A serum differential polypeptide detection system for rheumatic valvular disease

Abstract

The application discloses a serum differential polypeptide detection system for rheumatic valvular disease, comprising a data acquisition module, a data cleaning module, a clinical evaluation module, a correlation analysis module and a detection quality evaluation module, and provides an evaluation mechanism for clinical indexes of rheumatic valvular disease patients. The application carries out data mining on the basis of polypeptide detection historical data of the rheumatic valvular disease patients received by a hospital, forms a personalized serum differential polypeptide detection label, correlates the serum differential polypeptide detection label with clinical indexes of the rheumatic valvular disease patients, judges the clinical index sample set of the extracted rheumatic valvular disease patients by using the serum differential polypeptide detection label, evaluates the polypeptide fingerprint detection quality in combination with historical diagnosis results of doctors, and judges the consistency of the serum differential polypeptide detection label and the diagnosis results in the overall historical data.

Description

TECHNICAL FIELD

[0001] The application relates to a serum differential polypeptide detection system for rheumatic valvular disease and belongs to the technical field of serum polypeptide detection. BACKGROUND

[0002] Rheumatic valvular disease is a frequently-occurring disease in valvular heart disease, and valve replacement is the main means for treating rheumatic valvular disease at present. Abnormal left ventricular heart function is one of the most common symptoms of rheumatic valvular disease in clinic. The patient clinically shows that the heart rate is higher than the normal value of the heart rate, the left atrial diameter, the left ventricular end-diastolic diameter and the left ventricular end-systolic diameter are obviously higher than the healthy value, the ejection fraction and the fractional shortening are obviously lower than the healthy value, and the serum BNP level is obviously higher than the healthy value. For the patient combined with atrial fibrillation, the detection of multiple endogenous polypeptide components can positively affect the state evaluation of the patient's condition and heart function and the selection of intervention treatment methods. The serum differential polypeptide is obtained by detecting differential polypeptide fragments in blood and can help find potential molecular markers of some diseases in blood, thereby providing a data basis and basis for disease screening and diagnosis. Therefore, for the serum polypeptide detection of rheumatic valvular disease patients, screening out the significantly different polypeptides and performing quality evaluation on the polypeptides have important significance for the clinical evaluation of rheumatic valvular disease patients. Studies have shown that a high-efficiency reverse non-labeled quantitative liquid chromatography-mass spectrometry method can effectively perform non-labeled quantitative analysis on the polypeptides in the serum specimen of the patient, and there are obvious statistical differences in multiple protein-related polypeptides between the rheumatic valvular disease patients and the patients with healthy heart function. The polypeptides include protein-related polypeptides from histone H2B, villin-like protein, complement family c4-b and sperm domain protein.

[0003] In existing polypeptidomics research, polypeptide fingerprint patterns with significant differences between healthy groups and patient groups are screened out, and the polypeptide fingerprint patterns are used to mark rheumatic valve disease, without combining the actual clinical manifestations of rheumatic valve disease of patients to evaluate the detection quality of serum differential polypeptide detection, which is not conducive to doctors to make scientific and accurate clinical evaluation of rheumatic valve disease of patients according to polypeptide fingerprint patterns. In view of the above problems, the present application provides a serum differential polypeptide detection system for rheumatic valve disease, which is based on polypeptide detection historical data of rheumatic valve disease patients received by a hospital, starts from the differential polypeptide fingerprint pattern, forms a personalized serum differential polypeptide detection label, and forms a correlation between the serum differential polypeptide detection label and the clinical indicators of rheumatic valve disease of patients, uses the serum differential polypeptide detection label to judge the clinical indicator sample set of the extracted rheumatic valve disease patients, compares the historical diagnosis results of doctors, evaluates the detection quality of the polypeptide fingerprint pattern, judges the consistency between the serum differential polypeptide detection label and the diagnosis results in the overall historical data, and thus scientifically evaluates the rheumatic valve disease of patients according to different serum differential polypeptide labels, further improves the targeting of serum differential polypeptide detection of rheumatic valve disease patients, and helps to improve the accuracy and scientificity of clinical evaluation of doctors on the disease condition of patients. SUMMARY

[0004] The main purpose of the present application is to solve the problem that in existing polypeptidomics research, polypeptide fingerprint patterns with significant differences between healthy groups and patient groups are screened out, and the polypeptide fingerprint patterns are used to mark rheumatic valve disease, without combining the actual clinical manifestations of rheumatic valve disease of patients to evaluate the detection quality of serum differential polypeptide detection, which is not conducive to doctors to make scientific and accurate clinical evaluation of rheumatic valve disease of patients according to polypeptide fingerprint patterns, and a serum differential polypeptide detection system for rheumatic valve disease is provided.

[0005] The object of the present application can be achieved by adopting the following technical solutions:

[0006] A serum differential polypeptide detection system for rheumatic valvular disease comprises a data acquisition module, a data cleaning module, a clinical evaluation module, a correlation analysis module and a detection quality evaluation module, the clinical evaluation module uses a heart rate evaluation value positively correlated with the difference between the patient's heart rate and the normal value to evaluate the difference between the patient's heart rate and the normal heart rate value, uses a heart diastolic index positively correlated with the difference between the patient's left ventricular internal diameter, left ventricular end diastolic internal diameter and left ventricular end systolic internal diameter and the normal value to evaluate the difference between the patient and the normal heart diastolic data, uses a heart systolic evaluation index negatively correlated with the difference between the patient's ejection fraction, fractional shortening and the normal value to evaluate the difference between the patient's heart ejection and contraction and the normal value, and uses a serum BNP evaluation index positively correlated with the difference between the patient's serum BNP level and the normal value to evaluate the difference between the patient's serum BNP level and the normal value, the evaluation mechanism of the heart rate evaluation value, the heart diastolic index, the heart systolic evaluation index and the serum BNP evaluation index is as follows:

[0007] The evaluation formula of the heart rate evaluation value is:

[0008]

[0009] In the formula, I hr is the heart rate evaluation value, α1 is the heart rate adjustment coefficient, R h is the difference between the patient's heart rate and the normal value;

[0010] The evaluation formula of the heart diastolic index is:

[0011]

[0012] In the formula, I sz is the heart diastolic index, r1 is the difference between the patient's left ventricular internal diameter and the normal value, r2 is the difference between the patient's left ventricular end diastolic internal diameter and the normal value, r3 is the difference between the left ventricular end systolic internal diameter and the normal value, and α2 is the heart diastolic adjustment coefficient;

[0013] The evaluation formula of the heart systolic evaluation index is:

[0014] I ss = -α3(100k ef +log510k FS )+2;

[0015] In the formula, I ss is the heart systolic evaluation index, k ef is the patient's ejection fraction, α3 is the ejection fraction adjustment coefficient, and k FS is the patient's left ventricular short axis fractional shortening;

[0016] The evaluation formula of the serum BNP evaluation index is:

[0017]

[0018] I BNP is the serum BNP evaluation index, BNP is the serum BNP level of the patient, and a4 is the serum BNP adjustment coefficient.

[0019] As a further scheme of the present application, the clinical evaluation module takes the weighted sum of the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index, and the serum BNP evaluation index as the comprehensive evaluation index, the weights of the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index, and the serum BNP evaluation index are 0.25, 0.25, 0.25, and 0.25 respectively, and the evaluation mechanism of the comprehensive evaluation index is:

[0020] I Z = 0.25I hr + 0.25I sz + 0.25I ss + 0.25I BNP ;

[0021] I Z is the comprehensive evaluation index of the patient.

[0022] As a further scheme of the present application, the heart rate adjustment coefficients a1 and a2, the cardiac diastolic adjustment coefficient a3, the ejection fraction adjustment coefficient a4, and the serum BNP adjustment coefficient a4 in the evaluation mechanism of the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index, and the serum BNP evaluation index of the clinical evaluation module are obtained by training the historical data in the hospital patient detection database, so as to narrow the order of magnitude difference between the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index, and the serum BNP evaluation index.

[0023] As a further scheme of the present application, the data acquisition module uses data mining technology to mine the clinical detection heart rate, left ventricular internal diameter, left ventricular end-diastolic internal diameter, left ventricular end-systolic internal diameter, ejection fraction, left ventricular short-axis shortening rate, and serum BNP level of the rheumatic valvular disease patient in the hospital historical medical record, to form a clinical evaluation source database, simultaneously collects the polypeptide fingerprint of the patient, to form an original database of the polypeptide fingerprint of the rheumatic valvular disease, and simultaneously collects the evaluation results of the doctor on the rheumatic valvular disease patient for clustering analysis and collection, to form a doctor diagnosis database.

[0024] As a further scheme of the present application, the data cleaning module calculates the Euclidean distance between the peptide segment or protein containing missing values and the one without missing values, then selects a preset number of objects with the closest distance, averages or weights the values in the corresponding positions, and finally obtains the value representing the size of the missing value to complete the completely random missing due to the jitter of the mass spectrometer, the non-random missing due to the protein content being below the detection limit, and the random missing caused by the excessively long time gradient, and to standardize and regularize the cleaned polypeptide fingerprint, and to perform linear transformation on the standardized and regularized polypeptide fingerprint and then input the function The function value of the function f(x) is used to classify the polypeptide fingerprint, and the classification of the polypeptide fingerprint is used to form a polypeptide fingerprint tag library.

[0025] As a further scheme of the present application, the correlation analysis module is used to analyze the correlation between the polypeptide fingerprint tag library and the comprehensive evaluation index obtained by the clinical evaluation module, and to correlate the comprehensive evaluation with a set correlation degree, thereby forming a polypeptide fingerprint vector of rheumatic valve disease.

[0026] As a further scheme of the present application, the detection quality evaluation module extracts 100 cases of rheumatic valve disease patients from the hospital historical data, randomly extracts the polypeptide fingerprint tags of the patients, obtains the comprehensive evaluation index of the patients by using the correlation module, randomly extracts the rheumatic valve disease treating doctors to diagnose the rheumatic valve disease according to the comprehensive evaluation index, obtains the test diagnosis result, and compares the consistency of the test diagnosis result and the historical diagnosis result, and returns the result as 1 if the consistency is greater than or equal to 80%, and returns the value as 0 if the consistency is less than 80%, randomly extracts 100 times, and statistically analyzes the returned judgment values to evaluate the detection quality of the polypeptide fingerprint.

[0027] The serum differential polypeptide detection system for rheumatic valve disease according to the present application is based on the polypeptide detection historical data of the rheumatic valve disease patients received by the hospital, and starts from the differential polypeptide fingerprint to form a personalized serum differential polypeptide detection tag, correlates the serum differential polypeptide detection tag with the clinical indicators of the rheumatic valve disease patients, judges the clinical indicator sample set of the extracted rheumatic valve disease patients by using the serum differential polypeptide detection tag, compares the historical diagnosis results of the doctors, evaluates the detection quality of the polypeptide fingerprint, judges the consistency of the serum differential polypeptide detection tag and the diagnosis results in the overall historical data, and thus scientifically evaluates the rheumatic valve disease of the patients according to different serum differential polypeptide tags, further improves the targeting of the serum differential polypeptide detection of the rheumatic valve disease patients, and helps to improve the accuracy and scientificity of the clinical evaluation of the doctors on the patient's condition. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 is a structural block diagram according to the present application. DETAILED DESCRIPTION

[0029] In order to make the technical solution of the present application more clear and explicit for those skilled in the art, the present application is described in further detail below in combination with embodiments and drawings, but the embodiments of the present application are not limited thereto.

[0030] As shown in Figure 1 the serum differential polypeptide detection system for rheumatic valvular disease provided by the present embodiment includes a data acquisition module, a data cleaning module, a clinical evaluation module, a correlation analysis module and a detection quality evaluation module, the clinical evaluation module evaluates the difference between the patient's heart rate and the normal heart rate value by using the heart rate evaluation value positively correlated with the difference between the patient's heart rate and the normal value, evaluates the difference between the patient and the normal cardiac diastolic data by using the cardiac diastolic index positively correlated with the difference between the patient's left ventricular internal diameter, left ventricular end-diastolic internal diameter and left ventricular end-systolic internal diameter and the normal value, evaluates the difference between the patient's cardiac ejection and contraction and the normal value by using the cardiac ejection evaluation index negatively correlated with the difference between the patient's ejection fraction and the normal value, and evaluates the difference between the patient's serum BNP level and the normal value by using the serum BNP evaluation index positively correlated with the difference between the patient's serum BNP level and the normal value, and the evaluation mechanisms of the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index and the serum BNP evaluation index are as follows:

[0031] The evaluation formula of the heart rate evaluation value is:

[0032]

[0033] In the formula, I hr is the heart rate evaluation value, α1 is the heart rate adjustment coefficient, R h is the difference between the patient's heart rate and the normal value;

[0034] The evaluation formula of the cardiac diastolic index is:

[0035]

[0036] In the formula, I sz is the cardiac diastolic index, r1 is the difference between the patient's left ventricular internal diameter and the normal value, r2 is the difference between the patient's left ventricular end-diastolic internal diameter and the normal value, r3 is the difference between the patient's left ventricular end-systolic internal diameter and the normal value, and α2 is the cardiac diastolic adjustment coefficient;

[0037] The evaluation formula of the cardiac ejection evaluation index is:

[0038] I ss = -α3(100kef + log 510 k FS )+ 2;

[0039] I = 0.5 (1 - e ss is a heart stretching and contraction evaluation index, k ef is a patient's ejection fraction, and alpha 3 is an ejection fraction adjustment coefficient, k FS is a patient's left ventricular short axis fractional shortening rate.

[0040] The evaluation formula of the serum BNP evaluation index is as follows:

[0041]

[0042] I = 0.5 (1 - e BNP is a serum BNP evaluation index, BNP is a serum BNP level of a patient, and alpha 4 is a serum BNP adjustment coefficient.

[0043] The serum differential polypeptide detection system for rheumatic valvular disease provided by the application is based on the data mining of the polypeptide detection historical data of the patients with rheumatic valvular disease received by the hospital, starts from the fingerprint spectrum of the differential polypeptide, forms a personalized serum differential polypeptide detection label, and forms a correlation between the serum differential polypeptide detection label and the clinical index of the patient with rheumatic valvular disease, judges the clinical index sample set of the patient with rheumatic valvular disease extracted by using the serum differential polypeptide detection label, compares the historical diagnosis result of the doctor, evaluates the detection quality of the polypeptide fingerprint spectrum, judges the consistency between the serum differential polypeptide detection label and the diagnosis result in the overall historical data, and thus scientifically evaluates the rheumatic valvular disease of the patient according to different serum differential polypeptide labels, further improves the targeting of the serum differential polypeptide detection of the patient with rheumatic valvular disease, and helps to improve the accuracy and scientificity of the clinical evaluation of the doctor on the patient's condition.

[0044] The clinical evaluation module takes the weighted sum of the heart rate evaluation value, the heart diastolic index, the heart ejection evaluation index and the serum BNP evaluation index as a comprehensive evaluation index, the weights of the heart rate evaluation value, the heart diastolic index, the heart ejection evaluation index and the serum BNP evaluation index are respectively 0.25, 0.25, 0.25 and 0.25, and the evaluation mechanism of the comprehensive evaluation index is as follows:

[0045] I Z = 0.25I hr + 0.25I sz + 0.25I ss + 0.25I BNP ;

[0046] I = 0.5 (1 - e Z is a patient's comprehensive evaluation index.

[0047] The comprehensive evaluation index setting can comprehensively consider the heart rate evaluation value, the cardiac diastolic index, the cardiac systolic evaluation index and the serum BNP evaluation index, increase the comprehensive numerical change of the comprehensive evaluation index on the basis of the single index representation, solve the single function of the index, and increase the diversity of the observed data of the doctor.

[0048] The heart rate adjustment coefficients a1, a2, the cardiac diastolic adjustment coefficients a3, the ejection fraction adjustment coefficients a4 and the serum BNP adjustment coefficients a4 in the heart rate evaluation value, the cardiac diastolic index, the cardiac systolic evaluation index and the serum BNP evaluation index evaluation mechanism of the clinical evaluation module are obtained by training the historical data in the hospital patient detection database, and the order of magnitude difference between the heart rate evaluation value, the cardiac diastolic index, the cardiac systolic evaluation index and the serum BNP evaluation index is narrowed.

[0049] The setting of the heart rate adjustment coefficients a1, a2, the cardiac diastolic adjustment coefficients a3, the ejection fraction adjustment coefficients a4 and the serum BNP adjustment coefficients a4 facilitates the unification and narrowing of the order of magnitude of the heart rate evaluation value, the cardiac diastolic index, the cardiac systolic evaluation index and the serum BNP evaluation index according to the historical detection data of the hospital, avoids inaccurate judgment caused by the order of magnitude difference of the data, and further increases the similarity and linear fusion of the evaluation values.

[0050] The data acquisition module uses data mining technology to mine the highest frequency of clinical detection heart rate, left ventricular internal diameter, left ventricular end diastolic internal diameter, left ventricular end systolic internal diameter, ejection fraction, left ventricular short axis shortening rate and serum BNP level of rheumatic valve disease patients in the hospital historical medical records, forms a clinical evaluation source database, and collects the polypeptide fingerprint of the patient, forms an original database of the polypeptide fingerprint of rheumatic valve disease, and collects the evaluation results of the doctor on the rheumatic valve disease patients for clustering analysis and collection, forms a doctor diagnosis database.

[0051] Through the setting of the data acquisition module, the clinical representation data with higher frequency in the detection data of rheumatic valve disease patients can be mined as the evaluation original data of each evaluation index, the scientificity of the evaluation basic data is improved, the universal evaluation value of each evaluation index can be formed according to the clinical representation data of most patients, and the universality and accuracy of the evaluation model are improved.

[0052] The data cleaning module calculates the Euclidean distance between the peptide segment or protein containing missing values and the one without missing values, then selects a predetermined number of closest objects, averages or weights the values at the corresponding positions, and finally obtains the values to represent the size of the missing values, which are used to complete the completely random missing values caused by mass spectrometer jitter, non-random missing values caused by protein content below the detection limit, and random missing values caused by long time gradient, and to standardize and normalize the cleaned polypeptide fingerprint, and then to linearly transform the normalized and regularized polypeptide fingerprint and input the function The function value of the function f(x) is used to classify the polypeptide fingerprint, and the classification of the polypeptide fingerprint is used to form a polypeptide fingerprint tag library.

[0053] Through the setting of the data cleaning module, the missing values in the peptide segment or protein detection data can be filled in, and then the completed polypeptide fingerprint spectrum can be formed. By classifying the polypeptide fingerprint, a plurality of characteristic polypeptide fingerprint tags of rheumatic valve disease can be formed, and then the comprehensive evaluation index of patient evaluation can be quickly searched according to the polypeptide fingerprint tag, which is convenient for doctors to provide associated evaluation data, and thus the efficiency and accuracy of doctor's diagnosis and evaluation are improved, and a data foundation for doctors to scientifically diagnose rheumatic valve disease is laid.

[0054] The correlation analysis module is used to analyze the correlation between the polypeptide fingerprint tag library and the comprehensive evaluation index obtained by the clinical evaluation module, and to correlate the comprehensive evaluation with the polypeptide fingerprint tag with a set correlation degree, forming a polypeptide fingerprint vector of rheumatic valve disease.

[0055] Through the setting of the polypeptide fingerprint vector, the acquisition path of the comprehensive evaluation index can be formed according to the polypeptide fingerprint tag direction, and thus the acquisition efficiency of the comprehensive evaluation index is improved, laying a foundation for improving the efficiency of doctors to scientifically diagnose rheumatic valve disease.

[0056] The detection quality evaluation module extracts 100 cases of rheumatic valve disease patients from hospital historical data, randomly extracts the polypeptide fingerprint tags of the patients, obtains the comprehensive evaluation index of the patients by using the correlation module, randomly extracts the comprehensive evaluation index of the rheumatic valve disease patients, and diagnoses the rheumatic valve disease according to the comprehensive evaluation index, obtains the test diagnosis result, and compares the consistency of the test diagnosis result and the historical diagnosis result, the consistency is greater than or equal to 80%, the returned result is recorded as 1, the consistency is less than 80%, the returned value is recorded as 0, 100 times of random extraction are performed, the returned judgment values are counted, and the detection quality of the polypeptide fingerprint is evaluated.

[0057] The setting of the detection quality evaluation module can facilitate quality inspection of the evaluation value and the evaluation model according to the returned extraction judgment result, and further facilitate knowing the accuracy of the detection method, so as to provide statistical data for optimizing the value model and the evaluation index, and facilitate providing direction and idea for optimization and in-depth research of the later model.

[0058] In summary, in the embodiment, the serum differential polypeptide detection system for rheumatic valvular disease according to the embodiment can comprehensively consider the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index and the serum BNP evaluation index by setting the comprehensive evaluation index, increase the comprehensive evaluation index of the comprehensive numerical change on the basis of the single index representation, solve the single problem of the index function, and increase the diversity of the doctor's observation data. The setting of the heart rate adjustment coefficients α1, α2, the cardiac diastolic adjustment coefficient α3, the ejection fraction adjustment coefficient α4 and the serum BNP adjustment coefficient α4 facilitates unifying and narrowing the order of magnitude of the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index and the serum BNP evaluation index according to the historical detection data of the hospital, avoids inaccurate judgment caused by the order of magnitude difference of the data, and further increases the similarity and linear fusion of the evaluation value. The setting of the data acquisition module facilitates mining the clinical representation data with higher frequency in the detection data of the rheumatic valvular disease patient as the evaluation original data of each evaluation index, improves the scientificity of the evaluation basic data, facilitates forming the universal evaluation value of each evaluation index according to the clinical representation data of most patients, and further facilitates improving the universality and accuracy of the evaluation model. The setting of the data cleaning module facilitates filling the missing values in the peptide segment or protein detection data, and further facilitates forming the completed polypeptide fingerprint spectrum. By classifying the polypeptide fingerprint spectrum, the multiple characteristic polypeptide fingerprint spectrum labels of the rheumatic valvular disease can be formed, and the comprehensive evaluation index of the patient evaluation can be quickly searched according to the polypeptide fingerprint spectrum label, which facilitates providing the related evaluation data for the doctor, and further improves the efficiency and accuracy of the doctor's diagnosis and evaluation, and lays a data foundation for the doctor's scientific diagnosis of the rheumatic valvular disease. The setting of the polypeptide fingerprint spectrum vector facilitates forming the acquisition path of the comprehensive evaluation index according to the pointing property of the polypeptide fingerprint spectrum label, and further facilitates improving the acquisition efficiency of the comprehensive evaluation index, and lays a foundation for improving the efficiency of the doctor's scientific diagnosis of the rheumatic valvular disease. The setting of the detection quality evaluation module can facilitate quality inspection of the evaluation value and the evaluation model according to the returned extraction judgment result, and further facilitate knowing the accuracy of the detection method, so as to provide statistical data for optimizing the value model and the evaluation index, and facilitate providing direction and idea for optimization and in-depth research of the later model.

[0059] The above merely illustrates the further embodiments of the present application, but the protection scope of the present application is not limited thereto, any skilled person in the art can make equivalent replacements or changes according to the technical solutions and concepts of the present application within the disclosed scope, which shall all fall into the protection scope of the present application.

Claims

1. A serum differential polypeptide detection system for rheumatic valvular disease, characterized by, The system comprises a data collection module, a data cleaning module, a clinical evaluation module, a correlation analysis module and a detection quality evaluation module. The clinical evaluation module uses a heart rate evaluation value positively correlated with the difference between the heart rate of a patient and a normal value to evaluate the difference between the heart rate of the patient and the normal value, uses a cardiac diastolic index positively correlated with the difference between the left ventricular internal diameter, left ventricular end-diastolic internal diameter and left ventricular end-systolic internal diameter of the patient and normal values to evaluate the difference between the patient and normal cardiac diastolic data, uses a cardiac ejection evaluation index negatively correlated with the difference between the ejection fraction and shortening rate of the patient and normal values to evaluate the difference between the ejection and contraction of the heart of the patient and normal values, and uses a serum BNP evaluation index positively correlated with the difference between the serum BNP level of the patient and a normal value to evaluate the difference between the serum BNP level of the patient and the normal value. The evaluation mechanisms of the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index and the serum BNP evaluation index are as follows: The evaluation formula of the heart rate evaluation value is: wherein: I hr is the heart rate assessment value, a1is the heart rate adjustment coefficient, R h is the difference between the patient's heart rate and the normal value; The evaluation formula of the cardiac diastolic index is: In the formula, I sz is a diastolic index, r1 is the difference between the left ventricular internal diameter of the patient and the normal value, r2 is the difference between the left ventricular end-diastolic internal diameter of the patient and the normal value, r3 is the difference between the left ventricular end-systolic internal diameter and the normal value, and a2 is a diastolic adjustment coefficient. The evaluation formula of the cardiac ejection evaluation index is: I ss = -a3(100k ef + log510k FS )+ 2; wherein: I ss is a cardiac stretch assessment index, k ef is a patient ejection fraction, a3 is an ejection fraction adjustment factor, K FS is a patient left ventricular fractional shortening; The evaluation formula of the serum BNP evaluation index is: wherein: I BNP is the serum BNP assessment indicator, BNP is the serum detected BNP level of the patient, and a4 is the serum BNP adjustment coefficient.

2. A serum differential polypeptide detection system for rheumatic valvular disease according to claim 1, wherein, The clinical evaluation module takes the weighted sum of the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index and the serum BNP evaluation index as a comprehensive evaluation index, the weights of the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index and the serum BNP evaluation index are 0.25, 0.25, 0.25 and 0.25 respectively, and the evaluation mechanism of the comprehensive evaluation index is: I Z = 0.25 I hr + 0.25 I sz + 0.25 I ss + 0.25 I BNP ; In the formula: I Z is a comprehensive evaluation index for patients.

3. A serum differential polypeptide detection system for rheumatic valvular disease according to claim 1, wherein, The heart rate adjustment coefficients α1, α2, the cardiac diastolic adjustment coefficient α3, the ejection fraction adjustment coefficient α4 and the serum BNP adjustment coefficient α4 in the evaluation mechanisms of the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index and the serum BNP evaluation index are obtained by training the historical data in the hospital patient detection database, so as to narrow the order of magnitude difference between the heart rate evaluation value, the cardiac diastolic index, the cardiac ejection evaluation index and the serum BNP evaluation index.

4. A serum differential polypeptide detection system for rheumatic valvular disease according to claim 2, wherein, The data collection module uses data mining technology to mine the clinical detection heart rate, left ventricular internal diameter, left ventricular end-diastolic internal diameter, left ventricular end-systolic internal diameter, ejection fraction, left ventricular shortening rate and serum BNP level of rheumatic valvular disease patients in the hospital historical medical records to form a clinical evaluation source database. Meanwhile, the polypeptide fingerprint of the patient is collected to form an original database of the polypeptide fingerprint of rheumatic valvular disease, and the evaluation results of the doctor on the rheumatic valvular disease patients are clustered and collected to form a doctor diagnosis database.

5. A serum differential polypeptide detection system for rheumatic valvular disease according to claim 4, wherein, The data cleaning module calculates the Euclidean distance between the peptide segment or protein containing missing values and the one without missing values, then selects a predetermined number of closest objects, averages or weights the values in the corresponding positions, and finally obtains the values to represent the size of the missing values, complete random missing due to mass spectrometer jitter, non-random missing due to protein content below the detection limit, and random missing due to long time gradient, and standardizes and normalizes the cleaned polypeptide fingerprint, and then linearly transforms the polypeptide fingerprint into a function The function value of the function f(x) is used to classify the polypeptide fingerprint, and the classification of the polypeptide fingerprint is used to form a polypeptide fingerprint tag library.

6. A serum differential polypeptide detection system for rheumatic valvular disease according to claim 5, wherein, The correlation analysis module is used to analyze the correlation between the polypeptide fingerprint tag library and the comprehensive evaluation index obtained by the clinical evaluation module, and to correlate the comprehensive evaluation indexes with the polypeptide fingerprint tags in accordance with the set correlation degree to form a polypeptide fingerprint vector of rheumatic valvular disease.

7. A serum differential polypeptide detection system for rheumatic valvular disease according to claim 6, wherein, The detection quality evaluation module extracts 100 rheumatic valvular disease patients from historical data of the hospital, randomly extracts polypeptide fingerprint tags of the patients, obtains a comprehensive evaluation index of the patients by using the correlation analysis module, randomly extracts a rheumatic valvular disease treating doctor according to the comprehensive evaluation index to diagnose the rheumatic valvular disease, obtains a test diagnosis result, and compares consistency of the test diagnosis result and historical diagnosis result, returns a result as 1 when the consistency is greater than or equal to 80%, and returns a value as 0 when the consistency is less than 80%, randomly extracts 100 times, and statistically evaluates the returned judgment values to evaluate detection quality of the polypeptide fingerprint.

Images