A system and method for monitoring the risk of acute myocardial infarction prognosis

Abstract

The present application provides a system and method for monitoring the prognosis risk of acute myocardial infarction, including a prognosis portrait module, a risk association module and a cycle adjustment module; the prognosis portrait module can obtain a prognosis portrait, and obtain the medical examination cycle and cycle adjustment period of the medical examination feature according to the risk assessment level of the prognosis portrait; the risk association module records the degree of association between the medical examination feature and the physical sign observation feature associated with it, and adjusts the degree of association between the medical examination feature and the physical sign observation feature according to the abnormality of the physical sign observation feature within the medical examination cycle; the cycle adjustment module adjusts the medical examination cycle of the medical examination feature according to the abnormality of the physical sign observation feature obtained in the cycle adjustment period and the degree of association between the medical examination feature and the physical sign observation feature. The present application optimizes the examination cycle and improves the accuracy of the prognosis model data.

Description

Technical Field

[0001] The present application relates to the field of acute myocardial infarction prognosis, and specifically to an acute myocardial infarction prognosis risk monitoring system and method. Background Art

[0002] The prognosis of acute myocardial infarction refers to the patient's recovery and survival after acute myocardial infarction. The prognosis of myocardial infarction is affected by many factors, including the patient's personal condition, basic health status, degree of myocardial damage, degree of timely treatment, etc. Therefore, timely grasp of the risk characteristics related to the prognosis of myocardial infarction has a very important indicative role in the accuracy of predicting the prognosis of myocardial infarction.

[0003] The risk characteristics used to establish a myocardial infarction prognosis risk model generally include the patient's basic personal characteristics, physical sign observation characteristics, treatment characteristics and medical examination characteristics. Through the above characteristics, a risk monitoring model for myocardial infarction prognosis can be established. Among them, the patient's basic personal characteristics can be obtained through surveys and inquiries, physical sign observation characteristics can be obtained in real time during rounds, and medical examination characteristics need to be obtained through medical equipment and analysis of medical condition data.

[0004] The acquisition of each medical examination feature requires the use of professional medical equipment. Some features may even cause some harm to the patient's body during the acquisition process, consume a certain amount of medical resources, and are also expensive. Therefore, a method is needed that comprehensively considers the physical sign observation characteristics and treatment plans to provide optimization recommendations for the cycle of obtaining medical examination features.

[0005] In addition, in clinical practice, each patient has different physical constitutions, so the correlation between the characterization of physical sign observation characteristics and medical examination characteristics will also be different. If a unified standard is used, individual errors will often occur in judgment. Therefore, it is also necessary to adjust the degree of correlation between physical sign observation characteristics and medical examination characteristics based on actual individual circumstances. Summary of the invention

[0006] In order to solve the problem, the present application provides an acute myocardial infarction prognosis risk monitoring system, including a prognosis portrait module, a risk association module and a cycle adjustment module;

[0007] The prognostic portrait module can obtain a prognostic portrait based on personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics, and obtain a medical examination cycle and cycle adjustment period of the medical examination characteristics based on the risk assessment level of the prognostic portrait;

[0008] The risk association module records the degree of association between the medical examination feature and the physical sign observation feature associated therewith, and adjusts the degree of association between the medical examination feature and the physical sign observation feature according to the abnormality of the physical sign observation feature during the medical examination cycle;

[0009] The cycle adjustment module adjusts the medical examination cycle of the medical examination feature according to the abnormality of the physical sign observation feature obtained during the cycle adjustment period and the correlation degree between the medical examination feature and the physical sign observation feature.

[0010] Among them, the cycle adjustment period is included in the medical examination cycle, and the cycle adjustment period includes a first adjustment period and a second adjustment period. According to the abnormal situation of the physical sign observation characteristics in the first adjustment period, it is determined whether to enter the second adjustment period.

[0011] Among them, according to the abnormal situation of the vital sign observation characteristics in the first adjustment period, it is judged whether the vital sign observation characteristics enter the abnormal adjustment list. If it is judged that the vital sign observation characteristics enter the abnormal adjustment list, the step ends. If it is judged that the vital sign observation characteristics do not enter the abnormal adjustment list, the second adjustment period is entered, and according to the abnormal situation of the vital sign observation characteristics in the second adjustment period, it is judged whether the vital sign observation characteristics enter the abnormal adjustment list.

[0012] Among them, the medical examination features include endoscopy, biopsy tissue examination, abnormal neurological examination and cardiac ultrasound examination.

[0013] Among them, the categories of physical sign observation characteristics include blood pressure, blood sugar, blood lipids, heart rate, body temperature, white blood cell count and electrocardiogram.

[0014] The present application also provides a risk monitoring method of the acute myocardial infarction prognosis risk monitoring system as described above, comprising the following steps:

[0015] S1, obtain the prognostic portrait based on personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics, and obtain the risk assessment level EI of the prognostic portrait through the network neural model;

[0016] S2, set the prognostic profile to include DM medical examination features EA, EA = [EA1, EA2, EA3, ..., EA DM ], among which, the DI medical examination feature EA DI , obtain the medical examination characteristics EA under the EI risk assessment level DI The medical examination cycle is △TEI;

[0017] The initial medical examination cycle ΔTEI includes a cycle adjustment period ΔTDI, and the cycle adjustment period ΔTDI further includes a first adjustment period ΔTDI1 and a second adjustment period ΔTDI2.

[0018] S3, Set up medical examination feature EA DI Associated with DK-type physical sign observation features EC, EC = [EC, EC2, EC3, …, ECDK ], where the associated DZ-type physical sign observation feature is EC DZ ;

[0019] In the physical sign observation feature data obtained in the first adjustment period △TDI1 in the periodic adjustment period △TDI, there are DR physical sign observation feature categories that are abnormal, and the physical sign observation feature category ECA with abnormality is obtained, ECA=[ECA1, ECA2, ECA3, …, ECA DR ], where the abnormal DB-type physical sign observation feature ECA is set DB There are DM eigenvalues ​​in total, of which DF eigenvalues ​​are abnormal, and the DB-type physical sign observation feature ECA is obtained DB The abnormal characteristic value ECB = [ECB1, ECB2, ECB3, ..., ECB DF ], where the DGth abnormal feature value is ECB DG , set the DB type of physical sign observation feature ECA DB The normal threshold is U DB ;

[0020] Obtain the DB type of physical signs and observation characteristics ECA DB The abnormal distribution of φ = DF / DM;

[0021] The DGth abnormal characteristic value is obtained as ECB DG The abnormal difference △U BG =|ECB DG -U DB |;

[0022] Obtain the abnormal physical sign observation characteristics ECA of the DB category in the first adjustment period DB The first difference of the class anomaly ;

[0023] Set DB type physical sign observation feature ECA DB The class anomaly threshold is △UDB0;

[0024] When △UDA DB ≥△UDB0, the DB type of signs and features ECA DB and its class anomaly difference Enter the Medical Examination Feature EA DI The abnormal adjustment list TL;

[0025] When △UD DB <△UD D0 When , go to step S4;

[0026] S4, obtaining a physical sign observation feature in a second adjustment period ΔTDI2 after the first adjustment period ΔTDI1, and comparing it with the physical sign observation feature ECA of the DB class in the first adjustment period DB The first difference of the class abnormality is obtained in the same way as the DB class physical sign feature ECA DB The second difference of the class anomaly in the second adjustment period ,

[0027] when When the DB type of signs and characteristics ECA DB and its class anomaly difference Enter the Medical Examination Feature EA DI Adjustment list TL;

[0028] S5, set that after the adjustment period ends, the adjustment list TL includes DH type physical sign observation characteristics, TL = [ECC1, ECC2, ECC3, ..., ECC DH ], among which, the DA type of signs and observation characteristics ECC DA The class anomaly difference is △UDC DA , among which, the DA type of signs and observation characteristics ECC DA EA with medical examination features DI The correlation coefficient is λ DA ;

[0029] Obtain adjustment factor for medical examination cycle ,

[0030] The adjusted medical examination period △TEI'=FTL*△TEI is obtained.

[0031] The method further includes step S6, obtaining the DA-type physical sign observation feature ECC. DA The class anomaly difference is △UDC DA , Class DA signs and observation characteristics ECC DA EA with medical examination features DI The correlation coefficient is λ DA ; Set the correlation anomaly threshold △UDC0 and the correlation coefficient threshold λ0;

[0032] When △UDC DA ≥△UDC0, at the same time λ DA ≤λ0, the correlation coefficient λ DA Adjust to , where e is a natural constant.

[0033] Among them, in step S1, the method of obtaining the risk assessment level EI of the prognostic portrait through the network neural model is:

[0034] Taking personal characteristics, medical examination characteristics, physical sign observation signs and medical characteristics as input sample features, the SVM algorithm is as follows:

[0035] Set the objective function:

[0036] ,

[0037] Where W and b are the plane coefficients, Represents the classification label of the sample, =[-1,1], is the training sample; W is the plane coefficient, when extended to n-dimensional space, it is an n-dimensional vector such as: W=[W1,W2,...,W n ], is the transpose of W, ||W|| is the norm of the hyperplane;

[0038] Since the SVM objective function assumes that the data is linearly separable, but in reality there will be noisy data, slack variables and penalty parameters are added to increase the model tolerance through slack variables. ;

[0039] in, is the penalty coefficient, is a slack variable, which is represented by the distance from the misclassified point to the plane where the corresponding category support vector is located. , the penalty term is determined by all outliers;

[0040] The optimization problem is transformed into a dual problem using the Lagrange multiplier method and KKT conditions, and is solved using the SMO method. is the Lagrange multiplier. The dual problem obtained by mapping the model to a high dimension is:

[0041] ;

[0042] The kernel function selected in this article is the Gaussian function: ,

[0043] The above SVM classifier model is used to analyze the features and obtain the output results for risk assessment level judgment.

[0044] The beneficial effects achieved by this application are as follows:

[0045] This application can comprehensively analyze the correlation between physical sign observation characteristics and medical examination characteristics, adjust the cycle of obtaining medical examination characteristics, provide suggestions and reminders to medical staff and patients, provide references for disease examinations, optimize work efficiency, and avoid possible shortages and excessive examinations. At the same time, through comprehensive calculation of data, the degree of correlation between clinical physical sign observation signs and medical examination characteristics can be updated and modified to reduce individual errors and make the model evaluation results more optimized and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For those skilled in the art, other drawings can also be obtained based on these drawings.

[0047] Figure 1 This is a flow chart of the risk monitoring method of the acute myocardial infarction prognosis risk monitoring system of this application. DETAILED DESCRIPTION

[0048] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0049] Specifically, the present application provides an acute myocardial infarction prognosis risk monitoring system, including a prognosis portrait module, a risk association module and a cycle adjustment module.

[0050] Among them, the prognostic portrait module can obtain a prognostic portrait based on personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics, establish a myocardial infarction prognosis assessment model based on the prognostic portrait, evaluate the myocardial infarction prognosis risk level, and obtain the medical examination cycle and cycle adjustment period of the medical examination characteristics corresponding to the risk level.

[0051] Among them, the patient's personal characteristics are the patient's inherent physical conditions including age, gender, weight, previous medical history, etc.; physical sign observation characteristics are physical signs that can be obtained in a quick and easy way, including heart rate, body temperature, blood pressure, blood sugar, etc.; medical examination characteristics are those that need to be obtained through medical means using certain medical resources and technologies, including imaging examination characteristics (X-ray, CT scan, MRI and ultrasound, etc.) used to observe the structure and function of internal organs, endoscopic examination characteristics used to observe and examine the inside of cavities (digestive tract, respiratory tract, urinary tract, etc.), biopsy tissue examination characteristics obtained by obtaining tissue or cell samples for microscopic observation and analysis, nervous system examination characteristics used to evaluate the function and abnormality of the nervous system (electroencephalogram, magnetoencephalogram and neuromuscular electrogram, etc.), and cardiac ultrasound examination characteristics that use ultrasound technology to observe and evaluate the structure and function of the heart. Treatment features include thrombolytic therapy (intravenous injection of thrombolytic drugs, such as tissue plasminogen activator or urokinase, to dissolve blood clots in the coronary arteries and restore blood flow), cardiac catheter intervention (percutaneous coronary intervention or coronary artery bypass grafting to restore the patency of the coronary arteries), and drug therapy (use of antiplatelet drugs such as aspirin, clopidogrel, and anticoagulant drugs such as heparin, low molecular weight heparin, etc.);

[0052] The risk association module records the degree of association between the medical examination feature and the physical sign observation feature associated therewith, and adjusts the degree of association between the medical examination feature and the physical sign observation feature according to the abnormality of the physical sign observation feature during the medical examination cycle;

[0053] The cycle adjustment module adjusts the medical examination cycle of the medical examination feature according to the abnormality of the physical sign observation feature obtained during the cycle adjustment period and the correlation degree between the medical examination feature and the physical sign observation feature.

[0054] Specifically, a network neural model for myocardial infarction prognosis risk assessment is established based on personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics in the prognostic portrait. Specifically, it can be calculated by the SVM algorithm of the classification model, wherein personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics are used as input sample features, and the SVM algorithm is as follows:

[0055] Set the objective function: ,

[0056] Where W and b are the plane coefficients, Represents the classification label of the sample, =[-1,1], is the training sample; W is the plane coefficient, when extended to n-dimensional space, it is an n-dimensional vector such as: W=[W1,W2,...,W n ], is the transpose of W, ||W|| is the norm of the hyperplane;

[0057] Since the SVM objective function assumes that the data is linearly separable, but in reality there will be noisy data, slack variables and penalty parameters are added to increase the model tolerance through slack variables. ;

[0058] in, is the penalty coefficient, is a slack variable, which is represented by the distance from the misclassified point to the plane where the corresponding category support vector is located. , the penalty term is determined by all outliers;

[0059] The optimization problem is transformed into a dual problem using the Lagrange multiplier method and KKT conditions, and is solved using the SMO method. is the Lagrange multiplier. The dual problem obtained by mapping the model to a high dimension is:

[0060] ;

[0061] The kernel function selected in this article is the Gaussian function: .

[0062] The SVM classifier model is used to analyze the features of the received message and obtain the output result for risk assessment level judgment. For example, when the output is 1, it is a high risk level, when the output is 0, it is a medium risk level, and when the output is -1, it is a low risk level. The assessed risk level is obtained, and according to the risk level, the initial medical examination cycle is obtained by obtaining the medical examination features corresponding to the risk level.

[0063] For example, the prognostic risk level evaluated by the network neural model established based on personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics is a high-risk level. When the medical examination feature "cardiac ultrasound" is at a low-risk level, the initial medical examination cycle is 20 days; while in the high-risk level, the initial medical examination cycle is 3 days.

[0064] Wherein, the cycle adjustment period is included in the medical examination cycle, and the cycle adjustment period includes a first adjustment period and a second adjustment period. According to the abnormality of the physical sign observation characteristics in the first adjustment period, it is determined whether to enter the second adjustment period. According to the abnormality of the physical sign observation characteristics in the first adjustment period, it is determined whether the physical sign observation characteristics enter the abnormal adjustment list. If it is determined that the physical sign observation characteristics enter the abnormal adjustment list, the step ends. If it is determined that the physical sign observation characteristics do not enter the abnormal adjustment list, the second adjustment period is entered, and according to the abnormality of the physical sign observation characteristics in the second adjustment period, it is determined whether the physical sign observation characteristics enter the abnormal adjustment list.

[0065] In this embodiment, the obtained initial medical examination cycle is ΔTEI, wherein the initial medical examination cycle ΔTEI includes an initial cycle adjustment period ΔTDI (ΔTEI>ΔTDI), and the cycle adjustment period ΔTDI also includes a first adjustment period ΔTDI1 and a second adjustment period ΔTDI2.

[0066] Set the prognostic profile to include DM medical examination features EA, EA = [EA1, EA2, EA3, …, EA DM ], among which, the DI medical examination feature EA DI Associated with DK-type physical sign observation features EC, EC = [EC, EC2, EC3, …, EC DK ], where the associated DZ-type physical sign observation feature is EC DZ , set the DIth medical examination feature EA DI EC with DZ-type signs and observation characteristics DZ The correlation coefficient is λ DZ ;

[0067] It is set that among the physical sign observation feature data obtained in the first adjustment period △TDI1 in the periodic adjustment period △TDI, there are DR physical sign observation feature categories that are abnormal, and the physical sign observation feature category ECA with abnormality is obtained, ECA=[ECA1, ECA2, ECA3, …, ECA DR ];

[0068] Set the abnormal DB type of physical sign observation feature ECA DB There are DM feature values ​​in total, DF of which are abnormal, and the DB-type physical sign observation feature ECA is obtained DB The abnormal characteristic value ECB=[ECB1,ECB2,ECB3,…,ECB DF ], where the DGth abnormal feature value is ECB DG , set the DB type of physical sign observation feature ECA DB The normal threshold is U DB ;

[0069] Obtain the DB type of physical signs and observation characteristics ECA DB The abnormal distribution of φ = DF / DM;

[0070] The DGth abnormal characteristic value is obtained as ECB DG The abnormal difference △U BG =|ECB DG -U DB |;

[0071] Obtain the abnormal physical sign observation characteristics ECA of the DB category in the first adjustment periodDB The first difference of the class anomaly ;

[0072] Set DB type physical sign observation feature ECA DB The class anomaly threshold is △UDB0;

[0073] When △UDA DB ≥△UDB0, the DB type of signs and features ECA DB and its class anomaly difference Enter the Medical Examination Feature EA DI The abnormal adjustment list TL;

[0074] When △UD DB <△UD D0 At this time, the physical sign observation feature is obtained in the second adjustment period △TDI2 after the first adjustment period △TDI1 to compare with the physical sign observation feature ECA of the first adjustment period. DB The first difference of the class abnormality is obtained in the same way as the DB class physical sign feature ECA DB The second difference of the class anomaly in the second adjustment period ,

[0075] when When the DB type of signs and characteristics ECA DB and its class anomaly difference Enter the Medical Examination Feature EA DI Adjustment list TL;

[0076] After the adjustment period, the adjustment list TL is set to include DH type physical sign observation characteristics, TL = [ECC1, ECC2, ECC3, ..., ECC DH ], among which, the DA type of signs and observation characteristics ECC DA The class anomaly difference is △UDC DA , among which, the DA type of signs and observation characteristics ECC DA EA with medical examination features DI The correlation coefficient is λ DA ;

[0077] Obtain adjustment factor for medical examination cycle ,

[0078] The adjusted medical examination period △TEI'=FTL*△TEI is obtained.

[0079] In addition, in some clinical situations, the correlation between the physical sign observation characteristics and the medical examination characteristics in the adjustment list TL is very low, but in actual monitoring, it often appears at the same time as other physical sign observation characteristics with higher correlation. Therefore, it is also considered to adjust and improve its correlation accordingly.

[0080] Specifically, obtain the DA type of signs and observation characteristics ECC DA The class anomaly difference is △UDC DA , Class DA signs and observation characteristics ECC DA EA with medical examination features DI The correlation coefficient is λ DA ; Set the correlation anomaly threshold △UDC0 and the correlation coefficient threshold λ0;

[0081] When △UDC DA ≥△UDC0, at the same time λ DA ≤λ0, the correlation coefficient λ DA Adjust to , where e is a natural constant.

[0082] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application. Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A risk monitoring method for an acute myocardial infarction prognosis risk monitoring system, characterized in that the steps include: S0, provides an acute myocardial infarction prognosis risk monitoring system, including a prognosis portrait module, a risk association module, and a cycle adjustment module; The prognostic portrait module can obtain a prognostic portrait based on personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics, and obtain the medical examination cycle and cycle adjustment period of the medical examination characteristics according to the risk assessment level of the prognostic portrait; the risk association module records the degree of association between the medical examination characteristics and the physical sign observation characteristics associated with them, and adjusts the degree of association between the medical examination characteristics and the physical sign observation characteristics according to the abnormality of the physical sign observation characteristics within the medical examination cycle; the cycle adjustment module adjusts the medical examination cycle of the medical examination characteristics according to the abnormality of the physical sign observation characteristics obtained during the cycle adjustment period and the degree of association between the medical examination characteristics and the physical sign observation characteristics; S1, obtain the prognostic portrait based on personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics, and obtain the risk assessment level EI of the prognostic portrait through the network neural model; S2, set the prognostic profile to include DM medical examination features EA, EA = [EA1, EA2, EA3, ..., EA DM ], among which, the DI medical examination feature EA DI , obtain the medical examination characteristics EA under the EI risk assessment level DI The medical examination cycle is △TEI; The initial medical examination cycle △TEI includes a cycle adjustment period △TDI, and the cycle adjustment period △TDI also includes a first adjustment period △TDI1 and a second adjustment period △TDI2; S3, Set up medical examination feature EA DI Associated with DK-type physical sign observation features EC, EC = [EC, EC2, EC3, …, EC DK ], where the associated DZ-type physical sign observation feature is EC DZ ; In the physical sign observation feature data obtained in the first adjustment period △TDI1 in the periodic adjustment period △TDI, there are DR physical sign observation feature categories that are abnormal, and the physical sign observation feature category ECA with abnormality is obtained, ECA=[ECA1, ECA2, ECA3, …, ECA DR ], where the abnormal DB-type physical sign observation feature ECA is set DB There are DM eigenvalues ​​in total, of which DF eigenvalues ​​are abnormal, and the DB-type physical sign observation feature ECA is obtained DB The abnormal characteristic value ECB = [ECB1, ECB2, ECB3, ..., ECB DF ], where the DGth abnormal feature value is ECB DG , set the DB type of physical sign observation feature ECA DB The normal threshold is U DB ; Obtain the DB type of physical signs and observation characteristics ECA DB The abnormal distribution of φ = DF / DM; The DGth abnormal characteristic value is obtained as ECB DG The abnormal difference △U BG =|ECB DG -U DB |; Obtain the abnormal physical sign observation characteristics ECA of the DB category in the first adjustment period DB The first difference of the class anomaly ; Set DB type physical sign observation feature ECA DB The class anomaly threshold is △UDB0; When △UDA DB ≥△UDB0, the DB type of signs and features ECA DB and its class anomaly difference Enter the Medical Examination Feature EA DI The abnormal adjustment list TL; When △UD DB <△UD D0 When , go to step S4; S4, obtaining a physical sign observation feature in a second adjustment period ΔTDI2 after the first adjustment period ΔTDI1, and comparing it with the physical sign observation feature ECA of the DB class in the first adjustment period DB The first difference of the class abnormality is obtained in the same way as the DB class physical sign feature ECA DB The second difference of the class anomaly in the second adjustment period , when When the DB type of signs and characteristics ECA DB and its class anomaly difference Enter the Medical Examination Feature EA DI Adjustment list TL; S5, set that after the adjustment period ends, the adjustment list TL includes DH type physical sign observation characteristics, TL = [ECC1, ECC2, ECC3, ..., ECC DH ], among which, the DA type of signs and observation characteristics ECC DA The class anomaly difference is △UDC DA , among which, the DA type of signs and observation characteristics ECC DA EA with medical examination features DI The correlation coefficient is λ DA ; Obtain adjustment factor for medical examination cycle , The adjusted medical examination period △TEI'=FTL*△TEI is obtained.

2. The risk monitoring method of the acute myocardial infarction prognosis risk monitoring system according to claim 1, characterized in that: The cycle adjustment period is included in the medical examination cycle, and the cycle adjustment period includes a first adjustment period and a second adjustment period. According to the abnormal situation of the physical sign observation characteristics in the first adjustment period, it is determined whether to enter the second adjustment period.

3. The risk monitoring method of the acute myocardial infarction prognosis risk monitoring system according to claim 2, characterized in that: According to the abnormal situation of the vital sign observation characteristics in the first adjustment period, it is determined whether the vital sign observation characteristics enter the abnormal adjustment list. If it is determined that the vital sign observation characteristics enter the abnormal adjustment list, the step ends. If it is determined that the vital sign observation characteristics do not enter the abnormal adjustment list, the second adjustment period is entered. According to the abnormal situation of the vital sign observation characteristics in the second adjustment period, it is determined whether the vital sign observation characteristics enter the abnormal adjustment list.

4. The risk monitoring method of the acute myocardial infarction prognosis risk monitoring system according to claim 1, characterized in that: The medical examination features include endoscopy, biopsy, abnormal neurological examination and cardiac ultrasound.

5. The risk monitoring method of the acute myocardial infarction prognosis risk monitoring system according to claim 1, characterized in that: The categories of physical sign observation characteristics include blood pressure, blood sugar, blood lipids, heart rate, body temperature, white blood cell count and electrocardiogram.

6. The risk monitoring method of the acute myocardial infarction prognosis risk monitoring system according to claim 1, characterized in that: The step S6 is also included to obtain the DA-type physical sign observation feature ECC DA The class anomaly difference is △UDC DA , Class DA signs and observation characteristics ECC DA EA with medical examination features DI The correlation coefficient is λ DA ; Set the correlation anomaly threshold △UDC0 and the correlation coefficient threshold λ0; When △UDC DA ≥△UDC0, at the same time λ DA ≤λ0, the correlation coefficient λ DA Adjust to , where e is a natural constant.

Images