Method for non-invasive diagnosis of pulmonary arterial hypertension and related apparatus

Abstract

Disclosed in the present application are a method for non-invasive diagnosis of pulmonary arterial hypertension and a related apparatus, relating to the technical field of arterial detection. The method comprises: acquiring an echocardiographic result and right-heart catheterization pulmonary artery pressure data of a patient with suspected pulmonary arterial hypertension; according to the regurgitation spectrum deficiency degree of a tricuspid regurgitation spectrum, grading, on the basis of the TR spectrum quality grading standard, the quality of the tricuspid regurgitation spectrum; according to the echocardiographic result and the pulmonary artery pressure data, constructing, on the basis of a grading result, a personalized pulmonary arterial hypertension diagnosis model; and according to the diagnosis model, obtaining, on the basis of the echocardiographic result of a target patient with pulmonary arterial hypertension, a pulmonary arterial hypertension diagnosis result of the target patient. The present application can realize personalized and accurate diagnosis for different patients with pulmonary arterial hypertension.

Description

A non-invasive method and related device for diagnosing pulmonary hypertension Technical Field

[0001] This application relates to the field of arterial detection technology, and in particular to a method and related device for non-invasive diagnosis of pulmonary hypertension. Background Technology

[0002] Right heart catheterization is the gold standard for diagnosing pulmonary hypertension, but its invasive nature makes it unsuitable for screening and follow-up. Echocardiography, which can estimate pulmonary artery systolic pressure by measuring tricuspid regurgitation, has proven accurate and shows good concordance with right heart catheterization. However, not every patient with pulmonary hypertension has tricuspid regurgitation, and even when regurgitation is present, small amounts can lead to unclear regurgitation spectra and inaccurate measurements; this phenomenon is particularly common in early-stage pulmonary hypertension. Therefore, early-stage pulmonary hypertension is easily missed. Summary of the Invention

[0003] The purpose of this application is to provide a method and related device for non-invasive diagnosis of pulmonary hypertension, which can accurately diagnose patients with early pulmonary hypertension without trauma.

[0004] To achieve the above objectives, this application provides the following solution:

[0005] In a first aspect, this application provides a non-invasive method for diagnosing pulmonary hypertension, comprising:

[0006] Acquire echocardiographic results and right heart catheterization pulmonary artery pressure data of suspected pulmonary artery patients who underwent echocardiography and right heart catheterization within a set time period and whose ultrasound images were clear; the echocardiogram includes cardiac structural parameters, right ventricular systolic function parameters, and right ventricular hemodynamic parameters; the echocardiographic result is the tricuspid regurgitation spectrum.

[0007] Based on the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum, the quality of the tricuspid regurgitation spectrum is classified according to the TR spectrum quality grading standard; the grading results include grades with unidentifiable peaks and grades with identifiable peaks.

[0008] Based on echocardiographic results and right heart catheterization pulmonary artery pressure data, a pulmonary hypertension diagnostic model is constructed based on the quality grading of the tricuspid regurgitation spectrum. The pulmonary hypertension diagnostic model is used to diagnose pulmonary hypertension in patients suspected of having pulmonary artery disease whose tricuspid regurgitation spectrum quality is at a level where the peak value cannot be identified, based on a first calculation formula. The pulmonary hypertension diagnostic model is used to diagnose pulmonary hypertension in patients suspected of having pulmonary artery disease whose tricuspid regurgitation spectrum quality is at a level where the peak value can be identified, based on a second calculation formula.

[0009] Based on the pulmonary hypertension diagnostic model, and using the echocardiographic results of the target pulmonary artery patients, the diagnostic results of pulmonary hypertension in the target pulmonary artery patients are obtained.

[0010] Secondly, this application provides a non-invasive device for diagnosing pulmonary hypertension, comprising:

[0011] The data acquisition module is used to acquire the echocardiogram results and right heart catheterization pulmonary artery pressure data of patients suspected of having pulmonary artery disease who have undergone echocardiography and right heart catheterization within a set time period and whose ultrasound images are clear. The echocardiogram includes cardiac structural parameters, right ventricular systolic function parameters, and right ventricular hemodynamic parameters. The echocardiogram result is the tricuspid regurgitation spectrum.

[0012] The grading module is used to grade the quality of the tricuspid regurgitation spectrum based on the TR spectrum quality grading standard, according to the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum. The grading results include grades with unidentifiable peaks and grades with identifiable peaks.

[0013] The model building module is used to construct a pulmonary hypertension diagnostic model based on the quality grading results of the tricuspid regurgitation spectrum, according to echocardiographic results and right heart catheterization pulmonary artery pressure data. The pulmonary hypertension diagnostic model is used to diagnose pulmonary hypertension in suspected pulmonary artery patients whose tricuspid regurgitation spectrum quality is at a level where the peak value cannot be identified, based on a first calculation formula. The pulmonary hypertension diagnostic model is used to diagnose pulmonary hypertension in suspected pulmonary artery patients whose tricuspid regurgitation spectrum quality is at a level where the peak value can be identified, based on a second calculation formula.

[0014] The diagnostic module is used to obtain the diagnostic results of pulmonary hypertension in the target pulmonary artery patient based on the echocardiographic results of the target pulmonary artery patient according to the pulmonary hypertension diagnostic model.

[0015] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a non-invasive method for diagnosing pulmonary hypertension as described above.

[0016] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for non-invasive diagnosis of pulmonary hypertension as described above.

[0017] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements a method for non-invasive diagnosis of pulmonary hypertension as described above.

[0018] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0019] This application provides a non-invasive method and related apparatus for diagnosing pulmonary hypertension. The method involves collecting images and pressure data from suspected pulmonary hypertension patients who undergo echocardiography and right heart catheterization within a specific time period. Then, cardiac structural parameters, right ventricular function parameters, and hemodynamic parameters are extracted from the echocardiogram, and the tricuspid regurgitation spectrum is obtained. The quality of the tricuspid regurgitation spectrum is graded to select an appropriate calculation formula for pulmonary hypertension diagnosis. Next, a pulmonary hypertension diagnostic model is constructed using the echocardiogram, right heart catheterization data, and spectrum quality grading results to improve diagnostic accuracy. Finally, an accurate diagnosis of pulmonary hypertension is obtained based on the model and the echocardiographic results and pressure data of the target patients. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 is an application environment diagram of a non-invasive method for diagnosing pulmonary hypertension according to an embodiment of this application.

[0022] Figure 2 is a flowchart illustrating a non-invasive method for diagnosing pulmonary hypertension according to an embodiment of this application.

[0023] Figure 3 is a schematic diagram of the TR spectrum quality grading standard provided in an embodiment of this application.

[0024] Figure 4 is a schematic diagram of the functional modules of a non-invasive diagnostic device for pulmonary hypertension provided in an embodiment of this application.

[0025] Figure 5 is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] This embodiment describes a non-invasive method for diagnosing pulmonary hypertension, applicable to the environment shown in Figure 1. Terminal 102 and server 104 communicate via a network, and a data storage system stores the data required for server processing. Terminal 102 sends echocardiogram and right heart catheterization data to server 104, and server 104 returns the pulmonary hypertension diagnosis result to terminal 102.

[0028] As shown in Figure 2, a non-invasive method for diagnosing pulmonary hypertension is provided. This method is illustrated using server 104 in Figure 1 as an example, and includes the following steps 201 to 204. Wherein:

[0029] Step 201: Obtain echocardiogram results and right heart catheterization pulmonary artery pressure data of suspected pulmonary artery patients who underwent echocardiography and right heart catheterization within a set time period and whose ultrasound images are clear; the echocardiogram includes cardiac structural parameters, right ventricular systolic function parameters, and right ventricular hemodynamic parameters; the echocardiogram result is the tricuspid regurgitation spectrum.

[0030] Step 202: Based on the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum, classify the quality of the tricuspid regurgitation spectrum according to the TR spectrum quality grading standard; the grading results include the level of peaks that cannot be identified and the level of peaks that can be identified.

[0031] Step 203: Based on the echocardiogram results and right heart catheter pulmonary artery pressure data, and based on the quality grading results of the tricuspid regurgitation spectrum, construct a pulmonary hypertension diagnostic model; the pulmonary hypertension diagnostic model is used to diagnose pulmonary hypertension in patients suspected of having pulmonary artery disease whose tricuspid regurgitation spectrum quality is at a level where the peak value cannot be identified, based on the first calculation formula; the pulmonary hypertension diagnostic model is used to diagnose pulmonary hypertension in patients suspected of having pulmonary artery disease whose tricuspid regurgitation spectrum quality is at a level where the peak value can be identified, based on the second calculation formula.

[0032] Step 204: Based on the pulmonary hypertension diagnostic model and the echocardiographic results of the target pulmonary artery patient, obtain the pulmonary hypertension diagnostic results of the target pulmonary artery patient.

[0033] When performing step 201, the specific steps can be as follows:

[0034] This embodiment includes patients suspected of having pulmonary artery disease who underwent echocardiography and right heart catheterization within 7 days and whose ultrasound images were clear. The data collected included parameters of cardiac structure, right ventricular systolic function, right ventricular hemodynamics, and pulmonary artery pressure data from right heart catheterization.

[0035] When performing step 202, the specific steps can be as follows:

[0036] As shown in Figure 3, based on the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum, and using the TR spectrum quality grading standard, the quality of the tricuspid regurgitation spectrum is graded, specifically including:

[0037] When the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum is completely missing, the tricuspid regurgitation spectrum is set to level 0.

[0038] When the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum is greater than or equal to 2 / 3 of the complete regurgitation spectrum, the tricuspid regurgitation spectrum is set to level 1 (as shown in Figure 3A).

[0039] When the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum is greater than or equal to 1 / 3 of the complete regurgitation spectrum but less than 2 / 3 of the complete regurgitation spectrum, the tricuspid regurgitation spectrum is set to level 2 (as shown in B of Figure 3).

[0040] When the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum is less than 1 / 3 of the complete regurgitation spectrum, the tricuspid regurgitation spectrum is set to level 3 (as shown in C of Figure 3).

[0041] When the regurgitation spectrum of the tricuspid regurgitation spectrum is a complete regurgitation spectrum, the tricuspid regurgitation spectrum is set to level 4 (as shown in D of Figure 3).

[0042] Among them, the levels where peak values ​​cannot be identified include levels 0, 1, and 2. The levels where peak values ​​can be identified include levels 3 and 4.

[0043] When performing step 203,

[0044] The first calculation formula in the pulmonary hypertension diagnostic model is:

[0045] A1=-3.57+1.646×Notch-0.036×TVE+0.475×RVESA+0.251×LAEDA.

[0046] Wherein, Notch is the mid-systolic spectral notch of the right ventricular outflow tract, TVE is the tricuspid valve velocity E peak, RVESA is the right ventricular end-systolic area, and LAEDA is the left atrial end-diastolic area. A1 > 1.44 indicates pulmonary hypertension; A1 ≤ 1.44 indicates the absence of pulmonary hypertension.

[0047] The second calculation formula is:

[0048] A2=-5.038-0.064×TVE+2.17×TRV+0.352×RVESA.

[0049] Where TVE is the peak tricuspid regurgitation velocity (E-peak), TRV is the peak tricuspid regurgitation velocity, and RVESA is the right ventricular end-systolic area. A2 > 1.70 indicates pulmonary hypertension; A2 ≤ 1.70 indicates the absence of pulmonary hypertension.

[0050] Specifically, for patients with no or little tricuspid regurgitation, the spectral quality was grade 0 to 2, and the first calculation formula was constructed.

[0051] This embodiment performs ROC curve analysis on the output of the first calculation formula. On the training set, the AUC value reached 0.903 (95% confidence interval: 0.862 to 0.944, P-value: 0.524). A score exceeding 1.44 is considered the optimal cutoff value for the scoring model. The model has a specificity of 83%, a sensitivity of 83%, a positive predictive value of 97%, a negative predictive value of 46%, and an accuracy of 83%. The AUC values ​​for the internal and external validation sets are 0.814 and 0.868, respectively. (Specificity = True negative / (True negative + False positive); Sensitivity = True positive / (True positive + False negative); Positive predictive value = True positive / (True positive + False positive); Negative predictive value = True negative / (True negative + False negative); Accuracy = (True positive + True negative) / Total predictions).

[0052] Specifically, a second calculation formula was constructed for patients with clear tricuspid regurgitation spectrum (spectral quality of 3-4).

[0053] This embodiment performs ROC curve analysis on the output of the second calculation formula. The results show that the AUC on the training set is 0.925 (95% IC 0.892-0.958, P = 0.532). A score greater than 1.70 is the optimal cutoff value for the scoring model. Its specificity is 91%, sensitivity is 81%, positive predictive value is 98%, negative predictive value is 46%, and accuracy is 82%. The AUC on the internal validation set is 0.883. The AUC on external data validation is 0.917.

[0054] As shown in Figure 4, a non-invasive device for diagnosing pulmonary hypertension includes:

[0055] The data acquisition module 401 is used to acquire the echocardiogram results and right heart catheterization pulmonary artery pressure data of patients suspected of having pulmonary artery who have undergone echocardiography and right heart catheterization within a set time period and whose ultrasound images are clear. The echocardiogram includes cardiac structural parameters, right ventricular systolic function parameters, and right ventricular hemodynamic parameters. The echocardiogram result is the tricuspid regurgitation spectrum.

[0056] The grading module 402 is used to grade the quality of the tricuspid regurgitation spectrum based on the TR spectrum quality grading standard according to the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum; the grading results include the level of peaks that cannot be identified and the level of peaks that can be identified.

[0057] The model building module 403 is used to construct a pulmonary hypertension diagnostic model based on the quality grading results of the tricuspid regurgitation spectrum, according to the echocardiogram results and right heart catheter pulmonary artery pressure data. The pulmonary hypertension diagnostic model is used to diagnose pulmonary hypertension in patients suspected of having pulmonary artery disease whose tricuspid regurgitation spectrum quality is at a level where the peak value cannot be identified, based on the first calculation formula. The pulmonary hypertension diagnostic model is used to diagnose pulmonary hypertension in patients suspected of having pulmonary artery disease whose tricuspid regurgitation spectrum quality is at a level where the peak value can be identified, based on the second calculation formula.

[0058] The diagnostic module 404 is used to obtain the diagnostic result of pulmonary hypertension in the target pulmonary artery patient based on the echocardiographic results of the target pulmonary artery patient according to the pulmonary hypertension diagnostic model.

[0059] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as shown in Figure 5. The computer device includes a processor, memory, input / output interfaces (I / O), and communication interfaces.

[0060] A computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0061] A computer-readable storage medium is provided that stores a computer program, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0062] A computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0063] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. In summary, the content of this specification should not be construed as a limitation of this application.

Claims

1. A non-invasive method for diagnosing pulmonary hypertension, characterized in that, The method includes: Acquire echocardiographic results and right heart catheterization pulmonary artery pressure data of suspected pulmonary artery patients who underwent echocardiography and right heart catheterization within a set time period and whose echocardiographic images were clear; the echocardiogram includes cardiac structural parameters, right ventricular systolic function parameters, and right ventricular hemodynamic parameters; the echocardiographic result is a tricuspid regurgitation spectrum. Based on the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum, the quality of the tricuspid regurgitation spectrum is classified according to the TR spectrum quality grading standard; the grading results include a level where the peak cannot be identified and a level where the peak can be identified. Based on echocardiographic results and right heart catheterization pulmonary artery pressure data, and using the quality grading results of the tricuspid regurgitation spectrum, a pulmonary hypertension diagnostic model is constructed. This model is used, based on a first calculation formula, to diagnose pulmonary hypertension in patients suspected of having pulmonary artery disease whose tricuspid regurgitation spectrum quality is at a level where the peak value is unidentifiable. The second calculation formula is used to diagnose pulmonary hypertension in patients suspected of having pulmonary artery disease whose tricuspid regurgitation spectrum quality is at a level where the peak value is identifiable. Based on the pulmonary hypertension diagnostic model and the echocardiographic results of the target pulmonary artery patient, the diagnostic results of pulmonary hypertension for the target pulmonary artery patient are obtained.

2. The method for non-invasive diagnosis of pulmonary hypertension according to claim 1, characterized in that, The first calculation formula is: A1 = -3.57 + 1.646 × Notch - 0.036 × TVE + 0.475 × RVESA + 0.251 × LAEDA; Wherein, Notch is the mid-systolic spectral notch of the right ventricular outflow tract, TVE is the tricuspid valve velocity E peak, RVESA is the right ventricular end-systolic area, and LAEDA is the left atrial end-diastolic area. When A1>1.44, the patient is diagnosed with pulmonary hypertension, and when A1≤1.44, the patient is diagnosed with no pulmonary hypertension.

3. The method for non-invasive diagnosis of pulmonary hypertension according to claim 2, characterized in that, The second calculation formula is: A2 = -5.038 - 0.064 × TVE + 2.17 × TRV + 0.352 × RVESA; Among them, TVE is the tricuspid valve velocity peak E, TRV is the tricuspid regurgitation velocity peak, and RVESA is the right ventricular end-systolic area. When A2>1.70, the patient is diagnosed with pulmonary hypertension, and when A2≤1.70, the patient is diagnosed with no pulmonary hypertension.

4. The method for non-invasive diagnosis of pulmonary hypertension according to claim 3, characterized in that, Based on the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum, the quality of the tricuspid regurgitation spectrum is graded according to the TR spectrum quality grading standard, specifically including: When the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum is completely missing, the tricuspid regurgitation spectrum is set to level 0; When the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum is greater than or equal to 2 / 3 of the complete regurgitation spectrum, the tricuspid regurgitation spectrum is set to level 1; When the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum is greater than or equal to 1 / 3 of the complete regurgitation spectrum and less than 2 / 3 of the complete regurgitation spectrum, the tricuspid regurgitation spectrum is set to level 2. When the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum is less than 1 / 3 of the complete regurgitation spectrum, the tricuspid regurgitation spectrum is set to level 3; When the regurgitation spectrum of the tricuspid regurgitation spectrum is a complete regurgitation spectrum, the tricuspid regurgitation spectrum is set to level 4.

5. The method for non-invasive diagnosis of pulmonary hypertension according to claim 4, characterized in that, The levels at which the peak value cannot be identified include levels 0, 1, and 2.

6. The method for non-invasive diagnosis of pulmonary hypertension according to claim 5, characterized in that, The peak values ​​can be identified at levels 3 and 4.

7. A non-invasive device for diagnosing pulmonary hypertension, characterized in that, The device includes: The data acquisition module is used to acquire echocardiogram results and right heart catheterization pulmonary artery pressure data of patients suspected of having pulmonary artery disease who have undergone echocardiography and right heart catheterization within a set time period and whose ultrasound images are clear; the echocardiogram includes cardiac structural parameters, right ventricular systolic function parameters, and right ventricular hemodynamic parameters; the echocardiogram result is a tricuspid regurgitation spectrum; The grading module is used to grade the quality of the tricuspid regurgitation spectrum based on the TR spectrum quality grading standard according to the degree of missing regurgitation spectrum in the tricuspid regurgitation spectrum; the grading results include a level where the peak cannot be identified and a level where the peak can be identified. The model building module is used to construct a pulmonary hypertension diagnostic model based on the quality grading results of the tricuspid regurgitation spectrum, using echocardiographic results and right heart catheter pulmonary artery pressure data. The pulmonary hypertension diagnostic model is used to diagnose pulmonary hypertension in patients suspected of having pulmonary artery disease with a tricuspid regurgitation spectrum of unidentifiable peak quality, based on a first calculation formula. The pulmonary hypertension diagnostic model is also used to diagnose pulmonary hypertension in patients suspected of having pulmonary artery disease with a tricuspid regurgitation spectrum of identifiable peak quality, based on a second calculation formula. The diagnostic module is used to obtain the diagnostic result of pulmonary hypertension in the target pulmonary artery patient based on the echocardiographic results of the target pulmonary artery patient according to the pulmonary hypertension diagnostic model.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement a method for non-invasive diagnosis of pulmonary hypertension according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements a method for non-invasive diagnosis of pulmonary hypertension as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements a method for non-invasive diagnosis of pulmonary hypertension as described in any one of claims 1-6.

Images