CN118230956A - Acute myocardial infarction prognosis risk monitoring system and method thereof - Google Patents
Acute myocardial infarction prognosis risk monitoring system and method thereof Download PDFInfo
- Publication number
- CN118230956A CN118230956A CN202410438406.1A CN202410438406A CN118230956A CN 118230956 A CN118230956 A CN 118230956A CN 202410438406 A CN202410438406 A CN 202410438406A CN 118230956 A CN118230956 A CN 118230956A
- Authority
- CN
- China
- Prior art keywords
- feature
- medical examination
- period
- sign observation
- adjustment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004393 prognosis Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012544 monitoring process Methods 0.000 title claims abstract description 24
- 206010000891 acute myocardial infarction Diseases 0.000 title claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims abstract description 49
- 238000012502 risk assessment Methods 0.000 claims description 11
- 230000005856 abnormality Effects 0.000 claims description 8
- 230000001537 neural effect Effects 0.000 claims description 7
- 230000009977 dual effect Effects 0.000 claims description 6
- 210000004369 blood Anatomy 0.000 claims description 5
- 239000008280 blood Substances 0.000 claims description 5
- 238000002604 ultrasonography Methods 0.000 claims description 5
- 230000000747 cardiac effect Effects 0.000 claims description 4
- 238000001574 biopsy Methods 0.000 claims description 3
- 230000036772 blood pressure Effects 0.000 claims description 3
- 230000036760 body temperature Effects 0.000 claims description 3
- 238000001839 endoscopy Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 210000000653 nervous system Anatomy 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000004820 blood count Methods 0.000 claims description 2
- 210000000265 leukocyte Anatomy 0.000 claims description 2
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims 1
- 239000008103 glucose Substances 0.000 claims 1
- 150000002632 lipids Chemical class 0.000 claims 1
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000007689 inspection Methods 0.000 abstract 1
- 208000010125 myocardial infarction Diseases 0.000 description 7
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000004075 alteration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000003146 anticoagulant agent Substances 0.000 description 2
- 210000004351 coronary vessel Anatomy 0.000 description 2
- 208000011580 syndromic disease Diseases 0.000 description 2
- BSYNRYMUTXBXSQ-UHFFFAOYSA-N Aspirin Chemical compound CC(=O)OC1=CC=CC=C1C(O)=O BSYNRYMUTXBXSQ-UHFFFAOYSA-N 0.000 description 1
- 239000005552 B01AC04 - Clopidogrel Substances 0.000 description 1
- 206010019280 Heart failures Diseases 0.000 description 1
- HTTJABKRGRZYRN-UHFFFAOYSA-N Heparin Chemical compound OC1C(NC(=O)C)C(O)OC(COS(O)(=O)=O)C1OC1C(OS(O)(=O)=O)C(O)C(OC2C(C(OS(O)(=O)=O)C(OC3C(C(O)C(O)C(O3)C(O)=O)OS(O)(=O)=O)C(CO)O2)NS(O)(=O)=O)C(C(O)=O)O1 HTTJABKRGRZYRN-UHFFFAOYSA-N 0.000 description 1
- 208000007536 Thrombosis Diseases 0.000 description 1
- 102000003978 Tissue Plasminogen Activator Human genes 0.000 description 1
- 108090000373 Tissue Plasminogen Activator Proteins 0.000 description 1
- 102000003990 Urokinase-type plasminogen activator Human genes 0.000 description 1
- 108090000435 Urokinase-type plasminogen activator Proteins 0.000 description 1
- 229960001138 acetylsalicylic acid Drugs 0.000 description 1
- 229940127219 anticoagulant drug Drugs 0.000 description 1
- 229940127218 antiplatelet drug Drugs 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 229960003009 clopidogrel Drugs 0.000 description 1
- GKTWGGQPFAXNFI-HNNXBMFYSA-N clopidogrel Chemical compound C1([C@H](N2CC=3C=CSC=3CC2)C(=O)OC)=CC=CC=C1Cl GKTWGGQPFAXNFI-HNNXBMFYSA-N 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 239000003527 fibrinolytic agent Substances 0.000 description 1
- 210000001035 gastrointestinal tract Anatomy 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229960002897 heparin Drugs 0.000 description 1
- 229920000669 heparin Polymers 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000003055 low molecular weight heparin Substances 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 238000002582 magnetoencephalography Methods 0.000 description 1
- 208000037891 myocardial injury Diseases 0.000 description 1
- 238000010984 neurological examination Methods 0.000 description 1
- 230000002232 neuromuscular Effects 0.000 description 1
- 238000013146 percutaneous coronary intervention Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 210000002345 respiratory system Anatomy 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 230000002537 thrombolytic effect Effects 0.000 description 1
- 210000001635 urinary tract Anatomy 0.000 description 1
- 229960005356 urokinase Drugs 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application provides an acute myocardial infarction prognosis risk monitoring system and a method thereof, wherein the acute myocardial infarction prognosis risk monitoring system comprises a prognosis portrait module, a risk association module and a period adjustment module; the prognosis portrait module can obtain a prognosis portrait, and a medical examination period and a period adjustment period of a medical examination feature are obtained according to the risk evaluation grade of the prognosis portrait; the risk association module records the association degree between the medical examination feature and the associated sign observation feature, and adjusts the association degree between the medical examination feature and the sign observation feature according to the abnormal condition of the sign observation feature in the medical examination period; the period adjustment module adjusts the medical examination period of the medical examination feature according to the abnormal condition of the physical sign observation feature and the association degree of the medical examination feature and the physical sign observation feature, which are obtained in the period adjustment period. The application optimizes the inspection period and improves the accuracy of the prognosis model data.
Description
Technical Field
The application relates to the field of acute myocardial infarction prognosis, in particular to an acute myocardial infarction prognosis risk monitoring system and method.
Background
The acute myocardial infarction prognosis refers to the rehabilitation and survival condition of a patient after acute myocardial infarction, and is influenced by various factors including personal condition, basic health condition, myocardial injury degree, timely treatment degree and the like of the patient. Therefore, timely grasping risk features related to myocardial infarction prognosis has a very important indicating effect on myocardial infarction prognosis prediction accuracy.
The risk features used for establishing the myocardial infarction prognosis risk model generally comprise basic personal features, physical sign observation features, treatment features and medical examination features of a patient, through which the myocardial infarction prognosis risk monitoring model can be established, wherein the basic personal features of the patient can be obtained through investigation and inquiry, the physical sign observation features can be obtained in real time during ward round, and the medical examination features are required to be obtained through medical instruments and analysis of condition data.
The acquisition of each medical examination feature requires the use of specialized medical equipment, even some features can cause damage to the body of a patient during the acquisition process, certain consumption of medical resources can be realized, and the cost is high, so that a method for optimizing and suggesting the acquisition cycle of the medical examination feature is required by the comprehensive condition of the syndrome observation feature and the treatment scheme.
In addition, since clinically, the correlation between the characterization of the physical sign observation feature and the medical examination feature is different for each patient due to different physique, if a unified standard is used, an individual error is often generated in judgment, and therefore, the correlation degree between the physical sign observation feature and the medical examination feature needs to be adjusted according to the actual individual situation.
Disclosure of Invention
In order to solve the problem, the application provides an acute myocardial infarction prognosis risk monitoring system, which comprises a prognosis portrait module, a risk association module and a period adjustment module;
The prognosis portrait module can obtain prognosis portraits according to personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics, and obtain medical examination periods and period adjustment periods of the medical examination characteristics according to risk assessment grades of the prognosis portraits;
the risk association module records the association degree between the medical examination feature and the associated sign observation feature, and adjusts the association degree between the medical examination feature and the sign observation feature according to the abnormal condition of the sign observation feature in the medical examination period;
The period adjustment module adjusts the medical examination period of the medical examination feature according to the abnormal condition of the physical sign observation feature and the association degree of the medical examination feature and the physical sign observation feature, which are obtained in the period adjustment period.
The period adjustment period is included in the medical examination period, the period adjustment period includes a first adjustment period and a second adjustment period, and whether to enter the second adjustment period is judged according to abnormal conditions of physical sign observation features of the first adjustment period.
Judging whether the physical sign observation feature enters an abnormal adjustment list according to the abnormal condition of the physical sign observation feature in the first adjustment period, if so, ending the steps, if not, entering a second adjustment period, and judging whether the physical sign observation feature enters the abnormal adjustment list according to the abnormal condition of the physical sign observation feature in the second adjustment period.
Wherein the medical examination features include endoscopy, biopsy, abnormal neurological examination, and cardiac ultrasound examination.
Wherein the physical sign observation feature categories include blood pressure, blood sugar, blood fat, heart rate, body temperature, white blood cell count, and electrocardiogram.
The application also provides a risk monitoring method of the acute myocardial infarction prognosis risk monitoring system, which comprises the following steps:
S1, obtaining a prognosis portrait according to personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics, and obtaining a risk assessment grade EI of the prognosis portrait through a network neural model;
S2, setting a prognosis portrait to comprise DM medical examination features EA, EA= [ EA 1,EA2,EA3,…,EADM ] and obtaining a medical examination period of the medical examination feature EA DI under the EI risk assessment grade as delta TEI, wherein the DI-th medical examination feature EA DI;
wherein the initial medical examination period Δtei comprises a period adjustment period Δtdi, which period adjustment period Δtdi further comprises a first adjustment period Δtdi1 and a second adjustment period Δtdi2.
S3, setting a medical examination feature EA DI to be associated with a DK type sign observation feature EC, wherein the associated DZ type sign observation feature is EC DZ;
In the sign observation feature data obtained in the first adjustment period DeltaTDI 1 in the period adjustment period DeltaTDI, the common DR sign observation feature category is abnormal, a sign observation feature category ECA with abnormality is obtained, ECA= [ ECA 1,ECA2,ECA3,…,ECADR ] is obtained, wherein DB-th sign observation feature ECA DB with abnormality is set to include DM feature values, DF feature values are abnormal, an abnormal feature value ECB= [ ECB 1,ECB2,ECB3,…,ECBDF ] of DB-th sign observation feature ECA DB is obtained, DG abnormal feature value is ECB DG, and a normal threshold of DB-th sign observation feature ECA DB is set to be U DB;
Obtaining an abnormal distribution phi=df/DM of the DB-th sign-observing feature ECA DB;
Obtaining an abnormal difference DeltaU BG=|ECBDG-UDB I with the DG abnormal characteristic value of ECB DG;
Obtaining a class anomaly first difference value of the DB-th class anomaly sign observation feature ECA DB of the first adjustment period ；
Setting a class anomaly threshold value of the DB-th class sign observation feature ECA DB as delta UDB 0;
When delta UDA DB≥△UDB0 is adopted, the class DB sign observation feature ECA DB and class anomaly difference value thereof Entering an abnormality adjustment list TL of the medical examination feature EA DI;
when DeltaUD DB＜△UDD0, go to step S4;
S4, acquiring a sign observation feature in a second adjustment period DeltaTDI 2 after the first adjustment period DeltaTDI 1, and acquiring an abnormality-like second difference value of the DB-like sign feature ECA DB in the second adjustment period in the same manner as the abnormality-like first difference value of the DB-like sign observation feature ECA DB in the first adjustment period ，
When (when)When in use, class DB sign feature ECA DB and class anomaly difference value/>Entering an adjustment list TL of medical examination features EA DI;
S5, setting an adjustment list TL after the adjustment period is finished, wherein the adjustment list TL comprises DH type sign observation features, TL= [ ECC 1,ECC2,ECC 3,…,ECC DH ], the type anomaly difference value of the DA type sign observation feature ECC DA is delta UDC DA, and the association coefficient of the DA type sign observation feature ECC DA and the medical examination feature EA DI is lambda DA;
obtaining adjustment coefficients for a medical examination cycle ，
Obtain adjusted medical examination period Δtei' =ftl Δtei.
Step S6 is further included, wherein the class anomaly difference value of the DA class sign observation feature ECC DA is delta UDC DA, and the association coefficient of the DA class sign observation feature ECC DA and the medical examination feature EA DI is lambda DA; setting an association anomaly threshold DeltaUDC 0, and an association coefficient threshold lambda 0;
When DeltaUDC DA≥△UDC0 is performed simultaneously with lambda DA≤λ0, the correlation coefficient lambda DA is adjusted to be Where e is a natural constant.
In step S1, the method for obtaining the risk assessment level EI of the prognostic portrait by using the network neural model includes:
sample features with personal features, medical examination features, vital signs observations and medical features as inputs, the SVM algorithm is as follows:
Setting an objective function:
，
Wherein W and b are planar coefficients, Classification sign representing sample,/>=[-1,1]，/>Then it is a training sample; w is a planar coefficient, when extended to an n-dimensional space, an n-dimensional vector such as: w= [ W 1,W2,...,Wn ],/>Is the transpose of W, and W is the norm of the hyperplane;
Since the SVM objective function assumes that the data is linearly separable, but that noise data actually exists, a relaxation variable and a penalty parameter are added, and the model tolerance is increased through the relaxation variable ；
Wherein,For punishment coefficient,/>Is a relaxation variable, expressed by the distance from the misclassification point to the plane of the corresponding class support vector, correctly classifying the sample point/>The penalty term is determined by all outliers;
The optimization problem is converted into a dual problem by using a Lagrangian multiplier method and KKT conditions, and is solved by using an SMO method. Wherein the method comprises the steps of Is a lagrange multiplier. The form of the dual problem obtained by high-dimensional mapping of the model is:
；
The kernel function chosen here is a gaussian function: ，
And analyzing the characteristics by using the SVM classifier model to obtain an output result for risk assessment grade judgment.
The beneficial effects achieved by the application are as follows:
The application can adjust the cycle of acquiring the medical examination characteristics by requiring the correlation condition of the syndrome observation characteristics and the medical examination characteristics, and carry out advice reminding on medical care and patients, thereby providing reference for disease examination, optimizing the working efficiency and avoiding possible examination shortage and excessive examination. Meanwhile, the degree of association between the clinical sign observation sign and the medical examination feature can be updated and modified through comprehensive calculation of the data, so that individual errors are reduced, and the model evaluation result is more optimized and accurate.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings to those skilled in the art.
Fig. 1 is a flow chart of a risk monitoring method of the acute myocardial infarction prognosis risk monitoring system of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Specifically, the application provides an acute myocardial infarction prognosis risk monitoring system which comprises a prognosis portrait module, a risk association module and a period adjustment module.
The prognosis portrait module can obtain prognosis portraits according to personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics, establish a myocardial infarction prognosis evaluation model according to the prognosis portraits, evaluate myocardial infarction prognosis risk levels and obtain medical examination periods and period adjustment periods of the medical examination characteristics corresponding to the risk levels.
Wherein the personal characteristics of the patient are inherent physical conditions of the patient including age, sex, weight, past medical history, etc.; the physical sign observation features are physical signs which can be obtained in a rapid and simple way, and comprise heart rate, body temperature, blood pressure, blood sugar and the like; medical examination characteristics are those that need to be acquired by medical means using certain medical resources and techniques, including imaging examination characteristics (X-rays, CT scans, MRI, ultrasound, etc.) for observing the structure and function of internal organs, endoscopy characteristics for observing and examining conditions inside the lumen (digestive tract, respiratory tract, urinary tract, etc.), biopsy characteristics for microscopic observation and analysis by taking tissue or cell samples, cardiac ultrasound examination characteristics for assessing the function of the nervous system and abnormal nervous system examination characteristics (electroencephalograms, magnetoencephalography, neuromuscular grams, etc.), and for observing and assessing the structure and function of the heart by ultrasound techniques. The treatment characteristics include thrombolytic treatment (thrombolytic drug such as tissue type plasminogen activator or urokinase, etc. to dissolve thrombus in coronary artery, restore blood flow), cardiac catheterization treatment (percutaneous coronary intervention or coronary bypass grafting to restore patency of coronary artery), drug treatment (use of antiplatelet drug such as aspirin, clopidogrel, anticoagulant drug such as heparin, low molecular heparin, etc.);
the risk association module records the association degree between the medical examination feature and the associated sign observation feature, and adjusts the association degree between the medical examination feature and the sign observation feature according to the abnormal condition of the sign observation feature in the medical examination period;
The period adjustment module adjusts the medical examination period of the medical examination feature according to the abnormal condition of the physical sign observation feature and the association degree of the medical examination feature and the physical sign observation feature, which are obtained in the period adjustment period.
Specifically, a network neural model for myocardial infarction prognosis risk assessment is established according to personal features, medical examination features, physical sign observation features and medical features in a prognosis portrait, and specifically, the network neural model can be calculated through an SVM algorithm of a classification model, wherein the personal features, the medical examination features, the physical sign observation features and the medical features are taken as input sample features, and the SVM algorithm is as follows:
Setting an objective function: ，
Wherein W and b are planar coefficients, Classification sign representing sample,/>=[-1,1]，/>Then it is a training sample; w is a planar coefficient, when extended to an n-dimensional space, an n-dimensional vector such as: w= [ W 1,W2,...,Wn ],/>Is the transpose of W, and W is the norm of the hyperplane;
Since the SVM objective function assumes that the data is linearly separable, but that noise data actually exists, a relaxation variable and a penalty parameter are added, and the model tolerance is increased through the relaxation variable ；
Wherein,For punishment coefficient,/>Is a relaxation variable, expressed by the distance from the misclassification point to the plane of the corresponding class support vector, correctly classifying the sample point/>The penalty term is determined by all outliers;
The optimization problem is converted into a dual problem by using a Lagrangian multiplier method and KKT conditions, and is solved by using an SMO method. Wherein the method comprises the steps of Is a lagrange multiplier. The form of the dual problem obtained by high-dimensional mapping of the model is:
；
The kernel function chosen here is a gaussian function: 。
Analyzing the received message characteristics by using the SVM classifier model to obtain an output result, judging the risk evaluation level, for example, outputting a high risk level when 1, outputting a medium risk level when 0, outputting a low risk level when-1, obtaining an evaluated risk level, and obtaining an initial medical examination period obtained by medical examination characteristics corresponding to the risk level according to the risk level.
For example, the prognostic risk level estimated from the network neural model established by the personal feature, the medical examination feature, the physical observation feature, and the medical feature is a high risk level, and the initial medical examination period is 20 days under the condition of the low risk level of the medical examination feature "heart failure"; whereas in the case of high risk levels, the initial medical examination period is 3 days.
The period adjustment period is included in the medical examination period, the period adjustment period includes a first adjustment period and a second adjustment period, and whether to enter the second adjustment period is judged according to abnormal conditions of physical sign observation features of the first adjustment period. Judging whether the physical sign observation feature enters an abnormal adjustment list according to the abnormal condition of the physical sign observation feature in the first adjustment period, if so, ending the steps, if not, entering a second adjustment period, and judging whether the physical sign observation feature enters the abnormal adjustment list according to the abnormal condition of the physical sign observation feature in the second adjustment period.
In this embodiment, the initial medical examination period obtained is Δtei, wherein the initial medical examination period Δtei includes an initial period adjustment period Δtdi (Δtei > Δtdi) further including a first adjustment period Δtdi1 and a second adjustment period Δtdi2.
Setting a prognosis portrait to comprise DM medical examination features EA, EA= [ EA 1,EA2,EA3,…,EADM ] and DK type sign observation features EC, EC= [ EC, EC 2,EC3,…,ECDK ] associated with DI-th medical examination feature EA DI, wherein the associated DZ type sign observation feature is EC DZ, and setting the association coefficient of DI-th medical examination feature EA DI and DZ type sign observation feature EC DZ as lambda DZ;
In the sign observation feature data obtained in the first adjustment period DeltaTDI 1 in the period adjustment period DeltaTDI, the common DR sign observation feature class is abnormal, and the abnormal sign observation feature class ECA is obtained, wherein ECA= [ ECA 1,ECA2,ECA3,…,ECADR ];
Setting the abnormal DB type sign observation feature ECA DB to include DM feature values, wherein DF abnormal occurs to obtain an abnormal feature value ECB= [ ECB 1,ECB2,ECB3,…,ECBDF ] of the DB type sign observation feature ECA DB, wherein the DG abnormal feature value is ECB DG, and setting the normal threshold of the DB type sign observation feature ECA DB as U DB;
Obtaining an abnormal distribution phi=df/DM of the DB-th sign-observing feature ECA DB;
Obtaining an abnormal difference DeltaU BG=|ECBDG-UDB I with the DG abnormal characteristic value of ECB DG;
Obtaining a class anomaly first difference value of the DB-th class anomaly sign observation feature ECA DB of the first adjustment period ；
Setting a class anomaly threshold value of the DB-th class sign observation feature ECA DB as delta UDB 0;
When delta UDA DB≥△UDB0 is adopted, the class DB sign observation feature ECA DB and class anomaly difference value thereof Entering an abnormality adjustment list TL of the medical examination feature EA DI;
When Δud DB＜△UDD0, a second adjustment period Δtdi2 after the first adjustment period Δtdi1 acquires the sign-observing feature, and an abnormality-like second difference value of the DB-like sign-observing feature ECA DB in the second adjustment period is obtained in the same manner as the abnormality-like first difference value of the DB-like sign-observing feature ECA DB in the first adjustment period ，
When (when)When in use, class DB sign feature ECA DB and class anomaly difference value/>Entering an adjustment list TL of medical examination features EA DI;
After the adjustment period is finished, setting an adjustment list TL which comprises DH type sign observation features, wherein TL= [ ECC 1,ECC2,ECC 3,…,ECC DH ] is included, the type abnormal difference value of DA type sign observation feature ECC DA is delta UDC DA, and the association coefficient of DA type sign observation feature ECC DA and medical examination feature EA DI is lambda DA;
obtaining adjustment coefficients for a medical examination cycle ，
Obtain adjusted medical examination period Δtei' =ftl Δtei.
In addition, in some clinical situations, the correlation of the observed features of the sign in the adjustment list TL to the medical examination features is low, but in actual monitoring, it often occurs simultaneously with other observed features of the sign with higher correlation, and thus, it is also considered to correspondingly adjust the correlation thereof to be improved.
Specifically, the class anomaly difference value of the DA-th class sign observation feature ECC DA is Δudc DA, and the association coefficient of the DA-th class sign observation feature ECC DA and the medical examination feature EA DI is λ DA; setting an association anomaly threshold DeltaUDC 0, and an association coefficient threshold lambda 0;
When DeltaUDC DA≥△UDC0 is performed simultaneously with lambda DA≤λ0, the correlation coefficient lambda DA is adjusted to be Where e is a natural constant.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. The acute myocardial infarction prognosis risk monitoring system is characterized by comprising a prognosis portrait module, a risk association module and a period adjustment module;
The prognosis portrait module can obtain prognosis portraits according to personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics, and obtain medical examination periods and period adjustment periods of the medical examination characteristics according to risk assessment grades of the prognosis portraits;
the risk association module records the association degree between the medical examination feature and the associated sign observation feature, and adjusts the association degree between the medical examination feature and the sign observation feature according to the abnormal condition of the sign observation feature in the medical examination period;
The period adjustment module adjusts the medical examination period of the medical examination feature according to the abnormal condition of the physical sign observation feature and the association degree of the medical examination feature and the physical sign observation feature, which are obtained in the period adjustment period.
2. The acute myocardial infarction prognosis risk monitoring system as set forth in claim 1, wherein the cycle adjustment period is included in the medical examination cycle, the cycle adjustment period includes a first adjustment period and a second adjustment period, and whether to enter the second adjustment period is determined based on an abnormality of a sign observation feature of the first adjustment period.
3. The acute myocardial infarction prognosis risk monitoring system as set forth in claim 2, wherein,
Judging whether the physical sign observation feature enters an abnormal adjustment list according to the abnormal condition of the physical sign observation feature in the first adjustment period, if so, ending the steps, if not, entering a second adjustment period, and judging whether the physical sign observation feature enters the abnormal adjustment list according to the abnormal condition of the physical sign observation feature in the second adjustment period.
4. The acute myocardial infarction prognosis risk monitoring system as set forth in claim 1, wherein the medical examination features include endoscopy, biopsy, abnormal nervous system examination, and cardiac ultrasound examination.
5. The acute myocardial infarction prognosis risk monitoring system as set forth in claim 1, wherein the physical observation feature categories include blood pressure, blood glucose, blood lipid, heart rate, body temperature, white blood cell count, and electrocardiogram.
6. The risk monitoring method of an acute myocardial infarction prognosis risk monitoring system as set forth in claims 1 to 5, comprising the steps of:
S1, obtaining a prognosis portrait according to personal characteristics, medical examination characteristics, physical sign observation characteristics and medical characteristics, and obtaining a risk assessment grade EI of the prognosis portrait through a network neural model;
S2, setting a prognosis portrait to comprise DM medical examination features EA, EA= [ EA 1,EA2,EA3,…,EADM ] and obtaining a medical examination period of the medical examination feature EA DI under the EI risk assessment grade as delta TEI, wherein the DI-th medical examination feature EA DI;
Wherein the initial medical examination period Δtei comprises a period adjustment period Δtdi, which period adjustment period Δtdi further comprises a first adjustment period Δtdi1 and a second adjustment period Δtdi2;
S3, setting a medical examination feature EA DI to be associated with a DK type sign observation feature EC, wherein the associated DZ type sign observation feature is EC DZ;
In the sign observation feature data obtained in the first adjustment period DeltaTDI 1 in the period adjustment period DeltaTDI, the common DR sign observation feature category is abnormal, a sign observation feature category ECA with abnormality is obtained, ECA= [ ECA 1,ECA2,ECA3,…,ECADR ] is obtained, wherein DB-th sign observation feature ECA DB with abnormality is set to include DM feature values, DF feature values are abnormal, an abnormal feature value ECB= [ ECB 1,ECB2,ECB3,…,ECBDF ] of DB-th sign observation feature ECA DB is obtained, DG abnormal feature value is ECB DG, and a normal threshold of DB-th sign observation feature ECA DB is set to be U DB;
Obtaining an abnormal distribution phi=df/DM of the DB-th sign-observing feature ECA DB;
Obtaining an abnormal difference DeltaU BG=|ECBDG-UDB I with the DG abnormal characteristic value of ECB DG;
Obtaining a class anomaly first difference value of the DB-th class anomaly sign observation feature ECA DB of the first adjustment period ；
Setting a class anomaly threshold value of the DB-th class sign observation feature ECA DB as delta UDB 0;
When delta UDA DB≥△UDB0 is adopted, the class DB sign observation feature ECA DB and class anomaly difference value thereof Entering an abnormality adjustment list TL of the medical examination feature EA DI;
when DeltaUD DB＜△UDD0, go to step S4;
S4, acquiring a sign observation feature in a second adjustment period DeltaTDI 2 after the first adjustment period DeltaTDI 1, and acquiring an abnormality-like second difference value of the DB-like sign feature ECA DB in the second adjustment period in the same manner as the abnormality-like first difference value of the DB-like sign observation feature ECA DB in the first adjustment period ，
When (when)When in use, class DB sign feature ECA DB and class anomaly difference value/>Entering an adjustment list TL of medical examination features EA DI;
S5, setting an adjustment list TL after the adjustment period is finished, wherein the adjustment list TL comprises DH type sign observation features, TL= [ ECC 1,ECC2,ECC 3,…,ECC DH ], the type anomaly difference value of the DA type sign observation feature ECC DA is delta UDC DA, and the association coefficient of the DA type sign observation feature ECC DA and the medical examination feature EA DI is lambda DA;
obtaining adjustment coefficients for a medical examination cycle ，
Obtain adjusted medical examination period Δtei' =ftl Δtei.
7. The risk monitoring method of acute myocardial infarction prognosis risk monitoring system as set forth in claim 6, further comprising step S6, obtaining a class anomaly difference value of DA-th class sign observation feature ECC DA as Δudc DA, and a correlation coefficient of DA-th class sign observation feature ECC DA and medical examination feature EA DI as λ DA; setting an association anomaly threshold DeltaUDC 0, and an association coefficient threshold lambda 0;
When DeltaUDC DA≥△UDC0 is performed simultaneously with lambda DA≤λ0, the correlation coefficient lambda DA is adjusted to be Where e is a natural constant.
8. The method for risk monitoring of acute myocardial infarction prognosis risk monitoring system as set forth in claim 6, wherein in step S1, the method for obtaining the risk assessment level EI of the prognosis figure by using the network neural model is as follows:
sample features with personal features, medical examination features, vital signs observations and medical features as inputs, the SVM algorithm is as follows:
Setting an objective function: ，
Wherein W and b are planar coefficients, Classification sign representing sample,/>=[-1,1]，/>Then it is a training sample; w is a planar coefficient, when extended to an n-dimensional space, an n-dimensional vector such as: w= [ W 1,W2,...,Wn ],/>Is the transpose of W, and W is the norm of the hyperplane;
Since the SVM objective function assumes that the data is linearly separable, but that noise data actually exists, a relaxation variable and a penalty parameter are added, and the model tolerance is increased through the relaxation variable ；
Wherein,For punishment coefficient,/>Is a relaxation variable, expressed by the distance from the misclassification point to the plane of the corresponding class support vector, correctly classifying the sample point/>The penalty term is determined by all outliers;
The optimization problem is converted into a dual problem by using a Lagrangian multiplier method and KKT conditions, and is solved by using an SMO method. Wherein the method comprises the steps of Is a lagrange multiplier. The form of the dual problem obtained by high-dimensional mapping of the model is:
；
The kernel function chosen here is a gaussian function: ，
And analyzing the characteristics by using the SVM classifier model to obtain an output result for risk assessment grade judgment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410438406.1A CN118230956A (en) | 2024-04-12 | 2024-04-12 | Acute myocardial infarction prognosis risk monitoring system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410438406.1A CN118230956A (en) | 2024-04-12 | 2024-04-12 | Acute myocardial infarction prognosis risk monitoring system and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118230956A true CN118230956A (en) | 2024-06-21 |
Family
ID=91506482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410438406.1A Pending CN118230956A (en) | 2024-04-12 | 2024-04-12 | Acute myocardial infarction prognosis risk monitoring system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118230956A (en) |
-
2024
- 2024-04-12 CN CN202410438406.1A patent/CN118230956A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10722179B2 (en) | Residual-based monitoring of human health | |
| WO2022099668A1 (en) | Method and system for precise health management and risk early warning based on association between familial genetic disease and sign data | |
| JP2019514635A (en) | System and method for monitoring vascular health | |
| CN113509186B (en) | ECG classification system and method based on deep convolutional neural network | |
| Jalali et al. | Prediction of periventricular leukomalacia in neonates after cardiac surgery using machine learning algorithms | |
| Jalali et al. | Advanced analytics for outcome prediction in intensive care units | |
| CN109938723A (en) | A kind of method of discrimination and equipment of human body diseases risk | |
| Schmidt et al. | Coronary artery disease risk reclassification by a new acoustic-based score | |
| Rath et al. | An exhaustive review of machine and deep learning based diagnosis of heart diseases | |
| Zahid et al. | Mortality prediction with self normalizing neural networks in intensive care unit patients | |
| Gandhi et al. | Biosensor‐Assisted Method for Abdominal Syndrome Classification Using Machine Learning Algorithm | |
| CN113744865A (en) | Regression analysis-based pressure damage risk prediction model correction method | |
| Ma et al. | PPG-based continuous BP waveform estimation using polarized attention-guided conditional adversarial learning model | |
| CN115517682B (en) | Cognitive dysfunction prediction system based on gastrointestinal electric signals and construction method | |
| CN118230956A (en) | Acute myocardial infarction prognosis risk monitoring system and method thereof | |
| Hassanuzzaman et al. | Recognition of Pediatric Congenital Heart Diseases by Using Phonocardiogram Signals and Transformer-Based Neural Networks | |
| CN113593703A (en) | Device and method for constructing pressure damage risk prediction model | |
| Bahar et al. | Model Structure of Fetal Health Status Prediction | |
| Nour et al. | Machine Learning and Electrocardiography Signal‐Based Minimum Calculation Time Detection for Blood Pressure Detection | |
| Duggento et al. | Classification of real-world pathological phonocardiograms through multi-instance learning | |
| CN116189899B (en) | Emergency critical illness auxiliary evaluation system based on machine learning | |
| Khalaf et al. | Predicting Acute Respiratory Failure Using Fuzzy Classifier | |
| CN115886818B (en) | Depression anxiety disorder prediction system based on gastrointestinal electric signal and construction method thereof | |
| Faisal et al. | Analysis of significant factors for dengue infection prognosis using the self organizing map | |
| Ramkumar | Identification and Classification of Breast Cancer using Multilayer Perceptron Techniques for Histopathological Image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |