Surgical risk prediction method, device, and storage medium
By acquiring multi-dimensional assessment information and inputting it into the surgical risk assessment model, the problem of inaccurate surgical risk prediction was solved, the accuracy of surgical risk assessment and the objectivity of treatment decisions were improved, perioperative risks were reduced, and postoperative prognosis was improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- XIAN MARK MEDICAL TECH CO LTD
- Filing Date
- 2026-01-14
- Publication Date
- 2026-05-29
Smart Images
Figure CN122117240A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of medical technology, and more specifically, to a surgical risk prediction method, an electronic device, and a computer-readable storage medium. Background Technology
[0002] Transcatheter aortic valve replacement (TAVR) is an important minimally invasive technique for treating aortic valve disease. However, for patients with isolated severe aortic regurgitation (AR) and a left ventricular ejection fraction (LVEF) of less than 35%, the decision to perform TAVR is often subjectively made by physicians based on experience. This subjective decision-making leads to significant uncertainty regarding the suitability of TAVR for this population, resulting in high perioperative risks and, even if the procedure is successful, poor long-term outcomes, including high all-cause mortality and a high incidence of multiple adverse events, severely impacting overall treatment effectiveness and patient quality of life. Summary of the Invention
[0003] One objective of this application is to provide a new technical solution for surgical risk prediction, in order to solve the technical problems existing in related technologies, such as inaccurate surgical risk prediction, reliance on subjective experience in treatment decisions, and disconnect between risk prediction and final treatment plan, thereby improving the accuracy of prognosis prediction.
[0004] According to a first aspect of this application, a surgical risk prediction method is provided, comprising: Obtain preoperative multidimensional assessment information of the target subject; wherein, the multidimensional assessment information includes: left ventricular ejection fraction, first surgical risk score, second surgical risk score, NT-proBNP value, systolic pulmonary artery pressure and extracorporeal life support status; The preoperative multidimensional assessment information is input into the surgical risk assessment model to obtain the surgical risk prediction result of the target object; wherein, the surgical risk prediction result includes at least one of the following: surgical risk level, all-cause mortality risk value, composite adverse event risk value, and predicted change in left ventricular ejection fraction.
[0005] Optionally, the surgical risk prediction result includes a surgical risk level, and the method further includes: Based on the surgical risk level, the target intervention method is determined.
[0006] Optionally, the surgical risk level is one of the first risk level, the second risk level, and the third risk level; The determination of the target intervention method based on the surgical risk level includes: When the surgical risk level is the first risk level, the target intervention method is determined to be the first intervention method; wherein, the first intervention method is transcatheter valve replacement with extracorporeal life support; When the surgical risk level is the second risk level, the target intervention method is determined to be the second intervention method; wherein, the second intervention method is a transcatheter valve replacement without the application of extracorporeal life support; If the surgical risk level is the third risk level, the target intervention method is determined to be the second intervention method.
[0007] Optionally, the surgical risk prediction result includes a surgical risk level, which is one of a first risk level, a second risk level, and a third risk level; The method further includes: Obtain the peripheral vascular condition assessment results and aortic root anatomical parameters of the target object; Based on the surgical risk level, the peripheral vascular condition assessment results, and the aortic root anatomical parameters, the target surgical approach for transcatheter aortic replacement is determined; wherein, the target surgical approach is one of the transapical approach, the transfemoral approach, and the alternative approach.
[0008] Optionally, determining the target surgical approach for transcatheter aortic valve replacement based on the surgical risk level, the peripheral vascular condition assessment results, and the aortic root anatomical parameters includes: If the first preset condition is met, then the target surgical approach is determined to be the transapical approach: The first preset condition includes at least one of the following: The surgical risk level is classified as Level 1. The peripheral vascular condition assessment result indicated that the femoral artery approach was not suitable. At least one of the aortic root anatomical parameters satisfies the following conditions: the aortic valve annulus morphology is irregular, the ascending aortic diameter is greater than or equal to the diameter threshold, and the aortic angle is greater than or equal to the first angle threshold. If the second preset condition is met, then the target surgical approach is determined to be the femoral artery approach: The second preset condition includes: The surgical risk level is either level three or level two; The peripheral vascular condition assessment result indicates that the femoral artery approach is suitable. The aortic root anatomical parameters satisfy the following: the aortic valve annulus diameter is within a set diameter range, and the aortic angle is less than or equal to the second angle threshold. If the first preset condition and the second preset condition are not met, then the target surgical approach is determined to be an alternative approach.
[0009] Optionally, the surgical risk assessment model is determined through the following steps: Obtain the training sample set: Each training sample in the training sample set includes preoperative multidimensional assessment information, all-cause mortality status, composite adverse event status, surgical risk level, and left ventricular ejection fraction change. The surgical risk assessment model is trained using the training sample set to obtain the trained surgical risk assessment model; The trained surgical risk assessment model is corrected using a confounding factor correction algorithm to obtain the surgical risk assessment model.
[0010] Optionally, obtaining the training sample set includes: Obtain sample data from different sample objects to obtain a sample dataset; wherein, the sample data includes candidate feature groups corresponding to the sample objects, the all-cause mortality status of the samples, the composite adverse event status of the samples, and the change in left ventricular ejection fraction of the samples. For any candidate feature group of a sample, the preoperative multidimensional assessment information of the sample is selected from the candidate feature group; wherein, the preoperative multidimensional assessment information includes: left ventricular ejection fraction, first surgical risk score, second surgical risk score, NT-proBNP value, systolic pulmonary artery pressure and status of extracorporeal life support application. Based on the preoperative multidimensional assessment information of the sample subjects, the surgical risk level of the sample subjects is determined; The training sample set is obtained by taking the preoperative multidimensional assessment information of any sample object, the surgical risk level of the sample, the all-cause mortality status of the sample, the occurrence status of the composite adverse events of the sample, and the change in the left ventricular ejection fraction of the sample as a training sample.
[0011] Optionally, determining the surgical risk level of the sample object based on the preoperative multidimensional assessment information of the sample object includes: If the left ventricular ejection fraction is less than a first threshold and the first surgical risk score is greater than or equal to a second threshold, or if the left ventricular ejection fraction is less than a first threshold and the second surgical risk score is greater than or equal to a third threshold, the sample surgical risk level of the sample object is determined to be the first risk level. If the left ventricular ejection fraction is less than the first threshold, the first surgical risk score is less than the second threshold, and the second surgical risk score is less than the third threshold, the sample surgical risk level of the sample subject is determined to be the second risk level. If the left ventricular ejection fraction is greater than or equal to the first threshold, and the first surgical risk score is less than the second threshold and the second surgical risk score is less than the third threshold, the sample surgical risk level of the sample subject is determined to be the third risk level.
[0012] According to a second aspect of this application, an electronic device is also provided, comprising a memory and a processor, the memory being configured to store executable instructions; the processor being configured to operate under the control of the instructions to perform the method as described in the first aspect of this application.
[0013] According to a third aspect of this application, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the method described in the first aspect.
[0014] One beneficial effect of this application is that it obtains multi-dimensional preoperative assessment information of the target subject and inputs this information into a surgical risk assessment model to obtain a surgical risk prediction result for the target subject. This achieves accurate assessment of the surgical risk of the target subject based on multi-dimensional preoperative assessment information, solving the technical problems of inaccurate surgical risk prediction, reliance on subjective experience in treatment decisions, and a disconnect between risk prediction and the final treatment plan in related technologies, thereby improving the accuracy of prognosis prediction. Attached Figure Description
[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of the present application and, together with their description, serve to explain the principles of the present application.
[0016] Figure 1 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Figure 1 ; Figure 2 This is a schematic flowchart of a surgical risk prediction method according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Figure 2 . Detailed Implementation
[0017] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values of the components and steps set forth in these embodiments do not limit the scope of the present application.
[0018] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the scope of this application and its application or use.
[0019] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.
[0020] In all the examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.
[0021] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.
[0022] <Hardware Configuration> Figure 1 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Figure 1 .
[0023] like Figure 1 As shown, electronic device 100 can be, for example, a PC, a laptop, a server, etc.
[0024] In this embodiment, refer to Figure 1 As shown, the electronic device 100 may include a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a speaker 1700, a microphone 1800, etc.
[0025] Processor 1100 may be a mobile processor. Memory 1200 includes, for example, ROM (Read-Only Memory), RAM (Random Access Memory), and non-volatile memory such as a hard disk. Interface device 1300 includes, for example, a USB interface and a headphone jack. Communication device 1400 is capable of wired or wireless communication. Communication device 1400 may include short-range communication devices, such as any device that performs short-range wireless communication based on short-range wireless communication protocols such as Hilink, WiFi (IEEE 802.11), Mesh, Bluetooth, ZigBee, Thread, Z-Wave, NFC, UWB, and LiFi. Communication device 1400 may also include long-range communication devices, such as any device that performs WLAN, GPRS, or 2G / 3G / 4G / 5G long-range communication. Display device 1500 is, for example, an LCD screen or a touch screen, used to display the surgical risk prediction results of the target subject. Input device 1600 may include, for example, a touch screen or a keyboard. Users can input / output voice information through speaker 1700 and microphone 1800.
[0026] In this embodiment, the memory 1200 of the electronic device 100 is used to store instructions for controlling the processor 1100 to operate in order to at least execute the surgical risk prediction method according to any embodiment of this application. Those skilled in the art can design instructions based on the solutions disclosed in this application. How the instructions control the processor to operate is well known in the art and will not be described in detail here.
[0027] Despite Figure 1 The present invention illustrates multiple devices of electronic device 100, but may refer to only some of these devices. For example, electronic device 100 may refer only to memory 1200, processor 1100 and display device 1500.
[0028] <Method Implementation> Figure 2 This is a flowchart illustrating a surgical risk prediction method according to an embodiment of this application, which can be implemented by an electronic device 100.
[0029] according to Figure 2 As shown, the surgical risk prediction method of this embodiment may include the following steps S2100~S2200: Step S2100: Obtain preoperative multidimensional assessment information of the target subject; The multidimensional assessment information includes: left ventricular ejection fraction, first surgical risk score, second surgical risk score, NT-proBNP value, systolic pulmonary artery pressure, and status of extracorporeal life support application.
[0030] In this embodiment, the target group can be patients with simple severe aortic regurgitation with a left ventricular ejection fraction of less than 35%, or other patients with aortic regurgitation, or other subjects who need to undergo surgical risk assessment before aortic valve replacement surgery. There are no limitations here.
[0031] Preoperative multidimensional assessment information refers to the collection of clinical, imaging, and laboratory indicators across multiple dimensions of the target subject before transcatheter aortic valve replacement (TAVR). This multidimensional assessment information includes: left ventricular ejection fraction, primary surgical risk score, secondary surgical risk score, NT-proBNP value, systolic pulmonary artery pressure, and status of extracorporeal life support.
[0032] The left ventricular ejection fraction (LVEF) is a measure of the percentage of blood pumped out by the left ventricle during each contraction of the target individual, reflecting the target individual's cardiac pumping function.
[0033] The first surgical risk score (STS score, full name: Society of Thoracic Surgeons Score) is a cardiac surgery risk assessment system developed by the American College of Thoracic Surgeons to predict the risk of postoperative mortality and complications in target subjects.
[0034] The second surgical risk score (EuroSCORE II score, full name: European System for Cardiac Operative Risk Evaluation II) is the European Cardiac Surgery Risk Assessment System II, used to assess the risk of death of target subjects.
[0035] NT-proBNP (full name: N-terminal pro-B-type Natriuretic Peptide) is a biomarker released when cardiac function is impaired, used to assess the severity and prognosis of heart failure in target subjects.
[0036] Systolic pulmonary artery pressure (sPAP) reflects the pulmonary artery pressure of a target individual and is used to assess right ventricular function and pulmonary hypertension.
[0037] Extracorporeal life support (ECMO) status refers to whether extracorporeal membrane oxygenation (ECMO) is used for circulatory support during the perioperative period of TAVR. In other words, ECMO status includes both the use of ECMO and the absence of ECMO. The ECMO status is determined subjectively by experienced physicians based on the patient's physical condition and other factors.
[0038] Those skilled in the art should understand that the methods for determining parameters such as left ventricular ejection fraction, first surgical risk score, second surgical risk score, NT-proBNP value, and systolic pulmonary artery pressure are well-known in the field and will not be elaborated here.
[0039] For example, preoperative multidimensional assessment information of the target subjects can be collected through electronic medical record systems, imaging examinations (such as echocardiography and multi-slice spiral CT), and laboratory tests.
[0040] Step S2200: Input the preoperative multidimensional assessment information into the surgical risk assessment model to obtain the surgical risk prediction result of the target object; The surgical risk prediction results include at least one of the following: surgical risk level, all-cause mortality risk value, composite adverse event risk value, and predicted change in left ventricular ejection fraction.
[0041] In this embodiment, the surgical risk assessment model can be a predictive model based on the Cox proportional hazards regression model, used to predict the surgical risk level (i.e., one of the first risk level, the second risk level, and the third risk level), as well as the target subject's mortality risk (i.e., all-cause mortality risk value) and composite adverse event risk (i.e., composite adverse event risk value) within 2 years after surgery, and predict the improvement of left ventricular function (i.e., predict the change in left ventricular ejection fraction).
[0042] Surgical risk level is used to characterize the risk of the target subject during TAVR surgery.
[0043] Surgical risk levels are categorized into three levels, which increase in risk: Level 3 (low risk), Level 2 (medium-high risk), and Level 1 (high risk).
[0044] All-cause mortality risk value is used to characterize the probability that the target subject will die from any cause within 2 years after surgery.
[0045] Composite adverse event risk value is used to characterize the probability of the target subject experiencing a composite endpoint such as cardiovascular events or readmission within 2 years post-surgery.
[0046] The predicted change in left ventricular ejection fraction (LVEF) was used to characterize the change in LVEF in the target subjects 2 years post-surgery.
[0047] Surgical risk assessment models can provide a comprehensive output, from qualitative risk stratification to quantitative prognostic prediction, offering intuitive and quantifiable evidence for clinical decision-making and improving the objectivity and accuracy of treatment decisions.
[0048] In one embodiment of this application, the surgical risk assessment model in step S2200 is determined through the following steps S1100 to S1300: Step S1100, Obtain the training sample set: Each training sample in the training sample set includes preoperative multidimensional assessment information, all-cause mortality status, composite adverse event status, surgical risk level, and change in left ventricular ejection fraction.
[0049] In this embodiment, the preoperative multidimensional assessment information of the sample is basically the same as the concept in step S2100, and will not be elaborated here.
[0050] The all-cause mortality status of the sample includes two states: all-cause mortality occurred and no all-cause mortality occurred.
[0051] The status of composite adverse events in the sample includes two states: composite adverse events have occurred and composite adverse events have not occurred.
[0052] The surgical risk level of the sample is one of the first risk level, the second risk level, and the third risk level.
[0053] The surgical risk level of the sample is basically the same as the surgical risk level concept in step S2100, and will not be elaborated here.
[0054] The change in left ventricular ejection fraction (LVEF) in the sample was calculated as the difference between the sample's LVEF before TAVR (referred to as the first LVEF) and its LVEF two years after TAVR (referred to as the second LVEF). The change in LVEF was used to characterize the extent of improvement in the sample's left ventricle postoperatively.
[0055] In one embodiment of this application, step S1100, which involves obtaining the training sample set, includes steps S1100.1 to S1100.4.
[0056] Step S1100.1: Obtain sample data for different sample objects to obtain a sample dataset; wherein, the sample data includes candidate feature groups corresponding to the sample objects, all-cause mortality status of the samples, composite adverse event status of the samples, and changes in left ventricular ejection fraction of the samples.
[0057] In this embodiment, different sample subjects can be, for example, pure AR patients from multiple high-volume centers.
[0058] Candidate feature groups include demographic characteristics (age, sex, BMI, etc.), clinical history (comorbidities such as hypertension and diabetes), laboratory test indicators (NT-proBNP value, etc.), imaging parameters (anatomical parameters such as left ventricular ejection fraction measured by transthoracic echocardiography, systolic pulmonary artery pressure, and aortic valve annulus diameter measured by multi-slice spiral CT), risk scores (STS score, i.e., first surgical risk score, EuroSCORE II score, i.e., second surgical risk score), and extracorporeal life support application status (i.e., two statuses: application of extracorporeal life support and no application of extracorporeal life support).
[0059] Step S1100.2: For any candidate feature group of a sample object, filter out the preoperative multidimensional evaluation information of the sample object from the candidate feature group; The preoperative multidimensional assessment information of the sample includes: left ventricular ejection fraction, first surgical risk score, second surgical risk score, NT-proBNP value, systolic pulmonary artery pressure, and status of extracorporeal life support application.
[0060] In this embodiment, collinearity analysis was used to remove redundant variables from the candidate feature group and determine six core indicators (correlation coefficient > 0.8) as preoperative multidimensional evaluation information for the sample.
[0061] Then, for any candidate feature group of a sample object, the preoperative multidimensional assessment information of the sample object is selected from the candidate feature group to obtain the preoperative multidimensional assessment information of the sample object corresponding to different sample objects.
[0062] Step S1100.3: Determine the surgical risk level of the sample object based on the preoperative multidimensional assessment information of the sample object.
[0063] In one embodiment of this application, step S1100.3 determines the surgical risk level of the sample object based on the preoperative multidimensional assessment information of the sample object, including steps S1100.31 to S1100.33.
[0064] Step S1100.31: If the left ventricular ejection fraction is less than the first threshold and the first surgical risk score is greater than or equal to the second threshold, or if the left ventricular ejection fraction is less than the first threshold and the second surgical risk score is greater than or equal to the third threshold, determine the sample surgical risk level of the sample object as the first risk level.
[0065] In this embodiment, the first threshold can be, for example, 35%. The second threshold can be, for example, 8.9%, and the third threshold can be, for example, 10.2%.
[0066] The first risk level can also be called the high risk level.
[0067] Step S1100.32: If the left ventricular ejection fraction is less than the first threshold, the first surgical risk score is less than the second threshold, and the second surgical risk score is less than the third threshold, the sample surgical risk level of the sample object is determined to be the second risk level.
[0068] In this embodiment, the second risk level can also be referred to as the medium-to-high risk level.
[0069] For example, if a sample subject has a left ventricular ejection fraction less than the first threshold of 35%, an STS score (i.e., the first surgical risk score) less than the second threshold of 8.9%, and a EuroSCORE II score (i.e., the second surgical risk score) less than the third threshold of 10.2%, then the sample subject's surgical risk level is determined to be medium to high risk.
[0070] Step S1100.33: If the left ventricular ejection fraction is greater than or equal to the first threshold, and the first surgical risk score is less than the second threshold and the second surgical risk score is less than the third threshold, the sample surgical risk level of the sample object is determined to be the third risk level.
[0071] In this embodiment, the third risk level can also be referred to as the low risk level.
[0072] For example, if a sample subject has a left ventricular ejection fraction greater than or equal to the first threshold of 35%, and an STS score (i.e., the first surgical risk score) less than the second threshold of 8.9%, and a EuroSCORE II score (i.e., the second surgical risk score) less than the third threshold of 10.2%, then the sample subject's surgical risk level is determined to be low risk.
[0073] Step S1100.4: Take the preoperative multidimensional assessment information of any sample object, the surgical risk level of the sample, the all-cause mortality status of the sample, the composite adverse event status of the sample, and the change in left ventricular ejection fraction of the sample as a training sample to obtain the training sample set.
[0074] Step S1200: Train the surgical risk assessment model using the training sample set to obtain the trained surgical risk assessment model.
[0075] In this embodiment, the surgical risk assessment model adopts the Cox proportional hazards regression model, which uses the all-cause mortality status and the composite adverse event status of the sample as dual outcome variables for modeling.
[0076] The model training method used in this step is a conventional model training method, which will not be elaborated here.
[0077] Step S1300: The trained surgical risk assessment model is corrected using a confounding factor correction algorithm to obtain the surgical risk assessment model.
[0078] In this embodiment, the confounding factor correction algorithm uses the Covariate Balance Propensity Score (CBPS) and Inverse Probability Treatment Weighted (IPTW) method to control the influence of confounding factors such as age, comorbidities, and anatomical parameters on the model prediction results.
[0079] These algorithms are common in this field and will not be elaborated here.
[0080] After model training, the training sample set is weighted using a confounding factor correction algorithm to refit the model, ensuring that the association between the preoperative multidimensional assessment information of the samples and the all-cause mortality status and the composite adverse event status of the samples is not affected by confounding factors.
[0081] By using a confounding factor correction algorithm to correct the trained surgical risk assessment model, the robustness and prediction accuracy of the model can be improved, ensuring that the model output results are closer to the true values.
[0082] In one embodiment of this application, the surgical risk prediction result includes a surgical risk level, and the method further includes step S2300.
[0083] Step S2300: Determine the target intervention method based on the surgical risk level.
[0084] In this embodiment, the target intervention methods include transcatheter valve replacement with extracorporeal life support (i.e., the first intervention method) and transcatheter valve replacement without extracorporeal life support (i.e., the second intervention method).
[0085] Transcatheter valve replacement with extracorporeal life support can include prophylactic establishment of venous-arterial extracorporeal membrane oxygenation (VA-ECMO) support for the target subject before transcatheter aortic valve replacement and monitoring of multiple vital signs of the target subject after transcatheter aortic valve replacement.
[0086] Specifically, prior to transcatheter aortic valve replacement (TAVR), prophylactic establishment of venous-arterial extracorporeal membrane oxygenation (VA-ECMO) support for the target patient can be achieved by: inserting catheters via the femoral artery and femoral vein to establish an extracorporeal circulation system, pre-filling the catheters with lactated Ringer's solution, maintaining an activated clotting time (ACT) greater than 220 seconds during the procedure, controlling the ECMO flow rate at 2.5 to 3.0 liters per minute, and simultaneously lowering the patient's nasopharyngeal temperature to 34°C to stabilize hemodynamic status. The TAVR procedure is then completed with this support throughout the entire process.
[0087] After transcatheter aortic valve replacement surgery, monitoring multiple vital signs of the target subject can be specifically done as follows: after the target subject's vital signs stabilize, gradually warm them to normal body temperature (e.g., 37°C), then reduce the ECMO flow rate to below 2.5 liters (e.g., 2.0 liters), and finally achieve safe weaning from ECMO.
[0088] This transcatheter valve replacement procedure, which utilizes extracorporeal life support, provides reliable perioperative life protection for the target patients through a strategy of preoperative prophylactic implantation, intraoperative continuous circulatory support, and gradual weaning after surgery.
[0089] In one embodiment of this application, the surgical risk level is one of a first risk level, a second risk level, and a third risk level; Step S2300 determines the target intervention method based on the surgical risk level, including steps S2300.1 to S2300.3.
[0090] Step S2300.1: If the surgical risk level is the first risk level, determine the target intervention method as the first intervention method; The first intervention method is transcatheter valve replacement with extracorporeal life support.
[0091] Step S2300.2: If the surgical risk level is the second risk level, determine the target intervention method as the second intervention method; The second intervention method is a transcatheter valve replacement procedure without the application of extracorporeal life support.
[0092] Step S2300.3: If the surgical risk level is the third risk level, determine the target intervention method as the second intervention method.
[0093] In one embodiment of this application, the surgical risk prediction result includes a surgical risk level, which is one of a first risk level, a second risk level, and a third risk level; The method further includes steps S2400 to S2500.
[0094] Step S2400: Obtain the peripheral vascular condition assessment results and aortic root anatomical parameters of the target object.
[0095] In this embodiment, the peripheral vascular condition assessment result can be obtained by evaluating the anatomical and pathological status of peripheral vessels such as the femoral artery and iliac artery of the target subject through imaging examinations (such as computed tomography angiography, CTA). The core assessment dimensions include vessel diameter, degree of calcification, stenosis, tortuosity, and presence of anatomical variations, thus obtaining the peripheral vascular condition assessment result. Among them, the peripheral vascular condition assessment result includes two types: applicable to the femoral artery approach and not applicable to the femoral artery approach.
[0096] Obtaining aortic root anatomical parameters can refer to performing detailed three-dimensional reconstruction and measurement of the aortic root using multi-detector computed tomography (MDCT). The aortic root anatomical parameters include: aortic valve annulus diameter, shape (whether it is regular), ascending aorta diameter, and the angle between the aortic valve annulus plane and the aortic arch (i.e., the aortic angle).
[0097] Step S2500: Determine the target surgical approach for transcatheter aortic replacement surgery based on the surgical risk level, the peripheral vascular condition assessment results, and the aortic root anatomical parameters. The target surgical approach is one of the following: transapical approach, transfemoral approach, and alternative approach.
[0098] In this embodiment, the femoral artery approach can be achieved by percutaneous puncture of the femoral artery in the leg, with the valve delivered retrogradely upwards. The femoral artery approach is the least invasive and has the fastest recovery, making it the preferred minimally invasive route, but it depends on good peripheral vascularity and a smooth aortic anatomy.
[0099] The transapical approach involves making a small incision in the left chest and puncturing the apex of the heart to deliver the valves directly along the antegrade route. This route is the shortest and most direct, avoiding peripheral vascular problems and complex aortic anatomy, and is especially suitable for high-risk patients or those with poor peripheral vascular conditions. However, it is more invasive and requires access to the heart.
[0100] Alternative approaches can be used as backup routes (such as via the subclavian artery or carotid artery) when the two main approaches (i.e., the transapical approach and the transfemoral approach) are not feasible. Selection is highly individualized to address specific anatomical contraindications or vascular access barriers.
[0101] The surgical risk level, peripheral vascular condition assessment results, and aortic root anatomical parameters of the target patients were precisely matched with the optimal surgical approach. The matching logic was to weigh the degree of trauma against the feasibility of the approach: the least invasive transfemoral approach was prioritized. If it was limited by vascular or anatomical conditions, the more direct but slightly more invasive transapical approach was used. When neither was feasible, an individualized alternative was employed.
[0102] In one embodiment of this application, step S2500 determines the target surgical approach for transcatheter aortic valve replacement based on the surgical risk level, the peripheral vascular condition assessment results, and the aortic root anatomical parameters, including steps S2500.1 to S2500.3.
[0103] Step S2500.1: If the first preset condition is met, then the target surgical approach is determined to be the transapical approach. The first preset condition includes at least one of the following: The surgical risk level is classified as Level 1. The peripheral vascular condition assessment result indicated that the femoral artery approach was not suitable. At least one of the aortic root anatomical parameters satisfies the following conditions: the aortic valve annulus morphology is irregular, the ascending aortic diameter is greater than or equal to the diameter threshold, and the aortic angle is greater than or equal to the first angle threshold.
[0104] In this embodiment, if the surgical risk level is Level 1, it indicates that the target patient has extremely poor cardiac function (LVEF < 35%) and a high surgical risk, often requiring prophylactic ECMO support. The transapical approach provides the most direct and shortest delivery path, and under ECMO assistance, it can minimize blood flow interference to the fragile heart and ensure perioperative circulatory stability.
[0105] If the peripheral vascular condition assessment results indicate that the femoral artery approach is not suitable, then the transapical approach is selected.
[0106] When the aortic valve annulus morphology is irregular, such as an elliptical shape, it may affect valve anchoring. The transapical approach allows for more vertical and coaxial valve release, improving implantation accuracy.
[0107] If the diameter of the ascending aorta is greater than or equal to the diameter threshold (e.g., 42.6 mm), it indicates that significant aortic dilation will increase the difficulty of passage through the femoral artery delivery system and the risk of vascular complications, in which case the transapical approach is chosen.
[0108] If the aortic angle is greater than or equal to the first angle threshold (e.g., 50 degrees), it means that the angle is too steep and the femoral artery delivery catheter will be difficult to bend and coaxially align with the valve annulus, while the transapical approach is almost unaffected by this angle.
[0109] Step S2500.2: If the second preset condition is met, then the target surgical approach is determined to be the femoral artery approach. The second preset condition includes: The surgical risk level is either level three or level two; The peripheral vascular condition assessment result indicates that the femoral artery approach is suitable. The aortic root anatomical parameters satisfy the following: the aortic valve annulus diameter is within a set diameter range, and the aortic angle is less than or equal to the second angle threshold.
[0110] In this embodiment, the surgical risk level is level three or level two, indicating that the target patient's cardiac function is relatively good or poor but the surgical risk score is not high, and routine ECMO support is not required, making the femoral artery approach, which is less invasive, suitable.
[0111] The peripheral vascular condition assessment results indicate that the femoral artery approach is suitable, meaning that the path from the femoral artery and iliac artery to the aorta is unobstructed, has sufficient diameter, and is free of serious lesions, and can safely accommodate the delivery sheath. Therefore, the femoral artery approach is chosen.
[0112] The aortic valve annulus diameter is within a predetermined range (e.g., 25.8 to 28.7 mm), which has a high compatibility with most commercially available valve models, ensuring a proper implant size. Furthermore, the aortic angle is less than or equal to the second angle threshold (e.g., 47 degrees), indicating that the gentle angle facilitates the delivery system's smooth passage through the aortic arch and achieves good coaxiality. In this case, the femoral artery approach is chosen.
[0113] Step S2500.3: If the first preset condition and the second preset condition are not met, then the target surgical approach is determined to be an alternative approach.
[0114] In this embodiment, if neither the first preset condition nor the second preset condition is met, the target surgical approach is determined to be an alternative approach. The alternative approach can be, for example, via the subclavian artery, via the carotid artery, or via the aorta.
[0115] The specific alternative approach is not automatically specified by electronic devices, but requires experienced surgeons to make a comprehensive assessment and individualized decision based on more detailed imaging data (such as the aortic branches, ventricular morphology, and retrosternal space). This preserves necessary clinical decision-making space for complex and special cases, improving the safety of the surgery.
[0116] Based on the above, this application obtains multi-dimensional preoperative assessment information of the target subject and inputs this information into a surgical risk assessment model to obtain a surgical risk prediction result for the target subject. This achieves accurate assessment of the surgical risk of the target subject based on multi-dimensional preoperative assessment information, solving the technical problems of inaccurate surgical risk prediction, reliance on subjective experience in treatment decisions, and a disconnect between risk prediction and the final treatment plan in related technologies, thus improving the accuracy of prognosis prediction.
[0117] <Device Embodiment> Figure 3 This is a schematic block diagram of an electronic device 300 according to an embodiment of this application.
[0118] In this embodiment, as Figure 3 As shown, the electronic device 300 includes a processor 310 and a memory 320. The memory 320 stores programs or instructions that can run on the processor 310. When the program or instructions are executed by the processor 310, they implement the method described in the above-described method embodiments.
[0119] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the methods described in any of the above-described method embodiments.
[0120] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.
[0121] This disclosure may be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement any of the methods in the foregoing embodiments of this disclosure.
[0122] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media may include, for example, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), compact disc-read-only memory (CD-ROM), digital versatile disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any combination thereof. The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.
[0123] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include one or more of copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to computer-readable storage media in the respective computing / processing device.
[0124] The computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object programs written in any combination of one or more programming languages, including object-oriented programming languages (such as Smalltalk, C++, etc.) and conventional procedural programming languages (such as the "C" language or similar programming languages). The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network (e.g., a local area network or a wide area network), or it may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays, or programmable logic arrays, can execute computer-readable program instructions to implement various aspects of the embodiments of this disclosure by utilizing state information from the computer-readable program instructions.
[0125] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.
[0126] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.
[0127] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.
[0128] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. It should be noted that implementation in hardware, implementation in software, and implementation using a combination of software and hardware are all equivalent.
[0129] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, and are not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of this disclosure is defined by the appended claims.
Claims
1. A method for predicting surgical risks, characterized in that, include: Obtain preoperative multidimensional assessment information of the target subject; wherein, the multidimensional assessment information includes: left ventricular ejection fraction, first surgical risk score, second surgical risk score, NT-proBNP value, systolic pulmonary artery pressure and extracorporeal life support status; The preoperative multidimensional assessment information is input into the surgical risk assessment model to obtain the surgical risk prediction result of the target object; wherein, the surgical risk prediction result includes at least one of the following: surgical risk level, all-cause mortality risk value, composite adverse event risk value, and predicted change in left ventricular ejection fraction.
2. The method according to claim 1, characterized in that, The surgical risk prediction results include a surgical risk level, and the method further includes: Based on the surgical risk level, the target intervention method is determined.
3. The method according to claim 2, characterized in that, The surgical risk level is one of the first risk level, the second risk level, and the third risk level; The determination of the target intervention method based on the surgical risk level includes: When the surgical risk level is the first risk level, the target intervention method is determined to be the first intervention method; wherein, the first intervention method is transcatheter valve replacement with extracorporeal life support; When the surgical risk level is the second risk level, the target intervention method is determined to be the second intervention method; wherein, the second intervention method is a transcatheter valve replacement without the application of extracorporeal life support; If the surgical risk level is the third risk level, the target intervention method is determined to be the second intervention method.
4. The method according to claim 1, characterized in that, The surgical risk prediction result includes a surgical risk level, which is one of a first risk level, a second risk level, and a third risk level; The method further includes: Obtain the peripheral vascular condition assessment results and aortic root anatomical parameters of the target object; Based on the surgical risk level, the peripheral vascular condition assessment results, and the aortic root anatomical parameters, the target surgical approach for transcatheter aortic replacement is determined; wherein, the target surgical approach is one of the transapical approach, the transfemoral approach, and the alternative approach.
5. The method according to claim 4, characterized in that, The determination of the target surgical approach for transcatheter aortic valve replacement based on the surgical risk level, the peripheral vascular condition assessment results, and the aortic root anatomical parameters includes: If the first preset condition is met, then the target surgical approach is determined to be the transapical approach: The first preset condition includes at least one of the following: The surgical risk level is classified as Level 1. The peripheral vascular condition assessment result indicated that the femoral artery approach was not suitable. At least one of the aortic root anatomical parameters satisfies the following conditions: the aortic valve annulus morphology is irregular, the ascending aortic diameter is greater than or equal to the diameter threshold, and the aortic angle is greater than or equal to the first angle threshold. If the second preset condition is met, then the target surgical approach is determined to be the femoral artery approach: The second preset condition includes: The surgical risk level is either level three or level two; The peripheral vascular condition assessment result indicates that the femoral artery approach is suitable. The aortic root anatomical parameters satisfy the following: the aortic valve annulus diameter is within a set diameter range, and the aortic angle is less than or equal to the second angle threshold. If the first preset condition and the second preset condition are not met, then the target surgical approach is determined to be an alternative approach.
6. The method according to claim 1, characterized in that, The surgical risk assessment model was determined through the following steps: Obtain the training sample set: Each training sample in the training sample set includes preoperative multidimensional assessment information, all-cause mortality status, composite adverse event status, surgical risk level, and left ventricular ejection fraction change. The surgical risk assessment model is trained using the training sample set to obtain the trained surgical risk assessment model; The trained surgical risk assessment model is corrected using a confounding factor correction algorithm to obtain the surgical risk assessment model.
7. The method according to claim 6, characterized in that, The acquisition of the training sample set includes: Obtain sample data from different sample objects to obtain a sample dataset; wherein, the sample data includes candidate feature groups corresponding to the sample objects, the all-cause mortality status of the samples, the composite adverse event status of the samples, and the change in left ventricular ejection fraction of the samples. For any candidate feature group of a sample, the preoperative multidimensional assessment information of the sample is selected from the candidate feature group; wherein, the preoperative multidimensional assessment information includes: left ventricular ejection fraction, first surgical risk score, second surgical risk score, NT-proBNP value, systolic pulmonary artery pressure and status of extracorporeal life support application. Based on the preoperative multidimensional assessment information of the sample subjects, the surgical risk level of the sample subjects is determined; The training sample set is obtained by taking the preoperative multidimensional assessment information of any sample object, the surgical risk level of the sample, the all-cause mortality status of the sample, the occurrence status of the composite adverse events of the sample, and the change in the left ventricular ejection fraction of the sample as a training sample.
8. The method according to claim 7, characterized in that, The step of determining the surgical risk level of the sample subject based on the preoperative multidimensional assessment information of the sample subject includes: If the left ventricular ejection fraction is less than a first threshold and the first surgical risk score is greater than or equal to a second threshold, or if the left ventricular ejection fraction is less than a first threshold and the second surgical risk score is greater than or equal to a third threshold, the sample surgical risk level of the sample object is determined to be the first risk level. If the left ventricular ejection fraction is less than the first threshold, the first surgical risk score is less than the second threshold, and the second surgical risk score is less than the third threshold, the sample surgical risk level of the sample subject is determined to be the second risk level. If the left ventricular ejection fraction is greater than or equal to the first threshold, and the first surgical risk score is less than the second threshold and the second surgical risk score is less than the third threshold, the sample surgical risk level of the sample subject is determined to be the third risk level.
9. An electronic device comprising a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the method as described in any one of claims 1-8.
10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method according to any one of claims 1-8.