Method, System and Medium for Constructing a Data Classification Model of Coronary Atherosclerosis

Abstract

The present invention discloses a method, system and medium for constructing a data grading model of coronary atherosclerotic heart disease, belonging to the technical field of data analysis. The present invention includes: obtaining the diagnostic records of patients and calculating the comprehensive characteristic values of the diagnostic records; classifying and counting the diagnostic records of all patients, calculating the characteristic thresholds of each type of diagnostic records, and constructing a sclerosis grade model; calculating the characteristic change amount of patients and matching the target patients; obtaining the treatment records of the target patients, generating suggestion information, and improving the sclerosis grade model; according to the real-time diagnostic records of patients and the sclerosis grade model, outputting the sclerosis grade of patients and suggestion information; the present invention can not only make a more accurate and comprehensive assessment according to the diagnostic records of patients, but also recommend appropriate treatment plans for early patients, timely adjust medical intervention measures, and comprehensively improve the diagnosis and treatment effect and the patient health management level.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and specifically relates to a method, system and medium for constructing a coronary atherosclerotic data grading model. Background Art

[0002] Atherosclerosis refers to the deposition of substances such as lipids (such as cholesterol), calcium salts, inflammatory cells and fibrous tissues on the inner wall of arteries, forming plaques, resulting in hardening and narrowing of blood vessels. In severe cases, blood flow will be blocked, thereby affecting the blood supply of organs and tissues. This pathological process is a common form of arteriosclerosis and the main cause of cardiovascular diseases (such as coronary heart disease);

[0003] Existing grading models for atherosclerosis do not perform any invasive operations. Plasma samples of patients are collected, and by measuring the levels of biomarkers (such as cholesteryl sulfate, azelaic acid, tryptophan, etc.) in the plasma, the severity of atherosclerosis is distinguished for grading diagnosis;

[0004] However, grading only by detecting the biomarkers of patients has errors, and at the same time lacks comprehensive analysis of multi-dimensional atherosclerotic data of patients, and cannot accurately reflect the development process of atherosclerosis. Especially for early or mild patients, it cannot provide sufficiently accurate grading information and treatment suggestions;

[0005] Therefore, there is an urgent need for a coronary atherosclerotic data grading model construction system to solve the above problems. Summary of the Invention

[0006] The purpose of the present invention is to provide a method for constructing a coronary atherosclerotic data grading model to solve the problems raised in the above background art.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] A method for constructing a coronary atherosclerotic data grading model, the method includes the following steps:

[0009] S1. Obtain the diagnosis records of patients from the database, extract features from the diagnosis records to obtain the blood sample feature values and image feature values of the diagnosis records, and calculate the comprehensive feature values of the diagnosis records;

[0010] S2. Classify and count all the diagnosis records of patients to obtain the feature intervals of different types of diagnosis records, calculate the feature thresholds of each type of diagnosis record, and construct a sclerosis grade model;

[0011] S3. Screen out all the diagnostic records of a certain patient, calculate the characteristic change amount of this patient, and obtain the sclerosis level of this patient through the sclerosis level model to match the target patient; obtain the treatment records of the target patient, generate suggestion information, and improve the sclerosis level model;

[0012] S4. According to the real-time diagnostic records of the patient and the sclerosis level model, output the sclerosis level and suggestion information of the patient.

[0013] According to the above technical solution, the step S1 includes the following:

[0014] S1-1. Each time a patient undergoes a diagnosis, a diagnostic record is generated and stored in the database; the diagnostic record includes the patient number, diagnosis time, blood sample data, and imaging data;

[0015] S1-2. Extract biomarkers from the blood sample data of a certain diagnostic record. The biomarkers include lipid metabolism markers, inflammatory response markers, endothelial function markers, oxidative stress markers, plaque stability markers, and thrombosis markers; extract the content of each biomarker from the blood sample data of the diagnostic record, and use the formula: , calculate the blood sample characteristic value of this diagnostic record; where B1 represents the blood sample characteristic value of this diagnostic record, and α1 i represents the content weight of the i-th biomarker, and A1 i represents the content of the i-th biomarker;

[0016] The lipid metabolism markers include but are not limited to oxidized low-density lipoprotein and low-density lipoprotein cholesterol. The accumulation of lipid metabolism markers in the arterial wall is likely to form plaques; the inflammatory response markers include but are not limited to interleukin and tumor necrosis factor, which have an important impact on the development of atherosclerosis; the endothelial function markers include but are not limited to endothelin and vascular endothelial cell adhesion molecules, reflecting the impairment of vascular endothelial function and further causing atherosclerosis; the oxidative stress markers include but are not limited to malondialdehyde and superoxide dismutase, reflecting the level of oxidative stress, which plays an important role in the occurrence of atherosclerosis; the plaque stability markers include but are not limited to matrix metalloproteinase and lipoprotein phospholipase, which participate in the degradation of the vascular matrix and affect the formation and stability of plaques; the thrombosis markers include but are not limited to fibrinogen and dimer, which affect thrombosis formation and dissolution. Thrombosis formation is an important complication of atherosclerosis; when calculating the blood sample characteristic value of the diagnostic record, any one of the substances included in each marker is selected as a reference for calculation;

[0017] S1-3. Preprocess the imaging data of a certain diagnostic record. The preprocessing includes denoising, normalization, and contrast enhancement;

[0018] Use the edge detection algorithm to extract the inner wall contour and outer wall contour of the arterial blood vessel in the image data of the diagnostic record, count the pixel points of the inner wall contour of the arterial blood vessel to form an inner wall pixel point set; count the pixel points of the inner wall contour of the arterial blood vessel to form an outer wall pixel point set; select any pixel point in the image data of the diagnostic record, calculate the shortest distance between this pixel point and the inner wall pixel point set, denoted as D1; calculate the shortest distance between this pixel point and the outer wall pixel point set, denoted as D2; use the formula: D = |D1 - D2| to calculate the blood vessel wall thickness of the diagnostic record; where D represents the blood vessel wall thickness of the diagnostic record;

[0019] Use the threshold segmentation algorithm to extract the plaque area of the arterial blood vessel in the image data of the diagnostic record, count the total number of pixels in the plaque area of the arterial blood vessel in the image data of the diagnostic record, denoted as N; use the formula: S = N×V to calculate the plaque area of the diagnostic record; where S represents the plaque area of the diagnostic record, and V represents the actual physical area corresponding to each pixel in the image data of the diagnostic record;

[0020] The edge detection algorithm and the threshold segmentation algorithm are widely used in the analysis of medical images; the actual physical area corresponding to each pixel in the image data is determined by the spatial resolution; the spatial resolution refers to the size of each pixel in the actual physical space, which is set by the image acquisition device;

[0021] Use the formula: B2 = α2×D + α3×S to calculate the image feature value of the diagnostic record; where B2 represents the image feature value of the diagnostic record, α2 represents the weight of the blood vessel wall thickness, and α3 represents the weight of the plaque area;

[0022] The blood vessel wall thickness is one of the important indicators for evaluating atherosclerosis. The thickened blood vessel wall is often an early manifestation of atherosclerosis. Atherosclerosis is usually accompanied by the deposition of lipids, calcium, and fibrous tissue on the inner wall of the blood vessel, forming plaques. The plaque area is related to the severity of atherosclerosis. Larger plaques usually mean more severe lesions, which may lead to blood vessel stenosis or even complete occlusion; taking the blood vessel wall thickness and plaque area together with the blood sample characteristics as the detection conditions for atherosclerosis makes the grading result more accurate and comprehensive;

[0023] S1-4. Use the formula: C = β×B1 + (1 - β)×B2 to calculate the comprehensive feature value of the diagnostic record; where C represents the comprehensive feature value of the diagnostic record, and β represents the adjustment parameter.

[0024] According to the above technical solution, the step S2 includes the following:

[0025] S2-1. By performing expert annotation on the diagnostic records of patients, the diagnostic records are classified into different types, including mild sclerosis records, moderate sclerosis records, and severe sclerosis records;

[0026] Expert annotation refers to the process of a domain expert marking, classifying, or annotating data according to their own experience standards and requirements; it is widely used in machine learning and data analysis to further improve the training accuracy of the model;

[0027] S2-2. Statistically determine the minimum value of the comprehensive feature values corresponding to all diagnostic records of a certain type as the minimum value of the feature interval corresponding to the diagnostic records of this type; statistically determine the maximum value of the comprehensive feature values corresponding to all diagnostic records of a certain type as the maximum value of the feature interval corresponding to the diagnostic records of this type;

[0028] S2-3. Take the minimum value of the feature interval corresponding to the diagnostic records of the mild sclerosis record type as the first threshold; statistically count all diagnostic records whose comprehensive feature values are between the maximum value of the feature interval corresponding to the diagnostic records of the mild sclerosis record type and the minimum value of the feature interval corresponding to the diagnostic records of the moderate sclerosis record type and calculate the average value of the corresponding comprehensive feature values as the second threshold; statistically count all diagnostic records whose comprehensive feature values are between the maximum value of the feature interval corresponding to the diagnostic records of the moderate sclerosis record type and the minimum value of the feature interval corresponding to the diagnostic records of the severe sclerosis record type and calculate the average value of the corresponding comprehensive feature values as the third threshold;

[0029] Take the obtained first threshold, second threshold, and third threshold as the feature thresholds;

[0030] Calculate the feature thresholds based on the comprehensive feature values and the types of diagnostic records, providing a basis for model construction;

[0031] S2-4. Construct a sclerosis level model as follows: Patients with comprehensive feature values corresponding to diagnostic records less than the first threshold are in the first level of sclerosis; patients with comprehensive feature values corresponding to diagnostic records greater than or equal to the first threshold and less than the second threshold are in the second level of sclerosis; patients with comprehensive feature values corresponding to diagnostic records greater than or equal to the second threshold and less than the third threshold are in the third level of sclerosis; patients with comprehensive feature values corresponding to diagnostic records greater than or equal to the third threshold are in the fourth level of sclerosis;

[0032] Take the first level of sclerosis, the second level of sclerosis, the third level of sclerosis, and the fourth level of sclerosis as the sclerosis levels;

[0033] Among them, the first sclerosis level indicates that the patient does not have atherosclerosis.

[0034] According to the above technical solution, the step S3 includes the following:

[0035] S3-1. According to the patient number and diagnosis time in the diagnosis record, screen out all the diagnosis records of a certain patient and sort them in ascending order of the diagnosis time; calculate the average value of the difference between the comprehensive feature value corresponding to the latter diagnosis record and the comprehensive feature value corresponding to the former diagnosis record in all adjacent diagnosis records of this patient, as the feature change amount of this patient;

[0036] Input the comprehensive feature value corresponding to each diagnosis record of this patient into the sclerosis grade model, and through the sclerosis grade model, output the sclerosis grade of this patient in each diagnosis record;

[0037] S3-2. If the feature change amount of a certain patient is less than zero, and the sclerosis grade of this patient is all the second-stage sclerosis, then regard this patient as the target patient;

[0038] S3-3. Obtain the drug dosage, drug treatment course, diet control, exercise plan and psychological assistance treatment course of the target patient from the database, as the treatment record of the target patient;

[0039] Take the absolute value of the feature change amount corresponding to all target patients, screen out the target patient with the largest absolute value of the corresponding feature change amount, and use the treatment record of this patient as the recommended information;

[0040] Use the recommended information as the recommended information for the second-stage sclerosis;

[0041] In the early stage, atherosclerosis usually manifests as lipid deposition on the blood vessel wall and the formation of small plaques. At this time, the blood vessel wall thickens but is not severely stenosed; at this time, atherosclerosis can be effectively controlled and even reversed through lifestyle changes and drug treatment; by screening target patients and generating recommended information, treatment recommendations are provided for the treatment of early or mild patients.

[0042] According to the above technical solution, the step S4 includes the following:

[0043] According to the real-time diagnosis record of the patient, calculate the comprehensive feature value corresponding to the real-time diagnosis record of the patient, and input it into the sclerosis grade model. The sclerosis grade model outputs the sclerosis grade of the patient. If the patient is in the second sclerosis grade, the recommended information is also output at the same time.

[0044] A coronary atherosclerosis data grading model construction system, which includes an information collection module, an information processing module and an execution module;

[0045] The information collection module is used to collect the information required by the system; the information processing module is used to store, analyze and transmit the information of each module; the execution module is used to execute the information of the information processing module.

[0046] According to the above technical solution, the information collection module includes a diagnosis record unit and a treatment record unit;

[0047] The diagnostic record unit is used to collect the diagnostic records of patients; the treatment record unit is used to collect the treatment records of patients.

[0048] According to the above technical solution, the information processing module includes an information storage unit, an information analysis unit, and an information transmission unit;

[0049] The information storage unit is used to store the information obtained by the information acquisition module; the information analysis unit is used to analyze the information obtained by the information acquisition module; the information transmission unit is used for information transmission among various modules in the system.

[0050] According to the above technical solution, the execution module includes a visualization unit and a push unit;

[0051] The visualization unit is used to form visualization data of the sclerosis level and recommended information of the patient; the push unit is used to push the sclerosis level and recommended information of the patient.

[0052] A medium for constructing a coronary atherosclerotic data grading model, which includes a data storage medium for storing data.

[0053] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0054] The present invention realizes accurate disease grading by monitoring and analyzing data such as the historical diagnostic records and real-time diagnostic records of patients with coronary atherosclerotic heart disease, and optimizes the early treatment plan in real time by analyzing the characteristic changes of patients; the present invention can not only evaluate more accurately and comprehensively according to the diagnostic records of patients, but also recommend appropriate treatment plans for early patients, adjust medical intervention measures in a timely manner, and comprehensively improve the diagnosis and treatment effect and the level of patient health management. Description of the Drawings

[0055] The drawings are used to provide further understanding of the present invention, and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0056] Figure 1 is a schematic flowchart of the method for constructing a coronary atherosclerotic data grading model of the present invention;

[0057] Figure 2 is a schematic structural diagram of the system for constructing a coronary atherosclerotic data grading model of the present invention. Detailed Embodiments

[0058] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0059] Please refer to Figure 1 , the present invention provides a technical solution:

[0060] A method for constructing a coronary artery atherosclerosis data grading model, the method comprising the following steps:

[0061] S1. Obtain the diagnostic records of patients from the database, extract features from the diagnostic records, obtain the blood sample feature values and image feature values of the diagnostic records, and calculate the comprehensive feature values of the diagnostic records;

[0062] According to the above technical solution, the step S1 includes the following:

[0063] S1-1. Each time a patient undergoes a diagnosis, a diagnostic record is generated and stored in the database; the diagnostic record includes the patient number, diagnosis time, blood sample data, and image data;

[0064] S1-2. Extract biomarkers from the blood sample data of a certain diagnostic record, the biomarkers including lipid metabolism markers, inflammatory response markers, endothelial function markers, oxidative stress markers, plaque stability markers, and thrombosis markers; extract the contents of each biomarker from the blood sample data of the diagnostic record, and use the formula: , calculate the blood sample feature value of the diagnostic record; where B1 represents the blood sample feature value of the diagnostic record, and α1 i represents the content weight of the i-th biomarker, and A1 i represents the content of the i-th biomarker;

[0065] Lipid metabolism markers include, but are not limited to, oxidized low-density lipoprotein and low-density lipoprotein cholesterol. The accumulation of lipid metabolism markers in the arterial wall easily forms plaques. Inflammatory response markers include, but are not limited to, interleukin and tumor necrosis factor, which have an important impact on the development of atherosclerosis. Endothelial function markers include, but are not limited to, endothelin and vascular endothelial cell adhesion molecule, reflecting the impairment of vascular endothelial function and further causing atherosclerosis. Oxidative stress markers include, but are not limited to, malondialdehyde and superoxide dismutase, reflecting the level of oxidative stress, which plays an important role in the occurrence of atherosclerosis. Plaque stability markers include, but are not limited to, matrix metalloproteinase and lipoprotein phospholipase, which participate in the degradation of the vascular matrix and affect the formation and stability of plaques. Thrombosis markers include, but are not limited to, fibrinogen and dimer, which affect thrombosis formation and dissolution. Thrombosis is an important complication of atherosclerosis. When calculating the blood sample characteristic values of the diagnostic record, any one substance included in each marker is selected as a reference for calculation;

[0066] S1-3. Preprocess the image data of a certain diagnostic record, and the preprocessing includes denoising, normalization, and contrast enhancement;

[0067] Use an edge detection algorithm to extract the inner wall contour and outer wall contour of the arterial blood vessel in the image data of the diagnostic record, count the pixel points of the inner wall contour of the arterial blood vessel to form an inner wall pixel point set; count the pixel points of the inner wall contour of the arterial blood vessel to form an outer wall pixel point set; select any pixel point in the image data of the diagnostic record, calculate the shortest distance between this pixel point and the inner wall pixel point set, denoted as D1; calculate the shortest distance between this pixel point and the outer wall pixel point set, denoted as D2; use the formula: D = |D1 - D2| to calculate the blood vessel wall thickness of the diagnostic record; where D represents the blood vessel wall thickness of the diagnostic record;

[0068] Use a threshold segmentation algorithm to extract the plaque area of the arterial blood vessel in the image data of the diagnostic record, count the total number of pixels in the plaque area of the arterial blood vessel in the image data of the diagnostic record, denoted as N; use the formula: S = N × V to calculate the plaque area of the diagnostic record; where S represents the plaque area of the diagnostic record, and V represents the actual physical area corresponding to each pixel in the image data of the diagnostic record;

[0069] Edge detection algorithms and threshold segmentation algorithms are widely used in the analysis of medical images; the actual physical area corresponding to each pixel in the image data is determined by the spatial resolution; the spatial resolution refers to the size of each pixel in the actual physical space, which is set by the image acquisition device;

[0070] Calculate the image feature value of the diagnostic record using the formula: B2 = α2×D + α3×S; where B2 represents the image feature value of the diagnostic record, α2 represents the weight of the blood vessel wall thickness, and α3 represents the weight of the plaque area.

[0071] The blood vessel wall thickness is one of the important indicators for evaluating atherosclerosis. The thickened blood vessel wall is often an early manifestation of atherosclerosis. Atherosclerosis usually occurs with the deposition of lipids, calcium, and fibrous tissue on the inner wall of the blood vessel, forming plaques. The plaque area is related to the severity of atherosclerosis. Larger plaques usually mean more severe lesions, which may lead to blood vessel stenosis or even complete occlusion. Using the blood vessel wall thickness and plaque area together with blood sample characteristics as the detection conditions for atherosclerosis makes the grading results more accurate and comprehensive.

[0072] S1-4. Calculate the comprehensive feature value of the diagnostic record using the formula: C = β×B1 + (1 - β)×B2; where C represents the comprehensive feature value of the diagnostic record, and β represents the adjustment parameter.

[0073] S2. Classify and count the diagnostic records of all patients to obtain the feature intervals of different types of diagnostic records, calculate the feature thresholds for each type of diagnostic record, and construct a sclerosis grade model.

[0074] According to the above technical solution, step S2 includes the following:

[0075] S2-1. Divide the diagnostic records into different types by expert annotation of the patients' diagnostic records. The types include mild sclerosis records, moderate sclerosis records, and severe sclerosis records.

[0076] Expert annotation refers to the process of marking, classifying, or annotating data by experts in this field according to their own experience standards and requirements. It is widely used in machine learning and data analysis, aiming to further improve the training accuracy of the model.

[0077] S2-2. Statistically calculate the minimum value of the comprehensive feature values corresponding to all diagnostic records of a certain type as the minimum value of the feature interval corresponding to this type of diagnostic record. Statistically calculate the maximum value of the comprehensive feature values corresponding to all diagnostic records of a certain type as the maximum value of the feature interval corresponding to this type of diagnostic record.

[0078] S2-3. Take the minimum value of the corresponding characteristic interval of the diagnostic record with the type of mild sclerosis as the first threshold; count all the diagnostic records whose comprehensive characteristic values are between the maximum value of the corresponding characteristic interval of the diagnostic record with the type of mild sclerosis and the minimum value of the corresponding characteristic interval of the diagnostic record with the type of moderate sclerosis, and calculate the average value of the corresponding comprehensive characteristic values as the second threshold; count all the diagnostic records whose comprehensive characteristic values are between the maximum value of the corresponding characteristic interval of the diagnostic record with the type of moderate sclerosis and the minimum value of the corresponding characteristic interval of the diagnostic record with the type of severe sclerosis, and calculate the average value of the corresponding comprehensive characteristic values as the third threshold.

[0079] Take the obtained first threshold, second threshold and third threshold as the characteristic thresholds.

[0080] For example:

[0081] The corresponding characteristic interval of the diagnostic record with the type of mild sclerosis is [30, 60], the corresponding characteristic interval of the diagnostic record with the type of moderate sclerosis is [40, 70], and the corresponding characteristic interval of the diagnostic record with the type of severe sclerosis is [80, 85]; take the minimum value of the corresponding characteristic interval of the diagnostic record with the type of mild sclerosis as the first threshold, and the first threshold is 30; there are 5 diagnostic records whose comprehensive characteristic values are between the maximum value of the corresponding characteristic interval of the diagnostic record with the type of mild sclerosis and the minimum value of the corresponding characteristic interval of the diagnostic record with the type of moderate sclerosis, and the corresponding comprehensive characteristic values are 40, 40, 50, 60, 60 respectively, and calculate the average value of the corresponding comprehensive characteristic values as 50 as the second threshold, and the second threshold is 30; there are 3 diagnostic records whose comprehensive characteristic values are between the maximum value of the corresponding characteristic interval of the diagnostic record with the type of moderate sclerosis and the minimum value of the corresponding characteristic interval of the diagnostic record with the type of severe sclerosis, and the corresponding comprehensive characteristic values are 70, 75, 80 respectively, and calculate the average value of the corresponding comprehensive characteristic values as 75 as the third threshold, and the third threshold is 75.

[0082] Calculate the characteristic thresholds according to the comprehensive characteristic values and the types of diagnostic records, providing a construction basis for model construction.

[0083] S2-4. Construct a sclerosis level model as follows: Patients whose comprehensive characteristic values corresponding to the diagnostic records are less than the first threshold are in the first stage of sclerosis; patients whose comprehensive characteristic values corresponding to the diagnostic records are greater than or equal to the first threshold and less than the second threshold are in the second stage of sclerosis; patients whose comprehensive characteristic values corresponding to the diagnostic records are greater than or equal to the second threshold and less than the third threshold are in the third stage of sclerosis; patients whose comprehensive characteristic values corresponding to the diagnostic records are greater than or equal to the third threshold are in the fourth stage of sclerosis.

[0084] Take the first - stage hardening, second - stage hardening, third - stage hardening, and fourth - stage hardening as the hardening levels; among them, the first hardening level indicates that the patient has no atherosclerosis.

[0085] S3. Screen all the diagnostic records of a certain patient, calculate the characteristic change amount of the patient, and obtain the hardening level of the patient through the hardening level model to match the target patient; obtain the treatment records of the target patient, generate advice information, and improve the hardening level model.

[0086] According to the above - mentioned technical solution, step S3 includes the following:

[0087] S3 - 1. According to the patient number and diagnosis time in the diagnostic records, screen all the diagnostic records of a certain patient and sort them in ascending order of diagnosis time; calculate the average value of the difference between the comprehensive characteristic value corresponding to the latter diagnostic record and the comprehensive characteristic value corresponding to the former diagnostic record in all adjacent diagnostic records of the patient as the characteristic change amount of the patient.

[0088] Input the comprehensive characteristic value corresponding to each diagnostic record of the patient into the hardening level model, and output the hardening level of the patient in each diagnostic record through the hardening level model.

[0089] For example:

[0090] The comprehensive characteristic values corresponding to the diagnostic records of a certain patient are 40, 38, 35; the comprehensive characteristic values corresponding to the adjacent diagnostic records of the patient are 40 and 38, where the comprehensive characteristic value corresponding to the latter diagnostic record in the adjacent diagnostic records is 38 and the comprehensive characteristic value corresponding to the former diagnostic record is 40; the comprehensive characteristic values corresponding to the adjacent diagnostic records of the patient are 38 and 35, where the comprehensive characteristic value corresponding to the latter diagnostic record in the adjacent diagnostic records is 35 and the comprehensive characteristic value corresponding to the former diagnostic record is 38; calculate the average value of the difference between the comprehensive characteristic value corresponding to the latter diagnostic record and the comprehensive characteristic value corresponding to the former diagnostic record in all adjacent diagnostic records of the patient as [(38 - 40)+(35 - 38)] / 2=-2.5.

[0091] S3 - 2. If the characteristic change amount of a certain patient is less than zero and the hardening levels of the patient are all second - stage hardening, then take this patient as the target patient.

[0092] S3 - 3. Obtain the drug dosage, drug treatment course, diet control, exercise plan, and psychological assistance treatment course of the target patient from the database as the treatment records of the target patient.

[0093] Take the absolute values of the characteristic change amounts corresponding to all target patients, screen out the target patient with the largest absolute value of the corresponding characteristic change amount, and take the treatment records of this patient as the advice information.

[0094] Take the recommended information as the recommended information for secondary hardening;

[0095] In the early stage, atherosclerosis usually presents as lipid deposition on the blood vessel wall and the formation of small plaques. At this time, the blood vessel wall thickens but is not severely stenosed. At this point, atherosclerosis can be effectively controlled and even reversed through lifestyle changes and drug treatment. By screening target patients and generating recommended information, treatment recommendations are provided for the treatment of early or mild patients.

[0096] S4. According to the patient's real-time diagnosis record and the hardening level model, output the patient's hardening level and recommended information;

[0097] According to the above technical solution, step S4 includes the following:

[0098] According to the patient's real-time diagnosis record, calculate the comprehensive characteristic value corresponding to the patient's real-time diagnosis record, and input it into the hardening level model. The hardening level model outputs the patient's hardening level. If the patient is in the second hardening level, recommended information is also output.

[0099] Please refer to Figure 2 , the coronary atherosclerotic data grading model construction system, which includes an information collection module, an information processing module, and an execution module;

[0100] The information collection module is used to collect the information required by the system; the information processing module is used to store, analyze, and transmit the information of each module; the execution module is used to execute the information of the information processing module.

[0101] According to the above technical solution, the information collection module includes a diagnosis record unit and a treatment record unit;

[0102] The diagnosis record unit is used to collect the patient's diagnosis record; the treatment record unit is used to collect the patient's treatment record.

[0103] According to the above technical solution, the information processing module includes an information storage unit, an information analysis unit, and an information transmission unit;

[0104] The information storage unit is used to store the information obtained by the information collection module; the information analysis unit is used to analyze the information obtained by the information collection module; the information transmission unit is used for the information transmission of each module in the system.

[0105] According to the above technical solution, the execution module includes a visualization unit and a push unit;

[0106] The visualization unit is used to form visualization data of the patient's hardening level and recommended information; the push unit is used to push the patient's hardening level and recommended information.

[0107] Medium for constructing a data grading model for coronary atherosclerotic heart disease, the medium including a data storage medium for storing data.

[0108] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0109] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for constructing a coronary atherosclerotic data grading model, characterized in that: The method includes the following steps: S1-1. Each time a patient undergoes a diagnosis, a diagnosis record is generated and stored in the database; the diagnosis record includes the patient number, diagnosis time, blood sample data, and imaging data. S1-2. Extract biomarkers from the blood sample data of a certain diagnostic record, where the biomarkers include lipid metabolism markers, inflammatory response markers, endothelial function markers, oxidative stress markers, plaque stability markers, and thrombosis markers; extract the content of each biomarker from the blood sample data of the diagnostic record, and use the formula: , calculate the blood sample characteristic value of this diagnostic record; where B1 represents the blood sample characteristic value of this diagnostic record, and α1 i represents the content weight of the i-th biomarker, and A1 i represents the content of the i-th biomarker. S1-3. Preprocess the imaging data of a certain diagnosis record, and the preprocessing includes denoising, normalization, and contrast enhancement. Use an edge detection algorithm to extract the inner wall contour and outer wall contour of the arterial blood vessel in the imaging data of the diagnosis record, count the pixel points of the inner wall contour of the arterial blood vessel to form an inner wall pixel point set; count the pixel points of the inner wall contour of the arterial blood vessel to form an outer wall pixel point set; select any pixel point in the imaging data of the diagnosis record, calculate the shortest distance between this pixel point and the inner wall pixel point set, denoted as D1; calculate the shortest distance between this pixel point and the outer wall pixel point set, denoted as D2; use the formula: D = |D1 - D2| to calculate the blood vessel wall thickness of this diagnosis record; where D represents the blood vessel wall thickness of this diagnosis record. Use a threshold segmentation algorithm to extract the plaque area of the arterial blood vessel in the imaging data of the diagnosis record, count the total number of pixels in the plaque area of the arterial blood vessel in the imaging data of this diagnosis record, denoted as N; use the formula: S = N×V to calculate the plaque area of this diagnosis record; where S represents the plaque area of this diagnosis record, and V represents the actual physical area corresponding to each pixel in the imaging data of this diagnosis record. Use the formula: B2 = α2×D + α3×S to calculate the imaging feature value of this diagnosis record; where B2 represents the imaging feature value of this diagnosis record, α2 represents the weight of the blood vessel wall thickness, and α3 represents the weight of the plaque area. S1-4. Use the formula: C = β×B1 + (1 - β)×B2 to calculate the comprehensive feature value of this diagnosis record; where C represents the comprehensive feature value of this diagnosis record, and β represents the adjustment parameter. S2. Classify and count the diagnosis records of all patients to obtain the feature intervals of different types of diagnosis records, calculate the feature thresholds of each type of diagnosis record, and construct a sclerosis grade model. S3. Screen out all the diagnosis records of a certain patient, calculate the feature change amount of this patient, and obtain the sclerosis grade of this patient through the sclerosis grade model to match the target patient; obtain the treatment record of the target patient, generate a suggestion message, and improve the sclerosis grade model. S4. Output the sclerosis grade and suggestion message of the patient according to the real-time diagnosis record of the patient and the sclerosis grade model.

2. The method for constructing a coronary atherosclerotic data grading model according to claim 1, characterized in that: The step S2 includes the following: S2-1. By expert annotation of the diagnosis records of patients, divide the diagnosis records into different types, and the types include mild sclerosis records, moderate sclerosis records, and severe sclerosis records. S2-2. Statistically, the minimum value of the comprehensive feature values corresponding to all diagnosis records of a certain type is used as the minimum value of the feature interval corresponding to this type of diagnosis record; the maximum value of the comprehensive feature values corresponding to all diagnosis records of a certain type is used as the maximum value of the feature interval corresponding to this type of diagnosis record. S2-3. Take the minimum value of the corresponding characteristic interval of the diagnostic record with the type of mild sclerosis as the first threshold; count all the diagnostic records whose comprehensive characteristic values are between the maximum value of the corresponding characteristic interval of the diagnostic record with the type of mild sclerosis and the minimum value of the corresponding characteristic interval of the diagnostic record with the type of moderate sclerosis, and calculate the average value of the corresponding comprehensive characteristic values as the second threshold; count all the diagnostic records whose comprehensive characteristic values are between the maximum value of the corresponding characteristic interval of the diagnostic record with the type of moderate sclerosis and the minimum value of the corresponding characteristic interval of the diagnostic record with the type of severe sclerosis, and calculate the average value of the corresponding comprehensive characteristic values as the third threshold. Take the obtained first threshold, second threshold, and third threshold as the characteristic thresholds. S2-4. Construct a sclerosis level model as follows: For a patient whose comprehensive characteristic value corresponding to the diagnostic record is less than the first threshold, the patient is at the first level of sclerosis; for a patient whose comprehensive characteristic value corresponding to the diagnostic record is greater than or equal to the first threshold and less than the second threshold, the patient is at the second level of sclerosis; for a patient whose comprehensive characteristic value corresponding to the diagnostic record is greater than or equal to the second threshold and less than the third threshold, the patient is at the third level of sclerosis; for a patient whose comprehensive characteristic value corresponding to the diagnostic record is greater than or equal to the third threshold, the patient is at the fourth level of sclerosis. Take the first level of sclerosis, the second level of sclerosis, the third level of sclerosis, and the fourth level of sclerosis as the sclerosis levels.

3. The method for constructing a coronary atherosclerotic data grading model according to claim 2, wherein: The steps of S3 are as follows: S3-1. According to the patient number and diagnosis time in the diagnostic record, screen out all the diagnostic records of a certain patient and sort them in ascending order of diagnosis time; calculate the average value of the difference between the comprehensive characteristic value of the latter diagnostic record and the comprehensive characteristic value of the former diagnostic record in all adjacent diagnostic records of the patient as the characteristic change amount of the patient. Input the comprehensive characteristic value corresponding to each diagnostic record of the patient into the sclerosis level model, and through the sclerosis level model, output the sclerosis level of the patient in each diagnostic record. S3-2. If the characteristic change amount of a certain patient is less than zero and the sclerosis levels of the patient are all at the second level of sclerosis, then take this patient as the target patient. S3-3. Obtain the drug dosage, drug treatment course, diet control, exercise plan, and psychological assistance treatment course of the target patient from the database as the treatment record of the target patient. Take the absolute value of the characteristic change amount of all target patients, screen out the target patient with the largest absolute value of the corresponding characteristic change amount, and take the treatment record of this patient as the recommended information. Take the recommended information as the recommended information for the second level of sclerosis.

4. The method for constructing a coronary atherosclerotic data grading model according to claim 3, wherein: The steps of S4 are as follows: According to the real-time diagnostic record of the patient, calculate the comprehensive characteristic value corresponding to the real-time diagnostic record of the patient and input it into the sclerosis level model. The sclerosis level model outputs the sclerosis level of the patient. If the patient is at the second sclerosis level, the recommended information is also output.

5. Coronary atherosclerotic data grading model construction system, which is used to implement the coronary atherosclerotic data grading model construction method described in any one of claims 1-4, characterized in that: The system includes an information collection module, an information processing module, and an execution module. The information collection module is used to collect the information required by the system; the information processing module is used to store, analyze, and transmit the information of each module; the execution module is used to execute the information of the information processing module.

6. The coronary atherosclerotic data grading model construction system according to claim 5, characterized in that: The information collection module includes a diagnostic record unit and a treatment record unit. The diagnosis record unit is used to collect the diagnosis records of patients; the treatment record unit is used to collect the treatment records of patients.

7. The coronary atherosclerotic data grading model construction system according to claim 5, characterized in that: The information processing module includes an information storage unit, an information analysis unit, and an information transmission unit; The information storage unit is used to store the information obtained by the information acquisition module; the information analysis unit is used to analyze the information obtained by the information acquisition module; the information transmission unit is used for information transmission among various modules in the system.

8. The coronary atherosclerotic data grading model construction system according to claim 5, wherein: The execution module includes a visualization unit and a push unit; The visualization unit is used to form visualization data of the sclerosis grade and recommended information of the patient; the push unit is used to push the sclerosis grade and recommended information of the patient.

9. Medium for constructing a coronary atherosclerotic data grading model, which is used to implement the method for constructing a coronary atherosclerotic data grading model described in any one of claims 1-4, characterized in that: This medium includes a data storage medium for storing data.

Images