Coronary heart disease risk auxiliary assessment system based on smart medical care

By analyzing the degree of deviation of cardiac troponin concentration and the difference in score matrix of patients with coronary heart disease, the focus factor was calculated, and the problem that the existing score sheet could not reflect dynamic changes was solved, real-time attention adjustment for patients with coronary heart disease was achieved and Optimization of treatment strategy.

CN118658629BActive Publication Date: 2024-11-15PEKING UNIVERSITY THIRD HOSPITAL (THE THIRD CLINICAL MEDICAL SCHOOL OF PEKING UNIVERSITY)
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411147728.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-11-15
Estimated Expiration
2044-08-21

AI Technical Summary

Technical Problem

The existing coronary heart disease score sheet cannot effectively reflect the dynamic changes in patients' physiological indicators, resulting in poor results in determining attention and the inability to adjust treatment strategies in real time.

Method used

By obtaining multiple detection cardiac troponin concentration data of patients with coronary heart disease, analyzing its degree of deviation, using clustering algorithms and scoring matrix differences to calculate the factors of attention, comprehensively reflecting the changes in the patients' physiological indicators.

Benefits of technology

Real-time attention adjustment for patients with coronary heart disease is achieved, and it can promptly reflect fluctuations in physiological indicators, overcome the limitations of the traditional score list, and improve the adaptability of the treatment strategy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118658629B_ABST
    Figure CN118658629B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of medical informatics technology, and in particular to a coronary heart disease risk auxiliary assessment system based on smart medical care. The system includes a memory and a processor, and the processor executes a computer program stored in the memory to implement the following steps: obtaining various clinical physiological indicators of patients with coronary heart disease during each test, clustering all tests according to the difference in the degree of deviation of the concentration of cardiac troponin between two adjacent tests, combining the difference in the scoring results of the clinical physiological indicators of each test and its adjacent tests and the local density distribution within the cluster where each test is located, obtaining the scoring common factor of each test; evaluating the difference in the scoring results of the cluster where each test is located and the tests in other clusters, obtaining the scoring difference value corresponding to each test; and comprehensively analyzing the concentration change characterization value, the scoring common factor and the scoring difference value to determine the attention factor of each test. The present invention improves the accuracy of the determination result of the attention of patients with coronary heart disease.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of medical informatics, and in particular to a coronary heart disease risk auxiliary assessment system based on smart medical care. Background Art

[0002] In today's society, cardiovascular disease is one of the major diseases threatening human health. With the aging of the population and changes in lifestyle, the rising prevalence and mortality of coronary heart disease pose a huge challenge to the public health system. The rise of smart healthcare provides new solutions for the early diagnosis and risk assessment of coronary heart disease. The coronary heart disease risk auxiliary assessment system based on smart healthcare came into being. It uses advanced information technology and biomedical engineering, combined with clinical data and individual patient information, to achieve accurate prediction and management of coronary heart disease risks.

[0003] Cardiology diseases are often complex and changeable, so the risk assessment of cardiology diseases should be carried out quickly and accurately. Existing methods often use some scoring tools related to cardiology diseases to make a preliminary evaluation of patients, and determine the degree of attention to patients based on the evaluation results. There are 8 scoring tables commonly used in the diagnosis and treatment of coronary heart disease, specifically GRACE risk score, TIMI risk score, CRUSADE bleeding score, ACUITY bleeding risk score, DAPT score, China-PAR score, Duke exercise treadmill score, and SYNTAX score. Although these scoring tables have a certain effect on patients in clinical manifestations, these scoring tables are usually based on a one-time risk assessment and cannot better reflect the changes in the physiological indicators of patients with coronary heart disease as the treatment process continues or over time. Patients' lifestyle changes or treatment interventions may cause significant changes in patients' physiological indicators. Therefore, only based on the scoring table, it cannot accurately reflect the changes in patients' physiological indicators, which in turn leads to poor results in determining the degree of attention to patients with coronary heart disease. Summary of the invention

[0004] In order to solve the problem of poor accuracy of the attention determination results in the existing method of determining the attention of coronary heart disease patients based on a scoring table, the purpose of the present invention is to provide a coronary heart disease risk auxiliary assessment system based on smart medical care, and the technical solutions adopted are as follows:

[0005] The present invention provides a coronary heart disease risk auxiliary assessment system based on smart medical care, comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to implement the following steps:

[0006] Obtain various clinical physiological indicators of patients with coronary heart disease at each test, including cardiac troponin concentration;

[0007] Analyze the difference between the deviations of cardiac troponin concentrations between two adjacent tests to obtain a concentration change characterization value for each test; cluster all tests based on the concentration change characterization value; and obtain a common scoring factor corresponding to each test by combining the difference between the scoring results of clinical physiological indicators of each test and its adjacent tests in time and the local density distribution within the cluster where each test is located;

[0008] Evaluate the difference between the score results of the cluster where each test is located and the scores of the tests in other clusters to obtain the score difference value corresponding to each test;

[0009] The focus factors for each test are determined by comprehensively considering the concentration change characterization value, the common scoring factor and the scoring difference value.

[0010] Preferably, analyzing the difference between the deviations of the cardiac troponin concentrations of two adjacent tests to obtain a concentration change characterization value for each test includes:

[0011] The difference between the deviation degree of the cardiac troponin concentration of the candidate test and the deviation degree of the cardiac troponin concentration of the previous test of the candidate test is used as the concentration change characterization value of the candidate test;

[0012] The candidate detection is any detection.

[0013] Preferably, obtaining the deviation degree of the candidate detected cardiac troponin concentration includes:

[0014] The mean and overall dispersion of all detected cardiac troponin concentrations were calculated;

[0015] According to the difference between the cardiac troponin concentration of the candidate test and the mean value and the overall discreteness, the deviation degree of the cardiac troponin concentration of the candidate test is obtained, the difference between the cardiac troponin concentration of the candidate test and the mean value is positively correlated with the deviation degree, and the overall discreteness is negatively correlated with the deviation degree.

[0016] Preferably, clustering all detections based on the concentration change characterization value comprises:

[0017] Based on all concentration change characterization values, the K-means clustering algorithm was used to cluster all detections to obtain clusters.

[0018] Preferably, the method of combining the difference between the scoring results of the clinical physiological indicators of each test and the tests adjacent to it in time and the local density distribution within the cluster where each test is located to obtain the scoring common factor corresponding to each test includes:

[0019] Obtain the score sheet of clinical physiological indicators for each test;

[0020] According to the difference between the score matrix of the candidate detection and the next detection adjacent to it in time, a score difference index between the candidate detection and the next detection adjacent to it in time is obtained; wherein the score matrix is ​​composed of data in the score table;

[0021] According to the difference between the total scores of the candidate detection and other detections in its cluster, the score difference value and the local reachable density of all data points in the cluster where the candidate detection is located, the score common factor corresponding to the candidate detection is obtained, the difference between the total scores and the score difference index are negatively correlated with the score common factor, and the local reachable density is positively correlated with the score common factor.

[0022] Preferably, the scoring table of clinical physiological indicators detected each time includes 8 scoring tables, which are GRACE risk scoring table, TIMI risk scoring table, CRUSADE bleeding scoring table, ACUITY bleeding risk scoring table, DAPT scoring table, China-PAR scoring table, Duke treadmill scoring table and SYNTAX scoring table.

[0023] Preferably, the step of evaluating the difference between the score results of the cluster in which each detection is located and the scores of the detections in other clusters to obtain the score difference value corresponding to each detection includes:

[0024] According to the difference between the overall scores of all detections in the cluster where the candidate detection is located and the overall scores of detections in other clusters, a score difference value corresponding to the candidate detection is obtained, and the difference between the overall scores is positively correlated with the score difference value.

[0025] Preferably, obtaining a score difference value corresponding to the candidate detection according to the difference between the overall scores of all detections in the cluster where the candidate detection is located and the overall scores of detections in other clusters includes:

[0026] Calculate the difference between the overall scores of all tests in the cluster where the candidate test is located and the overall scores of the tests in each other cluster respectively, and record it as the first difference between the cluster where the candidate test is located and each other cluster;

[0027] Calculate the sum of the first differences between the cluster where the candidate detection is located and all other clusters;

[0028] The normalized result of the sum is used as the score difference value corresponding to the candidate detection.

[0029] Preferably, the comprehensive concentration change characterization value, the scoring common factor and the scoring difference value are used to determine the focus factor for each test, including:

[0030] The focus factor of each detection is obtained by combining the concentration change characterization value of each detection, the common scoring factor corresponding to each detection, and the score difference value corresponding to each detection. The concentration change characterization value is positively correlated with the score difference value, and the common scoring factor and the score difference value are negatively correlated with the score difference value.

[0031] Preferably, obtaining the difference between the scoring matrices includes:

[0032] The difference between two elements at the same position in the two score matrices is calculated, and the average of the differences between the two elements at all positions is taken as the difference between the corresponding two score matrices.

[0033] The present invention has at least the following beneficial effects:

[0034] The present invention takes into account that the existing method determines the degree of attention based on the scoring table of patients with coronary heart disease, does not fully combine the changes in the physiological indicators of patients, cannot effectively reflect the dynamic changes of individual physiological indicators, has the shortcomings of one-sidedness, staticness, and short-termism, resulting in some patients with coronary heart disease who need attention or adjustment of treatment strategies not receiving attention. The present invention first analyzes the difference between the deviation degrees of cardiac troponin concentrations of two adjacent tests, obtains the concentration change characterization value of each test of the coronary heart disease patient, which is used to reflect the degree of change of the cardiac troponin concentration of the patient at different tests, and then clusters all the tests based on the concentration change characterization value, analyzes the clustering results, obtains the scoring common factor corresponding to each test, and the scoring common factor is used to The method reflects the similarity of the scoring results of patients with coronary heart disease under similar clinical behaviors, and evaluates the difference in the scoring results of patients in different behavior clusters based on the difference between the cluster where each test is located and the corresponding scoring results of tests in other clusters. The attention factor of each test of patients with coronary heart disease is further determined by comprehensively combining the concentration change characterization value, the scoring common factor and the scoring difference value. The larger the attention factor, the more abnormal the change of the physiological indicators of the patients with coronary heart disease is, and the higher the attention should be given. The method provided by the present invention can adjust the attention to the patient in real time, reflect the specific fluctuation of the patient's current physiological indicators, overcome the limitations of traditional scoring tables, and can determine the attention to the patient in real time, so as to facilitate timely and appropriate adjustment of the treatment strategy of patients with coronary heart disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A flowchart of a method performed by a coronary heart disease risk auxiliary assessment system based on smart medical care provided by an embodiment of the present invention;

[0037] Figure 2 The present invention provides a flowchart of a method for obtaining common scoring factors according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following is a detailed description of a coronary heart disease risk auxiliary assessment system based on smart medical care proposed in accordance with the present invention in combination with the accompanying drawings and preferred embodiments.

[0039] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0040] The following is a detailed description of a specific scheme of a coronary heart disease risk auxiliary assessment system based on smart medical care provided by the present invention in conjunction with the accompanying drawings.

[0041] Example of coronary heart disease risk auxiliary assessment system based on smart medical care:

[0042] The specific scenario targeted by this embodiment is: when monitoring the symptoms of patients with coronary heart disease, in order to ensure monitoring efficiency, it is often necessary to pay higher attention to patients with abnormal changes in various clinical physiological indicators. This embodiment will analyze the changes in clinical physiological indicators of patients with coronary heart disease during multiple tests, determine the attention factor for each test, and then give appropriate attention to more timely monitoring and treatment of the condition of patients with coronary heart disease.

[0043] This embodiment proposes a coronary heart disease risk auxiliary assessment system based on smart medical care, which can achieve the following Figure 1 The specific steps are as follows:

[0044] Step S1, obtaining various clinical physiological indicators of the coronary heart disease patient during each test, wherein the clinical physiological indicators include the concentration of cardiac troponin.

[0045] First, the clinical physiological index data of patients with coronary heart disease during the treatment process are collected, including the patient's age, high-sensitivity C-reactive protein content, cardiac troponin concentration, blood creatinine content, white blood cell count, vein transplantation PCI, etc. The collected clinical physiological indicators mainly involve the parameters involved in the 8 large tables of coronary heart disease diagnosis and treatment evaluation, and are recorded and stored through electronic health records (electronic health records, HER). In specific applications, implementers can select the type of clinical physiological index data collected according to specific circumstances. Since patients with coronary heart disease will undergo multiple tests on their physiological index data during the treatment process, the clinical physiological indicators of patients with coronary heart disease are obtained at each test during the treatment process.

[0046] Step S2, analyzing the difference between the deviation degrees of cardiac troponin concentrations between each two adjacent tests to obtain a concentration change characterization value for each test; clustering all tests based on the concentration change characterization value; combining the difference between the scoring results of clinical physiological indicators of each test and its adjacent tests in time and the local density distribution within the cluster where each test is located to obtain a common scoring factor corresponding to each test.

[0047] Cardiac troponin is one of the biomarkers released into the blood after myocardial cell damage. In the case of coronary heart disease, especially in acute coronary syndrome (such as myocardial infarction), the concentration of cardiac troponin usually increases significantly. Therefore, changes in cardiac troponin concentration can reflect the degree and extent of myocardial damage.

[0048] Step S21, obtaining a concentration change characterization value for each test according to the difference between the deviation degrees of the cardiac troponin concentrations of two adjacent tests.

[0049] The concentration change of cardiac troponin in patients with coronary heart disease is one of the main biological indicators for evaluating coronary heart disease. By calculating the concentration change of cardiac troponin in patients with coronary heart disease, the clinical manifestations and daily life of the patients can be judged. If the concentration of cardiac troponin in patients with coronary heart disease decreases in a certain period, it means that the daily life of the patients with coronary heart disease in this period has inhibited the deterioration of coronary heart disease, slowed down its development speed, or the clinical treatment intervention effect is significant; on the contrary, it means that the daily life of the patients with coronary heart disease in this period is not conducive to the control of coronary heart disease or the clinical intervention effect is not significant. Based on this, this embodiment will evaluate the concentration change of cardiac troponin in patients with coronary heart disease.

[0050] The average value of all detected cardiac troponin concentrations and the overall dispersion of all detected cardiac troponin concentrations are calculated respectively, wherein the overall dispersion of cardiac troponin concentrations can be characterized by the standard deviation of all detected cardiac troponin concentrations, or by the variance of all detected cardiac troponin concentrations, or by indicators such as the range of all detected cardiac troponin concentrations. In the present embodiment, the standard deviation of all detected cardiac troponin concentrations is used to characterize the overall dispersion of cardiac troponin concentrations, that is, the standard deviation of all detected cardiac troponin concentrations is taken as the overall dispersion of all detected cardiac troponin concentrations.

[0051] Next, one detection is used as an example for explanation, and the method provided in this embodiment can be used to process other detections. Specifically, any detection is recorded as a candidate detection, and the deviation degree of the cardiac troponin concentration of the candidate detection is obtained according to the difference between the cardiac troponin concentration of the candidate detection and the average value and the overall dispersion degree, the difference between the cardiac troponin concentration of the candidate detection and the average value is positively correlated with the deviation degree, and the overall dispersion degree is negatively correlated with the deviation degree.

[0052] Among them, a positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship can be a multiplication relationship, an addition relationship, or the power of an exponential function; a negative correlation means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtraction relationship, a division relationship, etc., which is determined by actual application.

[0053] In this embodiment, a specific calculation formula for the degree of deviation is given, and the specific calculation formula for the degree of deviation of the concentration of cardiac troponin detected for the zth time is:

[0054] ;

[0055] in, Indicates the deviation of the cardiac troponin concentration detected for the zth time, represents the concentration of cardiac troponin detected at the zth time, represents the average of all detected cardiac troponin concentrations, represents the overall dispersion of all detected cardiac troponin concentrations, Indicates the preset first adjustment parameter, Indicates the absolute value sign.

[0056] In this embodiment, the preset first adjustment parameter is introduced into the calculation formula of the deviation degree in order to prevent the denominator from being 0. In this embodiment, the preset first adjustment parameter is 0.01. In specific applications, the implementer can set it according to specific circumstances. Characterizes the difference between the deviation degree of the cardiac troponin concentration detected at the zth time and the average value of all detected cardiac troponin concentrations. The larger the value, the greater the difference between the two, that is, the deviation degree of the cardiac troponin concentration detected at the zth time is less close to the average level. When the difference between the deviation degree of the cardiac troponin concentration detected at the zth time and the average value of all detected cardiac troponin concentrations is larger and the overall dispersion degree of all detected cardiac troponin concentrations is smaller, it means that the deviation degree of the cardiac troponin concentration detected at the zth time is greater, that is, the deviation degree of the cardiac troponin concentration detected at the zth time is greater.

[0057] Since the concentration of cardiac troponin in different coronary heart disease patients is different due to their age and physical health status, the same treatment intervention may have different final results for different people. Therefore, the difference between the deviation degree of cardiac troponin concentration between two adjacent tests is used to determine the concentration change characterization value of coronary heart disease patients.

[0058] Specifically, still taking the candidate detection as an example for explanation, the difference between the deviation degree of the cardiac troponin concentration of the candidate detection and the deviation degree of the cardiac troponin concentration of the previous detection of the candidate detection is used as the concentration change characterization value of the candidate detection. Among them, the difference between the deviation degrees of the cardiac troponin concentration can be represented by an absolute value of the difference between the two deviation degrees, by an index such as the square of the difference between the two deviation degrees, and in this embodiment, the absolute value of the difference between the deviation degree of the cardiac troponin concentration of the candidate detection and the deviation degree of the cardiac troponin concentration of the previous detection of the candidate detection is used as the concentration change characterization value of the candidate detection.

[0059] By adopting the above method, the concentration change characterization value of each detection can be obtained. It should be noted that: if the candidate detection is the first detection, that is, there is no previous detection before the candidate detection, then the concentration change characterization value of the candidate detection is set to the concentration change characterization value of the next detection of the candidate detection, that is, the concentration change characterization value of the next detection of the candidate detection is used as the concentration change characterization value of the candidate detection.

[0060] Step S22: clustering all detections based on the concentration change characterization value.

[0061] In the previous step, the changes in the concentration of cardiac troponin of each patient were analyzed. Different clinical behaviors will cause different changes in the cardiac troponin in the patient's body. Therefore, the changes in the concentration of cardiac troponin at different periods represent some clinical behaviors of the patient at different periods.

[0062] After obtaining the concentration change characterization value of each test of coronary heart disease patients, the time of each test is used as the horizontal coordinate, and the corresponding concentration change characterization value is used as the vertical coordinate to construct a rectangular coordinate system, and obtain the data points corresponding to each test in the coordinate system. Based on the concentration change characterization values ​​of all data points, the K-means clustering algorithm is used to cluster all data points to obtain multiple clusters. The implementer of the K-means clustering algorithm sets the k value according to the specific situation. The K-means clustering algorithm is a prior art and will not be described in detail here.

[0063] So far, multiple clusters have been obtained using the above method.

[0064] Step S23, combining the difference between the scoring results of the clinical physiological indicators of each test and the tests adjacent to it in time and the local density distribution within the cluster where each test is located, to obtain the scoring common factor corresponding to each test.

[0065] According to the clinical physiological index data collected in each test, the health status of the patient is assessed using the 8 commonly used coronary heart disease scoring tables, namely the GRACE risk score table, the TIMI risk score table, the CRUSADE bleeding score table, the ACUITY bleeding risk score table, the DAPT score table, the China-PAR score table, the Duke treadmill score table and the SYNTAX score table. The specific assessment process is an existing technology and will not be described in detail here.

[0066] After obtaining the 8 major scoring tables of clinical physiological indicators of each test of coronary heart disease patients, the candidate test is still used as an example for explanation. Specifically, according to the difference between the scoring matrix of the candidate test and the next test adjacent to it in time, the score difference value between the candidate test and the next test adjacent to it in time is obtained, and the difference between the scoring matrices is negatively correlated with the score difference value; wherein the scoring matrix is ​​composed of data in the scoring table; according to the difference between the total score of the candidate test and other tests in the cluster where it is located, the score difference value and the local reachable density of all data points in the cluster where the candidate test is located, the score common factor corresponding to the candidate test is obtained, the difference between the total scores and the score difference value are negatively correlated with the score common factor, and the local reachable density is positively correlated with the score common factor.

[0067] Among them, a positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship can be a multiplication relationship, an addition relationship, or the power of an exponential function; a negative correlation means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtraction relationship, a division relationship, etc., which is determined by actual application.

[0068] In this embodiment, a specific calculation formula for the scoring common factor is given, and the scoring common factor corresponding to the z-th detection can be expressed as:

[0069] ;

[0070] in, represents the common scoring factor corresponding to the z-th detection, C represents the number of data points in the cluster where the z-th detection is located, represents the total score of the zth test, represents the total score of the cth test except the zth test in the cluster where the zth test is located, It represents the score difference index between the cth detection excluding the zth detection in the cluster where the zth detection is located and the next detection adjacent to it in time. represents the local reachable density of the data points in the cluster where the z-th detection is located, represents an exponential function with a natural constant as base, Indicates the absolute value sign.

[0071] For any test, the method for obtaining the total score of the test is: the sum of all scores in all score tables corresponding to the test is taken as the total score of the test; the specific method for obtaining the score matrix of the test is: quantify all score tables corresponding to the test into matrices, that is, splice the data in all score tables together. Since the data of elements in different types of score tables may be different, the missing positions in the matrix are filled with 0 to obtain the score matrix of the test. This operation is a prior art and will not be described in detail here. The specific method for obtaining the difference between the score matrices of two tests is: calculate the difference between two elements at the same position in the two score matrices, and take the average of the difference between the two elements at all positions as the difference between the corresponding two score matrices. It indicates the difference between the total score of the zth test and the total score of the cth test excluding the zth test in the cluster where the zth test is located. The larger the value, the greater the difference between the two. When the difference between the total score of the zth test and the total score of the cth test excluding the zth test in the cluster where the zth test is located is greater, the score difference index between the test excluding the zth test in the cluster where the zth test is located and the next test adjacent to it in time is greater, and the local reachable density of the data points in the cluster where the zth test is located is smaller, it means that the difference between the two adjacent scoring evaluations is greater, and the credibility of the data is lower, that is, the score common factor corresponding to the zth test is smaller.

[0072] So far, using the above-provided method, the common scoring factors corresponding to each test of coronary heart disease patients can be obtained, such as Figure 2 As shown, the figure is a flow chart of the method for obtaining the common scoring factors.

[0073] Step S3, evaluating the difference between the scoring results of the cluster where each detection is located and the scores of the detections in other clusters, and obtaining the score difference value corresponding to each detection.

[0074] Since the scoring results of all tests in the same cluster are relatively similar, and the scoring results of tests in different clusters vary greatly, the difference between the score of each test combined with the clustering results and the scores of other tests will be evaluated next.

[0075] Specifically, a score difference value corresponding to the candidate detection is obtained according to the difference between the overall scores of all detections in the cluster where the candidate detection is located and the overall scores of detections in other clusters, and the difference between the overall scores is positively correlated with the score difference value.

[0076] Among them, the positive correlation relationship means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship can be a multiplication relationship, an addition relationship, and the power of an exponential function.

[0077] In this embodiment, a specific calculation process of the score difference value is given. The calculation method of the score difference value corresponding to the candidate detection is: respectively calculate the difference between the overall score of all detections in the cluster where the candidate detection is located and the overall score of detections in each other cluster, and record it as the first difference between the cluster where the candidate detection is located and each other cluster; calculate the sum of the first differences between the cluster where the candidate detection is located and all other clusters; and use the normalized result of the sum as the score difference value corresponding to the candidate detection. The score difference value corresponding to the zth detection can be expressed as:

[0078] ;

[0079] in, represents the score difference value corresponding to the z-th detection, B represents the number of clusters, represents the overall score of all tests in the cluster where the zth test is located, represents the overall score of all tests in the bth cluster except the cluster where the zth test is located, Indicates the absolute value sign.

[0080] For any cluster, the overall score of all tests in the cluster is obtained by taking the average of the total scores of all tests in the cluster as the overall score of all tests in the cluster. It represents the difference between the overall score of all tests in the cluster where the zth test is located and the overall score of all tests in the bth cluster except the cluster where the zth test is located. The larger the value, the greater the difference between the two. It is used to reflect the cumulative sum of the differences between the overall scores of the cluster where the zth test is located and other clusters. The greater the difference between the overall scores of the cluster where the zth test is located and other clusters, the greater the difference in the score sheet of patients with coronary heart disease under different clinical behaviors, that is, the score sheet reflects the patient's physiological condition more significantly, and the patient's clinical behavior can be clearly reflected in the score sheet, that is, the score sheet reflects the patient's health status more stably, and the score difference value corresponding to the zth test is greater.

[0081] By using the above method, the score difference value corresponding to each test of the coronary heart disease patient can be obtained.

[0082] Step S4, comprehensively analyzing the concentration change characterization value, the common scoring factor and the scoring difference value to determine the focus factor for each test.

[0083] The concentration change representation value of the coronary heart disease patient at each test calculated in the above steps is used to reflect the degree of change in the patient's cardiac troponin concentration at different tests. The scoring common factor is used to reflect the similarity of the scoring sheet of the coronary heart disease patients under similar clinical behaviors. The scoring difference value is used to reflect the difference in the scoring sheet of patients in different behavior clusters. Next, the concentration change representation value, the scoring common factor and the scoring difference value are comprehensively used to evaluate the degree of concern of the coronary heart disease patients and determine the concern factor for each test.

[0084] Specifically, the concentration change characterization value of each detection, the common scoring factor corresponding to each detection, and the score difference value corresponding to each detection are combined to obtain the focus factor of each detection, the concentration change characterization value is positively correlated with the score difference value, and the common scoring factor and the score difference value are both negatively correlated with the score difference value.

[0085] Among them, a positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship can be a multiplication relationship, an addition relationship, or the power of an exponential function; a negative correlation means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtraction relationship, a division relationship, etc., which is determined by actual application.

[0086] In this embodiment, a specific calculation formula of the attention factor is given, and the attention factor of the z-th detection can be expressed as:

[0087] ;

[0088] in, is the attention factor for the zth detection, represents the concentration change characteristic value detected for the zth time, represents the common scoring factor corresponding to the z-th test, represents the score difference value corresponding to the z-th detection, To preset the second adjustment parameter, Represents the normalization function.

[0089] In this embodiment, the preset second adjustment parameter is introduced into the calculation formula of the attention factor to prevent the denominator from being 0.01. In this embodiment, the preset second adjustment parameter is 0.01. In specific applications, the implementer can set it according to the specific situation. The larger it is, the better the stability of the scoring results of the z-th test of patients with coronary heart disease, that is, the higher the confidence of the scoring sheet of this test, that is, under the same clinical behavior, the greater the score similarity of the scoring sheet, the greater the difference in the partial scores of the scoring sheets of different clinical behaviors, that is, the greater the difference in scores of different behaviors. Therefore, when the concentration change representation value of the z-th test is larger, the smaller the score common factor corresponding to the z-th test, and the smaller the score difference value corresponding to the z-th test, it means that the stability of the patient's scoring sheet is worse, that is, the greater the attention factor of the z-th test, at this time, this test should be given higher attention, and the treatment plan of patients with coronary heart disease should be appropriately adjusted in time.

[0090] So far, the method provided in this embodiment has been used to determine the focus factor for each test during the treatment of patients with coronary heart disease.

[0091] This embodiment takes into account that the existing method determines the degree of attention based on the score sheet of patients with coronary heart disease, does not fully combine the changes in the physiological indicators of patients, cannot effectively reflect the dynamic changes of individual physiological indicators, and has the shortcomings of one-sidedness, staticness, and short-termism, resulting in some patients with coronary heart disease who need attention or adjustment of treatment strategies not receiving attention. This embodiment first analyzes the difference between the deviation degrees of cardiac troponin concentrations of two adjacent tests, and obtains the concentration change characterization value of each test of patients with coronary heart disease, which is used to reflect the degree of change of cardiac troponin concentration of patients at different tests. Then, all tests are clustered based on the concentration change characterization value, and the clustering results are analyzed to obtain the score common factor corresponding to each test. The score common factor is used to In order to reflect the similarity of the scoring sheets of coronary heart disease patients under similar clinical behaviors, the differences in the scoring sheets of patients in different behavior clusters were evaluated according to the differences between the cluster where each test was located and the corresponding scoring results of tests in other clusters. The attention factor of each test of the coronary heart disease patient was further determined by comprehensively combining the concentration change characterization value, the scoring common factor and the scoring difference value. The larger the attention factor, the more abnormal the change of the physiological indicators of the coronary heart disease patient is, and the higher the attention should be given. The method provided in this embodiment can adjust the attention to the patient in real time, reflect the specific fluctuation of the patient's current physiological indicators, overcome the limitations of traditional scoring sheets, and can determine the attention to the patient in real time, so as to facilitate timely and appropriate adjustment of the treatment strategy of the coronary heart disease patient.

[0092] In other embodiments, a device is also provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the method executed by the coronary heart disease risk auxiliary assessment system based on smart medical care. The device can be specifically a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute the method executed by the coronary heart disease risk auxiliary assessment system based on smart medical care provided in the above embodiment.

[0093] In other embodiments, a computer program product is also provided. When the computer program product runs on a computer, the computer executes the above-mentioned related steps to implement the method performed by the coronary heart disease risk auxiliary assessment system based on smart medical care provided in the above-mentioned embodiment.

[0094] In other embodiments, a computer-readable storage medium is also provided, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement the method performed by the coronary heart disease risk auxiliary assessment system based on smart medical care provided in the above-mentioned embodiment.

[0095] Among them, the provided systems, devices, computer program products, and computer-readable storage media are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above and will not be repeated here.

[0096] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A coronary heart disease risk auxiliary assessment system based on smart medical care, comprising a memory and a processor, characterized in that: The processor executes the computer program stored in the memory to implement the following steps: Obtain various clinical physiological indicators of patients with coronary heart disease at each test, including cardiac troponin concentration; Analyze the difference between the deviations of cardiac troponin concentrations between two adjacent tests to obtain a concentration change characterization value for each test; cluster all tests based on the concentration change characterization value; and obtain a common scoring factor corresponding to each test by combining the difference between the scoring results of clinical physiological indicators of each test and its adjacent tests in time and the local density distribution within the cluster where each test is located; Evaluate the difference between the score results of the cluster where each test is located and the scores of the tests in other clusters to obtain the score difference value corresponding to each test; The focus factor for each test is determined by combining the concentration change characterization value, the common scoring factor and the scoring difference value; The step of analyzing the difference between the deviations of cardiac troponin concentrations detected between two adjacent tests to obtain a concentration change characterization value for each test includes: The difference between the deviation degree of the cardiac troponin concentration of the candidate test and the deviation degree of the cardiac troponin concentration of the previous test of the candidate test is used as the concentration change characterization value of the candidate test; The candidate detection is any one detection; Obtaining the degree of deviation of the candidate test cardiac troponin concentration includes: The mean and overall dispersion of all detected cardiac troponin concentrations were calculated; According to the difference between the cardiac troponin concentration of the candidate detection and the mean value and the overall dispersion degree, the deviation degree of the cardiac troponin concentration of the candidate detection is obtained, wherein the difference between the cardiac troponin concentration of the candidate detection and the mean value is positively correlated with the deviation degree, and the overall dispersion degree is negatively correlated with the deviation degree; The clustering of all detections based on the concentration change characterization value comprises: Based on all the concentration change characterization values, the K-means clustering algorithm was used to cluster all the detections to obtain each cluster; The method combines the difference between the scoring results of the clinical physiological indicators of each test and the tests adjacent to it in time and the local density distribution within the cluster where each test is located to obtain the common scoring factor corresponding to each test, including: Obtain the score sheet of clinical physiological indicators for each test; According to the difference between the score matrix of the candidate detection and the next detection adjacent to it in time, a score difference index between the candidate detection and the next detection adjacent to it in time is obtained; wherein the score matrix is ​​composed of data in the score table; Obtaining a score common factor corresponding to the candidate detection according to the difference between the total scores of the candidate detection and other detections in the cluster to which it belongs, the score difference index, and the local reachable density of all data points in the cluster to which the candidate detection belongs, wherein the difference between the total scores and the score difference index are both negatively correlated with the score common factor, and the local reachable density is positively correlated with the score common factor; The step of evaluating the difference between the cluster where each detection is located and the score results corresponding to the detections in other clusters to obtain the score difference value corresponding to each detection includes: Obtaining a score difference value corresponding to the candidate detection according to the difference between the overall scores of all detections in the cluster where the candidate detection is located and the overall scores of detections in other clusters, wherein the difference between the overall scores is positively correlated with the score difference value; According to the difference between the overall scores of all tests in the cluster where the candidate test is located and the overall scores of tests in other clusters, the score difference value corresponding to the candidate test is obtained, including: Calculate the difference between the overall scores of all tests in the cluster where the candidate test is located and the overall scores of the tests in each other cluster respectively, and record it as the first difference between the cluster where the candidate test is located and each other cluster; Calculate the sum of the first differences between the cluster where the candidate detection is located and all other clusters; The normalized result of the sum is used as the score difference value corresponding to the candidate detection; The concentration change characterization value of each test, the common scoring factor corresponding to each test, and the score difference value corresponding to each test are combined to obtain the focus factor of each test, wherein the concentration change characterization value is positively correlated with the score difference value, and the common scoring factor and the score difference value are both negatively correlated with the score difference value; The following formula is used to calculate the deviation of the cardiac troponin concentration detected for the zth time: ; in, Indicates the deviation of the cardiac troponin concentration detected for the zth time, represents the concentration of cardiac troponin detected at the zth time, represents the average of all detected cardiac troponin concentrations, represents the overall dispersion of all detected cardiac troponin concentrations, Indicates the preset first adjustment parameter, Indicates the absolute value sign; The following formula is used to calculate the common scoring factor corresponding to the zth test: ; in, represents the common scoring factor corresponding to the z-th test, Indicates the number of data points in the cluster where the z-th detection is located, represents the total score of the zth test, represents the total score of the cth test except the zth test in the cluster where the zth test is located, It represents the score difference index between the cth detection excluding the zth detection in the cluster where the zth detection is located and the next detection adjacent to it in time. represents the local reachable density of the data points in the cluster where the z-th detection is located, represents an exponential function with a natural constant as base; The score difference value corresponding to the z-th test is calculated using the following formula: ; in, represents the score difference value corresponding to the z-th detection, represents the number of clusters, represents the overall score of all tests in the cluster where the zth test is located, represents the overall score of all tests in the bth cluster except the cluster where the zth test is located; The attention factor of the zth detection is calculated using the following formula: ; in, is the attention factor for the zth detection, represents the concentration change characteristic value detected for the zth time, represents the common scoring factor corresponding to the z-th test, represents the score difference value corresponding to the z-th detection, To preset the second adjustment parameter, Represents the normalization function.

2. The coronary heart disease risk auxiliary assessment system based on smart medical care according to claim 1 is characterized in that: The scoring sheet for clinical physiological indicators tested each time includes 8 major scoring sheets, namely GRACE risk score sheet, TIMI risk score sheet, CRUSADE bleeding score sheet, ACUITY bleeding risk score sheet, DAPT score sheet, China-PAR score sheet, Duke treadmill score sheet and SYNTAX score sheet.

3. The coronary heart disease risk auxiliary assessment system based on smart medical care according to claim 1 is characterized in that: Obtaining the differences between the scoring matrices, including: The difference between two elements at the same position in the two score matrices is calculated, and the average of the differences between the two elements at all positions is taken as the difference between the corresponding two score matrices.