Long-term prediction method and prediction model construction method for myocardial infarction in patients with type 2 diabetes

By constructing a prediction model for type 2 diabetes patients with different time lengths, combined with the comprehensive evaluation of multiple risk factors, the problem of low prediction accuracy in the existing technology is solved, and the accuracy of the risk of type 2 diabetes patients is achieved. Improvement of prediction and prognostic strategies.

CN116665911BActive Publication Date: 2024-11-26FUWAI HOSPITAL CHINESE ACAD OF MEDICAL SCI & PEKING UNION MEDICAL COLLEGE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310709782.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-06-15
Publication Date
2024-11-26
Estimated Expiration
2043-06-15

AI Technical Summary

Technical Problem

The prior art lacks a comprehensive assessment of multiple risk factors when evaluating the risk of myocardial infarction in patients with type 2 diabetes, and the prediction accuracy is limited and the model is single, which cannot effectively improve the prognosis strategy of patients.

Method used

Provide a long-term prediction method for myocardial infarction in patients with type 2 diabetes. By obtaining clinical variables and follow-up results of different time lengths, calculating information gain, screening out risk factors that cause myocardial infarction, and building a prediction model for different time lengths to improve prediction Accuracy.

Benefits of technology

Accurate prediction of time length and multiple risk factors is achieved, automatic identification of risk-free turning points to risk-free, and positioning key risk factors, which improves the accuracy of individual prognostic strategies.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116665911B_ABST
    Figure CN116665911B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention discloses a long-term prediction method for myocardial infarction in patients with type 2 diabetes and a method for constructing a prediction model. The prediction method includes: obtaining the length of time to be predicted; selecting the risk factors and prediction models that cause myocardial infarction in patients with type 2 diabetes according to the length of time; inputting the risk factor values ​​of the target patient into the prediction model to predict whether the target patient has a risk of myocardial infarction after the length of time. This embodiment selects different prediction models and risk factors for different lengths of time to be predicted, thereby improving the prediction accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of medical data processing, and in particular to a method for long-term prediction of myocardial infarction in patients with type 2 diabetes and a method for constructing a prediction model. Background Art

[0002] Type 2 diabetes is a major chronic disease that affects human health, and diabetes-related complications seriously affect the quality of life of diabetic patients. The main cause of death in diabetic patients is cardiovascular disease, and myocardial infarction is one of them. Accurately predicting the risk of myocardial infarction in patients with type 2 diabetes can improve the prognosis strategy of patients with type 2 diabetes and reduce the risk of myocardial infarction in patients.

[0003] At present, the prognosis assessment of patients with type 2 diabetes focuses on the impact of a single risk factor on the patient's prognosis, lacks a comprehensive assessment of multiple risk factors, and the prediction accuracy is limited. Although patents CN114898873A "A method and system for predicting cardiovascular disease risk in patients with prediabetes" and CN115527680A "A method for predicting the lifetime risk of cardiovascular disease in patients with type 2 diabetes" consider the comprehensive assessment of multiple risk factors, the model is single and the prediction accuracy is limited. Summary of the invention

[0004] The embodiment of the present invention provides a long-term prediction method for myocardial infarction in patients with type 2 diabetes and a prediction model construction method, which selects different prediction models and risk factors for different lengths of time to be predicted, thereby improving the prediction accuracy.

[0005] In a first aspect, an embodiment of the present invention provides a method for long-term prediction of myocardial infarction in patients with type 2 diabetes, comprising:

[0006] Get the length of time to be predicted;

[0007] According to the time length, selecting risk factors and prediction models for myocardial infarction in patients with type 2 diabetes;

[0008] The risk factor values ​​of the target patient are input into the prediction model to predict whether the target patient has a risk of myocardial infarction after the specified length of time.

[0009] In a second aspect, an embodiment of the present invention provides a method for constructing a long-term prediction model for myocardial infarction in patients with type 2 diabetes, comprising:

[0010] Obtain multiple clinical variables of multiple type 2 diabetes patients, as well as follow-up results of whether each type 2 diabetes patient has myocardial infarction after different lengths of time;

[0011] For each time length, perform the following operations respectively:

[0012] S1. Calculate the information gain of each clinical variable and follow-up results based on the patient data corresponding to the current time length;

[0013] S2. screening out risk factors for myocardial infarction in patients with type 2 diabetes from the multiple clinical variables based on the information gain;

[0014] S3. Using the risk factor values ​​and follow-up results of each patient as samples, a long-term prediction model for myocardial infarction in patients with type 2 diabetes is trained. The trained model inputs the patient's risk factor values, and outputs a prediction result of whether the patient will have a myocardial infarction after the current length of time.

[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0016] one or more processors;

[0017] a memory for storing one or more programs,

[0018] When the one or more programs are executed by the one or more processors, the one or more processors implement the long-term prediction method for myocardial infarction in patients with type 2 diabetes, or the method for constructing a long-term prediction model for myocardial infarction in patients with type 2 diabetes as described in any embodiment.

[0019] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for long-term prediction of myocardial infarction in patients with type 2 diabetes, or the method for constructing a long-term prediction model for myocardial infarction in patients with type 2 diabetes as described in any one of the embodiments.

[0020] The embodiment of the present invention selects an adaptive combination of risk factors and prediction models based on the length of time required by the patient, and predicts the risk of myocardial infarction in patients with type 2 diabetes after a specific length of time in the future, thereby achieving accurate prediction of time length and multiple risk factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 This is a flow chart of a method for long-term prediction of myocardial infarction in patients with type 2 diabetes provided by an embodiment of the present invention;

[0023] Figure 2A flowchart of a method for constructing a long-term prediction model for myocardial infarction in type 2 diabetic patients provided in an embodiment of the present invention;

[0024] Figure 3 It is a schematic diagram of sample projection in a linear discriminant analysis method provided by an embodiment of the present invention.

[0025] Figure 4 is a ROC curve diagram of the myocardial infarction prediction model for type 2 diabetes patients with a time length of 5 years provided by an embodiment of the present invention;

[0026] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0028] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0029] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] Figure 1 This is a flow chart of a method for long-term prediction of myocardial infarction in patients with type 2 diabetes provided by an embodiment of the present invention. The method is applicable to predicting whether a patient with type 2 diabetes will have a myocardial infarction event in the future, and is executed by an electronic device. Figure 1 As shown, the method specifically includes:

[0031] S110: Obtain the time length to be predicted.

[0032] Generally speaking, the time length is in years. Assuming that the time length is N years, this embodiment will predict whether a type 2 diabetic patient will have a myocardial infarction event N years in the future.

[0033] S120. Based on the time length, select risk factors and prediction models for myocardial infarction in patients with type 2 diabetes.

[0034] The risk factors here are factors related to myocardial infarction in patients with type 2 diabetes, including: sex (sex), age (age), smoking (smok), fasting blood glucose (fbg), blood glucose 1 hour after load (bg1), blood glucose 2 hours after load (bg2), blood pressure (sbp), diastolic blood pressure (dbp), body mass index (bmi), total cholesterol (tc) and triglycerides (tg). The prediction model here is a linear model about at least one risk factor; the weight in the linear model represents the contribution of each risk factor to the prediction result. The model is a binary classification model, the input is the value of at least one risk factor, and the output is the prediction result of whether the patient will have a myocardial infarction after N years. For example, an output of 1 indicates that a myocardial infarction will occur, and an output of 0 indicates that a myocardial infarction will not occur.

[0035] Furthermore, different time lengths correspond to different prediction models, and the types of risk factors included in each prediction model may be the same, or different, or partially the same and partially different, which is not limited in this embodiment. When there are multiple time lengths to be predicted, a prediction model and at least one risk factor that causes myocardial infarction in type 2 diabetic patients corresponding to each time length are selected. For example, when the time length to be predicted is 5 years, a prediction model y5=a1 is corresponding. 1,5 ×x1+a 2,5 ×x2+a 5,5 ×x5, where y5 represents the prediction result, x1, x2 and x5 represent the values ​​of each risk factor in the prediction model, and a 1,5 、a 2,5 and a 5,5 They represent the contribution of risk factors x1, x2 and x5 to the predicted result y5. When the time length to be predicted is 10 years, the prediction model is y 10 =a 1,10 ×x1+a 2,10 ×x2+a 10,10 × 10 , where y 10 Represents the prediction results, x1, x2 and x 10 Respectively represent the value of each risk factor in the prediction model, a 1,10 、a 2,10 and a10,10 Represent the risk factors x1, x2 and x 10 For the prediction result y 10 The two models include common risk factors x1 and x2, as well as their own individual risk factors x5 and x6. 10 .

[0036] S130, inputting the risk factor value of the target patient into the prediction model to predict whether the target patient has a risk of myocardial infarction after the specified period of time.

[0037] When there are multiple time lengths to be predicted, the value of at least one risk factor corresponding to each time length of the target patient is input into the prediction model corresponding to each time length to predict whether the target patient has a risk of myocardial infarction after each time length. This method can select an appropriate time length for prediction according to the patient's needs and concerns, and make accurate predictions at different time scales.

[0038] Optionally, after obtaining whether the target patient has a risk of myocardial infarction after each time length, the following steps may also be included:

[0039] Step 1: Arrange multiple recognition results in chronological order. That is, sort multiple recognition results in the order of the length of time to be predicted. For example, the length of time to be predicted includes: 5 years, 8 years, 10 years, 13 years, 15 years, 18 years, and 20 years, and the corresponding prediction results are also arranged in the order of increasing years.

[0040] Step 2: Identify the two time lengths before and after the sequence changes from no risk to risk. Usually, as time accumulates, the probability of myocardial infarction increases, which is represented by 0 in the first half and 1 in the second half in the risk sequence. At this time, pay attention to the two time lengths before and after the sequence changes from 0 to 1. The patient's health status will change between these two time lengths.

[0041] Step 3: Output the two time lengths and the corresponding risk factors in the prediction model whose weights are greater than the preset values, so as to provide prognostic recommendations for the target patient. Specifically, in the two time lengths (e.g., 10 years and 13 years), the time length for which the identification result is risk-free is called the first time length (10 years), and the time length for which the identification result is risky is called the second time length (13 years); extract the first prediction model corresponding to the first time length, and determine the first risk factor (e.g., age, smok, sbp) whose weight is greater than the preset value in the first prediction model; extract the second prediction model corresponding to the second time length, and determine the second risk factor (e.g., smok, bmi) whose weight is greater than the preset value in the second prediction model; recommend the first time length as the prognostic time, and recommend the first risk factor and the second risk factor together as the prognostic concern factors (age, smok, sbp, bmi).

[0042] This embodiment selects an appropriate risk factor combination and prediction model based on the time length required by the patient, predicts the risk of myocardial infarction in patients with type 2 diabetes after a specific time length in the future, and achieves accurate prediction of time length and multiple risk factors. It also characterizes the impact of each risk factor on the risk of myocardial infarction at each time length through the weights in the linear model, and provides guidance for the patient's prognosis plan. In particular, through continuous prediction of multiple time lengths, it is possible to automatically identify the turning point from no risk to risk identification, and locate the key risk factors before and after the turning point, which are used together as the improvement target of the prognosis plan, and improve the accuracy of the individual prognosis strategy through the prognosis time and prognosis factors.

[0043] Furthermore, the present invention also provides a method for constructing a long-term prediction model for myocardial infarction in patients with type 2 diabetes, using the baseline and follow-up data of the diabetes prevention study to establish a long-term prediction model for myocardial infarction in patients with type 2 diabetes as described in any of the above embodiments, and to verify the model. Figure 2 As shown, the method specifically includes:

[0044] S210. Obtain multiple clinical variables of multiple type 2 diabetes patients, and follow-up results of whether each type 2 diabetes patient develops myocardial infarction after different lengths of time.

[0045] Optionally, the multiple clinical variables include: gender, age, smoking, fasting blood glucose, blood glucose 1 hour after load, blood glucose 2 hours after load, blood pressure, diastolic blood pressure, body mass index, total cholesterol and triglycerides, duration of diabetes, history of hypertension, history of hyperlipidemia, family history of diabetes, glycosylated hemoglobin, renal function, etc.

[0046] S220: For each time length, perform the following operations respectively:

[0047] S1. Based on the patient data corresponding to the current time length, calculate the information gain of each clinical variable and the follow-up result. The specific calculation method is the existing technology.

[0048] S2. According to the information gain, the risk factors leading to myocardial infarction in patients with type 2 diabetes are screened out from the multiple clinical variables. In this embodiment, information gain is used to screen out some variables closely related to myocardial infarction from a large number of clinical variables as risk factors for modeling.

[0049] S3. Using the risk factor values ​​and follow-up results of each patient as samples, a long-term prediction model for myocardial infarction in patients with type 2 diabetes is trained. The trained model inputs the patient's risk factor values, and outputs a prediction result of whether the patient will have a myocardial infarction after the current length of time.

[0050] Optionally, a linear discriminant analysis is used to build a prediction model. The basic process is: project the training samples onto a straight line so that the projection points of samples of the same type are as close as possible and the projection points of samples of different types are as far apart as possible. Figure 3 For example, x1 and x2 represent feature variables, T1 and T2 represent two types of samples, corresponding to center point 1 and center point 2 respectively. x represents the variable, w represents the weight, y=wx represents the projected curve, and what needs to be learned is such a segmentation line or segmentation surface. After training, the prediction process is to project the sample to be predicted onto the learned segmentation line or segmentation surface, and judge its category according to the position of its projection point.

[0051] Optionally, after training, the model is trained and tested using a 10-fold cross-validation method. The test results are plotted as ROC curves, and the area under the curve is calculated to evaluate the performance of the prediction model. Specifically, the data set is divided into ten parts, 9 of which are used for training and 1 for validation in turn, and the average of the 10 results is used as an estimate of the accuracy of the algorithm. The advantage of this method is that randomly generated subsamples are repeatedly used for training and validation at the same time, and the results are validated each time, and all samples are tested once. The model evaluation indicators are the receiver operating characteristic curve (receiver operating characteristic curve, referred to as ROC curve) and the area under the ROC curve (Area Under ROC Curve, referred to as AUC value).

[0052] Specifically, the prediction models constructed in this embodiment are all binary classification models, and the prediction results include positive and negative classes, and there are four possibilities for the output results. A sample that is a positive class and is correctly predicted as a positive class is called a true positive (TP), a sample that is a negative class and is correctly predicted as a negative class is called a true negative (TN), a sample that is a positive class and is incorrectly predicted as a negative class is called a false negative (FN), and a sample that is a negative class and is incorrectly predicted as a positive class is called a false positive (FP).

[0053] Based on the above four types of outputs, the following two indicators are defined to characterize the model performance:

[0054]

[0055] Among them, TP rate represents the prediction accuracy of positive samples, N TP Represents the number of correct positive samples, N FN Indicates the number of false negative samples.

[0056]

[0057] Among them, TN rate represents the prediction accuracy of negative samples, N TN is the number of correct negative samples, N FP is the number of false positive samples.

[0058] TP rate and TN rate are used to evaluate the accuracy of positive and negative predictions, respectively. With TN rate as the horizontal axis and TP rate as the vertical axis, under the condition of different thresholds of the model, the ROC curve is formed to comprehensively evaluate the performance of the prediction model. The area under the ROC curve can also be used to quantitatively evaluate the performance of the prediction model.

[0059] For example, the 10-fold cross validation method was used to validate the myocardial infarction prediction model for type 2 diabetes patients with a time length of 5 years. The obtained ROC curve is as follows: Figure 4 As shown, the AUC value of the model is 0.7819, which fully demonstrates the accuracy of the model prediction.

[0060] The 10-fold cross-validation method was used to verify the myocardial infarction prediction model for type 2 diabetes patients with a time length of 10 years, and the ROC curve was obtained. The AUC value calculated by the ROC curve was 0.77127, which also proved the accuracy of the model prediction.

[0061] Optionally, the time length may also be 20 years, 30 years or longer, which is determined by the specific years of the follow-up data and is not limited in this embodiment.

[0062] Figure 5A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention is shown in FIG. Figure 5 As shown, the device includes a processor 60, a memory 61, an input device 62 and an output device 63; the number of processors 60 in the device can be one or more. Figure 5 A processor 60 is taken as an example; the processor 60, the memory 61, the input device 62 and the output device 63 in the device can be connected by a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0063] The memory 61 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the method for long-term prediction of myocardial infarction in patients with type 2 diabetes or the method for building a long-term prediction model of myocardial infarction in patients with type 2 diabetes in the embodiments of the present invention. The processor 60 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 61, that is, realizing the above-mentioned method for long-term prediction of myocardial infarction in patients with type 2 diabetes or the method for building a long-term prediction model of myocardial infarction in patients with type 2 diabetes.

[0064] The memory 61 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 61 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 61 may further include a memory remotely arranged relative to the processor 60, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0065] The input device 62 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 63 may include a display device such as a display screen.

[0066] An embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for long-term prediction of myocardial infarction in patients with type 2 diabetes or the method for constructing a long-term prediction model of myocardial infarction in patients with type 2 diabetes of any embodiment.

[0067] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0068] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0069] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0070] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for long-term prediction of myocardial infarction in patients with type 2 diabetes, characterized in that: include: Get multiple time lengths to be predicted; Selecting prediction models and at least one risk factor for myocardial infarction in patients with type 2 diabetes corresponding to each time length; wherein each time length is in years, and different time lengths correspond to different risk factors and prediction models; each prediction model is a linear model for at least one risk factor; Inputting the value of at least one risk factor corresponding to each time length of the target patient into the prediction model corresponding to each time length, respectively, to predict whether the target patient has a risk of myocardial infarction after each time length; Arrange multiple recognition results in chronological order; Identify the two time periods before and after the sequence changes from risk-free to risky; Outputting the two time lengths and the corresponding risk factors with weights greater than a preset value in the prediction model, so as to provide prognostic suggestions for the target patient; Among them, the construction methods of each prediction model include: Obtain multiple clinical variables of multiple type 2 diabetes patients, as well as follow-up results of whether each type 2 diabetes patient has myocardial infarction after different lengths of time; For each time length, perform the following operations respectively: S1. Calculate the information gain of each clinical variable and follow-up results based on the patient data corresponding to the current time length; S2. screening out risk factors for myocardial infarction in patients with type 2 diabetes from the multiple clinical variables based on the information gain; S3. Using the risk factor values ​​and follow-up results of each patient as samples, a long-term prediction model for myocardial infarction in patients with type 2 diabetes is trained. The trained model inputs the patient's risk factor values, and outputs a prediction result of whether the patient will have a myocardial infarction after the current length of time.

2. The prediction method according to claim 1, characterized in that: The outputting of the two time lengths and the corresponding risk factors with weights greater than a preset value in the prediction model, for providing prognostic suggestions for the target patient, includes: Among the two time lengths, a first time length during which the identification result is risk-free and a second time length during which the identification result is risky are distinguished; Determine a first prediction model corresponding to the first time length, and extract a first risk factor having a weight greater than a preset value in the first prediction model; Determine a second prediction model corresponding to the second time length, and extract a second risk factor having a weight greater than a preset value in the second prediction model; The first time length is suggested as the prognostic time, and the first risk factor and the second risk factor are jointly suggested as prognostic concern factors.

3. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the long-term prediction method for myocardial infarction in patients with type 2 diabetes as described in claim 1 or 2.

4. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the method for long-term prediction of myocardial infarction in patients with type 2 diabetes as claimed in claim 1 or 2 is implemented.