Methods, devices, electronic equipment and media for assessing the risk of pulmonary embolism

Abstract

This invention discloses a method, device, electronic equipment, and medium for assessing the risk of pulmonary embolism. It relies entirely on collected non-invasive objective data and eliminates subjective judgments based on medical history or physician experience, effectively avoiding risk misjudgments caused by subjective variables in the PESI / sPESI model. This ensures the consistency and reliability of the assessment results. The ratio of Qa to Qb is used as the core assessment indicator. This ratio is a continuous variable, eliminating the need for empirical segmentation of parameters and avoiding significant differences in assessment results among patients with similar conditions. The risk level is assessed based on the ratio of Qa to Qb obtained through hemodynamic simulation. The results perfectly match clinical understanding of the severity of pulmonary embolism, improving assessment accuracy. Simultaneously, it reduces patient examination trauma and avoids high equipment and operational costs.

Description

Technical Field

[0001] This invention belongs to the technical field of pulmonary embolism risk assessment, and particularly relates to a method, device, electronic device and medium for assessing the risk of pulmonary embolism. Background Technology

[0002] Pulmonary embolism (PE) is a common and fatal disease in the emergency department, with significant variations in short-term mortality rates. The mortality rate for non-severe cases is less than 2%, while the mortality rate for cases complicated by cardiopulmonary arrest exceeds 95%. Therefore, accurate assessment of the prognostic risk of patients with acute PE is crucial for clinical treatment decisions. Computed tomography pulmonary angiography (CTPA) is the gold standard for PE diagnosis. Clinically, PE patients are identified solely based on the International Classification of Diseases (ICD) code. This approach may include patients with similar symptoms to PE but who do not have PE, thus failing to accurately predict the 30-day mortality rate of CTPA-diagnosed patients. Furthermore, there is a lack of efficient risk assessment tools for CTPA-diagnosed patients, and existing assessment models have many limitations, failing to meet clinical needs.

[0003] Current mainstream pulmonary embolism risk assessment models have significant shortcomings: First, the Pulmonary Embolism Severity Index (PESI) and its simplified version (sPESI) rely on subjective variables such as history of malignant tumors and chronic cardiopulmonary diseases, which can easily lead to misjudgment of risk due to information bias during the consultation process. Second, while the PERFORM model abandons reliance on past medical history and assesses risk through objective parameters such as age and heart rate, the parameter segmentation depends on physician experience, and the discontinuous assessment indicators after segmentation may lead to significant differences in assessment results among patients with similar conditions. Furthermore, this model does not incorporate pulmonary artery hemodynamic parameters and cannot reflect the disease's progression. The inherent nature of the problem limits the accuracy of the assessment. Thirdly, fractional flow reserve (FFR), as the gold standard for assessing coronary artery stenosis, has been attempted to be extended to assess pulmonary artery stenosis. However, traditional FFR measurement is an invasive procedure with high costs. Moreover, symptomatic pulmonary embolism patients often have complete blockage of branch vessels, with FFR values ​​close to 0, making it impossible to distinguish the severity of blockage between major and terminal branches. Clinically, patients with major branch blockage are considered to be more severely affected and require timely treatment, while patients with terminal branch blockage are considered to be relatively milder and require further observation. Obviously, the FFR assessment results differ significantly from clinical understanding. Summary of the Invention

[0004] Based on this, and in response to the aforementioned technical problems, a method, device, electronic device, and medium for assessing the risk of pulmonary embolism are provided.

[0005] The technical solution adopted in this invention is as follows: As a first aspect of the present invention, a method for assessing the risk of pulmonary embolism is provided, characterized in that it includes: S101. Collect the patient's pulmonary artery imaging data, physiological parameters, and complete blood count data, including the mean pulmonary artery pressure; S102. Import the pulmonary artery imaging data into the vascular modeling software, establish a three-dimensional model of the pulmonary artery, and determine the centerline and inner diameter of the main trunk and branches of the pulmonary artery, as well as the vascular occlusion status. S103. Assuming that each capillary at the terminal end of the pulmonary artery supplies the same lung volume, the lung volume is determined based on the pulmonary artery imaging data. The lung volume supplied by each pulmonary artery outlet is calculated according to the following relationship between the vessel diameters before and after bifurcation: The nth power of the inner diameter of the vessel before bifurcation is equal to the sum of the nth power of the inner diameters of all pulmonary arteries after bifurcation, where n is the bifurcation coefficient. S104. Based on the vascular inner diameter of each pulmonary artery outlet, the corresponding blood supply lung volume, and the preset minimum vascular inner diameter, generate the corresponding microvascular tree model starting from each pulmonary artery outlet. S105. Based on the generated microvascular tree model and the patient's blood routine data, the microcirculation resistance value of each pulmonary artery outlet is calculated using Poiseuille's theorem and Farin's effect. S106. Using the microcirculation resistance value of each pulmonary artery outlet as the outlet boundary condition and the average pressure of the pulmonary artery as the inlet boundary condition, assuming that blood is an incompressible Newtonian fluid, inputting the blood viscosity and density based on the blood routine data, after discretizing the pulmonary artery three-dimensional model, solving the NS equation through steady-state numerical simulation method to obtain the velocity field and pressure field of blood flow in the pulmonary artery, and determining the total pulmonary artery flow rate Qa based on the velocity field; S107. Find similar branches for each occluded branch based on size similarity, determine the vascular diameter of the occluded branch outlet based on size similarity with similar branches, take the occluded branch outlet as the pulmonary artery outlet, and regenerate the corresponding microvascular tree model with each pulmonary artery outlet as the starting point through S103-S104. S108. Determine the location of pulmonary artery stenosis in the pulmonary artery three-dimensional model, eliminate vascular stenosis based on the blood vessel diameter upstream and downstream of the stenosis location, and obtain a stenosis-free pulmonary artery three-dimensional model. Based on the stenosis-free pulmonary artery three-dimensional model, determine the total pulmonary artery flow Qb through S104-S106. S109. Calculate the ratio of Qa to Qb, and assess the risk of pulmonary embolism based on the ratio: the lower the ratio, the higher the risk of pulmonary embolism.

[0006] As a second aspect of the present invention, a device for assessing the risk of pulmonary embolism is provided, characterized in that it comprises: The first module is used for S101 to collect the patient's pulmonary artery imaging data, physiological parameters and blood routine data, wherein the physiological parameters include mean pulmonary artery pressure; The second module is used in S102 to import the pulmonary artery imaging data into the vascular modeling software, establish a three-dimensional model of the pulmonary artery, and determine the centerline and inner diameter of the pulmonary artery trunk and its branches, as well as the vascular occlusion status. The third module, used in S103, assumes that the volume of the lung supplied by each capillary at the terminal pulmonary artery is the same. Based on the pulmonary artery imaging data, the volume of the lung is determined, and the volume of the lung supplied by each pulmonary artery outlet is calculated according to the following relationship between the inner diameters of the vessels before and after the bifurcation: The nth power of the inner diameter of the vessel before bifurcation is equal to the sum of the nth power of the inner diameters of all pulmonary arteries after bifurcation, where n is the bifurcation coefficient. The fourth module is used in S104 to generate a corresponding microvascular tree model starting from each pulmonary artery outlet, based on the vascular diameter of each pulmonary artery outlet, the corresponding blood supply lung volume, and the preset minimum vascular diameter. The fifth module, used in S105, calculates the microcirculatory resistance values ​​at each pulmonary artery outlet using Poiseuille's theorem and Farin's effect, based on the generated microvascular tree model and the patient's complete blood count data. The sixth module, used in S106, takes the microcirculation resistance value of each pulmonary artery outlet as the outlet boundary condition and the average pressure of the pulmonary artery as the inlet boundary condition. Assuming that blood is an incompressible Newtonian fluid, it inputs the blood viscosity and density based on the blood routine data, discretizes the pulmonary artery three-dimensional model, and solves the NS equation through steady-state numerical simulation to obtain the velocity field and pressure field of blood flow in the pulmonary artery. Based on the velocity field, it determines the total pulmonary artery flow rate Qa. The seventh module is used in S107 to find similar branches for each occluded branch based on size similarity, determine the vascular diameter of the occluded branch outlet based on size similarity with similar branches, take the occluded branch outlet as the pulmonary artery outlet, and regenerate the corresponding microvascular tree model from each pulmonary artery outlet in S103-S104. The eighth module is used for S108 to determine the location of pulmonary artery stenosis in the pulmonary artery three-dimensional model, eliminate vascular stenosis based on the vascular diameter upstream and downstream of the stenosis location to obtain a stenosis-free pulmonary artery three-dimensional model, and determine the total pulmonary artery flow Qb based on the stenosis-free pulmonary artery three-dimensional model through S104-S106. The ninth module is used in S109 to calculate the ratio of Qa to Qb and to assess the risk of pulmonary embolism based on the ratio: the lower the ratio, the higher the risk of pulmonary embolism.

[0007] As a third aspect of the present invention, an electronic device is provided, characterized in that it includes a storage module, the storage module including instructions loaded and executed by a processor, the instructions, when executed, causing the processor to perform the pulmonary embolism risk assessment method described in the first aspect above.

[0008] As a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing one or more programs, characterized in that, when the one or more programs are executed by a processor, they implement the pulmonary embolism risk assessment method described in the first aspect above.

[0009] The beneficial effects of this invention are as follows: 1. Completely eliminate subjective interference and improve the objectivity of assessment: This invention relies entirely on the collected non-invasive objective data and does not rely on subjective judgment steps based on medical history or doctor's experience. This effectively avoids the risk of misjudgment caused by subjective variables in the PESI / sPESI model and ensures the consistency and reliability of assessment results. 2. The ratio of Qa to Qb is used as the core assessment indicator. This ratio is a continuous variable, so there is no need to perform empirical segmentation of the parameter, thus avoiding the problem of significant differences in assessment results among patients with similar conditions.

[0010] 3. By completing the occluded branch outlet in S107 and eliminating stenosis in S108, pulmonary artery models were constructed before repair (including occlusion / stenosis) and after repair (no stenosis + complete outlet). Based on hemodynamic simulation, Qa and Qb were obtained, and their ratio quantifies the overall loss of blood supply capacity caused by pulmonary embolism. Compared with the limitation of FFR in distinguishing the severity of blockage between major and terminal branches, this ratio can intuitively reflect the difference in the impact of different blockage sites on pulmonary blood supply, making the assessment results fully consistent with the clinical understanding of the severity of pulmonary embolism, and providing a direct basis for precise stratified treatment.

[0011] 4. Incorporating hemodynamic parameters to improve assessment accuracy: Qa and Qb are calculated based on hemodynamic parameters (velocity field, pressure field). Compared with indirect clinical parameters such as age and heart rate that the PERFORM model relies on, hemodynamic parameters directly reflect the blood flow carrying capacity of the pulmonary artery and the functional damage caused by blockage. This makes risk assessment closer to the pathological nature of the disease and significantly improves the accuracy of the assessment results.

[0012] 5. Non-invasive and low-cost, with value for large-scale clinical promotion: The entire evaluation process can be completed with only routine clinical test data, without the need for invasive procedures like traditional FFR, which reduces the examination trauma to patients and avoids high equipment and operation costs. Attached Figure Description

[0013] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments: Figure 1 A flowchart of a method for assessing the risk of pulmonary embolism provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a pulmonary embolism risk assessment device provided in an embodiment of the present invention; Figure 3 A schematic diagram of an electronic device provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of a curve segment detector according to an embodiment of the present invention. Detailed Implementation

[0014] The embodiments of the present invention will be described below with reference to the accompanying drawings. It should be noted that the embodiments described in this specification are not exhaustive and do not represent the only embodiments of the present invention. The corresponding embodiments below are only for clearly illustrating the inventive content of this patent and are not intended to limit its implementation. For those skilled in the art, different variations and modifications can be made based on the embodiments described. Any variations or modifications that fall within the technical concept and inventive content of this invention and are obvious are also within the protection scope of this invention.

[0015] like Figure 1 As shown in the figure, this application provides a method for assessing the risk of pulmonary embolism, and the specific process is as follows: S101. Collect the patient's pulmonary artery imaging data, physiological parameters, and blood routine data.

[0016] The pulmonary artery imaging can be CTA or MRA, and the physiological parameters include mean pulmonary artery pressure and cardiac output.

[0017] S102. Import pulmonary artery imaging data into vascular modeling software, establish a three-dimensional model of the pulmonary artery, and determine the centerline and inner diameter of the main trunk and branches of the pulmonary artery, as well as the occlusion status of the vessel.

[0018] In this embodiment, the vascular modeling software uses the open-source software SimVascular, and based on open-source software such as Paraview and VMTK, the centerline and vascular diameter of the pulmonary artery trunk and its branches are determined using the maximum inscribed sphere algorithm. Simultaneously, as... Figure 4 As shown, a 2cm long curved segment detector is established along the center line of the blood vessel. The curved segment detector is divided into an anterior segment, a middle segment, and a posterior segment. Each segment is used to calculate the average inner diameter of the corresponding blood vessel segment. When the ratio of the average inner diameter calculated by the anterior segment to the average inner diameter calculated by the posterior segment is less than a threshold (e.g., 0.1), the blood vessel is considered to be occluded.

[0019] The length of the curved segment detector ranges from 1.5 to 3.5 cm and can be adjusted according to actual needs.

[0020] S103. Assuming that each capillary at the terminal end of the pulmonary artery supplies the same lung volume, determine the lung volume based on pulmonary artery imaging data, and calculate the lung volume supplied by each pulmonary artery outlet according to the following relationship between the inner diameters of the vessels before and after the bifurcation: The nth power of the pulmonary artery diameter before bifurcation equals the sum of the nth power of the diameters of all pulmonary arteries after bifurcation, where n is the bifurcation coefficient.

[0021] The pulmonary artery, originating from the right ventricle, continuously branches into multiple levels of arteries (main trunk → lobar arteries → segmental arteries → subsegmental arteries, etc.). The final opening of each branch is the pulmonary outlet, the boundary between the pulmonary artery and the pulmonary microcirculation. It directly connects to the precapillary arteries of the lungs and is the essential pathway for blood to flow into the lungs for gas exchange. The pulmonary artery has multiple outlets, each marking the starting point of the corresponding pulmonary microcirculation vessels and serving as a dedicated interface for blood to enter the pulmonary microvessels. Each pulmonary outlet corresponds to a specific volume of lung it supplies.

[0022] The "supply lung volume" of the pulmonary artery outlet refers to the volume of the lung area covered by all the microcirculatory vessels downstream of the outlet. However, the number of pulmonary capillaries is enormous and cannot be directly measured by imaging data. Therefore, indirect calculation is required to ensure that the blood supply range of each outlet can be quantified.

[0023] The physical meaning of the relationship between the inner diameter of the blood vessel before and after the bifurcation is that the blood supply capacity (blood flow) of the blood vessel is positively correlated with the nth power of the inner diameter of the blood vessel (derived from Poiseuille's law: blood flow is proportional to the fourth power of the inner diameter), which is essentially the conservation of the blood supply capacity of the blood vessel before and after the bifurcation. Assuming that each capillary at the terminal pulmonary artery supplies the same lung volume, the "supply lung volume at the exit" is directly proportional to the "supply capacity at the exit." The supply capacity is essentially determined by the nth power of the exit's inner diameter. We consider the "pulmonary trunk" as the "pre-bifurcation vessel" and all "pulmonary artery exits" as "all vessels after bifurcation." The total supply capacity of the trunk (the nth power of the trunk's inner diameter) corresponds to the lung volume, and the supply capacity of a single pulmonary artery exit (the nth power of the exit's inner diameter) corresponds to its supply lung volume. Therefore, we have "the nth power of the trunk's inner diameter / lung volume = the nth power of the single exit's inner diameter / the lung volume supplied by that exit." Replacing the nth power of the trunk's inner diameter with the sum of the nth powers of all exit inner diameters, we can calculate the supply lung volume of each pulmonary artery exit using the following formula: Among them, V i V represents the volume of the supply lung corresponding to the i-th pulmonary artery outlet. total r represents the volume of the lungs. i represents the inner diameter of the i-th pulmonary artery outlet, m represents the total number of pulmonary artery outlets, and k represents the summation index variable for all pulmonary artery outlets.

[0024] The purpose of step S103 is to define the boundaries of the microvascular tree model in step S104. The supply lung volume of each pulmonary artery outlet determines the number of bifurcations and branches of its downstream microvascular tree.

[0025] S104. Based on the vascular diameter of each pulmonary artery outlet, the corresponding supply lung volume, and the preset minimum vascular diameter, generate a corresponding microvascular tree model starting from each pulmonary artery outlet. The specific process is as follows: S41. Treat the pulmonary artery outlet as a parent vessel and execute S42. S42. The lung volume supplied by the parent blood vessel is equivalent to a sphere. A point on the surface of the sphere is taken as the corresponding point of the parent blood vessel. The sphere is divided into two hemispheres through this point. The centroids of the two hemispheres are found. The centroids are connected to the corresponding point to form two line segments, which represent the two daughter blood vessels after the parent blood vessel branches. Where r... child =0.5 1 / n ×r parent r child Represents the inner diameter of the offspring vessel; the inner diameters of the two offspring vessels are equal, r. parent The inner diameter of the blood vessel in the parent generation represents the volume of the lung supplied by the blood vessel in the offspring generation, which is the volume of the corresponding hemisphere.

[0026] S43. If the inner diameter of the offspring vessel is greater than the minimum inner diameter of the vessel, then the offspring vessel is treated as the parent vessel, and the process returns to S42 until the inner diameter of the offspring vessel is less than or equal to the minimum inner diameter of the vessel.

[0027] In this embodiment, the minimum blood vessel inner diameter is 0.005 mm.

[0028] S105. Based on the generated microvascular tree model and the patient's complete blood count data, the microcirculatory resistance values ​​at each pulmonary artery outlet are calculated using Poiseuille's theorem and Faring's effect. The specific process is as follows: The resistance values ​​of each segment of the blood vessel were calculated using Poiseuille's theorem, with the viscosity coefficient given by the Farin effect. The hematocrit in the Farin effect was determined by the patient's complete blood count data. The microcirculatory resistance values ​​of each pulmonary artery outlet were calculated using the series and parallel resistance theorem.

[0029] S106. Using the microcirculation resistance value of each pulmonary artery outlet as the outlet boundary condition and the average pulmonary artery pressure as the inlet boundary condition, assuming that blood is an incompressible Newtonian fluid, inputting blood viscosity and density based on routine blood data, and discretizing the pulmonary artery three-dimensional model (mesh generation, determining the computational domain), the NS equation (core equation of fluid mechanics) is solved by steady-state numerical simulation method to obtain the velocity field and pressure field of blood flow in the pulmonary artery, and the total pulmonary artery flow rate Qa is determined based on the velocity field.

[0030] This embodiment calibrates the bifurcation coefficient n based on cardiac output, ensuring that the simulated total pulmonary artery flow Qa closely approximates the actual measured cardiac output of the patient. The specific process is as follows: a. In S103, n first takes a preset initial value, which is randomly selected as 3 or 2.85; b. After obtaining the total pulmonary artery flow rate Qa through S103-S106, calculate the relative error between the total pulmonary artery flow rate Qa and the cardiac output. The relative error is calculated as follows: (total pulmonary artery flow rate Qa - cardiac output) ÷ cardiac output × 100%. c. If the relative error is less than 1%, then n remains unchanged and the iteration ends. If the relative error is greater than 1%, then n is corrected using Newton's iteration method and b is returned.

[0031] S107. Based on size similarity, find similar branches for each occluded branch. Determine the vascular diameter of the occluded branch outlet based on the size similarity with the similar branches. Take the occluded branch outlet as the pulmonary artery outlet. Then, in steps S103-S104, regenerate the corresponding microvascular tree model starting from each pulmonary artery outlet. The specific process is as follows: S71. Measure the cross-sectional area (cross-sectional area of ​​the vascular lumen, the same below) of each pulmonary artery outlet; the cross-sectional area can be measured directly or calculated from the inner diameter.

[0032] S72. Measure the cross-sectional area of ​​each branch, where the cross-sectional area of ​​the occluded branch K is S. K ; S73. Assuming that for the same patient, the pulmonary artery branch structures are similar when their sizes are close (area ratio between 0.75 and 1.25), calculate the size similarity between the occluded branch K and each non-occluded branch. Size similarity = S K The cross-sectional area of ​​the non-blocking branch is used to determine the similarity between the non-blocking branches and the non-blocking branches whose size similarity values ​​fall within a preset range (0.75-1.25). These non-blocking branches are considered similar branches K to the blocking branch K. * The cross-sectional area is S K* The occlusion branch K and the similar branch K * Size similarity d=S K / S K* ; S74. Determine similar branches K * The cross-sectional area S of all i pulmonary artery outlets K*i ; S75. Calculate the cross-sectional area S of all i exits of the blocked branch K. Ki =d×S K*i Based on the cross-sectional area S of all i exits Ki Determine the inner diameter of the blood vessels for all i outlets; S76. Taking the occluded branch outlet as the pulmonary artery outlet, and regenerating the corresponding microvascular tree model from each pulmonary artery outlet using S103-S104.

[0033] The purpose of step S107 is to restore the outlets of all blocked branches to a state where gas exchange can be completed through microcirculation.

[0034] S108. Determine the location of pulmonary artery stenosis in the 3D model of the pulmonary artery. Eliminate vascular stenosis based on the vascular diameter upstream and downstream of the stenosis location to obtain a 3D model of the artery without stenosis. Based on the 3D model of the artery without stenosis, determine the total pulmonary artery flow Qb through S104-S106.

[0035] The location of pulmonary artery stenosis can also be determined using a curve segment detector. When the average inner diameter calculated in the middle segment is less than the average inner diameter calculated in the anterior and posterior segments, the segment corresponding to the middle segment is considered to be the pulmonary artery stenosis segment.

[0036] Through the regeneration of the microvascular tree model in step S107 and the elimination of stenosis in step S108, the three-dimensional arterial model can simulate the ideal state of the patient's lungs without embolism, thereby obtaining the total pulmonary artery flow Qb under the ideal state of no embolism.

[0037] In eliminating vascular stenosis, the theoretical normal inner diameter of the stenotic segment is determined based on the inner diameters of the vessel upstream and downstream of the stenotic segment, and the stenotic segment is corrected using this theoretical normal inner diameter. In this embodiment, the theoretical normal radius of the stenotic segment can be obtained by linear interpolation along the vessel centerline based on the inner diameters upstream and downstream of the stenotic segment, thus achieving vascular repair.

[0038] S109. Calculate the ratio of Qa to Qb and assess the risk of pulmonary embolism based on the ratio: the lower the ratio, the greater the blood flow loss caused by pulmonary embolism, and the higher the risk of pulmonary embolism.

[0039] Specifically, when assessing the risk of pulmonary embolism, the risk can be classified based on the ratio: when the ratio is ≥0.8, it is considered low risk; when 0.5 ≤ ratio <0.8, it is considered medium risk; and when the ratio is <0.5, it is considered high risk.

[0040] As can be seen from the above, the beneficial effects of the pulmonary embolism risk assessment method provided in this application embodiment are as follows: 1. Completely eliminate subjective interference and improve the objectivity of assessment: This invention relies entirely on the collected non-invasive objective data and does not rely on subjective judgment steps based on medical history or doctor's experience. This effectively avoids the risk of misjudgment caused by subjective variables in the PESI / sPESI model and ensures the consistency and reliability of assessment results. 2. The ratio of Qa to Qb is used as the core assessment indicator. This ratio is a continuous variable, so there is no need to perform empirical segmentation of the parameter, thus avoiding the problem of significant differences in assessment results among patients with similar conditions.

[0041] 3. By completing the occluded branch outlet in S107 and eliminating stenosis in S108, pulmonary artery models were constructed before repair (including occlusion / stenosis) and after repair (no stenosis + complete outlet). Based on hemodynamic simulation, Qa and Qb were obtained, and their ratio quantifies the overall loss of blood supply capacity caused by pulmonary embolism. Compared with the limitation of FFR in distinguishing the severity of blockage between major and terminal branches, this ratio can intuitively reflect the difference in the impact of different blockage sites on pulmonary blood supply, making the assessment results fully consistent with the clinical understanding of the severity of pulmonary embolism, and providing a direct basis for precise stratified treatment.

[0042] 4. Incorporating hemodynamic parameters to improve assessment accuracy: Qa and Qb are calculated based on hemodynamic parameters (velocity field, pressure field). Compared with indirect clinical parameters such as age and heart rate that the PERFORM model relies on, hemodynamic parameters directly reflect the blood flow carrying capacity of the pulmonary artery and the functional damage caused by blockage. This makes risk assessment closer to the pathological nature of the disease and significantly improves the accuracy of the assessment results.

[0043] 5. Non-invasive and low-cost, with value for large-scale clinical promotion: The entire evaluation process can be completed with only routine clinical test data, without the need for invasive procedures like traditional FFR, which reduces the examination trauma to patients and avoids high equipment and operation costs.

[0044] 6. Based on the theory of similarity of vascular bifurcation (for the same patient, the pulmonary artery branch structures are similar in size), the size parameters of the occluded branch outlet are supplemented. Combined with the bifurcation coefficient n calibrated by the patient's cardiac output, a microvascular tree model is generated to ensure that the calculation of Qa and Qb fits the individual's anatomical structure and physiological characteristics, further improving the accuracy of the assessment.

[0045] 7. By performing patient-specific calibration on the bifurcation coefficient n and matching similar branch size, it can be adapted to patients of different ages, lung volumes, and vascular anatomy, breaking through the limitation of the traditional model that "general parameters are adapted to all patients".

[0046] The following describes in detail one or more embodiments of the pulmonary embolism risk assessment device of the present invention. Those skilled in the art will understand that these devices can be configured using commercially available hardware components through the steps taught in this solution. Figure 2 An embodiment of the present invention provides a device for assessing the risk of pulmonary embolism, such as... Figure 2 As shown, the device includes a first module 11, a second module 12, a third module 13, a fourth module 14, a fifth module 15, a sixth module 16, a seventh module 17, an eighth module 18, and a ninth module 19.

[0047] The first module 11 is used for S101 to collect the patient's pulmonary artery imaging data, physiological parameters, and blood routine data.

[0048] The pulmonary artery imaging can be CTA or MRA, and the physiological parameters include mean pulmonary artery pressure and cardiac output.

[0049] The second module 12 is used for S102 to import pulmonary artery imaging data into vascular modeling software, establish a three-dimensional model of the pulmonary artery, and determine the centerline and inner diameter of the main trunk and branches of the pulmonary artery as well as the vascular occlusion status.

[0050] In this embodiment, the vascular modeling software uses the open-source software SimVascular, and based on open-source software such as Paraview and VMTK, the centerline and vascular diameter of the pulmonary artery trunk and its branches are determined using the maximum inscribed sphere algorithm. Simultaneously, as... Figure 4 As shown, a 2cm long curved segment detector is established along the center line of the blood vessel. The curved segment detector is divided into an anterior segment, a middle segment, and a posterior segment. Each segment is used to calculate the average inner diameter of the corresponding blood vessel segment. When the ratio of the average inner diameter calculated by the anterior segment to the average inner diameter calculated by the posterior segment is less than a threshold (e.g., 0.1), the blood vessel is considered to be occluded.

[0051] The length of the curved segment detector ranges from 1.5 to 3.5 cm and can be adjusted according to actual needs.

[0052] Module 3, 13, is used for S103. Assuming that the lung volume supplied by each capillary at the terminal pulmonary artery is the same, the lung volume is determined based on pulmonary artery imaging data. According to the following relationship between the inner diameters of the vessels before and after the bifurcation, the lung volume supplied by each pulmonary artery outlet is calculated: The nth power of the pulmonary artery diameter before bifurcation equals the sum of the nth power of the diameters of all pulmonary arteries after bifurcation, where n is the bifurcation coefficient.

[0053] The pulmonary artery, originating from the right ventricle, continuously branches into multiple levels of arteries (main trunk → lobar arteries → segmental arteries → subsegmental arteries, etc.). The final opening of each branch is the pulmonary outlet, the boundary between the pulmonary artery and the pulmonary microcirculation. It directly connects to the precapillary arteries of the lungs and is the essential pathway for blood to flow into the lungs for gas exchange. The pulmonary artery has multiple outlets, each marking the starting point of the corresponding pulmonary microcirculation vessels and serving as a dedicated interface for blood to enter the pulmonary microvessels. Each pulmonary outlet corresponds to a specific volume of lung it supplies.

[0054] The "supply lung volume" of the pulmonary artery outlet refers to the volume of the lung area covered by all the microcirculatory vessels downstream of the outlet. However, the number of pulmonary capillaries is enormous and cannot be directly measured by imaging data. Therefore, indirect calculation is required to ensure that the blood supply range of each outlet can be quantified.

[0055] The physical meaning of the relationship between the inner diameter of the blood vessel before and after the bifurcation is that the blood supply capacity (blood flow) of the blood vessel is positively correlated with the nth power of the inner diameter of the blood vessel (derived from Poiseuille's law: blood flow is proportional to the fourth power of the inner diameter), which is essentially the conservation of the blood supply capacity of the blood vessel before and after the bifurcation. Assuming that each capillary at the terminal pulmonary artery supplies the same lung volume, the "supply lung volume at the exit" is directly proportional to the "supply capacity at the exit." The supply capacity is essentially determined by the nth power of the exit's inner diameter. We consider the "pulmonary trunk" as the "pre-bifurcation vessel" and all "pulmonary artery exits" as "all vessels after bifurcation." The total supply capacity of the trunk (the nth power of the trunk's inner diameter) corresponds to the lung volume, and the supply capacity of a single pulmonary artery exit (the nth power of the exit's inner diameter) corresponds to its supply lung volume. Therefore, we have "the nth power of the trunk's inner diameter / lung volume = the nth power of the single exit's inner diameter / the lung volume supplied by that exit." Replacing the nth power of the trunk's inner diameter with the sum of the nth powers of all exit inner diameters, we can calculate the supply lung volume of each pulmonary artery exit using the following formula: Among them, V i V represents the volume of the supply lung corresponding to the i-th pulmonary artery outlet. total r represents the volume of the lungs. i represents the inner diameter of the i-th pulmonary artery outlet, m represents the total number of pulmonary artery outlets, and k represents the summation index variable for all pulmonary artery outlets.

[0056] The purpose of step S103 is to define the boundaries of the microvascular tree model in step S104. The supply lung volume of each pulmonary artery outlet determines the number of bifurcations and branches of its downstream microvascular tree.

[0057] Module 4, 14, is used in S104 to generate a corresponding microvascular tree model starting from each pulmonary artery outlet, based on the vascular diameter of each pulmonary artery outlet, the corresponding supply lung volume, and the preset minimum vascular diameter. The specific process is as follows: S41. Treat the pulmonary artery outlet as a parent vessel and execute S42. S42. The lung volume supplied by the parent blood vessel is equivalent to a sphere. A point on the surface of the sphere is taken as the corresponding point of the parent blood vessel. The sphere is divided into two hemispheres through this point. The centroids of the two hemispheres are found. The centroids are connected to the corresponding point to form two line segments, which represent the two daughter blood vessels after the parent blood vessel branches. Where r... child =0.5 1 / n ×r parent r child Represents the inner diameter of the offspring vessel; the inner diameters of the two offspring vessels are equal, r. parent The inner diameter of the blood vessel in the parent generation represents the volume of the lung supplied by the blood vessel in the offspring generation, which is the volume of the corresponding hemisphere.

[0058] S43. If the inner diameter of the offspring vessel is greater than the minimum inner diameter of the vessel, then the offspring vessel is treated as the parent vessel, and the process returns to S42 until the inner diameter of the offspring vessel is less than or equal to the minimum inner diameter of the vessel.

[0059] In this embodiment, the minimum blood vessel inner diameter is 0.005 mm.

[0060] Module 5, Section 15, is used in S105 to calculate the microcirculatory resistance values ​​at each pulmonary artery outlet using Poiseuille's theorem and Farin's effect, based on the generated microvascular tree model and the patient's complete blood count data. The specific process is as follows: The resistance values ​​of each segment of the blood vessel were calculated using Poiseuille's theorem, with the viscosity coefficient given by the Farin effect. The hematocrit in the Farin effect was determined by the patient's complete blood count data. The microcirculatory resistance values ​​of each pulmonary artery outlet were calculated using the series and parallel resistance theorem.

[0061] Module 6, 16, is used in S106. It uses the microcirculation resistance value of each pulmonary artery outlet as the outlet boundary condition and the average pulmonary artery pressure as the inlet boundary condition. Assuming that blood is an incompressible Newtonian fluid, it inputs blood viscosity and density based on routine blood data. After discretizing the 3D model of the pulmonary artery (mesh generation, determination of the computational domain), it solves the NS equation (core equation of fluid mechanics) through steady-state numerical simulation to obtain the velocity field and pressure field of blood flow in the pulmonary artery. Based on the velocity field, it determines the total pulmonary artery flow rate Qa.

[0062] This embodiment calibrates the bifurcation coefficient n based on cardiac output, ensuring that the simulated total pulmonary artery flow Qa closely approximates the actual measured cardiac output of the patient. The specific process is as follows: a. In S103, n first takes a preset initial value, which is randomly selected as 3 or 2.85; b. After obtaining the total pulmonary artery flow rate Qa through S103-S106, calculate the relative error between the total pulmonary artery flow rate Qa and the cardiac output. The relative error is calculated as follows: (total pulmonary artery flow rate Qa - cardiac output) ÷ cardiac output × 100%. c. If the relative error is less than 1%, then n remains unchanged and the iteration ends. If the relative error is greater than 1%, then n is corrected using Newton's iteration method and b is returned.

[0063] Module 7, Section 17, is used in S107 to find similar branches for each occluded branch based on size similarity. The vascular diameter of the occluded branch outlet is determined based on the size similarity with the similar branches, and the occluded branch outlet is taken as the pulmonary artery outlet. Then, in S103-S104, corresponding microvascular tree models are regenerated, each starting from the pulmonary artery outlet. The specific process is as follows: S71. Measure the cross-sectional area (cross-sectional area of ​​the vascular lumen, the same below) of each pulmonary artery outlet; the cross-sectional area can be measured directly or calculated from the inner diameter.

[0064] S72. Measure the cross-sectional area of ​​each branch, where the cross-sectional area of ​​the occluded branch K is S. K ; S73. Assuming that for the same patient, the pulmonary artery branch structures are similar when their sizes are close (area ratio between 0.75 and 1.25), calculate the size similarity between the occluded branch K and each non-occluded branch. Size similarity = S K The cross-sectional area of ​​the non-blocking branch is used to determine the similarity between the non-blocking branches and the non-blocking branches whose size similarity values ​​fall within a preset range (0.75-1.25). These non-blocking branches are considered similar branches K to the blocking branch K. * The cross-sectional area is S K* The occlusion branch K and the similar branch K * Size similarity d=S K / S K* ; S74. Determine similar branches K * The cross-sectional area S of all i pulmonary artery outlets K*i ; S75. Calculate the cross-sectional area S of all i exits of the blocked branch K. Ki =d×S K*i Based on the cross-sectional area S of all i exits Ki Determine the inner diameter of the blood vessels for all i outlets; S76. Taking the occluded branch outlet as the pulmonary artery outlet, and regenerating the corresponding microvascular tree model from each pulmonary artery outlet using S103-S104.

[0065] The purpose of step S107 is to restore the outlets of all blocked branches to a state where gas exchange can be completed through microcirculation.

[0066] Module 8, 18, is used in S108 to determine the location of pulmonary artery stenosis in the pulmonary artery 3D model, eliminate vascular stenosis based on the vascular diameter upstream and downstream of the stenosis location, and obtain a stenosis-free pulmonary 3D model. Based on the stenosis-free pulmonary 3D model, the total pulmonary artery flow Qb is determined through S104-S106.

[0067] The location of pulmonary artery stenosis can also be determined using a curve segment detector. When the average inner diameter calculated in the middle segment is less than the average inner diameter calculated in the anterior and posterior segments, the segment corresponding to the middle segment is considered to be the pulmonary artery stenosis segment.

[0068] Through the regeneration of the microvascular tree model in step S107 and the elimination of stenosis in step S108, the three-dimensional arterial model can simulate the ideal state of the patient's lungs without embolism, thereby obtaining the total pulmonary artery flow Qb under the ideal state of no embolism.

[0069] In eliminating vascular stenosis, the theoretical normal inner diameter of the stenotic segment can be determined based on the inner diameters of the vessel upstream and downstream of the stenotic segment, and then used to correct the stenotic segment. In this embodiment, the theoretical normal radius of the stenotic segment can be obtained by linear interpolation along the vessel centerline based on the inner diameters upstream and downstream of the stenotic segment, thus achieving vascular repair.

[0070] Module 9, 19, is used for S109 to calculate the ratio of Qa to Qb. The risk of pulmonary embolism is assessed based on the ratio: the lower the ratio, the greater the blood flow loss caused by pulmonary embolism, and the higher the risk of pulmonary embolism.

[0071] Specifically, when assessing the risk of pulmonary embolism, the risk can be classified based on the ratio: when the ratio is ≥0.8, it is considered low risk; when 0.5 ≤ ratio <0.8, it is considered medium risk; and when the ratio is <0.5, it is considered high risk.

[0072] In summary, the pulmonary embolism risk assessment device provided in the above embodiments can perform the pulmonary embolism risk assessment methods provided in the foregoing embodiments.

[0073] Similar to the above concept, Figure 3 A schematic block diagram of the structure of an electronic device provided by an embodiment of the present invention is shown.

[0074] For example, the electronic device includes a storage module 21 and a processor 22. The storage module 21 includes instructions loaded and executed by the processor 22, which, when executed, cause the processor 22 to perform the steps described in the above-described section of this specification, "A Method for Assessing the Risk of Pulmonary Embolism," according to various exemplary embodiments of the present invention.

[0075] It should be understood that processor 22 can be a Central Processing Unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, the general-purpose processor can be a microprocessor or any conventional processor.

[0076] This invention also provides a computer-readable storage medium that stores one or more programs, which, when executed by a processor, implement the steps described in the above-described method for assessing the risk of pulmonary embolism according to various exemplary embodiments of the invention.

[0077] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer-readable storage media (or non-transitory media) and communication media (or transient media).

[0078] As is known to those skilled in the art, the term computer-readable storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer-readable storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0079] For example, the computer-readable storage medium may be an internal storage unit of the electronic device described in the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., provided on the electronic device.

[0080] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for assessing the risk of pulmonary embolism, characterized in that, include: S101. Collect the patient's pulmonary artery imaging data, physiological parameters, and complete blood count data, including the mean pulmonary artery pressure; S102. Import the pulmonary artery imaging data into the vascular modeling software, establish a three-dimensional model of the pulmonary artery, and determine the centerline and inner diameter of the main trunk and branches of the pulmonary artery, as well as the vascular occlusion status. S103. Assuming that each capillary at the terminal end of the pulmonary artery supplies the same lung volume, the lung volume is determined based on the pulmonary artery imaging data. The lung volume supplied by each pulmonary artery outlet is calculated according to the following relationship between the vessel diameters before and after bifurcation: The nth power of the inner diameter of the vessel before bifurcation is equal to the sum of the nth power of the inner diameters of all pulmonary arteries after bifurcation, where n is the bifurcation coefficient. S104. Based on the vascular inner diameter of each pulmonary artery outlet, the corresponding blood supply lung volume, and the preset minimum vascular inner diameter, generate the corresponding microvascular tree model starting from each pulmonary artery outlet. S105. Based on the generated microvascular tree model and the patient's blood routine data, the microcirculation resistance value of each pulmonary artery outlet is calculated using Poiseuille's theorem and Farin's effect. S106. Using the microcirculation resistance value of each pulmonary artery outlet as the outlet boundary condition and the average pressure of the pulmonary artery as the inlet boundary condition, assuming that blood is an incompressible Newtonian fluid, inputting the blood viscosity and density based on the blood routine data, after discretizing the pulmonary artery three-dimensional model, solving the NS equation through steady-state numerical simulation method to obtain the velocity field and pressure field of blood flow in the pulmonary artery, and determining the total pulmonary artery flow rate Qa based on the velocity field; S107. Find similar branches for each occluded branch based on size similarity, determine the vascular diameter of the occluded branch outlet based on size similarity with similar branches, take the occluded branch outlet as the pulmonary artery outlet, and regenerate the corresponding microvascular tree model with each pulmonary artery outlet as the starting point through S103-S104. S108. Determine the location of pulmonary artery stenosis in the pulmonary artery three-dimensional model, eliminate vascular stenosis based on the blood vessel diameter upstream and downstream of the stenosis location, and obtain a stenosis-free pulmonary artery three-dimensional model. Based on the stenosis-free pulmonary artery three-dimensional model, determine the total pulmonary artery flow Qb through S104-S106. S109. Calculate the ratio of Qa to Qb, and assess the risk of pulmonary embolism based on the ratio: the lower the ratio, the higher the risk of pulmonary embolism.

2. The method for assessing the risk of pulmonary embolism according to claim 1, characterized in that, S102 further includes: The centerline and inner diameter of the pulmonary artery trunk and its branches were determined using the maximum inscribed sphere algorithm. A curved segment detector is established that moves along the centerline of the blood vessel. This curved segment detector is divided into an anterior segment, a middle segment, and a posterior segment. Each segment is used to calculate the average inner diameter of the corresponding blood vessel segment. When the ratio of the average inner diameter calculated by the anterior segment to the average inner diameter calculated by the posterior segment is less than a threshold, the blood vessel is considered to be occluded.

3. The method for assessing the risk of pulmonary embolism according to claim 1, characterized in that, The physiological parameter also includes cardiac output, and the method further includes calibrating n based on the cardiac output: a. In S103, n is first taken as a preset initial value; b. After obtaining the total pulmonary artery flow rate Qa through S103-S106, calculate the relative error between the total pulmonary artery flow rate Qa and the cardiac output. c. If the relative error is less than 1%, then n remains unchanged and the iteration ends. If the relative error is greater than 1%, then n is corrected by Newton's iteration method and b is returned.

4. The method for assessing the risk of pulmonary embolism according to claim 3, characterized in that, The initial value is either 3 or 2.

85.

5. The method for assessing the risk of pulmonary embolism according to claim 1, characterized in that, S103 further includes: The supply lung volume for each pulmonary artery outlet is calculated using the following formula: Among them, V i V represents the volume of the supply lung corresponding to the i-th pulmonary artery outlet. total r represents the volume of the lungs. i represents the inner diameter of the i-th pulmonary artery outlet, m represents the total number of pulmonary artery outlets, and k represents the summation index variable for all pulmonary artery outlets.

6. The method for assessing the risk of pulmonary embolism according to claim 1, characterized in that, S104 further includes: S41. Treat the pulmonary artery outlet as a parent vessel and execute S42. S42. The volume of the lung supplying the parent blood vessel is equivalent to a sphere. A corresponding point is taken on the surface of this sphere, dividing the sphere into two hemispheres. The centroids of the two hemispheres are found, and these centroids are connected to the corresponding points to form two line segments. These segments represent the two daughter blood vessels after the parent blood vessel branches, where r... child =0.5 1 / n ×r parent r child Represents the inner diameter of the offspring vessel; the inner diameters of the two offspring vessels are equal, r. parent The inner diameter of the parent blood vessel is represented by the volume of the lung supplied by the offspring blood vessel, which is the volume of the corresponding hemisphere. S43. If the inner diameter of the offspring blood vessel is greater than the minimum blood vessel inner diameter, then the offspring blood vessel is taken as the parent blood vessel, and the process returns to S42 until the inner diameter of the offspring blood vessel is less than or equal to the minimum blood vessel inner diameter.

7. The method for assessing the risk of pulmonary embolism according to claim 1, characterized in that, S107 further includes: S71. Measure the cross-sectional area of ​​each pulmonary artery outlet; S72. Measure the cross-sectional area of ​​each branch, where the cross-sectional area of ​​the occluded branch K is S. K ; S73. Calculate the dimensional similarity between the occluded branch K and each non-occluded branch. Dimensional similarity = S K The cross-sectional area of ​​the non-blocking branch is used to determine the similarity between the non-blocking branches and the non-blocking branches whose size similarity values ​​fall within a preset range. These non-blocking branches are considered similar branches K to the blocking branch K. * The cross-sectional area is S K* The occlusion branch K and the similar branch K * Size similarity d=S K / S K* ; S74. Determine similar branches K * The cross-sectional area S of all i exits K*i ; S75. Calculate the cross-sectional area S of all i exits of the blocked branch K. Ki =d×S K*i Based on the cross-sectional area S of all i exits Ki Determine the inner diameter of the blood vessels for all i outlets.

8. A device for assessing the risk of pulmonary embolism, characterized in that, include: The first module is used for S101 to collect the patient's pulmonary artery imaging data, physiological parameters and blood routine data, wherein the physiological parameters include mean pulmonary artery pressure; The second module is used in S102 to import the pulmonary artery imaging data into the vascular modeling software, establish a three-dimensional model of the pulmonary artery, and determine the centerline and inner diameter of the pulmonary artery trunk and its branches, as well as the vascular occlusion status. The third module, used in S103, assumes that the volume of the lung supplied by each capillary at the terminal pulmonary artery is the same. Based on the pulmonary artery imaging data, the volume of the lung is determined, and the volume of the lung supplied by each pulmonary artery outlet is calculated according to the following relationship between the inner diameters of the vessels before and after the bifurcation: The nth power of the inner diameter of the vessel before bifurcation is equal to the sum of the nth power of the inner diameters of all pulmonary arteries after bifurcation, where n is the bifurcation coefficient. The fourth module is used in S104 to generate a corresponding microvascular tree model starting from each pulmonary artery outlet, based on the vascular diameter of each pulmonary artery outlet, the corresponding blood supply lung volume, and the preset minimum vascular diameter. The fifth module, used in S105, calculates the microcirculatory resistance values ​​at each pulmonary artery outlet using Poiseuille's theorem and Farin's effect, based on the generated microvascular tree model and the patient's complete blood count data. The sixth module, used in S106, takes the microcirculation resistance value of each pulmonary artery outlet as the outlet boundary condition and the average pressure of the pulmonary artery as the inlet boundary condition. Assuming that blood is an incompressible Newtonian fluid, it inputs the blood viscosity and density based on the blood routine data, discretizes the pulmonary artery three-dimensional model, and solves the NS equation through steady-state numerical simulation to obtain the velocity field and pressure field of blood flow in the pulmonary artery. Based on the velocity field, it determines the total pulmonary artery flow rate Qa. The seventh module is used in S107 to find similar branches for each occluded branch based on size similarity, determine the vascular diameter of the occluded branch outlet based on size similarity with similar branches, take the occluded branch outlet as the pulmonary artery outlet, and regenerate the corresponding microvascular tree model from each pulmonary artery outlet in S103-S104. The eighth module is used for S108 to determine the location of pulmonary artery stenosis in the pulmonary artery three-dimensional model, eliminate vascular stenosis based on the vascular diameter upstream and downstream of the stenosis location to obtain a stenosis-free pulmonary artery three-dimensional model, and determine the total pulmonary artery flow Qb based on the stenosis-free pulmonary artery three-dimensional model through S104-S106. The ninth module is used in S109 to calculate the ratio of Qa to Qb and to assess the risk of pulmonary embolism based on the ratio: the lower the ratio, the higher the risk of pulmonary embolism.

9. An electronic device, characterized in that, The system includes a storage module comprising instructions loaded and executed by a processor, which, when executed, cause the processor to perform a method for assessing the risk of pulmonary embolism according to any one of claims 1-7.

10. A computer-readable storage medium storing one or more programs, characterized in that, When the one or more programs are executed by the processor, they implement the method for assessing the risk of pulmonary embolism as described in any one of claims 1-7.

Images