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

Abstract

The present application provides an acute myocardial infarction prognosis risk monitoring system and a monitoring method thereof, including a basic feature module, a physical sign observation module and an observation adjustment module; wherein the basic feature module includes a basic personal submodule and a basic bad submodule, the basic personal submodule can obtain a basic personal score according to the basic personal features; the basic bad submodule can obtain a basic bad score according to the basic bad features; the physical sign observation module includes an observation period and an observation cycle, the observation period is used to set the duration of observing the physical sign features, and the observation cycle is used to set the cycle of observing the physical sign features within the observation period; the observation adjustment module can comprehensively consider the basic personal score and the basic bad score, set the observation period and the observation cycle, and then adjust the observation period and the observation cycle according to the acquired physical sign features. The present application optimizes the data observation cycle and improves the accuracy of the prognosis model.

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] Acute myocardial infarction (AMI) is a serious cardiovascular disease caused by insufficient blood supply to the myocardium due to coronary artery stenosis or blockage, which leads to ischemic necrosis of myocardial tissue. Acute myocardial infarction used to occur more frequently in middle-aged and elderly people over 40 years old, but in recent years, due to long working hours, staying up late, smoking, improper diet and other problems, it has also shown a sharp increase in young people.

[0003] The prognosis of acute myocardial infarction refers to the patient's recovery and survival status 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, and degree of timely treatment. For example, early diagnosis and timely treatment can significantly improve the prognosis of myocardial infarction, but if there are complications, a large range of myocardial damage, etc., it may lead to adverse prognoses such as heart failure, recurrent myocardial infarction, and heart failure. Therefore, timely grasping 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. Specifically, the risk characteristics related to the prognosis of myocardial infarction generally include the patient's basic personal characteristics, physical sign observation characteristics, treatment characteristics, and medical examination characteristics; among them, the patient's basic personal characteristics are the patient's inherent physical conditions, including age, gender, weight, previous medical history, etc. The physical sign observation characteristics are physical signs that can be obtained in a relatively simple and quick way, including heart rate, body temperature, blood pressure, blood sugar, etc. These characteristics can be collected in real time by medical staff during consultations and ward rounds or obtained by the patients themselves. Medical examination characteristics are those that require medical means and use of certain medical resources and technologies, including imaging examination characteristics (X-rays, CT scans, 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, neurological examination characteristics (electroencephalogram, magnetoencephalogram) used to evaluate the function and abnormality of the nervous system, and cardiac ultrasound examination characteristics using ultrasound technology to observe and evaluate the structure and function of the heart. Treatment characteristics include thrombolytic therapy (through intravenous injection of thrombolytic drugs, such as tissue plasminogen activator or urokinase, to dissolve blood clots in the coronary artery and restore blood flow), cardiac catheter intervention (percutaneous coronary intervention or coronary artery bypass grafting to restore the patency of the coronary artery), and drug therapy (using antiplatelet drugs such as aspirin, clopidogrel, anticoagulants such as heparin, low molecular weight heparin, etc.).

[0004] Based on the above characteristics, a risk monitoring model for myocardial infarction prognosis can be established to form a prediction of myocardial infarction prognosis under the digital medical system. In order to ensure the accuracy of the risk monitoring model for myocardial infarction prognosis, a large number of real-time risk characteristics related to myocardial infarction prognosis are needed as a basis. Among them, since the observation and acquisition of physical sign observation feature data is relatively convenient and quick, it is often easy to over-collect or under-collect. In order to ensure that the collected observation data is representative of the prognosis judgment and avoid the occurrence of a large amount of repeated redundant data that leads to deviations in prognosis judgment, an observation cycle with optimization rules that can be followed during data collection is needed, and a method that can scientifically adjust the observation cycle according to actual conditions is needed. Summary of the invention

[0005] In order to solve the problem, the present application provides an acute myocardial infarction prognosis risk monitoring system, including a basic feature module, a physical sign observation module and an observation adjustment module;

[0006] The basic feature module includes a basic personal submodule and a basic bad submodule, wherein the basic personal submodule can obtain a basic personal score according to the basic personal features; and the basic bad submodule can obtain a basic bad score according to the basic bad features.

[0007] The physical sign observation module includes an observation period and an observation cycle, wherein the observation period is used to set the duration of observing physical sign characteristics, and the observation cycle is used to set the cycle of observing physical sign characteristics within the observation period;

[0008] The observation adjustment module can comprehensively consider the basic personal score and the basic bad score, set the observation period and observation cycle, and then adjust the observation period and observation cycle according to the acquired physical sign characteristics.

[0009] The basic personal submodule obtains a basic personal score representing the personal risk situation through the characteristic values ​​of the basic personal characteristics and the corresponding risk coefficients, as well as the basic thresholds of the basic personal characteristics and the corresponding risk coefficients.

[0010] The basic adverse condition submodule obtains a basic adverse condition score representing the adverse physical condition risk situation through the adverse basic condition category and its risk coefficient.

[0011] Among them, the observation adjustment module obtains the basic characteristic score according to the basic personal score and the basic bad score, sets the observation period and observation cycle according to the basic characteristic score, obtains the physical sign characteristics during the observation period and observation cycle, and then adjusts the observation period and observation cycle according to the change trend of the obtained physical sign characteristics.

[0012] Among them, the basic personal characteristics include age, gender, height and weight, the basic adverse characteristics include hypertension, hyperglycemia, hyperlipidemia, coronary heart disease, drinking history and smoking history, and the physical signs include heart rate, body temperature, blood pressure, blood sugar, electrocardiogram and heart and lung murmurs.

[0013] The present application also provides a monitoring method using the acute myocardial infarction prognosis risk monitoring system as described above, comprising:

[0014] S1, set the basic personal characteristics to include m basic personal characteristic categories WAA, WAA = [WAA1, WAA2, WAA3, ..., WAA m ], where the i-th basic feature WA i The characteristic value of i , according to WA i The characteristic value UA i Get the corresponding risk factor RA i , set the i-th basic feature WA i The basic threshold is UA0, and according to the risk factor RA0 corresponding to UA0, the basic personal score FWAA= ;

[0015] The basic bad features are set to include n basic bad feature categories WAB, among which the p basic bad feature categories that actually occur are placed in the basic bad feature statistical list LAB, LAB = [WAB1, WAB2, WAB3, …, WAB p ], obtain the defect distribution ε=p / n, and calculate the jth basic defect feature WA according to the basic defect feature statistics list j The risk factor RB j , get the basic bad score FWAB= ;

[0016] Get the basic feature score FWA=FWAA+FWAB;

[0017] S2, performing physical sign characteristic observation in a first physical sign observation period in a first observation period △T1 according to the obtained basic characteristic score FWA;

[0018] The initial observation period is set to △T0, and the initial vital sign observation period is set to ω0, where △T0=ξω0, 2≤ξ≤10, ξ is an integer;

[0019] Get the first observation period ;

[0020] Among them, the first sign observation period of the first observation period ;

[0021] S3, setting the abnormal physical sign feature WD1 in the physical sign features obtained in the first observation period △T1 to include k1 abnormal categories WDA, WDA = [WDA1, WDA2, WDA3, ..., WDA k1 ], where the abnormal physical sign feature WDA of type z1 is set z1 The weight coefficient is λ z1 , signs WDA z1 The normal threshold is UZ 01 , among which, the abnormal signs and features of category z1 are WDA z1 In the observation period △T1, there are r1 abnormalities, among which the characteristic value UJ of the c1th abnormal sign feature is c1 With normal threshold UZ 01 The abnormal difference △U c1 =UJ c1 -UZ 01 ;

[0022] Obtain the z1th abnormal sign WDA in the first observation period △T1 z The category difference ;

[0023] Get the first observation score for the first observation period △T1 ;

[0024] S4, setting the observation score threshold F0;

[0025] When F1≤F0, continue observation with the first sign observation period ω1;

[0026] When F1>F0, go to step S5;

[0027] S5, in the αth (α>1) observation period △T α Observe the cycle ω with the αth sign α Observe, where △T α <△T α-1 ;

[0028] Among them, the αth observation period , obtain the αth sign observation cycle , proceed to step S6;

[0029] S6, set the abnormal physical sign feature WD2 that occurs during the observation period to include k2 abnormal categories WDB, WDB=[WDB1, WDB2, WDB3, ..., WDB k2 ], among which, the sign WDA z2 The normal threshold is UZ 02 , set the z2nd category abnormal signs WDA z2During the observation period, there are r2 abnormalities, and the characteristic value of the c2th abnormal sign feature is UJ c2 with WDA z2 The normal threshold UZ 20 The abnormal difference △U c2 =UJ c2 -UZ 02 , obtain the z2nd category of abnormal signs WDA during the observation period z2 The category difference ;

[0030] Get the observation score for the αth observation period ;

[0031] When F α ≤F0, observe the αth sign during the period ω α Continue to observe for signs;

[0032] When F α ≥F α-1 When , go to step S7;

[0033] F0<F α <F α-1 When the first abnormal distribution growth rate δ is obtained α-1 =(F α-1 -F α ) / r1;

[0034] Get the second abnormal distribution growth rate δ α =(F α -F0) / r2;

[0035] When δ α ≤δ α-1 When the αth sign is observed, the cycle ω α Continue to observe for signs;

[0036] When δ α >δ α-1 When , go to step S7;

[0037] S7, in the α+1th observation period △T α+1 Take the α+1th observation period ω α+1 Observe, where △T α+1 <△T α , go to step S6.

[0038] In step S5, the minimum observation period ΔT is set. min ;

[0039] When △T α >△T min When , go to step S6;

[0040] When △T α ≤△T min When the minimum observation period △T min Observe the physical signs and characteristics.

[0041] The beneficial effects achieved by this application are as follows:

[0042] The monitoring method provided in the present application can help establish an accurate risk monitoring model for the prognosis of myocardial infarction, can ensure the provision of an accurate data basis for the prediction of the prognosis of myocardial infarction, can provide reminders and suggestions for observing relevant data to medical personnel, ward rounds personnel and individual patients, avoid missed inspections resulting in insufficient data collection, and avoid frequent observations resulting in waste of manpower and material resources and increased mental stress. The present application optimizes the periodic allocation algorithm to ensure that the collected observation data is representative of the prognosis judgment, avoids the occurrence of a large amount of repeated redundant data that may lead to deviations in the prognosis judgment, and improves the accuracy of the data basis of the myocardial infarction prognosis model. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] 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.

[0044] Figure 1 This is a flow chart of a risk monitoring method for an acute myocardial infarction prognosis risk monitoring system for this application. DETAILED DESCRIPTION

[0045] 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.

[0046] The present application provides a risk monitoring system, including a basic feature module, a physical sign observation module and an observation adjustment module; wherein the basic feature module includes a basic personal submodule and a basic adverse submodule, the basic personal submodule can obtain a basic personal score according to the basic personal features; the basic adverse submodule can obtain a basic adverse score according to the basic adverse features; the observation adjustment module can comprehensively consider the basic personal score and the basic adverse score to adjust the observation period and observation cycle; the physical sign observation module observes the physical sign features related to the prognosis risk of myocardial infarction according to the observation period and observation cycle adjusted by the observation adjustment module.

[0047] The basic personal submodule obtains a basic personal score representing the basic personal risk situation through the characteristic values ​​of the basic personal characteristics and the corresponding risk coefficients, as well as the basic thresholds of the basic personal characteristics and the corresponding risk coefficients.

[0048] Specifically, the basic personal characteristics are set to include m basic personal characteristic categories WAA, WAA = [WAA1, WAA2, WAA3, ..., WAA m ], where the i-th basic feature WA i The characteristic value of i , according to WA i The characteristic value UA i Get the corresponding risk factor RA i , set the i-th basic feature WA i The basic threshold is UA0, and according to the risk factor RA0 corresponding to UA0, the basic personal score FWAA= .

[0049] The basic adverse submodule obtains the basic adverse score representing the basic physical adverse risk situation through the basic adverse category and its risk coefficient. Specifically, the basic adverse feature is set to include n basic adverse feature categories WAB, wherein the actual p basic adverse categories are placed in the adverse feature statistical list LAB, LAB = [WAB1, WAB2, WAB3, ..., WAB p ], and obtain the defect distribution ε=p / n, set the jth basic defect feature WA in the basic defect feature statistics list j The risk factor is RB j , get the basic bad score FWAB=

[0050] The basic feature score FWA is obtained as FWAA+FWAB.

[0051] In a specific embodiment, the basic personal characteristics include three characteristic categories: age, gender and weight (BMI). A basic threshold is set for each characteristic category. For example, the basic threshold of age is set to 50 years old, and the corresponding risk factor is set to 1. When the age exceeds 50 years old, the risk factor increases accordingly, as shown in Table 1, which is a numerical comparison table of age growth and risk factor in this embodiment. In the existing clinical data, it can be found that there are more male patients with myocardial infarction than female patients, and the incidence rate of female patients is relatively low, because estrogen has an anti-atherosclerotic effect. Therefore, in the gender characteristics, the risk factor of males is set to be greater than that of females. The specific values ​​of the risk factor are shown in Table 2. The body mass index (BMI), also known as the body mass index, is calculated by dividing the weight (kg) by the square of the height (m). It can reflect the density of the human body and the degree of fatness and thinness to a certain extent. Therefore, in this embodiment, the basic threshold of BMI is set to 24. When the patient's BMI is higher than 24, the risk factor will increase with the degree of obesity. The specific values ​​are shown in Table 3:

[0052]

[0053] In this embodiment, according to the above values, the patient A to be predicted for the risk of myocardial infarction prognosis is 55 years old, male, with a BMI of 25.5, and a history of hypertension, hyperlipidemia, smoking, and drinking for more than 3 years. At this time, according to Table 1, Table 2, and Table 3, the basic personal score FWAA=(1.2-1)+(1.4-1)+(1.2-1)=0.8 can be obtained; the basic adverse characteristics account for 4 out of a total of 6 items, and the adverse distribution is 2 / 3, and the basic adverse score FWAB=(0.2+0.2+0.1+0.1) 2 / 3 =0.7

[0054] Patient A's basic characteristic WA score FWA=FWAA+FWAB=0.8+0.7=1.5.

[0055] The observation adjustment module obtains a basic characteristic score according to the basic personal score and the basic bad score, sets an observation period and an observation cycle according to the basic characteristic score, obtains physical sign characteristics during the observation period and the observation cycle, and then adjusts the observation period and the observation cycle according to the obtained characteristics.

[0056] Specifically, according to the obtained basic characteristic scores, physical sign observation is performed in a first physical sign observation period in a first observation period;

[0057] The initial value of the observation period is set to △T0, and the initial value of the physical sign observation period is set to ω0, where △T0=ξω0, 2≤ξ≤8, ξ is an integer;

[0058] Get the first observation period , obtain the first sign observation period ;

[0059] In the first observation period △T1, the patient's physical signs are observed with the first physical sign observation period ω1. In the physical sign data obtained, the abnormal physical sign WD1 is set to include k1 abnormal categories WDA, WDA = [WDA1, WDA2, WDA3, ..., WDA k1 ], among which, the abnormal signs of category z1 WDA z1 The weight coefficient is λ z1 , set the sign WDA z1 The normal threshold is UZ 01 , abnormal signs of category z1 WDA z1 In the first observation period △T1, there are r1 abnormalities, among which the c1th abnormal sign UJ c1 With normal threshold -UZ 01 The abnormal difference △U c1 =UJ c1 -UZ 01 , then the z1th abnormal sign WDA in the first observation period △T1 can be obtained z The category difference ;

[0060] Similarly, the differences of all categories in the first observation period can be obtained to obtain the first observation score of the first observation period. ;

[0061] Set the observation score threshold F0,

[0062] When F1≤F0, continue observation with the first sign observation period ω1;

[0063] When F1>F0, observation is performed in the second observation period △T2 with the second physical sign observation cycle ω2, wherein △T2<△T1;

[0064] Specifically, the second observation period , obtain the first sign observation period ;

[0065] In the physical sign data observed in the second observation period △T1 with the second physical sign observation cycle ω2, abnormal physical signs WD2 appear including k2 abnormal categories WDB, WDB= [WDB1, WDB2, WDB3, ..., WDB k2 ], among which, the second category of abnormal signs WDA z2 The normal threshold is UZ 20 , set the z2nd category abnormal signs WDA z2 In the second observation period △T2, r2 anomalies occur, among which the c2th anomaly data UJ c2The abnormal difference △U c2 =UJ c2 -UZ 20 , obtain the z2th abnormal sign WDA in the second observation period △T2 z2 The category difference ,

[0066] Get the second observation score ;

[0067] When F2<F0, continue observation with the second sign observation period ω2;

[0068] When F2>F1, observation is performed in the third observation period △T3 with the third physical sign observation period ω3, wherein △T3<△T2;

[0069] Among them, the third observation period , obtain the third sign observation period ;

[0070] And so on, repeat the above steps until the observation period reaches the minimum observation period △T min When the minimum observation period △T is maintained min Make an observation.

[0071] When F0≤F2≤F1,

[0072] Get the first abnormal distribution growth rate δ1=(F1-F0) / r1

[0073] Second abnormal distribution growth rate δ2 = (F2-F1) / r2

[0074] When δ2<δ1, continue observation with the second sign observation period ω2

[0075] When δ2≥δ1, observe in the third observation period △T3 with the third physical sign observation period ω3, wherein △T3<△T2;

[0076] Among them, the third observation period , obtain the third sign observation period ;

[0077] And so on, repeat the above steps and set the minimum observation period △T min , when the adjusted observation period reaches the minimum observation period △T min When the minimum observation period △T is maintained min Make an observation.

[0078] Specifically, the physical sign observation characteristics WB observed during the observation period may include heart rate, body temperature, blood pressure, blood sugar, heart murmur examination, edema degree examination and other physical signs that are easy to obtain during the observation process. The physical sign observation characteristics WB can be obtained during ward rounds, nursing, and daily examinations.

[0079] 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 using an acute myocardial infarction prognosis risk monitoring system, wherein the acute myocardial infarction prognosis risk monitoring system comprises a basic feature module, a physical sign observation module and an observation adjustment module; wherein: The basic feature module includes a basic personal submodule and a basic bad submodule, wherein the basic personal submodule can obtain a basic personal score according to the basic personal features; the basic bad submodule can obtain a basic bad score according to the basic bad features; the physical sign observation module includes an observation period and an observation cycle, wherein the observation period is used to set the duration of observing the physical sign features, and the observation cycle is used to set the period of observing the physical sign features within the observation period; the observation adjustment module can comprehensively consider the basic personal score and the basic bad score, set the observation period and the observation cycle, and then adjust the observation period and the observation cycle according to the acquired physical sign features; It is characterized by comprising the following steps: S1, set the basic personal characteristics to include m basic personal characteristic categories WAA, WAA = [WAA1, WAA2, WAA3, ..., WAA m ], where the i-th basic feature WA i The characteristic value of i , according to WA i The characteristic value UA i Get the corresponding risk factor RA i , set the i-th basic feature WA i The basic threshold is UA0, and according to the risk factor RA0 corresponding to UA0, the basic personal score FWAA= ; The basic bad features are set to include n basic bad feature categories WAB, among which the p basic bad feature categories that actually occur are placed in the basic bad feature statistical list LAB, LAB = [WAB1, WAB2, WAB3, …, WAB p ], obtain the defect distribution ε=p / n, and calculate the jth basic defect feature WA according to the basic defect feature statistics list j The risk factor RB j , get the basic bad score FWAB= ; Get the basic feature score FWA=FWAA+FWAB; S2, performing physical sign characteristic observation in a first physical sign observation period in a first observation period △T1 according to the obtained basic characteristic score FWA; The initial observation period is set to △T0, and the initial vital sign observation period is set to ω0, where △T0=ξω0, 2≤ξ≤10, ξ is an integer; Get the first observation period ; Among them, the first sign observation period of the first observation period ; S3, setting the abnormal physical sign feature WD1 in the physical sign features obtained in the first observation period △T1 to include k1 abnormal categories WDA, WDA = [WDA1, WDA2, WDA3, ..., WDA k1 ], where the abnormal sign feature WDA of type z1 is set z1 The weight coefficient is λ z1 , signs WDA z1 The normal threshold is UZ 01 , among which, the abnormal signs and features of category z1 are WDA z1 In the observation period △T1, there are r1 abnormalities, among which the characteristic value UJ of the c1th abnormal sign feature is c1 With normal threshold UZ 01 The abnormal difference △U c1 =UJ c1 -UZ 01 ; Obtain the z1th abnormal sign WDA in the first observation period △T1 z The category difference ; Get the first observation score for the first observation period △T1 ; S4, setting the observation score threshold F0; When F1≤F0, continue observation with the first sign observation period ω1; When F1>F0, go to step S5; S5, the αth observation period ΔT after the first observation period α Observe the cycle ω with the αth sign α Observe, where △T α <△T α-1 ; Among them, the αth observation period , obtain the αth sign observation cycle , proceed to step S6; S6, set the abnormal physical sign feature WD2 that occurs during the observation period to include k2 abnormal categories WDB, WDB=[WDB1, WDB2, WDB3, ..., WDB k2 ], among which, the sign WDA z2 The normal threshold is UZ 02 , set the z2nd category abnormal signs WDA z2 During the observation period, there are r2 abnormalities, and the characteristic value of the c2th abnormal sign feature is UJ c2 with WDA z2 The normal threshold UZ 20 The abnormal difference △U c2 =UJ c2 -UZ 02 , obtain the z2nd category of abnormal signs WDA during the observation period z2 The category difference ; Get the observation score for the αth observation period ; When F α ≤F0, observe the αth sign during the period ω α Continue to observe for signs; When F α ≥F α-1 When , go to step S7; F0<F α <F α-1 When , we get the first abnormal distribution growth rate δ α-1 =(F α-1 -F α ) / r1; Get the second abnormal distribution growth rate δ α =(F α -F0) / r2; When δ α ≤δ α-1 When the αth sign is observed, the cycle ω α Continue to observe for signs; When δ α >δ α-1 When , go to step S7; S7, in the α+1th observation period △T α+1 Take the α+1th observation period ω α+1 Observe, where △T α+1 <△T α , go to step S6.

2. The risk monitoring method using the acute myocardial infarction prognosis risk monitoring system according to claim 1, characterized in that: The basic personal characteristics include age, gender, height and weight, the basic adverse characteristics include hypertension, hyperglycemia, hyperlipidemia, coronary heart disease, drinking history and smoking history, and the physical characteristics include heart rate, body temperature, blood pressure, blood sugar and cardiopulmonary murmurs.

3. The risk monitoring method using the acute myocardial infarction prognosis risk monitoring system as claimed in claim 1, characterized in that: In step S5, the minimum observation period ΔT is set min ; When △T α >△T min When , go to step S6; When △T α ≤△T min When the minimum observation period △T min Observe the physical signs and characteristics.

Images