CN115862843A - Auxiliary identification system and equipment for myocardial muscle calcium egg rising type and cardiovascular diseases - Google Patents
Auxiliary identification system and equipment for myocardial muscle calcium egg rising type and cardiovascular diseases Download PDFInfo
- Publication number
- CN115862843A CN115862843A CN202211600107.0A CN202211600107A CN115862843A CN 115862843 A CN115862843 A CN 115862843A CN 202211600107 A CN202211600107 A CN 202211600107A CN 115862843 A CN115862843 A CN 115862843A
- Authority
- CN
- China
- Prior art keywords
- unit
- muscle calcium
- calcium egg
- myocardial muscle
- characteristic
- 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.)
- Granted
Links
- 208000024172 Cardiovascular disease Diseases 0.000 title claims abstract description 107
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 title claims abstract description 96
- 229910052791 calcium Inorganic materials 0.000 title claims abstract description 96
- 239000011575 calcium Substances 0.000 title claims abstract description 96
- 230000002107 myocardial effect Effects 0.000 title claims abstract description 88
- 210000003205 muscle Anatomy 0.000 title claims abstract description 80
- 230000000630 rising effect Effects 0.000 title claims abstract description 52
- 230000000302 ischemic effect Effects 0.000 claims abstract description 80
- 238000000605 extraction Methods 0.000 claims abstract description 65
- 238000012544 monitoring process Methods 0.000 claims abstract description 15
- 238000007637 random forest analysis Methods 0.000 claims abstract description 13
- 230000036772 blood pressure Effects 0.000 claims abstract description 9
- 101100537532 Rattus norvegicus Tnni3 gene Proteins 0.000 claims description 62
- 102100026893 Troponin T, cardiac muscle Human genes 0.000 claims description 57
- 101710165323 Troponin T, cardiac muscle Proteins 0.000 claims description 57
- 238000003062 neural network model Methods 0.000 claims description 34
- 201000010099 disease Diseases 0.000 claims description 19
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 19
- 210000004165 myocardium Anatomy 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000001575 pathological effect Effects 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 238000000034 method Methods 0.000 abstract description 19
- 238000005516 engineering process Methods 0.000 abstract description 3
- 235000013601 eggs Nutrition 0.000 description 64
- 238000003066 decision tree Methods 0.000 description 17
- 230000000694 effects Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 10
- 238000012549 training Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 6
- 206010000891 acute myocardial infarction Diseases 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 206010019280 Heart failures Diseases 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 208000028867 ischemia Diseases 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 208000004476 Acute Coronary Syndrome Diseases 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000000747 cardiac effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000037891 myocardial injury Diseases 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 206010002388 Angina unstable Diseases 0.000 description 1
- 208000002251 Dissecting Aneurysm Diseases 0.000 description 1
- 208000032843 Hemorrhage Diseases 0.000 description 1
- 208000009525 Myocarditis Diseases 0.000 description 1
- 206010028851 Necrosis Diseases 0.000 description 1
- 208000007718 Stable Angina Diseases 0.000 description 1
- 208000009609 Takotsubo Cardiomyopathy Diseases 0.000 description 1
- 102000004903 Troponin Human genes 0.000 description 1
- 108090001027 Troponin Proteins 0.000 description 1
- 208000007814 Unstable Angina Diseases 0.000 description 1
- 230000010100 anticoagulation Effects 0.000 description 1
- 206010002895 aortic dissection Diseases 0.000 description 1
- 206010003119 arrhythmia Diseases 0.000 description 1
- 230000006793 arrhythmia Effects 0.000 description 1
- 208000034158 bleeding Diseases 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 201000004332 intermediate coronary syndrome Diseases 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000008065 myocardial cell damage Effects 0.000 description 1
- 208000031225 myocardial ischemia Diseases 0.000 description 1
- 230000017074 necrotic cell death Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
An auxiliary identification system and equipment for myocardial muscle calcium egg rising type and cardiovascular diseases belong to the technical field of myocardial muscle calcium egg identification technology and cardiovascular disease identification technology. The method aims to solve the problems that the existing cTn index judgment depending on artificial ischemic/non-ischemic cardiovascular diseases has low identification efficiency and can increase misdiagnosis or delay treatment risks. The myocardial muscle calcium egg rising type auxiliary identification system comprises a state information acquisition unit for acquiring and extracting characteristics based on blood pressure and heartbeat data, a myocardial muscle calcium egg monitoring unit for recording and monitoring cTn indexes at different time periods, a myocardial muscle calcium egg characteristic extraction unit for extracting characteristics according to the cTn indexes, an electrocardiosignal characteristic extraction unit for analyzing electrocardiosignals and acquiring electrocardiosignal characteristics, and an auxiliary identification unit for identifying the myocardial muscle calcium egg rising type of the myocardial muscle calcium egg rising type by using a random forest classifier based on the basic characteristics.
Description
Technical Field
The invention belongs to the technical field of myocardial muscle calcium egg identification and cardiovascular disease identification.
Background
Cardiac troponin cTn is an important component of medical evaluation of cardiovascular critical diseases such as Acute Coronary Syndrome (ACS). Although cTn is a marker of myocardial injury, but is not unique to Acute Myocardial Infarction (AMI) -associated coronary ischemia, studies have shown that up to 45% of patients with cTn elevation have non-ischemic cardiovascular disease. Misdiagnosis can increase the risk of bleeding due to excessive anticoagulation treatment and the probability of cardiac catheter intervention and stenting, and delay the treatment of the disease.
At present, the judgment of the myocardial calvin level increase type basically depends on the clinical experience of a doctor, namely, the doctor judges whether the myocardial calvin level increase is possibly caused by ischemic cardiovascular diseases or non-ischemic cardiovascular diseases based on basic index detection data, then further arranges detection aiming at the possibility of the ischemic cardiovascular diseases or the non-ischemic cardiovascular diseases according to the basic judgment, or further arranges detection aiming at the possibility of specific diseases corresponding to the ischemic cardiovascular diseases or the non-ischemic cardiovascular diseases, and finally realizes the confirmation of the diseases and determines a corresponding treatment scheme.
Therefore, the identification of the type of the myocardial muscle calcium egg elevation depends too much on the clinical experience of doctors, which requires the doctors to have very rich clinical experience, and for doctors with less clinical experience, especially for practicing doctors or doctors with less time, the difficulty of clinical identification is increased, thereby increasing the risk of misdiagnosis or delayed treatment. Moreover, the doctor needs to know the electrocardiogram and the cTn indexes and needs to know and analyze more examination indexes by virtue of clinical experience to judge whether the cTn is increased due to the non-ischemic cardiovascular disease or not, so that the judgment time is prolonged, the working time of the doctor is increased in a phase-changing manner on the premise that the number of patients to be diagnosed is determined, and the risk of delaying treatment is increased for each individual patient.
Disclosure of Invention
The invention aims to solve the problems that the identification efficiency is low in the conventional cTn index judgment depending on artificial ischemic/non-ischemic cardiovascular diseases and the misdiagnosis or treatment delay risk is possibly increased.
An auxiliary identification system for the increase type of a cardiac muscle calcium egg comprises a state information acquisition unit, a cardiac muscle calcium egg monitoring unit, a cardiac muscle calcium egg characteristic extraction unit, an electrocardiosignal characteristic extraction unit and an auxiliary identification unit for the increase type of the cardiac muscle calcium egg;
a status information acquisition unit: the system is used for acquiring the state information of a patient, and comprises blood pressure p and heartbeat data n, wherein the unit of the blood pressure p is mmHg, and the unit of the heartbeat data n is times/minutes; taking p/120 as a first state characteristic and taking p/n as a second state characteristic;
myocardial muscle calcium egg monitoring unit: the system is used for recording and monitoring the indexes of cTnI and cTnT in different time periods;
a myocardial muscle calcium egg feature extraction unit: taking the current cTnI and cTnT indexes as a first cTnI characteristic and a first cTnT characteristic; the current cTnI/cTnI 24-48 As a second cTnI characteristic, cTnI 24-48 The cTnI corresponding to 24-48 hours after onset, if not 24-48 Data, or the time for obtaining the cTnI currently does not exceed 24-48 hours after the onset of disease, setting the second cTnI characteristic as 1; similarly, the current cTnT/cTnT 24-48 As a second cTnI characteristic, cTnT 24-48 The cTnT corresponding to 24-48 hours after onset, if not 24-48 Data, or the time for obtaining the cTnT currently does not exceed 24-48 hours after the onset of disease, setting the second cTnT characteristic as 1;
electrocardiosignal feature extraction unit: the electrocardiosignal analyzing device is used for analyzing the electrocardiosignal and acquiring the electrocardiosignal characteristics;
an auxiliary identification unit for the myocardial muscle calcium egg rising type: and recording the characteristics extracted by the state information acquisition unit, the myocardial muscle calcium egg characteristic extraction unit and the electrocardiosignal characteristic extraction unit as basic characteristics and taking the basic characteristics as input, calling a random forest classifier to judge the myocardial muscle calcium egg rising type, wherein the random forest classifier is a binary classifier, and the classified myocardial muscle calcium egg rising type comprises cTn rising caused by ischemic cardiovascular diseases and cTn rising caused by non-ischemic cardiovascular diseases.
Furthermore, the electrocardiosignal feature extraction unit comprises an electrocardiosignal preprocessing subunit, a QRS wave band feature extraction subunit, an ST segment feature extraction subunit and a T wave feature extraction subunit; wherein, the first and the second end of the pipe are connected with each other,
an electrocardiosignal preprocessing subunit: analyzing the electrocardiosignal to obtain the position of QRS wave band, ST segment and T wave of the electrocardiosignal, and extracting corresponding signals;
a QRS wave band feature extraction subunit: according to the QRS wave band signal, judging the QRS wave band width, and recording as a first electrocardiogram characteristic; meanwhile, judging whether the Q wave has pathological Q wave, and recording as a second electrocardio characteristic;
an ST-segment feature extraction subunit: judging whether the ST segment is raised or lowered according to the ST segment signal, and recording as a third electrocardiogram characteristic;
t wave feature extraction subunit: and judging whether the T wave is inverted and vertical according to the T wave signal, and recording as a fourth electrocardiogram characteristic.
Further, the myocardial muscle calcium egg monitoring unit is further used for comparing the cTnI index and the cTnT index of each time period with the cTnI threshold value and the cTnT threshold value respectively, and when the cTnI > the cTnI threshold value and/or the cTnT > the cTnT threshold value, the myocardial muscle calcium egg is considered to be in an abnormal condition or an alarm condition when being increased.
A computer storage medium for assisted identification of type of cardiac muscle calcium egg elevation, the storage medium having stored therein at least one instruction that is loaded and executed by a processor to implement an assisted identification system of type of cardiac muscle calcium egg elevation.
An auxiliary identification device for the type of the increase of the myocardial calvital egg, which comprises a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to realize the auxiliary identification system for the type of the increase of the myocardial calvital egg.
An assisted identification system for cardiovascular disease, comprising: the device comprises an auxiliary identification module for myocardial muscle calcium egg rising type, an image data acquisition and characteristic module and a cardiovascular disease identification module;
the myocardial muscle calcium egg rising type auxiliary identification module is used for identifying cTn rising caused by ischemic cardiovascular diseases and cTn rising caused by non-ischemic cardiovascular diseases by utilizing a myocardial muscle calcium egg rising type auxiliary identification system, and simultaneously recording the characteristics extracted by a state information acquisition unit, a myocardial muscle calcium egg characteristic extraction unit and an electrocardiosignal characteristic extraction unit in the myocardial muscle calcium egg rising type auxiliary identification system as basic characteristics;
the image data acquisition and feature module comprises an image data acquisition unit and an image feature extraction unit; wherein the content of the first and second substances,
an image data acquisition unit: acquiring corresponding image data according to the selection of a doctor or the type of the preset image data;
an image feature extraction unit: taking the image acquired by the image data acquisition unit as input, and extracting a characteristic diagram through a characteristic extraction network;
the cardiovascular disease identification module comprises a characteristic adjusting unit, a neural network selecting unit, an ischemic cardiovascular disease identification unit and a non-ischemic cardiovascular disease identification unit; wherein the content of the first and second substances,
a feature adjusting unit: converting the image data acquisition and feature map extracted by the feature module into one-dimensional features with fixed length;
a neural network selection unit: according to the judgment result of the auxiliary judgment unit for the myocardial muscle calcium egg rising type, selecting and calling an ischemic cardiovascular disease judgment unit or a non-ischemic cardiovascular disease judgment unit;
ischemic cardiovascular disease identification unit: taking the one-dimensional features and all basic feature vectors which are converted into fixed lengths as input, and calling a neural network model for judging ischemic cardiovascular diseases to judge ischemic cardiovascular diseases;
non-ischemic cardiovascular disease identification unit: and taking the one-dimensional features and all basic feature vectors which are converted into fixed lengths as input, and calling a neural network model for identifying the non-ischemic cardiovascular diseases to identify the non-ischemic cardiovascular diseases.
Further, the neural network models in the ischemic cardiovascular disease identification unit and the non-ischemic cardiovascular disease identification unit are multilayer perceptrons.
Furthermore, the multilayer perceptron consists of an input layer, three hidden layers and an output layer;
the first layer is an input layer, and the input layer splices the one-dimensional features converted into fixed lengths and all basic features;
the three hidden layers are used for learning the relation between the features;
the last layer is an output layer which outputs the judgment result of the non-ischemic cardiovascular disease.
Further, the feature extraction network in the image feature extraction unit adopts ResNet50.
Furthermore, an auxiliary identification module for myocardial muscle calcium egg rising type, an image data acquisition module and a cardiovascular disease identification module are deployed on different devices or computers, and all the modules communicate through interfaces to realize data transmission and acquisition;
alternatively, the first and second electrodes may be,
two or three of the myocardial muscle calcium egg rising type auxiliary identification module, the image data acquisition module and the cardiovascular disease identification module are also deployed on the same device or computer, and data among the modules are directly stored and called through a database or transmitted and acquired through a data interface.
Has the advantages that:
1. according to the method, the characteristics extracted by the state information acquisition unit, the myocardial muscle calcium egg characteristic extraction unit and the electrocardiosignal characteristic extraction unit are used as basic characteristics to judge the rising type of the myocardial muscle calcium egg through research, so that the judgment accuracy can be greatly improved, and more accurate reference is provided for doctors. Therefore, the difficulty degree of clinical judgment is reduced, the risk of misdiagnosis or delayed treatment is reduced, and the advantages of the invention are more obvious especially for doctors with less clinical experience. Meanwhile, compared with manual judgment, the method has the advantages that the judgment is faster, the working time of doctors is reduced or effectively controlled, or the number of the reception visits in unit time can be increased, the medical efficiency is improved, and the utilization rate of medical resources is ensured.
2. When the auxiliary identification system of the myocardial muscle calcium egg rising type is used as a module to participate in the auxiliary identification of cardiovascular diseases, the characteristic space can be expanded integrally, so that the expression capability of the characteristics can be fully exerted, comprehensive utilization of comprehensive deep characteristics is realized, the subsequent classification and the convergence effect of the subsequent classification are avoided, and the integral classification capability is improved equivalently.
Drawings
Fig. 1 is a schematic diagram of an auxiliary identification system for myocardial muscle calcium egg elevation types.
Fig. 2 is a schematic diagram of an auxiliary identification system for cardiovascular diseases.
Detailed Description
The first embodiment is as follows: the present embodiment is described in connection with figure 1,
the present embodiment is a myocardial muscle calcium egg elevation type auxiliary identification system, including:
a status information acquisition unit: the system is used for acquiring the state information of a patient, and comprises blood pressure p and heartbeat data n, wherein the unit of the blood pressure p is mmHg, and the unit of the heartbeat data n is times/minutes; taking p/120 as a first state characteristic and taking p/n as a second state characteristic;
myocardial muscle calcium egg monitoring unit: the system is used for recording and monitoring the indexes of cTnI and cTnT in different time periods; the method is also used for comparing the cTnI index and the cTnT index of each time period with the cTnI threshold and the cTnT threshold respectively, and when the cTnI > the cTnI threshold and/or the cTnT > the cTnT threshold, the myocardial muscle calcium egg rise is considered to be in an abnormal condition or an alarm condition. The myocardial muscle calcium egg index threshold may be set based on expert libraries or the experience of a doctor.
Myocardial muscle calcium egg characteristic extraction unit: taking the current cTnI and cTnT indexes as a first cTnI characteristic and a first cTnT characteristic; the current cTnI/cTnI 24-48 As a second cTnI characteristic, cTnI 24-48 Is cTnI corresponding to 24-48 hours after onset of disease, if there is no cTnI 24-48 Data, or the time for obtaining the cTnI currently does not exceed 24-48 hours after the onset of disease, setting the second cTnI characteristic as 1; similarly, the current cTnT/cTnT 24-48 As a second cTnT feature, cTnT 24-48 The cTnT corresponding to 24-48 hours after onset, if not 24-48 Data, or the time for obtaining the cTnT currently does not exceed 24-48 hours after the onset of disease, setting the second cTnT characteristic as 1;
electrocardiosignal characteristic extraction unit: it is used for carrying out analysis and obtaining electrocardiosignal characteristics to electrocardiosignal, it includes:
an electrocardiosignal preprocessing subunit: analyzing the electrocardiosignal to obtain the position of QRS wave band, ST segment and T wave of the electrocardiosignal, and extracting corresponding signals;
a QRS wave band feature extraction subunit: according to the QRS wave band signal, judging the QRS wave band width to be recorded as a first electrocardiogram characteristic; meanwhile, judging whether the Q wave has pathological Q wave, and recording as a second electrocardio characteristic;
an ST-segment feature extraction subunit: judging whether the ST segment is raised or lowered according to the ST segment signal, and recording as a third electrocardiogram characteristic;
t wave feature extraction subunit: judging whether T wave inversion and erection occur according to the T wave signal, and recording as a fourth electrocardiogram characteristic;
an auxiliary identification unit for the myocardial muscle calcium egg rising type: the features extracted by the state information acquisition unit, the myocardial muscle calcium egg feature extraction unit and the electrocardiosignal feature extraction unit are recorded as basic features (a first state feature, a second state feature, a first cTnI feature, a first cTnT feature and a second cTnI feature) and used as input, a random forest classifier is called to judge the myocardial muscle calcium egg rising type, the random forest classifier is a binary classifier, and the classified myocardial muscle calcium egg rising type comprises cTn rising caused by ischemic cardiovascular diseases and cTn rising caused by non-ischemic cardiovascular diseases.
The random forest classifier is stored in the data, is constructed in advance, and is directly called and loaded by the auxiliary identification unit of the myocardial muscle calcium egg rising type for identifying the myocardial muscle calcium egg rising type when in use.
The construction process of the random forest classifier is as follows:
s1: acquiring state information of a patient, monitoring and acquiring an electrocardiosignal, a cTnI index and a cTnT index, and acquiring corresponding characteristics according to the processing modes of a state information acquisition unit, a myocardial calvital characteristic extraction unit and an electrocardiosignal characteristic extraction unit; simultaneously labeling cTn of different patients correspondingly, wherein the labels are cTn increase caused by blood cardiovascular diseases and cTn increase caused by non-ischemic cardiovascular diseases;
establishing a data set by using the information, randomly sampling in the data set, and respectively building a training set and a testing set; meanwhile, the test set is averagely divided into 3 groups;
s2: based on the training set, sampling for N times by using a Bagging algorithm and setting back to establish a decision tree;
s3: verifying each decision tree by using 3 groups of test sets respectively, and recording the classification accuracy of each group of data sets
i =1, \ 8230, N denotes the ith decision tree, and j =1,2,3 denotes the jth data set of the ith tree;
s4: calculate the average of the accuracy measured for 3 test sets
As the accuracy of the ith decision tree;
s5: sorting all decision trees in a descending order according to the classification accuracy;
s6: taking one test set in the 3 groups of test sets as a determined data set, calculating and storing inner product values among decision trees by adopting a vector inner product method aiming at the determined data set, and searching for an inner product threshold value n by using a grid search algorithm; reserving a decision tree of which the inner product of the vector is less than or equal to an inner product threshold;
for the decision trees with the vector inner product higher than the inner product threshold, marking the decision trees with low classification accuracy in each pair of decision trees for calculating the vector inner product as deletable;
s7: deleting the decision trees marked as deletable in sequence from low to high according to the classification accuracy until the number of the remaining decision trees is N; if the quantity of the decision trees is larger than N after the marked deletable decision trees are deleted, the decision trees are continuously deleted in the reserved decision trees from low to high according to the classification accuracy until the quantity of the remaining decision trees is N;
s8: and (4) voting by using a classifier to determine a final classification result, so as to obtain the constructed random forest classifier.
In fact, the neural network model can be used for classifying the cTn rising type (corresponding training of the neural network model is needed), and theoretically, the neural network model should be better. However, in the research of the present invention, considering that the following implementation of specific discrimination of various caused cTn rise types focuses more on multiple classifications, it is more appropriate to use a neural network model. If a neural network model is subsequently adopted, when the neural network model is also adopted, because the mode of extracting deeper features of basic features by the neural network model is similar, the deep features extracted by the two network models have certain similarity, so that the method is not beneficial to mining more features of data, namely, the method is not beneficial to extracting more angles and more spaces and utilizing the deep features, so that the neural network model is completely adopted for processing, compared with the effect of directly adopting the two neural network models to process the neural network model with the optimal processing effect to carry out multi-classification processing, and the capability of improving the whole effect is limited. Then based on conventional knowledge it would be assumed that: therefore, the method is not as good as the method which directly adopts a neural network model for processing, because the traditional cognition is considered, the effect improvement capability is limited, a training link needs to be added, the actual processing links are more, the processing efficiency is low, and the resources are wasted.
For classification, at the initial stage of machine learning technology, a bayesian estimation algorithm, a random forest algorithm, a support vector machine algorithm and the like are generally adopted, but in recent years, with the development of a neural network, the neural network model has incomparable advantages, and as long as the neural network model is built reasonably, the processing effect of the neural network model is better than that of a machine learning model of the first generation. At present, the classification is generally processed by adopting a neural network model, all the competitions in the world are basically processed by adopting the neural network model, and excellent results are obtained, so that the neural network model has very strong classification capability, and is not only suitable for two-classification, but also very suitable for multiple-classification. Thus, in the light of the present invention, without the intensive studies related thereto, it is generally recognized that: compared with the classification processing capability of directly adopting one neural network model, the improvement of the classification effect of the two neural network models is limited, and the neural network model is very suitable for multi-classification, so that based on the purpose of final cardiovascular disease identification, technicians in the field generally take basic characteristics as input and directly carry out multi-classification by adopting one neural network model, thereby not only obtaining more and more classification effects, but also greatly reducing training work.
It also needs to be pointed out that: the above description is based on the conclusion that conventional studies have concluded that the present invention is initially considered, but in intensive studies it has been found that although cTn is a marker of myocardial injury, it is not characteristic of acute myocardial infarction-related coronary ischemia, and it is considered that in heart failure caused by non-ischemic or coronary artery disease, a slight increase in circulating cTn is also frequently observed, compared to heart failure caused by ischemic heart disease, indicating that these patients also have sustained myocardial cell damage or necrosis. Thus, cTn is not considered suitable for being described as disease-specific, but more suitable for being described as organ-specific. Therefore, if the direct judgment of the disease by using the related features of the cTn in combination with other features is not beneficial to the expression of the related features of the cTn for the disease discrimination capability, or the cTn increase caused by both ischemic cardiovascular disease and non-ischemic cardiovascular disease, the discrimination expression capability of the cTn increase index between specific types under both ischemic cardiovascular disease and non-ischemic cardiovascular disease is limited. Based on this, the present invention changes the strategy of fully analyzing the expression space formed by the cTn increase and other basic features, and then distinguishing the categories corresponding to the cTn increase index, i.e. ischemic cardiovascular disease and non-ischemic cardiovascular disease, based on the expression space, and it is noted that the distinction between ischemic cardiovascular disease and non-ischemic cardiovascular disease (rather than between the specific categories under the two items) is not made by using the expression capacity of the cTn increase index for distinguishing between the specific categories under the two items, but rather as the amount of the expansion expression space. After the cTn is distinguished to be raised due to ischemic cardiovascular diseases/non-ischemic cardiovascular diseases, the cTn is further classified based on a specific disease under a cardiovascular disease item under a certain condition, and at the moment, the related indexes of the cTn are utilized again to actually utilize the expression function of the cTn in the disease (note that the expression function is the expression capability, and the distinguishing capability of the cTn between specific types of the ischemic cardiovascular diseases and the non-ischemic cardiovascular diseases is not emphasized), so that the two-section discrimination is found to have more practical significance on the basis of the research of the invention (the two-section discrimination is used for assisting a doctor to distinguish the cTn raised due to the ischemic cardiovascular diseases and the non-cardiovascular diseases), and the classification accuracy of a specific basic classification can be improved.
The innovation of the invention is that:
1. according to the method, the characteristics extracted by the state information acquisition unit, the myocardial muscle calcium egg characteristic extraction unit and the electrocardiosignal characteristic extraction unit are used as basic characteristics to judge the rising type of the myocardial muscle calcium egg through research, so that the judgment accuracy can be greatly improved, and more accurate reference is provided for doctors. Therefore, the difficulty degree of clinical judgment is reduced, the risk of misdiagnosis or delayed treatment is reduced, and the advantages of the invention are more obvious especially for doctors with less clinical experience. Meanwhile, compared with manual judgment, the method has the advantages that the judgment is faster, the working time of doctors is reduced or effectively controlled, or the number of the reception visits in unit time can be increased, the medical efficiency is improved, and the utilization rate of medical resources is ensured.
2. When the auxiliary identification system of the myocardial muscle calcium egg rising type participates in auxiliary identification of cardiovascular diseases as a module, the characteristic space can be expanded integrally, so that the expression capability of the characteristics can be fully exerted, comprehensive utilization of the comprehensive deep characteristics is realized, the subsequent classification and the convergence effect of the positions are avoided, and the integral classification capability is improved equivalently.
The second embodiment is as follows:
the present embodiment is a computer storage medium having at least one instruction stored therein, the at least one instruction being loaded and executed by a processor to implement the system for assisted identification of a type of elevated cardiac muscle calcium eggs.
It should be understood that any method described herein, including any methods described herein, may accordingly be provided as a computer program product, software, or computerized method, which may include a non-transitory machine-readable medium having stored thereon instructions, which may be used to program a computer system, or other electronic device. Storage media may include, but is not limited to, magnetic storage media, optical storage media; a magneto-optical storage medium comprising: read only memory ROM, random access memory RAM, erasable programmable memory (e.g., EPROM and EEPROM), and flash memory layers; or other type of media suitable for storing electronic instructions.
The third concrete implementation mode:
the embodiment is an auxiliary identification device for the type of the elevation of the myocardial muscle calcium egg, the device comprises a processor and a memory, the device can be a computer, and can also be a specially developed device for auxiliary identification of the type of the elevation of the myocardial muscle calcium egg, and it should be understood that any device comprising the processor and the memory described in the present invention can also comprise other units and modules which perform display, interaction, processing, control and other functions through signals or instructions;
the memory has at least one instruction stored therein, and the at least one instruction is loaded and executed by the processor to implement the system for assisted identification of a type of cardiac muscle calcium egg elevation.
The fourth concrete implementation mode: the present embodiment is described in connection with figure 2,
the present embodiment is a cardiovascular disease identification assisting system, including: the device comprises an auxiliary identification module for myocardial muscle calcium egg rising type, an image data acquisition and characteristic module and a cardiovascular disease identification module;
the auxiliary identification module for the myocardial muscle calcium egg rising type, the image data acquisition module and the cardiovascular disease identification module can be deployed on different equipment or computers, and all the modules communicate through interfaces to realize data transmission and acquisition; two or three of the myocardial muscle calcium egg rising type auxiliary identification module, the image data acquisition module and the cardiovascular disease identification module can also be deployed on the same equipment or computer, can be an integral system which operates cooperatively, data among the modules can be directly stored and called through a database, and can also be different independent operation systems, and data transmission and acquisition are realized through virtual data interfaces.
The auxiliary identification module for the myocardial muscle calcium egg rising type comprises: namely, the auxiliary identification system for the myocardial muscle calcium egg rising type specifically comprises:
a status information acquisition unit: the system is used for acquiring the state information of a patient, and comprises blood pressure p and heartbeat data n, wherein the unit of the blood pressure p is mmHg, and the unit of the heartbeat data n is sub/min; taking p/120 as a first state characteristic and taking p/n as a second state characteristic;
myocardial muscle calcium egg monitoring unit: the system is used for recording and monitoring the indexes of cTnI and cTnT in different time periods; the method is also used for comparing the cTnI index and the cTnT index of each time period with the cTnI threshold value and the cTnT threshold value respectively, and when the cTnI > the cTnI threshold value and/or the cTnT > the cTnT threshold value, the myocardial muscle calcium egg rise is considered to be in an abnormal condition or a warning condition. The myocardial muscle calcium egg index threshold may be set based on expert libraries or the experience of a doctor.
A myocardial muscle calcium egg feature extraction unit: taking the current cTnI and cTnT indexes as a first cTnI characteristic and a first cTnT characteristic; the current cTnI/cTnI 24-48 As a second cTnI feature, cTnI 24-48 Is cTnI corresponding to 24-48 hours after onset of disease, if there is no cTnI 24-48 Data, or the time for obtaining the cTnI currently does not exceed 24-48 hours after the onset of disease, setting the second cTnI characteristic as 1; similarly, the current cTnT/cTnT 24-48 As a second cTnT feature, cTnT 24-48 The cTnT corresponding to 24-48 hours after onset, if not 24-48 Data, or the time for obtaining the cTnT currently does not exceed 24-48 hours after the onset of disease, setting a second cTnT characteristic as 1;
electrocardiosignal characteristic extraction unit: it is used for carrying out analysis and obtaining electrocardiosignal characteristics to electrocardiosignal, it includes:
an electrocardiosignal preprocessing subunit: analyzing the electrocardiosignal to obtain the position of QRS wave band, ST segment and T wave of the electrocardiosignal, and extracting corresponding signals;
a QRS wave band feature extraction subunit: according to the QRS wave band signal, judging the QRS wave band width, and recording as a first electrocardiogram characteristic; meanwhile, judging whether the Q wave has pathological Q wave, and recording as a second electrocardio characteristic;
an ST-segment feature extraction subunit: judging whether the ST segment is raised or lowered according to the ST segment signal, and recording as a third electrocardiogram characteristic;
t wave feature extraction subunit: judging whether T wave inversion and erection occur according to the T wave signal, and recording as a fourth electrocardiogram characteristic;
an auxiliary identification unit for the myocardial muscle calcium egg rising type: recording the characteristics extracted by the state information acquisition unit, the myocardial calcium egg characteristic extraction unit and the electrocardiosignal characteristic extraction unit as basic characteristics and taking the basic characteristics as input, calling a random forest classifier to judge the myocardial calcium egg rising type, wherein the random forest classifier is a two-classifier, and the classified myocardial calcium egg rising type comprises cTn rising caused by ischemic cardiovascular diseases and cTn rising caused by non-ischemic cardiovascular diseases;
the image data acquisition and feature module comprises an image data acquisition unit and an image feature extraction unit;
an image data acquisition unit: acquiring corresponding image data according to the selection of a doctor or the type of the preset image data;
the module can acquire image data wanted by a doctor through an interface, can temporarily set the type of the image data when the doctor uses the module every time, can also be preset and cannot be modified without special requirements, and the interface acquires the corresponding image data through the preset type of the image data; the image data includes, but is not limited to, echocardiography;
an image feature extraction unit: taking the image acquired by the image data acquisition unit as input, and extracting a characteristic diagram through a characteristic extraction network; in the embodiment, the feature extraction network adopts ResNet50;
the cardiovascular disease identification module comprises a characteristic adjusting unit, a neural network selecting unit, an ischemic cardiovascular disease identification unit and a non-ischemic cardiovascular disease identification unit;
a feature adjusting unit: converting the image data acquisition and feature map extracted by the feature module into one-dimensional features with fixed length;
a neural network selection unit: according to the judgment result of the auxiliary judgment unit for the myocardial muscle calcium egg rising type, selecting and calling an ischemic cardiovascular disease judgment unit or a non-ischemic cardiovascular disease judgment unit;
ischemic cardiovascular disease identification unit: taking the one-dimensional features and all basic feature vectors which are converted into fixed lengths as input, and calling a neural network model for judging ischemic cardiovascular diseases to judge ischemic cardiovascular diseases; the identification result comprises acute myocardial infarction, unstable angina and stable angina;
the neural network model for ischemic cardiovascular disease identification is also trained in advance and stored in the data.
In the embodiment, a multilayer perceptron is directly adopted and consists of an input layer, three hidden layers and an output layer;
the first layer is an input layer, and the input layer splices the one-dimensional features converted into fixed lengths and all basic features;
the three hidden layers are used for learning the relation between the features;
the last layer is an output layer which outputs the judgment result of the ischemic cardiovascular disease.
Other neural network models may be used in practice.
Non-ischemic cardiovascular disease identification unit: taking the one-dimensional features and all basic feature vectors which are converted into fixed lengths as input, and calling a neural network model for non-ischemic cardiovascular disease judgment to judge non-ischemic cardiovascular diseases; the identification result comprises non-ischemia-induced heart failure, arrhythmia, myocarditis, aortic dissection, takotsubo cardiomyopathy and the like;
similarly, a neural network model for ischemic cardiovascular disease identification is also trained in advance and stored in the data.
In the embodiment, a multilayer perceptron is directly adopted and consists of an input layer, three hidden layers and an output layer;
the first layer is an input layer, and the input layer splices the one-dimensional features converted into fixed lengths and all basic features;
the three hidden layers are used for learning the relation between the features;
the last layer is an output layer which outputs the judgment result of the non-ischemic cardiovascular disease.
Other neural network models may be used in practice.
When the auxiliary identification system of the myocardial muscle calcium egg rising type participates in auxiliary identification of cardiovascular diseases as a module, the characteristic space can be expanded integrally, so that the expression capability of the characteristics can be fully exerted, comprehensive utilization of the comprehensive deep characteristics is realized, the subsequent classification and the convergence effect of the positions are avoided, and the integral classification capability is improved equivalently.
Meanwhile, the method respectively adopts two neural network models for ischemic cardiovascular disease identification and non-ischemic cardiovascular disease identification, so that each feature can be ensured to have specific feature contribution capacity under the respective identification model in the training process, and the network model obtained by the model after training has identification specificity (the direct surface is different from the model parameter), and the model is favorable for the expression of the feature in the space of the respective model so as to improve the identification accuracy rate in respective conditions.
The above-described calculation examples of the present invention are merely to explain the calculation model and the calculation flow of the present invention in detail, and are not intended to limit the embodiments of the present invention. It will be apparent to those skilled in the art that other variations and modifications of the present invention can be made based on the above description, and it is not intended to be exhaustive or to limit the invention to the precise form disclosed, and all such modifications and variations are possible and contemplated as falling within the scope of the invention.
Claims (10)
1. An auxiliary identification system for the type of the elevation of the myocardial muscle calcium egg is characterized by comprising a state information acquisition unit, a myocardial muscle calcium egg monitoring unit, a myocardial muscle calcium egg characteristic extraction unit, an electrocardiosignal characteristic extraction unit and an auxiliary identification unit for the type of the elevation of the myocardial muscle calcium egg;
a status information acquisition unit: the system is used for acquiring the state information of a patient, and comprises blood pressure p and heartbeat data n, wherein the unit of the blood pressure p is mmHg, and the unit of the heartbeat data n is sub/min; taking p/120 as a first state characteristic and taking p/n as a second state characteristic;
myocardial muscle calcium egg monitoring unit: the system is used for recording and monitoring the indexes of cTnI and cTnT in different time periods;
myocardial muscle calcium egg characteristic extraction unit: taking the current cTnI and cTnT indexes as a first cTnI characteristic and a first cTnT characteristic; the current cTnI/cTnI 24-48 As a second cTnI feature, cTnI 24-48 The cTnI corresponding to 24-48 hours after onset, if not 24-48 Data, or the time for obtaining the cTnI currently does not exceed 24-48 hours after the onset of disease, setting the second cTnI characteristic as 1; similarly, the current cTnT/cTnT 24-48 As a second cTnT feature, cTnT 24-48 The cTnT corresponding to 24-48 hours after onset, if not 24-48 Data, or the time for obtaining the cTnT currently does not exceed 24-48 hours after the onset of disease, setting the second cTnT characteristic as 1;
electrocardiosignal characteristic extraction unit: the electrocardiosignal analyzing device is used for analyzing the electrocardiosignal and acquiring the electrocardiosignal characteristics;
the auxiliary identification unit for the myocardial muscle calcium egg rising type comprises: and recording the characteristics extracted by the state information acquisition unit, the myocardial muscle calcium egg characteristic extraction unit and the electrocardiosignal characteristic extraction unit as basic characteristics and taking the basic characteristics as input, calling a random forest classifier to judge the myocardial muscle calcium egg rising type, wherein the random forest classifier is a binary classifier, and the classified myocardial muscle calcium egg rising type comprises cTn rising caused by ischemic cardiovascular diseases and cTn rising caused by non-ischemic cardiovascular diseases.
2. The system for assisting in determining the type of myocardial muscle calcium egg elevation as claimed in claim 1, wherein the electrocardiosignal feature extraction unit comprises an electrocardiosignal preprocessing subunit, a QRS band feature extraction subunit, an ST-segment feature extraction subunit, and a T-wave feature extraction subunit; wherein the content of the first and second substances,
an electrocardiosignal preprocessing subunit: analyzing the electrocardiosignal to obtain the position of QRS wave band, ST segment and T wave of the electrocardiosignal, and extracting corresponding signals;
a QRS wave band feature extraction subunit: according to the QRS wave band signal, judging the QRS wave band width, and recording as a first electrocardiogram characteristic; meanwhile, judging whether the Q wave has pathological Q wave, and recording as a second electrocardio characteristic;
an ST-segment feature extraction subunit: judging whether the ST segment is raised or lowered according to the ST segment signal, and recording as a third electrocardiogram characteristic;
t wave feature extraction subunit: and judging whether the T wave is inverted and vertical according to the T wave signal, and recording as a fourth electrocardiogram characteristic.
3. The system for assisting identification of a type of cardiac muscle calcium egg increase according to claim 1 or 2, wherein the cardiac muscle calcium egg monitoring unit is further configured to compare the cTnI and cTnT indexes for each time period with the cTnI threshold and the cTnT threshold, respectively, and when the cTnI > the cTnI threshold and/or the cTnT > the cTnT threshold, the cardiac muscle calcium egg increase is considered to be in an abnormal condition or an alarm condition.
4. A computer storage medium for auxiliary identification of type of cardiac muscle calcium egg elevation, the storage medium having stored therein at least one instruction, the at least one instruction being loaded and executed by a processor to implement an auxiliary identification system of type of cardiac muscle calcium egg elevation according to any one of claims 1 to 3.
5. An auxiliary identification device for myocardial muscle calcium egg elevation type, characterized in that the device comprises a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to realize the auxiliary identification system for myocardial muscle calcium egg elevation type according to one of claims 1 to 3.
6. An auxiliary recognition system for cardiovascular diseases, comprising: the device comprises an auxiliary identification module for myocardial muscle calcium egg rising type, an image data acquisition and characteristic module and a cardiovascular disease identification module;
the myocardial muscle calcium egg elevation type auxiliary identification module is used for identifying cTn elevation caused by ischemic cardiovascular diseases and cTn elevation caused by non-ischemic cardiovascular diseases by using the myocardial muscle calcium egg elevation type auxiliary identification system as claimed in any one of claims 1 to 3, and simultaneously recording the characteristics extracted by the state information acquisition unit, the myocardial muscle calcium egg characteristic extraction unit and the electrocardiosignal characteristic extraction unit in the myocardial muscle calcium egg elevation type auxiliary identification system as basic characteristics;
the image data acquisition and feature module comprises an image data acquisition unit and an image feature extraction unit; wherein the content of the first and second substances,
an image data acquisition unit: acquiring corresponding image data according to the selection of a doctor or the type of the preset image data;
an image feature extraction unit: taking the image acquired by the image data acquisition unit as input, and extracting a characteristic diagram through a characteristic extraction network;
the cardiovascular disease identification module comprises a characteristic adjusting unit, a neural network selecting unit, an ischemic cardiovascular disease identification unit and a non-ischemic cardiovascular disease identification unit; wherein, the first and the second end of the pipe are connected with each other,
a feature adjusting unit: converting the image data acquisition and feature map extracted by the feature module into one-dimensional features with fixed length;
a neural network selection unit: according to the judgment result of the auxiliary judgment unit for the myocardial muscle calcium egg rising type, selecting and calling an ischemic cardiovascular disease judgment unit or a non-ischemic cardiovascular disease judgment unit;
ischemic cardiovascular disease identification unit: taking the one-dimensional features and all basic feature vectors which are converted into fixed lengths as input, and calling a neural network model for judging ischemic cardiovascular diseases to judge ischemic cardiovascular diseases;
non-ischemic cardiovascular disease identification unit: and taking the one-dimensional features and all basic feature vectors which are converted into fixed lengths as input, and calling a neural network model for identifying the non-ischemic cardiovascular diseases to identify the non-ischemic cardiovascular diseases.
7. The system of claim 6, wherein the neural network models in the ischemic cardiovascular disease identification unit and the non-ischemic cardiovascular disease identification unit are multi-layered perceptrons.
8. The system of claim 7, wherein the multi-layered sensor comprises an input layer, three hidden layers and an output layer;
the first layer is an input layer, and the input layer splices the one-dimensional features converted into fixed lengths and all basic features;
the three hidden layers are used for learning the relation between the features;
the last layer is an output layer which outputs the judgment result of the non-ischemic cardiovascular disease.
9. The system of claim 8, wherein the image feature extraction unit further comprises a ResNet50 network.
10. The cardiovascular disease auxiliary identification system according to any one of claims 6 to 8, wherein the myocardial muscle calcium egg elevation type auxiliary identification module, the image data acquisition module and the cardiovascular disease identification module are deployed on different devices or computers, and each module communicates through an interface to realize data transmission and acquisition;
alternatively, the first and second electrodes may be,
two or three of the myocardial muscle calcium egg rising type auxiliary identification module, the image data acquisition module and the cardiovascular disease identification module are also deployed on the same equipment or computer, and data among the modules are directly stored and retrieved through a database or transmitted and retrieved through a data interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211600107.0A CN115862843B (en) | 2022-12-12 | 2022-12-12 | Auxiliary identification system and equipment for myocardial troponin elevation type and cardiovascular diseases |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211600107.0A CN115862843B (en) | 2022-12-12 | 2022-12-12 | Auxiliary identification system and equipment for myocardial troponin elevation type and cardiovascular diseases |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115862843A true CN115862843A (en) | 2023-03-28 |
| CN115862843B CN115862843B (en) | 2024-02-02 |
Family
ID=85672553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211600107.0A Active CN115862843B (en) | 2022-12-12 | 2022-12-12 | Auxiliary identification system and equipment for myocardial troponin elevation type and cardiovascular diseases |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115862843B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070241068A1 (en) * | 2006-04-13 | 2007-10-18 | Pamula Vamsee K | Droplet-based washing |
| CN103549949A (en) * | 2013-10-21 | 2014-02-05 | 华南理工大学 | Myocardial ischemia auxiliary detecting method based on deterministic learning theory |
| CN107184198A (en) * | 2017-06-01 | 2017-09-22 | 广州城市职业学院 | A kind of electrocardiosignal classifying identification method |
| CN109841278A (en) * | 2017-11-28 | 2019-06-04 | 长庚医疗财团法人林口长庚纪念医院 | A method of the screening of coronary disease disease is carried out with angiocarpy mark and rote learning operation method |
| CN111292853A (en) * | 2020-01-15 | 2020-06-16 | 长春理工大学 | Cardiovascular disease risk prediction network model based on multiple parameters and construction method thereof |
| CN111657921A (en) * | 2020-07-01 | 2020-09-15 | 杭州脉流科技有限公司 | Real-time electrocardio abnormality monitoring method and device, computer equipment and storage medium |
| CN113903466A (en) * | 2021-09-26 | 2022-01-07 | 新乡医学院第一附属医院 | Data processing device and system for auxiliary evaluation of risk degree of cardiovascular diseases of population and application of data processing device and system |
| CN114366116A (en) * | 2022-01-28 | 2022-04-19 | 南方医科大学 | Parameter acquisition method based on Mask R-CNN network and electrocardiogram |
-
2022
- 2022-12-12 CN CN202211600107.0A patent/CN115862843B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070241068A1 (en) * | 2006-04-13 | 2007-10-18 | Pamula Vamsee K | Droplet-based washing |
| CN103549949A (en) * | 2013-10-21 | 2014-02-05 | 华南理工大学 | Myocardial ischemia auxiliary detecting method based on deterministic learning theory |
| CN107184198A (en) * | 2017-06-01 | 2017-09-22 | 广州城市职业学院 | A kind of electrocardiosignal classifying identification method |
| CN109841278A (en) * | 2017-11-28 | 2019-06-04 | 长庚医疗财团法人林口长庚纪念医院 | A method of the screening of coronary disease disease is carried out with angiocarpy mark and rote learning operation method |
| CN111292853A (en) * | 2020-01-15 | 2020-06-16 | 长春理工大学 | Cardiovascular disease risk prediction network model based on multiple parameters and construction method thereof |
| CN111657921A (en) * | 2020-07-01 | 2020-09-15 | 杭州脉流科技有限公司 | Real-time electrocardio abnormality monitoring method and device, computer equipment and storage medium |
| CN113903466A (en) * | 2021-09-26 | 2022-01-07 | 新乡医学院第一附属医院 | Data processing device and system for auxiliary evaluation of risk degree of cardiovascular diseases of population and application of data processing device and system |
| CN114366116A (en) * | 2022-01-28 | 2022-04-19 | 南方医科大学 | Parameter acquisition method based on Mask R-CNN network and electrocardiogram |
Non-Patent Citations (3)
| Title |
|---|
| 王玻: ""缺血性心脏病的实验室诊断进展"", 《引进国外医药技术与设备》, vol. 4, no. 5, pages 2 * |
| 陈文佳: ""心肌肌钙蛋白在非缺血性心血管疾病中的研究进展"", 《分子生物医学》, vol. 27, no. 05, pages 845 - 849 * |
| 韦信暖: ""高敏心肌肌钙蛋白Ⅰ阳性患者的疾病谱特征分析"", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》, no. 03, pages 062 - 11 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115862843B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11134880B2 (en) | Automatic method to delineate or categorize an electrocardiogram | |
| US10758139B2 (en) | Automatic method to delineate or categorize an electrocardiogram | |
| US20200337580A1 (en) | Time series data learning and analysis method using artificial intelligence | |
| Sk et al. | Coronary Heart Disease Prediction and Classification using Hybrid Machine Learning Algorithms | |
| JP6986724B2 (en) | ECG interference identification method based on artificial intelligence | |
| WO2017072250A1 (en) | An automatic method to delineate or categorize an electrocardiogram | |
| CN108090509B (en) | Data length self-adaptive electrocardiogram classification method | |
| US11331034B2 (en) | Automatic method to delineate or categorize an electrocardiogram | |
| CN110638430B (en) | Method for building cascade neural network ECG signal arrhythmia classification model | |
| CN110020636B (en) | Ventricular premature beat intelligent analysis method based on abnormal characteristic value | |
| CN113113130A (en) | Tumor individualized diagnosis and treatment scheme recommendation method | |
| CN112932433B (en) | Arrhythmia automatic classification method of electrocardiogram | |
| CN111956208B (en) | ECG signal classification method based on ultra-lightweight convolutional neural network | |
| CN110558975B (en) | Electrocardiosignal classification method and system | |
| CN111145912A (en) | Machine learning-based prediction device for personalized ovulation promotion scheme | |
| CN113095302A (en) | Depth model for arrhythmia classification, method and apparatus using the same | |
| CN114970637A (en) | Lightweight arrhythmia classification method based on deep learning | |
| Thuraisingham | A classification system to detect congestive heart failure using second-order difference plot of RR intervals | |
| Li et al. | Research on massive ECG data in XGBoost | |
| Janghorbani et al. | Prediction of acute hypotension episodes using logistic regression model and support vector machine: A comparative study | |
| Guanglong et al. | ECG signal classification algorithm based on fusion features | |
| US6941288B2 (en) | Online learning method in a decision system | |
| CN115862843A (en) | Auxiliary identification system and equipment for myocardial muscle calcium egg rising type and cardiovascular diseases | |
| Pabitha et al. | A Comparative Study of Deep Learning Models for ECG Signal-based User Classification | |
| CN111261283A (en) | Electrocardiosignal deep neural network modeling method based on pyramid type convolution layer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |