electronic device may further include a communication interface 1003 and a bus 1004. Fig.10 As shown, the processor 1001, the memory 1002, and the communication interface 1003 are connected via a bus 1004 and communicate with each other.

[0132] The communication interface 1003 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0133] Bus 1004 includes hardware, software or both, and couples the components of the electronic device to each other. For example, but not limitation, the bus may include Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), Hyper Transport (HT) interconnection, Industry Standard Architecture (ISA) bus, InfiniBand Interconnection, Low Pin Count (LPC) bus, Memory Bus, Micro Channel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus or other suitable bus or two or more of these combinations. Where appropriate, bus 1004 may include one or more buses. Although the present application embodiment describes and illustrates a specific bus, the present application considers any suitable bus or interconnection.

[0134] The electronic device can execute the marker determination method in the embodiment of the present application, thereby realizing the combination Figure 1-Figure 9 Described are methods and devices for determining markers.

[0135] In addition, in combination with the marker determination method in the above embodiments, the present application embodiment may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the marker determination methods in the above embodiments is implemented.

[0136] In an optional embodiment, in combination with the marker determination method in the above-mentioned embodiment, the embodiment of the present application may provide a computer program product for implementation, and the instructions in the computer program product are executed by a processor of an electronic device, so that the electronic device can implement any one of the marker determination methods in the above-mentioned embodiments.

[0137] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is 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 the steps after understanding the spirit of the present application.

[0138] The functional blocks shown in the above structural block diagram 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 function card, etc. 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 on a transmission medium or a communication link by a data signal carried in a carrier. "Machine-readable medium" may include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0139] 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.

[0140] Aspects of the present disclosure are described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments 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 functions / actions 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 the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0141] 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 marker determination method, characterized in that: include: Acquiring first expression amounts and second expression amounts of multiple microRNAs of multiple target subjects during the perioperative period, wherein the first expression amount represents the expression amounts of the multiple microRNAs of the target subjects at a first preset time before the operation, and the second expression amount represents the expression amounts of the multiple microRNAs of the target subjects at a second preset time after the operation, wherein the target subjects include patients who have undergone coronary artery bypass grafting; Determining, from a plurality of microRNAs, a first microRNA that is different from a preset control group according to the first expression amount, the second expression amount, and the first variation at different preset time points, wherein the first variation represents the variation between the first expression amount and the second expression amount at different preset time points; Inputting the first expression amount, the second expression amount and the first change amount into a preset screening model, so that the preset screening model screens the second microRNA according to the first expression amount, the second expression amount and the first change amount of each microRNA, wherein the second microRNA represents a microRNA associated with a cardiovascular and cerebrovascular medical event; For each of the target subjects, drawing a curve of the change trajectory of the expression level of each microRNA in the target subject during the perioperative period according to the first expression level and the second expression level; Determining a third microRNA according to the expression change trajectory curve of each target object, wherein the third microRNA represents a microRNA whose expression change trajectory is different from that of a preset control group; A first candidate target marker is determined based on the first microRNA, the second microRNA and the third microRNA, so as to predict the probability of the target subject having adverse cardiovascular and cerebrovascular events within a preset time in the future based on the first candidate target marker.

2. The method according to claim 1, characterized in that The method of determining, from a plurality of microRNAs, a first microRNA that is different from a preset control group according to the first expression amount, the second expression amount, and the first change amount at different preset time points, includes: For each microRNA, the first expression amount, the second expression amount and the first change amount are divided into different subgroups according to the operation type and the expected event type, wherein the subgroups include an event group and a control group; In each subgroup, the occurrence frequency of candidate microRNAs in different subgroups is counted, wherein the candidate microRNAs include microRNAs whose difference between the change amount or state amount of each microRNA of the target object in the event group and the change amount or state amount of the microRNA corresponding to the target object in the control group is greater than a preset difference; The candidate microRNA whose appearance frequency is greater than the preset frequency is determined as the first microRNA.

3. The method according to claim 1, characterized in that The step of inputting the first expression amount, the second expression amount and the first change amount into a preset screening model, so that the preset screening model screens the second microRNA according to the first expression amount, the second expression amount and the first change amount of each microRNA, comprises: For each microRNA, the first expression amount, the second expression amount and the first change amount are input into a preset screening model to obtain a correlation coefficient between each microRNA and cardiovascular and cerebrovascular medical events; Determining a plurality of second candidate microRNAs according to the correlation coefficient and a preset correlation coefficient threshold; The second candidate microRNA that meets the preset expression screening condition is determined as the second microRNA, and the preset screening condition includes that the correlation coefficient between the second candidate microRNA and cardiovascular and cerebrovascular medical events is greater than a preset threshold.

4. The method according to claim 3, characterized in that: Before inputting the first expression amount, the second expression amount and the first change amount into a preset screening model so that the preset screening model screens the second microRNA according to the first expression amount, the second expression amount and the first change amount of each microRNA, the method further includes: Acquire multiple training samples, wherein the training samples include the state expression amount of each microRNA of multiple training subjects at multiple time points during the perioperative period and the corresponding time point-specific correlation coefficient, wherein the correlation coefficient represents the correlation between the state expression amount and cardiovascular and cerebrovascular medical events; Inputting the state expression into the initial regression model to obtain a prediction correlation coefficient; Determining a loss function of the initial regression model according to the predicted correlation coefficient and the historical correlation coefficient; When the loss function does not meet the convergence condition, the model parameters of the initial regression model are adjusted to optimize the initial regression model until the loss function meets the convergence condition, thereby obtaining a preset screening model.

5. The method according to any one of claims 1 to 4, characterized in that: The step of determining the third microRNA according to the expression level change trajectory curve of each target object includes: Obtaining the type of surgery and the type of cardiovascular and cerebrovascular medical events of each target object; Grouping the plurality of target objects according to the operation type and the cardiovascular and cerebrovascular medical event type to obtain a plurality of second groups; For each second group, comparing the expression change trajectory curves of each microRNA of each target object to obtain a differential expression change trajectory curve, wherein the differential expression change trajectory curve represents an expression change trajectory curve in which the change trend of the microRNA is inconsistent with the change trend of the microRNA of a preset control group; The microRNA corresponding to the differential expression change trajectory curve is determined as the third microRNA.

6. The method according to claim 5, characterized in that After determining the first candidate target marker according to the first microRNA, the second microRNA and the third microRNA, the method further includes: Determine a first ratio of any two first candidate target markers based on the first expression level and the second expression level, wherein the first ratio represents an expression ratio of any two first candidate markers for the same target object within a first preset time or a second preset time; Acquire first characteristic information of the target object, where the first characteristic information includes basic information and treatment method of the target object; Inputting the first characteristic information and the first ratio into a preset risk classification model to perform regression analysis on the first ratio to obtain the risk probability corresponding to each of the first characteristic information and the first ratio and the cardiovascular and cerebrovascular medical event, wherein the preset risk classification model is used to analyze the risk relationship between the first characteristic information, the first ratio and the cardiovascular and cerebrovascular medical event; When the risk probability is not a preset ratio, the first candidate target marker corresponding to the first ratio is determined as the second candidate target marker.

7. The method according to claim 6, characterized in that The step of inputting the first characteristic information and the first ratio into a preset risk classification model to perform regression analysis on the first ratio to obtain the risk probability corresponding to each of the first characteristic information and the first ratio and a cardiovascular and cerebrovascular medical event includes: For each first characteristic information and first ratio, determine the regression coefficient of the first ratio in a preset risk classification model based on the basic information and treatment method using a maximum likelihood estimation method; Based on the regression coefficient, the risk probability corresponding to each of the first feature information and the first ratio and the cardiovascular and cerebrovascular medical event is determined.

8. The method according to claim 6, characterized in that After determining the first candidate target marker corresponding to the first ratio as the second candidate target marker, the method further includes: Combining the plurality of the first ratios in any number to obtain a plurality of verification combinations; Inputting the first ratio into a preset binary classification model to obtain a receiver operating characteristic curve corresponding to the first ratio; Integrating the operating characteristic curve to obtain an area under the curve corresponding to the first ratio; Performing multiple cross-validations on the multiple validation combinations to obtain a weight corresponding to each first ratio in each validation, and calculating a weight variation coefficient of each validation combination; The second candidate target marker corresponding to the first ratio in the verification combination corresponding to which the area under the curve is greater than the preset area and the weight variation coefficient is lower than the preset threshold is determined as the final target marker.

9. The method according to claim 8, characterized in that After determining the second candidate target marker corresponding to the first ratio in the verification combination corresponding to the area under the curve being greater than the preset area and the weight variation coefficient being lower than the preset threshold as the final target marker, the method further includes: Obtaining a third expression level and a fourth expression level of the final target marker of the subject to be predicted during the perioperative period and second characteristic information; Predicting the risk probability of the subject to be predicted to have a cardiovascular and cerebrovascular medical event within a preset time period in the future according to the second feature information, the third expression value and the fourth expression value, to obtain the predicted probability of the cardiovascular and cerebrovascular medical event; Based on the predicted probability, a preventive strategy is determined.

10. A kit, characterized in that: The kit comprises a microRNA reagent, wherein the microRNA reagent is obtained by the marker determination method according to any one of claims 1 to 9.

11. The kit according to claim 10, characterized in that The microRNAs include miR-425-5p, miR-23a-3p, miR-181a-5p, miR-22-3p, miR-122-5p, miR-99a-5p, miR-499a-5p and miR-133a-3p.

12. A marker determination device, characterized in that: The device comprises: an acquisition module, configured to acquire first expression amounts and second expression amounts of multiple microRNAs of multiple target subjects during the perioperative period, wherein the first expression amount indicates the expression amounts of multiple microRNAs of the target subjects at a first preset time before the operation, and the second expression amount indicates the expression amounts of multiple microRNAs of the target subjects at a second preset time after the operation, wherein the target subjects include patients who have undergone coronary artery bypass grafting; a determination module, configured to determine, from a plurality of microRNAs, a first microRNA that is different from a preset control group according to the first expression amount, the second expression amount, and a first change amount at different preset time points, wherein the first change amount represents a change amount between the first expression amount and the second expression amount at different preset time points; A screening module, for inputting the first expression amount, the second expression amount and the first change amount into a preset screening model, so that the preset screening model screens the second microRNA according to the first expression amount, the second expression amount and the first change amount of each microRNA, wherein the second microRNA represents a microRNA associated with a cardiovascular and cerebrovascular medical event; A drawing module, for drawing, for each target object, a curve of expression change trajectory of each microRNA of the target object during the perioperative period according to the first expression amount and the second expression amount; The determination module is further used to determine a third microRNA according to the expression change trajectory curve of each target object, wherein the third microRNA represents a microRNA whose expression change trajectory is different from that of a preset control group; The determination module is also used to determine a first candidate target marker based on the first microRNA, the second microRNA and the third microRNA, so as to predict the probability of the target object experiencing adverse cardiovascular and cerebrovascular events within a preset time in the future based on the first candidate target marker.

13. 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 marker determination method according to any one of claims 1 to 9 is implemented.

14. 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 marker determination method according to any one of claims 1 to 9 is implemented.

15. 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 executes the marker determination method as described in any one of claims 1-9.

Images