Clinical data processing method and device for rheumatic heart valve disease

Abstract

The present invention relates to the field of data processing technology, and discloses a clinical data processing method and device for rheumatic heart valve disease. The method comprises: obtaining a plurality of clinical data; wherein the clinical data comprises first clinical data corresponding to a plurality of first patients with good angioplasty effects, and second clinical data corresponding to a plurality of second patients with poor angioplasty effects; analyzing a plurality of clinical data to obtain probability values ​​corresponding to each clinical data; analyzing a plurality of clinical data and probability values ​​to determine that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the anterior mitral leaflet angle. By implementing the technical solution of the present invention, the anterior mitral leaflet angle is determined through analysis as an independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty, which provides important guidance for clinical practice and helps to improve the treatment effect and prognosis of patients.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a clinical data processing method and device for rheumatic heart valve disease. Background Art

[0002] After a diagnosis of rheumatic valvular heart disease, mitral valvuloplasty is the preferred surgical approach if the anatomy is determined to be suitable. Patients who undergo mitral valvuloplasty at higher-level centers may have better long-term outcomes than those who undergo mitral valvuloplasty.

[0003] However, the current selection of patients for mitral valvuloplasty mainly depends on the surgeon's subjective experience during the operation, which is highly non-reproducible and will lead to uncertainty and inconsistency in patient selection. At the same time, during the operation, the surgeon can only observe the static structure and cannot comprehensively and dynamically evaluate the functional abnormality of the entire mitral valve, which may lead to inaccurate assessment of the condition and affect the quality and results of surgical decision-making. Summary of the invention

[0004] In view of this, the present invention provides a clinical data processing method and device for rheumatic heart valve disease to solve the problems of subjective experience dependence, non-reproducibility and inability to dynamically detect mitral valve dysfunction in current mitral valvuloplasty.

[0005] In a first aspect, the present invention provides a clinical data processing method for rheumatic heart valvular disease, comprising: acquiring multiple clinical data; wherein the clinical data include first clinical data corresponding to multiple first patients with good angioplasty results, and second clinical data corresponding to multiple second patients with poor angioplasty results; the multiple second patients with poor angioplasty results are used to characterize patients who have failed intraoperative mitral valvuloplasty and switched to mitral valve replacement, and patients who have more than mild stenosis or regurgitation in a follow-up before discharge after mitral valvuloplasty; analyzing multiple clinical data to obtain probability values ​​corresponding to each clinical data; wherein, for any clinical data, the probability value is used to characterize the degree of difference between the first clinical data and the second clinical data; analyzing multiple clinical data and probability values, determining that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the mitral valve annular angle; wherein the mitral valve annular angle represents the angle between the line connecting the mitral valve annular root and the mitral valve annular tip in mid-diastole on the standard four-chamber heart section and the mitral valve annulus.

[0006] The clinical data processing method for rheumatic heart valve disease provided in the embodiment of the present invention obtains multiple clinical data, including data of multiple first patients and multiple second patients. This comprehensive data collection is helpful for comprehensively evaluating the effect of the operation. The patients are divided into two groups, those with good shaping surgery effect and those with poor shaping surgery effect, thereby distinguishing the clinical data under different results, which helps to deeply understand the differences in surgical effects and may provide clues for further intervention. By analyzing the clinical data, the probability values ​​corresponding to each clinical data are obtained. These values ​​can be used to quantify the degree of difference between the first clinical data and the second clinical data, so that the data differences under different results can be objectively evaluated. It was determined that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the anterior mitral leaflet annular angle, which is of great significance for clinical practice, because the anterior mitral leaflet annular angle can help doctors better predict the effect of the operation and provide a basis for pre-operative decision-making.

[0007] In an optional embodiment, multiple clinical data include the patient's baseline characteristics, the patient's echocardiographic measurement results, the patient's surgical conditions, and the patient's early efficacy; the baseline characteristics are used to characterize the patient's initial state before the start of treatment; the surgical conditions are used to characterize the type of surgery the patient received and the surgical results; the early efficacy is used to characterize the patient's condition in the early postoperative period after surgical treatment; the echocardiographic measurement results are used to characterize the patient's heart structure and function; the echocardiographic measurement results include the mitral valve annular angle; obtaining the mitral valve annular angle includes: obtaining echocardiograms of multiple patients; based on the echocardiograms, measuring the angle between the line connecting the mitral valve annular root and the mitral valve annular tip and the mitral valve annulus.

[0008] The clinical data processing method for rheumatic heart valve disease provided by the embodiment of the present invention, the clinical data covers multiple aspects such as the patient's baseline characteristics, echocardiographic measurement results, surgical conditions, and early efficacy. This comprehensiveness helps to comprehensively evaluate the patient's condition and treatment effect. By including multiple aspects of data such as baseline characteristics, echocardiographic measurement results, and surgical conditions, the study can observe the patient's condition from different angles, which helps to more comprehensively understand the patient's disease state and treatment effect. Echocardiographic measurement results provide objective cardiac structure and function data, which helps doctors to more accurately evaluate the patient's condition and provide an objective basis for the selection of treatment options. In particular, the method for measuring the annular angle of the anterior leaflet of the mitral valve is clearly defined, and this parameter can be accurately obtained through echocardiographic measurement. This quantification helps to improve the accuracy and comparability of the data.

[0009] In an optional implementation, multiple clinical data are analyzed to obtain probability values ​​corresponding to each clinical data, including: entering the multiple clinical data into a data statistics tool to obtain probability values ​​corresponding to each clinical data.

[0010] The clinical data processing method for rheumatic heart valve disease provided by the embodiment of the present invention, the statistical tool can convert the clinical data into numerical values, and then calculate the probability value, which helps to quantify the clinical observations and experimental results, making them easier to understand and compare. The probability value is an objective measurement, which is not affected by subjective bias. The probability value calculated by the statistical tool can help medical researchers or clinicians make objective decisions. Using statistical tools to calculate the probability value can improve the efficiency and accuracy of data analysis, and avoid the errors and inconsistencies that may be caused by manual calculations. The probability value can help researchers evaluate the correlation and impact between different variables, and provide guidance and direction for further research.

[0011] In an optional embodiment, multiple clinical data and probability values ​​are analyzed to determine that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the mitral valve anterior leaflet angle, including: entering multiple clinical data and probability values ​​into a univariate logistic regression analysis model to obtain a first probability value corresponding to each clinical data; wherein the first probability value is used to characterize whether the influence of each clinical data on the efficacy of rheumatic mitral valvuloplasty is statistically significant; the clinical data corresponding to the probability value less than a first preset threshold in the first probability value are determined as candidate clinical data; the candidate clinical data are entered into a multivariate logistic regression analysis model to determine that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the mitral valve anterior leaflet angle.

[0012] The clinical data processing method for rheumatic heart valve disease provided by the embodiment of the present invention systematically analyzes the relationship between various clinical data and the efficacy of rheumatic mitral valvuloplasty surgery through a univariate logistic regression analysis model, which helps to determine the degree of influence of each clinical variable on the surgical effect. Using the first probability value to characterize whether the influence of various clinical data on the surgical efficacy is statistically significant helps to determine which clinical factors have a significant impact on the surgical effect, thereby helping doctors to better evaluate the patient's prognosis and formulate a treatment plan. Determining the clinical data corresponding to the probability value less than the first preset threshold as candidate clinical data can help screen out the most potential predictive factors, thereby reducing unnecessary data analysis and improving efficiency. Through the multivariate logistic regression analysis model, it is determined that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty surgery is the mitral anterior leaflet annular angle, which helps doctors to more accurately evaluate the patient's prognosis and provide guidance for personalized treatment. Using the logistic regression analysis model, combined with statistical methods, it is possible to determine the main factors affecting the surgical efficacy while considering multiple clinical factors, thereby improving the accuracy and reliability of the prediction. By identifying independent predictive factors, practical guidance can be provided to clinicians to help better assess patient prognosis and develop personalized treatment plans.

[0013] In an optional embodiment, the candidate clinical data are entered into a multivariate logistic regression analysis model to determine that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the mitral valve anterior leaflet angle, including: entering the candidate clinical data into a multivariate logistic regression analysis model to obtain a second probability value corresponding to each candidate clinical data; and determining the candidate clinical data of the mitral valve anterior leaflet angle corresponding to the probability value in the second probability value that is less than a second preset threshold as an independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty.

[0014] The clinical data processing method for rheumatic heart valve disease provided in an embodiment of the present invention further analyzes the impact of candidate clinical data on the efficacy of rheumatic mitral valvuloplasty surgery through a multifactor logistic regression analysis model, which helps to identify more critical predictive factors. Determining the candidate clinical data corresponding to the probability value in the second probability value that is less than the second preset threshold as a predictive factor helps to screen out the most influential and predictive factors, thereby improving the accuracy and reliability of the model. By screening out independent predictive factors, the doctor's decision-making process can be simplified, allowing him to focus more on key clinical variables, thereby improving the efficiency and accuracy of decision-making. After determining the independent predictive factor, the treatment plan can be optimized according to the specific circumstances of the factor to improve the treatment effect and the patient's prognosis.

[0015] In a second aspect, the present invention provides a method for verifying the prediction of the anterior mitral leaflet angle, which is implemented based on the clinical data processing method for rheumatic heart valvular disease of the first aspect, and includes: obtaining the anterior mitral leaflet angle data corresponding to multiple patients, and the corresponding rheumatic mitral valvuloplasty surgery efficacy data; sorting the anterior mitral leaflet angle data from small to large, and calculating the true positive rate and false positive rate corresponding to each anterior mitral leaflet angle data according to the rheumatic mitral valvuloplasty surgery efficacy data; drawing a subject curve according to the true positive rate and the false positive rate; calculating the area under the curve corresponding to the subject curve according to a preset numerical integration rule; judging whether the area under the curve is greater than a third preset threshold, and outputting a prediction value assessment of the anterior mitral leaflet angle data according to the judgment result.

[0016] The verification method for predicting the anterior mitral leaflet angle provided in the embodiment of the present invention comprehensively evaluates the severity of mitral valve disease and the efficacy of surgery by combining the anterior mitral leaflet angle data and the efficacy data of rheumatic mitral valvuloplasty, and has a more comprehensive evaluation capability. The use of objective indicators such as true positive rate and false positive rate for evaluation reduces the influence of subjective factors and improves the objectivity and credibility of the evaluation results. By drawing the receiver operating characteristic curve, the trade-off relationship between the true positive rate and the false positive rate under different thresholds is intuitively displayed, helping to determine the best prediction model. The area under the ROC curve is calculated using the numerical integration rule to more directly quantify the accuracy and stability of the prediction model. By setting a preset threshold, the evaluation results are made operational, and corresponding clinical decisions can be made according to specific circumstances.

[0017] In a third aspect, the present invention provides a clinical data processing device for rheumatic heart valvular disease, comprising: an acquisition module, for acquiring multiple clinical data; wherein the clinical data include first clinical data corresponding to multiple first patients with good angioplasty results, and second clinical data corresponding to multiple second patients with poor angioplasty results; the multiple second patients with poor angioplasty results are used to characterize patients who have failed intraoperative mitral valvuloplasty and switched to mitral valve replacement, and who have more than mild stenosis or regurgitation in a follow-up before discharge after mitral valvuloplasty; an analysis module, for analyzing multiple clinical data to obtain probability values ​​corresponding to each clinical data; wherein, for any clinical data, the probability value is used to characterize the degree of difference between the first clinical data and the second clinical data; a determination module, for analyzing multiple clinical data and probability values, and determining that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the mitral valve anterior leaflet annular angle; wherein the mitral valve anterior leaflet annular angle represents the angle between the line connecting the mitral valve anterior leaflet root and the mitral valve anterior leaflet cusp in mid-diastole of the standard four-chamber heart section and the mitral valve annulus.

[0018] In a fourth aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to execute the clinical data processing method for rheumatic heart valve disease of the first aspect or any corresponding embodiment thereof, or the verification method for predicting the anterior leaflet angle of the mitral valve of the second aspect.

[0019] In a fifth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the clinical data processing method for rheumatic heart valve disease of the first aspect or any corresponding embodiment thereof, or the verification method for predicting the anterior leaflet angle of the mitral valve of the second aspect.

[0020] In a sixth aspect, the present invention provides a computer program product comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the clinical data processing method for rheumatic heart valve disease of the first aspect or any corresponding embodiment thereof, or the verification method for predicting the anterior leaflet angle of the mitral valve of the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 is a flow chart of a clinical data processing method for rheumatic heart valve disease according to an embodiment of the present invention;

[0023] Figure 2 is a schematic diagram of the anterior leaflet angle of the mitral valve according to an embodiment of the present invention;

[0024] Figure 3 is a flow chart of another clinical data processing method for rheumatic heart valve disease according to an embodiment of the present invention;

[0025] Figure 4 is a flow chart of a verification method for predicting the anterior leaflet angle of a mitral valve according to an embodiment of the present invention;

[0026] Figure 5 is a schematic diagram of a subject curve according to an embodiment of the present invention;

[0027] Figure 6 is a structural block diagram of a clinical data processing device for rheumatic heart valve disease according to an embodiment of the present invention;

[0028] Figure 7 is a structural block diagram of a verification device for predicting anterior mitral leaflet angle according to an embodiment of the present invention;

[0029] Figure 8 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0031] Rheumatic heart disease is one of the most common cardiovascular diseases. It is estimated that there are about 40.5 million patients with rheumatic heart disease worldwide, causing more than 300,000 deaths each year. Due to autoimmune mechanisms and hemodynamic reasons, rheumatic heart disease often affects the valves, causing rheumatic heart valve disease. The latest "Chinese Expert Consensus on Indications for Surgical Treatment of Rheumatic Mitral Valve Disease" (hereinafter referred to as Expert Consensus) recommends that appropriate patients should choose rheumatic mitral valve repair as a treatment option.

[0032] However, rheumatic mitral valvuloplasty is not suitable for all patients, and rheumatic lesions cannot achieve nearly 100% valvuloplasty like degenerative mitral valvuloplasty. The selection of patients for rheumatic mitral valvuloplasty is an important clinical issue in clinical practice. Currently, the selection of patients for mitral valvuloplasty mainly depends on the subjective experience of the surgeon under direct vision during the operation. This subjective experience is highly non-reproducible, which is not conducive to the promotion of rheumatic mitral valvuloplasty. In addition, only static structures can be observed under direct vision during the operation, and the functional lesions of the entire mitral valve device cannot be dynamically evaluated, which may cause misjudgment and affect the patient's prognosis.

[0033] In view of this, the technical solution of the present invention proposes a method for predicting the efficacy of rheumatic mitral valve repair surgery in patients with rheumatic mitral valve repair surgery through preoperative objective indicators, thereby guiding the screening of suitable patients for rheumatic mitral valve repair surgery in clinical practice.

[0034] According to an embodiment of the present invention, an embodiment of a clinical data processing method for rheumatic heart valve disease is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] In this embodiment, a clinical data processing method for rheumatic heart valve disease is provided, which can be used in a computer device. Figure 1 FIG. 1 is a flow chart of a clinical data processing method for rheumatic heart valve disease according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0036] Step S101, obtaining multiple clinical data; wherein the clinical data include first clinical data corresponding to multiple first patients with good mitral valvuloplasty results, and second clinical data corresponding to multiple second patients with poor mitral valvuloplasty results; the multiple second patients with poor mitral valvuloplasty results are used to characterize patients who have failed intraoperative mitral valvuloplasty and are converted to mitral valve replacement, and patients who have more than mild stenosis or regurgitation in the follow-up before discharge after mitral valvuloplasty.

[0037] Multiple clinical data are multiple types of medical data collected in medical research or clinical practice. Specifically, multiple clinical data are collected, which may include basic information, medical history, clinical examination results, operation records, etc. of the patient.

[0038] The first clinical data corresponding to the first patient with good mitral valvuloplasty results refers to clinical data of a patient who underwent mitral valvuloplasty and had good results. The first patient is a patient whose mitral valve function is well restored after the operation without obvious complications such as stenosis or regurgitation.

[0039] The second clinical data corresponding to the second patient with poor mitral valvuloplasty refers to the clinical data of patients who underwent mitral valvuloplasty but had poor surgical results. The second patient is a patient who needs to be converted to mitral valve replacement after a failed mitral valvuloplasty, or a patient who was found to have more than mild stenosis or regurgitation during a follow-up examination before discharge after mitral valvuloplasty, which indicates that the mitral valvuloplasty did not achieve the expected therapeutic effect. Among them, the degree of mitral stenosis is determined based on the valve orifice area (mild>2.5cm2, 1.5cm2<moderate≤2.5cm2, severe≤1.5cm2), and the degree of mitral regurgitation is determined based on the regurgitation area (mild<4cm2, 4cm2≤moderate<8cm2, severe≥8cm2).

[0040] Step S102, analyzing multiple clinical data to obtain probability values ​​corresponding to each clinical data; wherein, for any clinical data, the probability value is used to characterize the degree of difference between the first clinical data and the second clinical data.

[0041] The probability value is used to characterize the degree of difference in a certain clinical data between the first patient with a good plastic surgery effect and the second patient with a poor plastic surgery effect. Specifically, statistical tools and techniques are used to perform statistical analysis on the collected multiple clinical data, such as descriptive statistics, variance analysis, regression analysis, etc., to explore the difference and correlation between the first clinical data and the second clinical data for any clinical data.

[0042] For each clinical data item, the probability of occurrence in two groups of patients (the first patient and the second patient) is calculated. Specifically, this can be achieved by comparing the frequencies of corresponding data in the two groups of patients or applying a statistical model, which is not limited here.

[0043] Step S103, analyzing multiple clinical data and probability values, determining that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty surgery is the mitral valve anterior leaflet angle; wherein the mitral valve anterior leaflet angle represents the angle between the line connecting the mitral valve anterior leaflet root and the mitral valve anterior leaflet tip in mid-diastole of the standard four-chamber heart section and the mitral valve annulus.

[0044] The independent predictive factor is the only factor related to the predicted result (rheumatic mitral valvuloplasty efficacy) determined in the statistical analysis. Specifically, the only predictive factor for predicting the rheumatic mitral valvuloplasty efficacy is determined by statistically analyzing multiple clinical data and corresponding probability values.

[0045] The mitral annular angle is a specific cardiac anatomical measurement used to assess the morphology and functional status of the mitral valve. The mitral annular angle is determined by measuring the angle between the line connecting the mitral annular root and the mitral annular tip and the mitral annulus in mid-diastole in the standard four-chamber view. Figure 2 shown.

[0046] The clinical data processing method for rheumatic heart valve disease provided in the embodiment of the present invention obtains multiple clinical data, including data of multiple first patients and multiple second patients. This comprehensive data collection is helpful for comprehensively evaluating the effect of the operation. The patients are divided into two groups, those with good shaping surgery effect and those with poor shaping surgery effect, thereby distinguishing the clinical data under different results, which helps to deeply understand the differences in surgical effects and may provide clues for further intervention. By analyzing the clinical data, the probability values ​​corresponding to each clinical data are obtained. These values ​​can be used to quantify the degree of difference between the first clinical data and the second clinical data, so that the data differences under different results can be objectively evaluated. It was determined that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the anterior mitral leaflet annular angle, which is of great significance for clinical practice, because the anterior mitral leaflet annular angle can help doctors better predict the effect of the operation and provide a basis for pre-operative decision-making.

[0047] In this embodiment, a clinical data processing method for rheumatic heart valve disease is provided, which can be used in a computer device. Figure 3 FIG. 1 is a flow chart of a clinical data processing method for rheumatic heart valve disease according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0048] Step S201, obtaining multiple clinical data; wherein the clinical data include first clinical data corresponding to multiple first patients with good mitral valvuloplasty results, and second clinical data corresponding to multiple second patients with poor mitral valvuloplasty results; the multiple second patients with poor mitral valvuloplasty results are used to characterize patients who have failed intraoperative mitral valvuloplasty and are converted to mitral valve replacement, and patients who have more than mild stenosis or regurgitation in the follow-up before discharge after mitral valvuloplasty.

[0049] Among them, multiple clinical data include patients' baseline characteristics, patients' echocardiographic measurement results, patients' surgical conditions, and patients' early efficacy.

[0050] Baseline characteristics are the initial status or basic characteristics of the patient before receiving treatment. Specifically, they may include age, gender, height, weight, medical history (such as hypertension, diabetes, etc.), symptoms (such as dyspnea, chest pain, etc.), and other information related to the patient's overall health and disease status, as shown in Table 1.

[0051] Table 1

[0052]

[0053] The surgical condition refers to the type of surgery the patient received and the results of the surgery. Specifically, it may include information such as the type of surgery (such as the specific method of mitral valvuloplasty), the time and process of the surgery, and complications of the surgery, as shown in Table 2.

[0054] Table 2

[0055]

[0056] Early efficacy refers to the early condition of the patient after surgical treatment. This may include postoperative recovery, symptom improvement, changes in cardiac function, etc., as shown in Table 3. The evaluation of early efficacy can provide preliminary information about the effect of surgical treatment.

[0057] Table 3

[0058]

[0059] Echocardiographic measurements are data obtained through echocardiography and are used to evaluate the patient's heart structure and function. Specifically, echocardiography can provide detailed information about the internal structure of the heart (such as the size of the heart chamber, myocardial thickness, etc.) and function (such as cardiac systolic and diastolic function), as shown in Table 4. Among them, an important indicator in the echocardiographic measurement results is the anterior leaflet angle of the mitral valve, which is used as a key factor in predicting the efficacy of surgery.

[0060] Table 4

[0061]

[0062] Table 4 continued:

[0063]

[0064] Specifically, the above step S201 includes: step a, obtaining the annular angle of the anterior leaflet of the mitral valve.

[0065] Obtaining the anterior mitral leaflet angle is an important step in echocardiography to evaluate the morphology and function of the mitral valve.

[0066] In some optional implementations, the above step a includes:

[0067] Step a1, obtaining echocardiograms of multiple patients.

[0068] Echocardiograms are performed on multiple patients. Specifically, the patient is asked to lie on an examination table in a specific position, usually on the left side. The patient is connected to a surface electrocardiogram monitoring device to record the heart's electrical activity, which helps the doctor accurately identify the different phases of the heart cycle on the heart image. The doctor selects the appropriate type and frequency of echocardiogram probe, such as using a Philips IE 33 system and a specific probe (S5-1 probe or X5-1 probe). The doctor will use the echocardiogram probe to scan along the patient's chest to obtain real-time images of the heart. The doctor usually adjusts the position and angle of the probe to obtain different cross-sectional images of the heart and ensure that comprehensive information about the heart's structure and function is obtained.

[0069] Step a2, measuring the angle between the line connecting the root of the anterior mitral leaflet and the tip of the anterior mitral leaflet and the mitral valve annulus according to the echocardiogram.

[0070] After obtaining an echocardiogram, the physician uses imaging software or a manual measurement tool to measure the angle between the line connecting the anterior mitral leaflet root and the anterior mitral leaflet cusp and the mitral annulus, which is not limited here. This measurement is usually performed in mid-diastole in a standard four-chamber view.

[0071] In the above-mentioned embodiment, the clinical data covers multiple aspects such as the patient's baseline characteristics, echocardiographic measurement results, surgical conditions, and early efficacy. This comprehensiveness helps to comprehensively evaluate the patient's condition and treatment effect. By including multiple aspects of data such as baseline characteristics, echocardiographic measurement results, and surgical conditions, the study can observe the patient's condition from different angles, which helps to more comprehensively understand the patient's disease state and treatment effect. Echocardiographic measurement results provide objective cardiac structure and function data, which helps doctors to more accurately evaluate the patient's condition and provide an objective basis for the selection of treatment options. In particular, the method for measuring the anterior leaflet annular angle of the mitral valve is clearly defined, and this parameter can be accurately obtained through echocardiographic measurement. This quantification helps to improve the accuracy and comparability of the data.

[0072] Step S202, analyzing multiple clinical data to obtain probability values ​​corresponding to each clinical data; wherein, for any clinical data, the probability value is used to characterize the degree of difference between the first clinical data and the second clinical data.

[0073] Specifically, the above step S202 includes: entering multiple clinical data into a data statistical tool to obtain probability values ​​corresponding to each clinical data.

[0074] Data statistical tools are software or tools used to collect, analyze, and interpret data. For example, they can be statistical software programs such as R, data analysis libraries in Python (such as Pandas, NumPy, SciPy, etc.), SPSS, SAS, etc., or online statistical analysis platforms such as Google Sheets, IBM Watson Analytics, etc. Specifically, multiple clinical data are input into the selected data statistical tool, for example, multiple clinical data are input into the data table or data frame of the tool in an appropriate format, ensuring that each clinical parameter or indicator has a corresponding data column. According to the purpose of the analysis and the type of data, appropriate statistical methods are selected for calculation, such as descriptive statistical analysis (such as mean, standard deviation, frequency distribution), hypothesis testing (such as t-test, analysis of variance), correlation analysis (such as Pearson correlation coefficient), etc.

[0075] Using the selected statistical method, each clinical data is analyzed and the corresponding probability value is calculated. Specifically, the probability value can be the P value (P-value) corresponding to each clinical data in Tables 1 to 4 above, which is used to evaluate the result of the hypothesis test. For comparing the first clinical data and the second clinical data, a t-test can be used to compare whether the two groups of means are significantly different, and then the P value is obtained by calculating the t statistic. When the P value <0.05, the difference is considered to be statistically significant.

[0076] For the contents of Table 1, there were 167 patients. Among them, 112 patients (67.7%) had good angioplasty (first patient), 55 patients (32.9%) had poor angioplasty (second patient), 47 patients (85.5%) tried angioplasty and then arthroplasty, 1 patient (1.8%) had moderate stenosis and reflux after angioplasty, and 7 patients (12.7%) had moderate reflux after angioplasty. There was no significant difference in the proportion of males (22.3% VS 34.5%, P = 0.134), BMI (23.9 VS 24.0, P = 0.885), and BSA (1.8 ± 0.2 VS 1.7 ± 0.2, P = 0.485) between the two groups. The age of the group with poor angioplasty was significantly older (57.0 VS 64.0, P = 0.002). In terms of medical history, hypertension was the most common disease, and patients in the poor angioplasty group had more hypertension history (23.2% VS 40.0%, P = 0.038). Other medical histories, including smoking history (8.9% VS 18.2%, P = 0.140), drinking history (8.0% VS 7.3%, P = 0.491), diabetes history (8.0% VS 7.3%, P = 0.998), and stroke history (2.7% VS 10.9%, P = 0.060), were not significantly different between the two groups. There was also no significant difference in the history of mitral valvular balloon angioplasty (2.7% VS 10.9%, P = 0.996), the proportion of atrial fibrillation (67.9% VS 78.2%, P = 0.229), and the New York Heart Association heart function classification (P = 0.849). It is worth noting that the patients with poor angioplasty had more left atrial thrombus (5.4% VS 16.4%, P = 0.040).

[0077] According to the contents in Table 2, there was no significant difference in the combined surgeries between the two groups, such as combined coronary artery bypass grafting, combined aortic valve surgery, combined radiofrequency ablation of atrial fibrillation, and combined tricuspid valvuloplasty. There was no significant difference in the extracorporeal circulation time, aortic clamping time, and mechanical ventilation time between the two groups.

[0078] According to the contents in Table 3, there were no significant differences between the two groups in terms of postoperative death, reoperation, acute heart failure, acute renal failure, stroke, severe infection, ICU time, and hospital stay. In the group with poor angioplasty effect, one patient (1.8%) had moderate stenosis and reflux after angioplasty, and seven patients (12.7%) had moderate reflux after angioplasty.

[0079] According to the contents in Table 4, there were no significant differences in general ultrasound indicators between the two groups, such as aortic sinus diameter, ascending aorta diameter, right atrial diameter, pulmonary artery trunk diameter, pulmonary artery velocity, pulmonary artery pressure, ventricular septal motion amplitude, left ventricular end-diastolic diameter, left ventricular end-systolic diameter, left ventricular ejection fraction, and left ventricular minor axis shortening. The left atrial diameter of the patients in the group with poor angioplasty was significantly larger (48.5VS 51.0, P = 0.009), the ventricular septum thickness was thicker (9.0VS10.0, P = 0.011), the left ventricular posterior wall thickness was thicker (9.0VS 9.0, P = 0.024), and the mitral valve area was smaller (1.3VS1.0, P < 0.001). The mitral valve lesions in the two groups were mainly mixed lesions, which were 87.5% and 81.8% respectively, with no statistical difference (P = 0.308). The patients in the group with poor angioplasty had more severe mitral stenosis (P=0.023), and no statistical difference in regurgitation (P=0.769). The patients in the group with poor angioplasty had higher total Wilkins score (9.0VS12.0, P<0.001), shorter posterior leaflet length (2.1VS2.1, P=0.004), thicker rough band thickness of anterior leaflet zone 2 (0.5VS 0.5, P=0.005), and smaller annular angle of mitral leaflet (41.2±8.9VS27.9±10.1, P<0.001). There were no significant differences in other special indicators such as anterior leaflet length, rough band thickness of posterior leaflet zone 2, anterior commissural thickness, posterior commissural thickness, BT-angle, median angle of anterior leaflet, left-right diameter of mitral valve annulus, and anterior-posterior diameter of mitral valve annulus.

[0080] In the above-mentioned implementation mode, statistical tools can convert clinical data into numerical values, and then calculate probability values, which helps to quantify clinical observations and experimental results, making them easier to understand and compare. Probability values ​​are objective measurements that are not affected by subjective biases. The probability values ​​calculated by statistical tools can help medical researchers or clinicians make objective decisions. Using statistical tools to calculate probability values ​​can improve the efficiency and accuracy of data analysis, avoiding errors and inconsistencies that may be caused by manual calculations. Probability values ​​can help researchers evaluate the correlation and impact between different variables, and provide guidance and direction for further research.

[0081] Step S203, analyzing multiple clinical data and probability values, determining that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty surgery is the mitral valve anterior leaflet angle; wherein the mitral valve anterior leaflet angle represents the angle between the line connecting the mitral valve anterior leaflet root and the mitral valve anterior leaflet tip in mid-diastole on a standard four-chamber heart section and the mitral valve annulus.

[0082] Specifically, the above step S203 includes:

[0083] Step S2031, input multiple clinical data and probability values ​​into a univariate logistic regression analysis model to obtain a first probability value corresponding to each clinical data; wherein the first probability value is used to indicate whether the influence of each clinical data on the efficacy of rheumatic mitral valvuloplasty surgery is statistically significant.

[0084] The univariate logistic regression analysis model is used to explore the relationship between an independent variable (various clinical data) and a binary dependent variable (plasty effect). Specifically, multiple clinical data and probability values ​​are input into the univariate logistic regression model. In this model, a clinical data variable will be selected as the independent variable, and the binary dependent variable of the plasty effect will be the target to be predicted.

[0085] In univariate logistic regression, the first probability value is the probability that the dependent variable takes the value of 1 (i.e., the mitral valve repair surgery is effective) under the given independent variable conditions, calculated according to the univariate logistic regression analysis model. The first probability value can reflect the impact of current clinical data on the efficacy of rheumatic mitral valve repair surgery. For each clinical data variable, there will be a corresponding first probability value.

[0086] Specifically, each clinical data and the corresponding probability value (P value) in Tables 1 to 4 were entered into a univariate logistic regression analysis model to obtain a first probability value corresponding to each clinical data, as shown in Table 5.

[0087] Table 5

[0088]

[0089] Table 5 continued:

[0090]

[0091] Step S2032: determine the clinical data corresponding to the probability value less than the first preset threshold in the first probability value as candidate clinical data.

[0092] The first preset threshold is a probability value, such as 0.05. If the probability value of a certain clinical data is less than the first preset threshold, it is determined to be statistically significant. The first probability value output by the model is compared with the first preset threshold, and the clinical data corresponding to the probability value less than the first preset threshold is determined as the candidate clinical data.

[0093] Specifically, the clinical data in Tables 1 to 4 and the corresponding probability values ​​(P values) were entered into the univariate logistic regression analysis model, and the first preset threshold values ​​corresponding to age, history of hypertension, history of stroke, left atrial thrombus, left atrial diameter, pulmonary artery pressure, interventricular septum thickness, left ventricular posterior wall thickness, mitral valve area, degree of mitral stenosis, total Wilkins score, leaflet activity, subvalvular thickening, leaflet thickness, leaflet calcification, posterior leaflet length, mitral valve anterior leaflet zone 2 transparent zone thickness, and mitral valve anterior leaflet zone 2 rough zone thickness were less than 0.05, which was statistically significant.

[0094] Step S2033, entering the candidate clinical data into a multi-factor logistic regression analysis model, and determining that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the anterior leaflet angle of the mitral valve.

[0095] These candidate clinical data were entered into a multivariate logistic regression analysis model, which can simultaneously consider the effects of multiple variables (multiple candidate clinical data) on the results (the effect of the mitral valve repair surgery) and the interactions between these variables. In the multivariate logistic regression model, the coefficients of each variable are analyzed to determine which variables are independent and significant predictors. The coefficients indicate the degree of influence of each variable on the results, and the statistical test can determine whether the influence is significant. In this process, the anterior mitral leaflet angle was found to be a significant and independent predictor. This means that the anterior mitral leaflet angle has an important independent effect on predicting the efficacy of rheumatic mitral valve repair surgery, considering other possible factors. By determining the anterior mitral leaflet angle as an independent predictor, more accurate information can be provided for the prediction of surgical efficacy.

[0096] In some optional implementations, the above step S2033 includes:

[0097] Step b1, inputting the candidate clinical data into a multi-factor logistic regression analysis model to obtain a second probability value corresponding to each item of candidate clinical data.

[0098] The previously determined candidate clinical data are entered into the multivariate logistic regression analysis model, and these candidate clinical data are used as independent variables to predict the outcome variables of the efficacy of rheumatic mitral valvuloplasty. Through the model fitting process, the second probability value corresponding to each candidate clinical data can be obtained. These second probability values ​​reflect the model's prediction of the results corresponding to each candidate clinical data.

[0099] Step b2, determining the candidate clinical data of the anterior mitral leaflet angle corresponding to the probability value less than the second preset threshold value in the second probability value as an independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty.

[0100] A second preset threshold value, such as 0.05, is determined. If the probability value of a candidate clinical data is less than the second preset threshold value, it is determined to be statistically significant. The candidate clinical data corresponding to the probability value whose second probability value is less than the threshold value is screened out, i.e., the candidate clinical data of the anterior mitral leaflet angle, and the anterior mitral leaflet angle is determined as an independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty.

[0101] Specifically, the candidate clinical data with a P value < 0.05 in Table 5 were entered into the multivariate logistic regression analysis model, including age, history of hypertension, history of stroke, left atrial thrombus, left atrial diameter, pulmonary artery pressure, ventricular septum thickness, left ventricular posterior wall thickness, mitral valve orifice area, degree of mitral stenosis, total Wilkins score, leaflet activity, subvalvular thickening, leaflet thickness, leaflet calcification, posterior leaflet length, mitral valve anterior leaflet zone 2 zona pellucida thickness, and mitral valve anterior leaflet zone 2 roughness thickness. In the multivariate analysis, it was found that the mitral valve anterior leaflet annular angle was an independent predictor of the efficacy of rheumatic mitral valvuloplasty (OR = 0.850, 95% CI: 0.789-0.915, P = 0.000), as shown in Table 6.

[0102] Table 6

[0103]

[0104] The clinical data processing method for rheumatic heart valve disease provided by the embodiment of the present invention systematically analyzes the relationship between various clinical data and the efficacy of rheumatic mitral valvuloplasty surgery through a univariate logistic regression analysis model, which helps to determine the degree of influence of each clinical variable on the surgical effect. Using the first probability value to characterize whether the influence of various clinical data on the surgical efficacy is statistically significant helps to determine which clinical factors have a significant impact on the surgical effect, thereby helping doctors to better evaluate the patient's prognosis and formulate a treatment plan. Determining the clinical data corresponding to the probability value less than the first preset threshold as candidate clinical data can help screen out the most potential predictive factors, thereby reducing unnecessary data analysis and improving efficiency. Through a multi-factor logistic regression analysis model, it is determined that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty surgery is the mitral anterior leaflet annular angle, which helps doctors to more accurately evaluate the patient's prognosis and provide guidance for personalized treatment. Using the logistic regression analysis model, combined with statistical methods, the main factors affecting the surgical efficacy can be determined under the condition of considering multiple clinical factors, thereby improving the accuracy and reliability of the prediction. By determining the independent predictive factors, practical guidance can be provided to clinicians to help better evaluate the patient's prognosis and formulate personalized treatment plans. Through the multivariate logistic regression analysis model, further in-depth analysis of the impact of candidate clinical data on the efficacy of rheumatic mitral valvuloplasty surgery can help identify more critical predictive factors. Determining the candidate clinical data corresponding to the probability value in the second probability value that is less than the second preset threshold as a predictive factor helps to screen out the most influential and predictive factors, thereby improving the accuracy and reliability of the model. By screening out independent predictive factors, the doctor's decision-making process can be simplified, allowing them to focus more on key clinical variables, thereby improving the efficiency and accuracy of decision-making. After determining the independent predictive factor, the treatment plan can be optimized according to the specific situation of the factor to improve the treatment effect and patient prognosis.

[0105] In this embodiment, a verification method for predicting the anterior leaflet angle of a mitral valve is provided, which can be used in a computer device. Figure 4 is a flow chart of a verification method for predicting the anterior leaflet angle of the mitral valve according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0106] Step S301, obtaining the mitral valve anterior leaflet angle data corresponding to multiple patients and the corresponding rheumatic mitral valvuloplasty surgery efficacy data.

[0107] The mitral valve anterior leaflet annular angle data is the angle between the line connecting the mitral valve anterior leaflet root and the mitral valve annulus at mid-diastole in the standard four-chamber heart section and the mitral valve annulus. Specifically, the mitral valve anterior leaflet annular angle data corresponding to multiple patients are measured and recorded by cardiac ultrasound examination (echocardiography).

[0108] The efficacy data of rheumatic mitral valvuloplasty refers to the postoperative efficacy of patients who undergo rheumatic mitral valvuloplasty, i.e., good and poor valvuloplasty effects. Specifically, the efficacy data of rheumatic mitral valvuloplasty can be obtained based on medical records and clinical databases.

[0109] Step S302, sorting the mitral valve anterior leaflet annular angle data from small to large, and calculating the true positive rate and false positive rate corresponding to each mitral valve anterior leaflet annular angle data according to the rheumatic mitral valvuloplasty surgery efficacy data.

[0110] According to the efficacy data of rheumatic mitral valvuloplasty, each mitral valve anterior leaflet annular angle data is classified, that is, the shaping operation effect is good or the shaping operation effect is not good. According to the classification results, the true positive rate and false positive rate corresponding to each mitral valve anterior leaflet annular angle data are calculated. The true positive rate indicates the proportion of the corresponding annular angle data that is correctly predicted as effective when the surgical effect is good. The false positive rate indicates the proportion of the corresponding annular angle data that is incorrectly predicted as effective when the surgical effect is not good. Among them, the true positive rate can also be called sensitivity, and the false positive rate can also be called 1-specificity.

[0111] Step S303: draw a subject curve according to the true positive rate and the false positive rate.

[0112] The true positive rate and false positive rate corresponding to each mitral valve anterior leaflet angle data were plotted as a receiver operating characteristic (ROC) to evaluate the performance of the classification model under different thresholds.

[0113] Specifically, Figure 5 As shown in the figure, the true positive rate (sensitivity) is used as the ordinate and the false positive rate (1-specificity) is used as the abscissa to draw the subject curve.

[0114] Step S304, calculating the area under the curve corresponding to the subject curve according to a preset numerical integration rule.

[0115] The area under the curve (AUC) is the area between the ROC curve and the horizontal axis, and is used to characterize the performance of the classification model (predicting the efficacy of rheumatic mitral valvuloplasty), that is, AUC is used to evaluate the performance of the model based on the mitral valve anterior leaflet annular angle data to predict the efficacy of rheumatic mitral valvuloplasty. According to the preset numerical integration rules, an appropriate method is selected to calculate the area under the curve. The method may include the rectangular method, the trapezoidal method, and the Simpson's rule, etc., which are not limited here. Using the selected numerical integration method, the area under the ROC curve is approximately calculated, for example, the area under the curve is divided into simple geometric shapes, and the areas of these shapes are calculated. The areas of each geometric shape calculated by numerical integration are added to obtain the total area under the ROC curve, that is, AUC. The performance of the model is evaluated based on the calculated area under the curve. A larger AUC value generally indicates that the model has better performance, while a smaller AUC value indicates that the model has poor performance.

[0116] Step S305, determining whether the area under the curve is greater than a third preset threshold, and outputting a prediction value assessment of the anterior leaflet angle data of the mitral valve according to the determination result.

[0117] The third preset threshold is set for the AUC value. When the AUC is greater than the third preset threshold, it indicates that the performance of the model is good, that is, it has good efficacy in predicting the efficacy of rheumatic mitral valvuloplasty. If the AUC value is greater than the third preset threshold, it can be determined that the mitral valve anterior leaflet annulus angle data has good efficacy in predicting the efficacy of rheumatic mitral valvuloplasty.

[0118] The verification method for predicting the anterior mitral leaflet angle provided in the embodiment of the present invention comprehensively evaluates the severity of mitral valve disease and the efficacy of surgery by combining the anterior mitral leaflet angle data and the efficacy data of rheumatic mitral valvuloplasty, and has a more comprehensive evaluation capability. The use of objective indicators such as true positive rate and false positive rate for evaluation reduces the influence of subjective factors and improves the objectivity and credibility of the evaluation results. By drawing the receiver operating characteristic curve, the trade-off relationship between the true positive rate and the false positive rate under different thresholds is intuitively displayed, helping to determine the best prediction model. The area under the ROC curve is calculated using the numerical integration rule to more directly quantify the accuracy and stability of the prediction model. By setting a preset threshold, the evaluation results are made operational, and corresponding clinical decisions can be made according to specific circumstances.

[0119] like Figure 5 The total area under the ROC curve is 0.843. Since the AUC value ranges from 0 to 1, where 0.5 represents random guessing and 1 represents perfect prediction, 0.843 indicates that the model has good predictive ability, that is, it can be determined that the anterior mitral leaflet angle has good efficacy in predicting the efficacy of rheumatic mitral valvuloplasty.

[0120] Furthermore, on the ROC curve, the corresponding cutoff values ​​when the true positive rate and false positive rate are both 95% are selected, and these cutoff values ​​are 37.7° and 26.7°, respectively. When the patient's anterior leaflet annulus angle is greater than 37.7°, the true positive rate is 95%, which means that the prediction accuracy under this condition is high, and the patient has a high probability of benefiting from rheumatic mitral valvuloplasty. When the patient's anterior leaflet annulus angle is less than 26.7°, the false positive rate is 95%, which means that a certain proportion of patients are actually not suitable for rheumatic mitral valvuloplasty, but should choose mitral valve replacement surgery.

[0121] The verification method for predicting the anterior mitral leaflet angle provided by the embodiment of the present invention establishes a method for screening patients for rheumatic mitral valvuloplasty based on the anterior mitral leaflet angle. When patients with rheumatic mitral valve disease are admitted to the hospital, only one ultrasound index is measured. When the anterior mitral leaflet angle of the patient is greater than 37.7°, rheumatic mitral valvuloplasty can be the first choice. When the anterior mitral leaflet angle is less than 26.7°, the early effect of the mitral valve repair surgery is poor, so mitral valve replacement surgery is the first choice, thereby guiding clinical practice.

[0122] In this embodiment, a clinical data processing device for rheumatic heart valve disease is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0123] This embodiment provides a clinical data processing device for rheumatic heart valve disease, such as Figure 6 As shown, including:

[0124] The first acquisition module 401 is used to acquire multiple clinical data; wherein the clinical data include first clinical data corresponding to multiple first patients with good mitral valvuloplasty results, and second clinical data corresponding to multiple second patients with poor mitral valvuloplasty results; the multiple second patients with poor mitral valvuloplasty results are used to characterize patients who have failed intraoperative mitral valvuloplasty and are converted to mitral valve replacement, and patients who have more than mild stenosis or regurgitation in the follow-up before discharge after mitral valvuloplasty.

[0125] The analysis module 402 is used to analyze multiple clinical data to obtain probability values ​​corresponding to each clinical data; wherein, for any clinical data, the probability value is used to characterize the degree of difference between the first clinical data and the second clinical data.

[0126] Determination module 403 is used to analyze multiple clinical data and probability values ​​to determine that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty surgery is the mitral valve anterior leaflet annular angle; wherein the mitral valve anterior leaflet annular angle represents the angle between the mitral valve anterior leaflet root and the mitral valve annulus at mid-diastole in the standard four-chamber heart section and the mitral valve annulus.

[0127] In some optional embodiments, the plurality of clinical data includes baseline characteristics of the patient, echocardiographic measurement results of the patient, surgical conditions of the patient, and early efficacy of the patient; the baseline characteristics are used to characterize the initial state of the patient before the start of treatment; the surgical conditions are used to characterize the type of surgery received by the patient and the results of the surgery; the early efficacy is used to characterize the early postoperative condition of the patient after surgical treatment; the echocardiographic measurement results are used to characterize the cardiac structure and function of the patient; the echocardiographic measurement results include the anterior leaflet angle of the mitral valve; the first acquisition module 401 includes:

[0128] The acquisition submodule is used to acquire the annular angle of the anterior leaflet of the mitral valve.

[0129] In some optional implementations, the acquisition submodule includes:

[0130] An acquisition unit for acquiring echocardiograms of multiple patients.

[0131] The measuring unit is used to measure the angle between the line connecting the root of the anterior leaflet of the mitral valve and the tip of the anterior leaflet of the mitral valve and the valvular ring of the mitral valve according to the echocardiogram.

[0132] In some optional implementations, the analysis module 402 includes:

[0133] The first statistical submodule is used to input multiple clinical data into the data statistical tool to obtain the probability value corresponding to each clinical data.

[0134] In some optional implementations, the determining module 403 includes:

[0135] The second statistical submodule is used to enter multiple clinical data and probability values ​​into a univariate logistic regression analysis model to obtain a first probability value corresponding to each clinical data; wherein the first probability value is used to characterize whether the influence of each clinical data on the efficacy of rheumatic mitral valvuloplasty surgery is statistically significant.

[0136] The determination submodule is used to determine the clinical data corresponding to the probability value less than the first preset threshold value in the first probability value as candidate clinical data.

[0137] The third statistical submodule is used to enter the candidate clinical data into a multivariate logistic regression analysis model to determine that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the anterior leaflet angle of the mitral valve.

[0138] In some optional implementations, the third statistics submodule includes:

[0139] The statistical unit is used to input the candidate clinical data into a multi-factor logistic regression analysis model to obtain a second probability value corresponding to each item of candidate clinical data.

[0140] The determination unit is used to determine the candidate clinical data of the anterior mitral leaflet angle corresponding to the probability value less than the second preset threshold value in the second probability value as an independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty.

[0141] This embodiment provides a verification device for predicting the anterior leaflet angle of the mitral valve. Figure 7 As shown, including:

[0142] The second acquisition module 501 is used to acquire the mitral valve anterior leaflet annular angle data corresponding to multiple patients, and the corresponding rheumatic mitral valvuloplasty surgery efficacy data.

[0143] The sorting module 502 is used to sort the anterior mitral leaflet angle data from small to large, and calculate the true positive rate and false positive rate corresponding to each anterior mitral leaflet angle data according to the rheumatic mitral valvuloplasty surgery efficacy data.

[0144] The drawing module 503 is used to draw a subject curve according to the true positive rate and the false positive rate.

[0145] The calculation module 504 is used to calculate the area under the curve corresponding to the subject curve according to a preset numerical integration rule.

[0146] The judgment module 505 is used to judge whether the area under the curve is greater than a third preset threshold value, and output a prediction value assessment of the anterior leaflet angle data of the mitral valve according to the judgment result.

[0147] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0148] The clinical data processing device for rheumatic heart valvular disease and the verification device for predicting the anterior mitral leaflet angle in this embodiment are presented in the form of functional units, where the units refer to ASIC (Application Specific Integrated Circuit) circuits, processors and memories that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0149] The clinical data processing device for rheumatic heart valve disease provided by the embodiment of the present invention obtains a plurality of clinical data, including data of a plurality of first patients and a plurality of second patients. This comprehensive data collection is helpful for comprehensively evaluating the effect of the operation. The patients are divided into two groups, those with good anatomy and those with poor anatomy, thereby distinguishing the clinical data under different results, which helps to gain a deeper understanding of the differences in the effects of the operation and may provide clues for further intervention. By analyzing the clinical data, the probability values ​​corresponding to each item of clinical data are obtained. These values ​​can be used to quantify the degree of difference between the first clinical data and the second clinical data, so that the data differences under different results can be objectively evaluated. It was determined that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the annular angle of the anterior leaflet of the mitral valve, which is of great significance for clinical practice, because the annular angle of the anterior leaflet of the mitral valve can help doctors better predict the effect of the operation and provide a basis for preoperative decision-making.

[0150] The verification device for predicting the anterior mitral leaflet angle provided in the embodiment of the present invention comprehensively evaluates the effectiveness of the anterior mitral leaflet angle in predicting the efficacy of rheumatic mitral valvuloplasty surgery by calculating the subject curve and the area under the curve, and provides a comprehensive evaluation of the overall performance of the prediction model. The subject curve provides an intuitive graphical display that can clearly show the performance characteristics of the model. Doctors and researchers can understand the predictive ability of the model by observing the shape of the curve and the area under the curve. By comparing the area under the subject curve with the preset threshold, it is possible to directly determine whether the effectiveness of the model has reached the expected level, so that the effectiveness evaluation of the model has clear standards and comparability. After determining that the anterior mitral leaflet angle has good effectiveness in predicting the efficacy of rheumatic mitral valvuloplasty surgery, it can provide important reference information for clinicians to help them more accurately evaluate the prognosis of patients and formulate reasonable treatment plans.

[0151] The embodiment of the present invention also provides a computer device having the above Figure 6 The clinical data processing device for rheumatic heart valve disease shown, and Figure 7 The validation device for predicting the anterior mitral leaflet annular angle is shown.

[0152] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 8As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0153] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0154] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0155] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0156] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0157] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 8 The example of connecting through bus is taken in the following.

[0158] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0159] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0160] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0161] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A clinical data processing method for rheumatic heart valve disease, characterized in that: The method comprises: Acquire multiple clinical data; wherein, the clinical data include first clinical data corresponding to multiple first patients with good mitral valvuloplasty results, and second clinical data corresponding to multiple second patients with poor mitral valvuloplasty results; the multiple second patients with poor mitral valvuloplasty results are used to characterize patients who have failed intraoperative mitral valvuloplasty and have undergone mitral valve replacement, and patients who have more than mild stenosis or regurgitation in a follow-up examination before discharge after mitral valvuloplasty; wherein, the multiple clinical data include the patient's baseline characteristics, the patient's echocardiographic measurement results, the patient's surgical conditions, and the patient's early efficacy; the baseline characteristics are used to characterize the patient's initial state before the start of treatment; the surgical conditions Used to characterize the type of surgery a patient has undergone and the results of the surgery; the early efficacy is used to characterize the early postoperative condition of a patient after surgical treatment; the echocardiographic measurement results are used to characterize the patient's heart structure and function; the echocardiographic measurement results include the mitral valve anterior leaflet annular angle, and the mitral valve annular angle represents the angle between the line connecting the mitral valve anterior leaflet root and the mitral valve annular tip at mid-diastole on a standard four-chamber heart section and the mitral valve annulus; obtaining the mitral valve annular angle includes: obtaining echocardiograms of multiple patients; and measuring, based on the echocardiograms, the angle between the mitral valve anterior leaflet root and the mitral valve annular tip and the mitral valve annulus; Analyze the multiple clinical data to obtain probability values ​​corresponding to each clinical data; wherein, for any clinical data, the probability value is used to characterize the degree of difference between the first clinical data and the second clinical data; wherein, statistical tools and techniques are used to perform statistical analysis on the multiple clinical data collected to explore the difference and correlation between the first clinical data and the second clinical data for any clinical data; Analyze the multiple clinical data and the probability values ​​to determine that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the mitral anterior leaflet angle, including: entering the multiple clinical data and the probability values ​​into a univariate logistic regression analysis model to obtain a first probability value corresponding to each clinical data; wherein the first probability value is used to characterize whether the influence of each clinical data on the efficacy of rheumatic mitral valvuloplasty is statistically significant; determine the clinical data corresponding to the probability value less than a first preset threshold value in the first probability value as candidate clinical data; enter the candidate clinical data into a multivariate logistic regression analysis model to determine the probability of predicting the efficacy of rheumatic mitral valvuloplasty. The independent predictor of the efficacy of the surgery is the anterior mitral leaflet angle, including: entering the candidate clinical data into the multifactorial logistic regression analysis model to obtain the second probability value corresponding to each of the candidate clinical data; determining the candidate clinical data of the anterior mitral leaflet angle corresponding to the probability value less than the second preset threshold in the second probability value as the independent predictor of the efficacy of the rheumatic mitral valvuloplasty surgery; the unifactorial logistic regression analysis model is used to explore the relationship between each clinical data and the effect of the mitral valvuloplasty surgery; the multifactorial logistic regression model is used to simultaneously consider the influence of multiple candidate clinical data on the effect of the mitral valvuloplasty surgery, as well as the interaction between the multiple candidate clinical data; Among them, the candidate clinical data are entered into the multifactor logistic regression analysis model, and the multifactor logistic regression model simultaneously considers the influence of multiple candidate clinical data on the effect of the shaping operation, as well as the interaction between the multiple candidate clinical data; in the multifactor logistic regression model, the coefficients of each candidate clinical data are analyzed to determine which candidate clinical data are independent and significant predictive factors, and the coefficient represents the degree of influence of each candidate clinical data on the effect of the shaping operation, while the statistical test can determine whether the influence is significant; in this process, the anterior leaflet angle of the mitral valve is found to be a significant and independent predictive factor; considering other possible factors, the anterior leaflet angle of the mitral valve has an important independent influence on predicting the efficacy of rheumatic mitral valvuloplasty; by determining the anterior leaflet angle of the mitral valve as an independent predictive factor, more accurate information is provided for the prediction of the surgical efficacy.

2. The method according to claim 1, characterized in that The analyzing the plurality of clinical data to obtain probability values ​​corresponding to each of the clinical data includes: The multiple clinical data are input into a data statistical tool to obtain the probability value corresponding to each clinical data.

3. A verification method for predicting the anterior leaflet angle of the mitral valve, characterized in that: The clinical data processing method for rheumatic heart valve disease according to claim 1 is implemented, comprising: Obtain the mitral valve anterior leaflet angle data and the corresponding rheumatic mitral valvuloplasty surgery efficacy data for multiple patients; The anterior mitral leaflet angle data are sorted from small to large, and the true positive rate and false positive rate corresponding to each anterior mitral leaflet angle data are calculated according to the rheumatic mitral valvuloplasty surgery efficacy data; Plotting a subject curve according to the true positive rate and the false positive rate; Calculating the area under the curve corresponding to the subject curve according to a preset numerical integration rule; Determine whether the area under the curve is greater than a third preset threshold, and output a prediction value assessment of the mitral valve anterior leaflet annular angle data based on the determination result.

4. A clinical data processing device for rheumatic heart valve disease, characterized in that: The device comprises: An acquisition module is used to acquire a plurality of clinical data; wherein the clinical data include first clinical data corresponding to a plurality of first patients with good angioplasty results, and second clinical data corresponding to a plurality of second patients with poor angioplasty results; the plurality of second patients with poor angioplasty results are used to characterize patients who have failed mitral valvuloplasty during surgery and have undergone mitral valve replacement, and patients who have more than mild stenosis or regurgitation in a follow-up examination before discharge after mitral valvuloplasty; wherein the plurality of clinical data include the patient's baseline characteristics, the patient's echocardiographic measurement results, the patient's surgical conditions, and the patient's early efficacy; the baseline characteristics are used to characterize the patient's initial state before the start of treatment; The surgical condition is used to characterize the type of surgery the patient received and the surgical results; the early efficacy is used to characterize the early postoperative condition of the patient after surgical treatment; the echocardiographic measurement results are used to characterize the patient's heart structure and function; the echocardiographic measurement results include the mitral valve anterior leaflet annular angle, and the mitral valve annular angle represents the angle between the mitral valve anterior leaflet root and the mitral valve annulus cusp in mid-diastole of the standard four-chamber heart section and the mitral valve annulus; obtaining the mitral valve annular angle includes: obtaining echocardiograms of multiple patients; and measuring the angle between the mitral valve annular root and the mitral valve annulus cusp according to the echocardiogram; An analysis module, configured to analyze the plurality of clinical data to obtain probability values ​​corresponding to each of the clinical data; wherein, for any clinical data, the probability value is used to characterize the degree of difference between the first clinical data and the second clinical data; wherein, statistical tools and techniques are used to perform statistical analysis on the plurality of clinical data collected to explore the difference and correlation between the first clinical data and the second clinical data for any clinical data; A determination module is used to analyze the multiple clinical data and the probability values ​​to determine that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the anterior mitral leaflet angle, including: entering the multiple clinical data and the probability values ​​into a univariate logistic regression analysis model to obtain a first probability value corresponding to each of the clinical data; wherein the first probability value is used to characterize whether the influence of each of the clinical data on the efficacy of rheumatic mitral valvuloplasty is statistically significant; the clinical data corresponding to the probability value less than a first preset threshold value in the first probability value is determined as candidate clinical data; the candidate clinical data is entered into a multivariate logistic regression analysis model to determine that the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty is the anterior mitral leaflet angle, including: entering the candidate clinical data into the multivariate logistic regression analysis model to obtain a second probability value corresponding to each of the candidate clinical data; the candidate clinical data of the anterior mitral leaflet angle corresponding to the probability value less than a second preset threshold value in the second probability value is determined as the independent predictive factor for predicting the efficacy of rheumatic mitral valvuloplasty; the univariate logistic regression analysis The model is used to explore the relationship between various clinical data and the effect of plastic surgery; the multivariate logistic regression model is used to simultaneously consider the impact of multiple candidate clinical data on the effect of plastic surgery, as well as the interaction between the multiple candidate clinical data; wherein, the candidate clinical data are entered into the multivariate logistic regression analysis model, and the multivariate logistic regression model simultaneously considers the impact of multiple candidate clinical data on the effect of plastic surgery, as well as the interaction between the multiple candidate clinical data; in the multivariate logistic regression model, by analyzing the coefficients of each candidate clinical data, it is determined which candidate clinical data are independent and significant predictive factors, and the coefficient represents the degree of influence of each candidate clinical data on the effect of plastic surgery, and the statistical test can determine whether the influence is significant; in this process, the anterior mitral leaflet angle was found to be a significant and independent predictive factor; considering other possible factors, the anterior mitral leaflet angle has an important independent influence on predicting the efficacy of rheumatic mitral valve plastic surgery; by determining the anterior mitral leaflet angle as an independent predictive factor, more accurate information is provided for the prediction of surgical efficacy.

5. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the clinical data processing method for rheumatic heart valve disease described in any one of claims 1 to 3, or the verification method for predicting the anterior leaflet angle of the mitral valve described in claim 4 by executing the computer instructions.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the clinical data processing method for rheumatic heart valve disease described in claim 1 or 2, or the verification method for predicting the anterior leaflet angle of the mitral valve described in claim 3.

7. A computer program product, characterized in that It comprises computer instructions, wherein the computer instructions are used to cause a computer to execute the clinical data processing method for rheumatic heart valve disease as described in claim 1 or 2, or the verification method for predicting the anterior leaflet angle of the mitral valve as described in claim 3.

Images