Preoperative risk assessment method and system for urinary surgery

Abstract

The invention discloses a urinary surgery preoperative risk assessment method and system, and the method comprises the following steps: dividing a urinary surgery operation process into a plurality of operation units, and each operation unit represents a key step in the operation process; performing preliminary risk assessment on each operation unit based on historical data, determining a risk value of the operation unit, and dividing the operation unit into three risk categories of low risk, medium risk and high risk according to the risk value of the operation unit; for a low-risk operation unit, directly calling a text template in a historical database, and generating standardized prompt information; for the medium-risk operation unit, constructing a multi-dimensional thermodynamic rendering diagram in combination with the specific medical record and image data of the patient; for a high-risk operation unit, on the basis of generating the thermal rendering diagram, a dynamic interactive anatomical model is constructed, a detailed risk assessment result is output, and the method has the advantages that the operation operation unit can be subdivided, and the risk can be quantitatively assessed.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information technology, and particularly to a method and system for preoperative risk assessment in urology surgery. Background Art

[0002] In urology surgery, preoperative risk assessment is a crucial link to ensure the success of the surgery and the safety of the patient. Traditional risk assessment methods mainly rely on doctors' experience and subjective judgment. Although this method can provide effective risk assessment to a certain extent, it has obvious limitations. First of all, the experience and knowledge levels of doctors vary, resulting in significant fluctuations in the results of risk assessment due to individual differences among doctors. According to the "Statistical Report on Complications of Urology Surgery in China (2022)", the surgical complication rate caused by traditional empirical judgment methods is as high as 12.7%, and 45% of them are due to insufficient preoperative risk assessment. Secondly, traditional methods are difficult to conduct detailed and quantitative risk assessment on each operation step during the surgery, and cannot accurately identify high-risk steps, thus making it impossible to formulate targeted preventive measures before the surgery.

[0003] With the continuous development of medical technology, especially the wide application of digital and intelligent technologies in the medical field, new ideas and methods have been provided for preoperative risk assessment in urology surgery. However, existing digital risk assessment systems often focus on the overall simulation and analysis of the surgical process, lacking the subdivision and quantitative assessment of surgical operation units, resulting in limited accuracy and practicality of risk assessment. At the same time, these systems usually require a large amount of computing resources and have deficiencies in real-time feedback and dynamic adjustment, making it difficult to meet the actual clinical needs. Therefore, it is necessary to design a method and system for preoperative risk assessment in urology surgery that can subdivide surgical operation units and quantitatively assess risks. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for preoperative risk assessment in urology surgery to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: A method and system for preoperative risk assessment in urology surgery, including the following steps:

[0006] Step S1: Divide the urology surgery process into several operation units, and each operation unit represents a key step in the surgery process;

[0007] Step S2: Conduct a preliminary risk assessment on each operation unit based on historical data, determine its risk value, and classify the operation unit into three risk categories of low, medium, and high risk according to the risk value of the operation unit;

[0008] Step S3: For low-risk operation units, directly call the text templates in the historical database to generate standardized prompt messages;

[0009] Step S4: For medium-risk operation units, combine the specific medical records and imaging data of the patient to construct a multi-dimensional heat map;

[0010] Step S5: For high-risk operation units, on the basis of generating a heat map, construct a dynamic interactive anatomical model and output a detailed risk assessment result;

[0011] Step S6: During the simulated operation process, the system monitors the operation trajectory of the doctor in real time, calculates the deviation between the actual operation and the ideal path, and thus conducts dynamic feedback and decision optimization.

[0012] According to the above technical solution, the step S1 further includes:

[0013] Step S11: Collect historical urological surgery data, where the historical urological surgery data includes surgical records, doctor's notes, and patient feedback, and then analyze the surgical process through natural language processing NLP algorithms, and identify the main steps in the surgery through keyword extraction technology;

[0014] Step S12: Based on the common standard operation procedures during the surgery, decompose the surgical process into several independent operation units; among them, each unit needs to meet the requirements of operation independence and risk quantifiability.

[0015] According to the above technical solution, the specific method for the preliminary risk assessment of each operation unit based on historical data in the step S2 is as follows:

[0016] Through the risk quantification model R i =α·P i +β·S i Calculate the risk value R i of each unit, where P i is the historical error probability, obtained based on the historical error rate of this step statistically in the hospital database; S i is the severity of the consequence, obtained by the expert committee according to the clinical impact score, and α and β are the weight coefficients of the historical error rate and the severity of the consequence respectively, and α is slightly greater than β.

[0017] According to the above technical solution, the specific method for classifying each operation unit into three categories of low, medium, and high risks according to its risk value in the step S2 includes:

[0018] Set the first-level risk threshold f 1 and the second-level risk threshold f 2 , where f 1 <f 2 ;

[0019] When R i ≤f 1 it indicates that the historical error rate is extremely low and the consequences are controllable, and the target operation unit is classified as a low-risk operation unit;

[0020] When f < R i ≤f 2 it indicates that there is a certain probability of complication risk, but it can be avoided through prediction, and the target operation unit is classified as a medium-risk operation unit;

[0021] When R i >f 2 it indicates a step with high operation difficulty and serious consequences, and the target operation unit is classified as a high-risk operation unit.

[0022] According to the above technical solution, the step S4 further includes:

[0023] Based on the patient's CT / MRI image data, construct a multi-dimensional thermal rendering map to visually label the risk areas;

[0024] Calculate the thermal value H(x, y, z) of each voxel point, and its expression is as follows: where D k is the quantization value of the k-th risk dimension in three-dimensional space, w k is the dimension weight, which is determined comprehensively by expert experience and historical data statistics, and its acquisition logic expression is as follows:

[0025]

[0026] where, E k is the expert experience weighting coefficient, C k is the historical data statistics weighting coefficient; and the values of 0.7 and 0.3 in the formula are mixing coefficients;

[0027] Finally, based on the calculated value, overlay the thermal map on the patient's three-dimensional anatomical model, and the red highlighted area indicates high risk.

[0028] According to the above technical solution, the specific steps of constructing a dynamic interactive anatomical model and outputting a detailed risk assessment result in the step S5 are as follows:

[0029] Model generation: Integrate the image data and biomechanical parameters, and use finite element analysis to simulate tissue deformation;

[0030] Risk animation simulation: When the simulated operation exceeds the safety threshold, the model automatically plays a pre-generated blood vessel rupture animation and gives a prompt;

[0031] Multi-parameter fusion scoring: Combine mechanical feedback and physiological parameters to generate a comprehensive risk index R综合 , further assisting doctors in making precise decisions during high-risk steps, and its expression is as follows: R 综合 =λ 1 ·R 力 +λ 2 ·R 生 , where λ 1 and λ 2 are both clinically verified weight coefficients, R 力 represents the mechanical risk, and R 生 represents the physiological risk.

[0032] According to the above technical solution, the step S6 further includes:

[0033] Comparing the current instrument path with the ideal path, calculating the deviation value ΔY, and its expression is:

[0034] where O 实 represents the actual path coordinate sequence of the doctor's simulated operation, and O 理 represents the ideal path coordinate sequence based on historical successful cases; ΔY is the deviation value, indicating the degree of deviation of the current operation from the ideal state;

[0035] Obtaining the risk dynamic warning threshold θ, and when the calculated deviation value ΔY > θ, immediately adjusting the risk prompt intensity of the heat map.

[0036] According to the above technical solution, the urological preoperative risk assessment system includes:

[0037] Step decomposition module: used to parse historical surgical records and expert knowledge bases, split the surgical process into independent operation units, and generate a standardized unit list;

[0038] Risk assessment module: used to calculate the risk value of each operation unit according to historical data and the scoring rules of clinical experts, and classify it into low, medium, and high risk categories;

[0039] Simulation processing module: used to generate a dynamic interactive surgical simulation diagram based on the patient's imaging data, surgical process simulation, and mechanical analysis, and perform real-time monitoring and simulation of the operation steps;

[0040] Dynamic feedback module: used to provide real-time dynamic feedback according to the deviation between the real-time monitoring result and the historical ideal path, prompt the doctor to adjust the operation path, and automatically adjust the heat map update frequency and prompt intensity according to the doctor's skill level.

[0041] According to the above technical solution, the simulation processing module further includes:

[0042] Low-risk text processor: used to call the text template library to generate natural language prompts;

[0043] Medium - risk heat renderer: used to generate multi - dimensional heat maps based on patient imaging data;

[0044] High - risk dynamic modeler: constructs an interactive 3D anatomical model using finite element analysis to simulate tissue deformation and risk animation.

[0045] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0046] (1) Through the subdivided operation units of the surgical process, the present invention conducts a preliminary risk assessment based on historical data for each operation unit and quantifies it into low, medium, and high - risk categories. This method makes the risk assessment more meticulous and accurate, and can provide more targeted preoperative preparations and preventive measures for doctors;

[0047] (2) For operation units with different risk categories, the present invention adopts different processing strategies. For low - risk operation units, it directly calls the text templates in the historical database to generate standardized prompt information, significantly saving computing power; for medium - and high - risk operation units, it combines the specific medical records and imaging data of the patient to construct multi - dimensional heat renderings and dynamic interactive anatomical models to ensure the comprehensiveness and accuracy of risk assessment. This hierarchical processing method effectively optimizes the allocation of computing resources and improves the operating efficiency of the system;

[0048] (3) By simulating the system's real - time monitoring of the doctor's operation trajectory during the surgical process, calculating the deviation between the actual operation and the ideal path, and then conducting dynamic feedback and decision optimization. This real - time dynamic feedback mechanism can help doctors adjust the operation path in a timely manner, reduce risks for subsequent surgeries, and improve the surgical success rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention.

[0050] In the drawings:

[0051] Figure 1 is a schematic diagram of a preoperative risk assessment method for urology in the present invention;

[0052] Figure 2 is a schematic diagram of the composition of a preoperative risk assessment system for urology in the present invention;

[0053] Figure 3 is a schematic diagram of the composition of the simulation processing module in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0055] Embodiment 1

[0056] Please refer to Figure 1 , the present invention provides a technical solution: a method for preoperative risk assessment in urology, including the following steps:

[0057] Step S1: Divide the urological surgical process into several operation units, and each operation unit represents a key step in the surgical process;

[0058] Step S2: Conduct a preliminary risk assessment on each operation unit based on historical data, determine its risk value, and classify the operation units into three risk categories of low, medium, and high risk according to the risk value of the operation unit;

[0059] Step S3: For low-risk operation units, directly call the text template in the historical database to generate standardized prompt information. Exemplarily, for perirenal fat stripping: the historical bleeding rate is 0.5%, it is recommended to use blunt dissection instruments. This process does not require three-dimensional modeling simulation operation, only a text matching algorithm, which significantly saves computing power;

[0060] Step S4: For medium-risk operation units, construct a multi-dimensional heat map in combination with the patient's specific medical record and imaging data;

[0061] Step S5: For high-risk operation units, on the basis of generating a heat map, construct a dynamic interactive anatomical model and output a detailed risk assessment result;

[0062] Step S6: During the simulated surgical process, the system monitors the doctor's operation trajectory in real time, calculates the deviation between the actual operation and the ideal path, so as to perform dynamic feedback and decision optimization.

[0063] Step S1 further includes:

[0064] Step S11: Collect historical urological surgical data, where the historical urological surgical data includes surgical records, doctor's notes, and patient feedback. Then analyze the surgical process through the natural language processing NLP algorithm, and identify the main steps in the surgery through keyword extraction technology, such as "incise the skin", "dissect the tissue", etc.;

[0065] Step S12: Based on the common standard operation procedures during the surgery, break down the surgical process into several independent operation units. For example, partial nephrectomy can be split into units such as "renal artery positioning", "tumor boundary marking", "tissue resection", "wound suture", etc.

[0066] Among them, each unit needs to meet the requirements of operation independence (low coupling degree between units) and risk quantifiability (able to extract historical error rates and consequence data).

[0067] The specific method for the preliminary risk assessment of each operation unit based on historical data in Step S2 is as follows:

[0068] Calculate the risk value R of each unit through the risk quantification model R i =α·P i +β·S i where P i is the historical error probability, obtained based on the historical error rate of this step statistically from the hospital database; S i is the severity of consequences, obtained by the expert committee according to the clinical impact score. α and β are the weight coefficients of the historical error rate and the severity of consequences respectively, and α is slightly greater than β. Through clinical data verification, it shows that the contribution of the historical error rate to the overall risk is slightly higher than the severity of consequences, meeting the balance requirement of "high-frequency low-risk operations" and "low-frequency high-risk operations" in actual surgery. By replacing the traditional subjective classification with a quantification formula, the repeatability and consistency of risk grading are ensured. At the same time, the weight coefficients can be adjusted according to different surgical types, thereby enhancing the flexibility of the system. Exemplarily, for tumor surgery, S i can be emphasized, and for routine surgery, P i can be emphasized. i .

[0069] The specific method for classifying the operation units into three categories of low, medium, and high risks according to their risk values in Step S2 includes:

[0070] Set the first-level risk threshold f 1 and the second-level risk threshold f 2 , where f 1 <f 2 ;

[0071] When R i ≤f 1 , it indicates that the historical error rate is extremely low and the consequences are controllable, such as the steps of conventional instrument operations, and the target operation unit is classified as a low-risk operation unit;

[0072] When f < R i ≤f 2 , it indicates that there is a certain probability of complication risk, but it can be avoided through prediction, such as the separation in the area with dense blood vessels, and the target operation unit is classified as a medium-risk operation unit;

[0073] When R i > f 2 it represents a step with high operation difficulty and serious consequences, such as resection when a tumor invades important organs. The target operation unit is divided into a high-risk operation unit.

[0074] Step S4 further includes:

[0075] Based on the patient's CT / MRI image data, construct a multi-dimensional thermal rendering map to visually label the risk area;

[0076] Calculate the thermal value H(x, y, z) of each voxel point, and its expression is as follows: Through three-dimensional thermal value calculation, accurately label the patient's personalized risk area to assist the doctor in avoiding high-risk operation paths, where D k is the quantization value of the k-th risk dimension in three-dimensional space, w k is the dimension weight, which is comprehensively determined by expert experience and historical data statistics. Its acquisition logic expression is as follows:

[0077]

[0078] where, E k is the expert experience weighting coefficient, which is scored by the doctor according to clinical importance. Exemplarily, the blood vessel distance weight is set to 0.8, and the tissue thickness weight is set to 0.5. C k is the historical data statistics weighting coefficient, which is calculated based on the correlation between complications and each dimension, such as the correlation coefficient between blood vessel distance and bleeding rate; and the values of 0.7 and 0.3 in the formula are mixing coefficients, which rely on expert experience first, and at the same time are corrected by data-driven, taking into account clinical authority and objectivity, avoiding misjudgment caused by sample deviation of pure data-driven models (such as rare cases), and can also automatically increase the relevant dimension weight for special patients (such as blood vessel variation) to enhance the pertinence of risk assessment;

[0079] Finally, based on the calculated value, overlay the thermal map on the patient's three-dimensional anatomical model, and the red highlighted area represents high risk.

[0080] The specific steps for constructing a dynamic interactive anatomical model and outputting a detailed risk assessment result in step S5 are as follows:

[0081] Model generation: Integrate image data and biomechanical parameters, and use finite element analysis (FEA) to simulate tissue deformation. For example, when simulating the traction of the ureter by a surgical forceps, calculate the tissue stress distribution in real time and predict the rupture probability;

[0082] Risk animation simulation: When the simulated operation exceeds the safety threshold, such as stress > 50 kPa, the model automatically plays a pre-generated blood vessel rupture animation and gives a prompt, such as "The pulling force exceeds the limit, and the expected blood loss > 200 ml".

[0083] Multi-parameter fusion scoring: Combine mechanical feedback (instrument pressure) and physiological parameters (intraoperative blood pressure fluctuations) to generate a comprehensive risk index R 综合 , which further helps the doctor make accurate decisions in high-risk steps. Its expression is as follows: R 综合 =λ 1 ·R 力 +λ 2 ·R 生 , where λ 1 , λ 2 are both clinically verified weight coefficients, R 力 represents the mechanical risk, and R 生 represents the physiological risk.

[0084] Step S6 further includes:

[0085] Compare the current instrument path with the ideal path and calculate the deviation value ΔY. Its expression is:

[0086] where O 实 represents the sequence of actual path coordinates of the doctor's simulated operation. The acquisition method is as follows: Use a 6-DOF electromagnetic sensor installed at the tip of the surgical instrument to collect the three-dimensional coordinates (x, y, z) and attitude (pitch angle, yaw angle, roll angle) of the instrument tip in real time. Eliminate the sensor jitter noise through Kalman Filter. Based on the DICOM coordinate system of the preoperative CT / MRI image, convert the sensor coordinate system to the patient's anatomical coordinate system. Finally, record the instrument tip coordinates according to the time stamp to generate a discrete path point set. Its expression is: O 实 ={(x 1 ,y 1 ,z 1 ,θ 1 ),(x 2 ,y 2 ,z 2 ,θ 2 ),…,(x T ,y T ,z T ,θ T )}, where θ t is the instrument attitude angle; O 理Denote the ideal path coordinate sequence based on historical successful cases, which is obtained as follows: collect cases without complications in previous surgeries, including instrument path data, imaging data, and postoperative follow-up results, normalize all paths to the same time step according to the surgical procedure duration, then map the anatomical structures of different patients to the standard template space (such as the MNI space) to eliminate individual size differences, use K-means clustering for the normalized paths, screen out the cluster center path as the ideal path candidate, and finally, the doctor evaluates the clinical rationality of the candidate path and determines the ideal path. Its expression is where N is the number of successful cases of the same type; ΔY is the deviation value, indicating the degree of deviation of the current operation from the ideal state; through path comparison, the doctor is prompted to correct the operation in real time, and the deviation value ΔY can be recorded as an indicator for evaluating the doctor's skills, helping novice doctors quickly improve their technical level;

[0087] Obtain the dynamic risk warning threshold θ. When the calculated deviation value ΔY > θ, immediately adjust the risk prompt intensity of the heat map; through unitized layering, it not only realizes the full-process coverage evaluation of complex surgeries but also significantly reduces computational redundancy through dynamic resource allocation. The multi-modal visualization technology transforms abstract risks into intuitive visual and mechanical feedback, providing an upgrade path for doctors from "experience-based decision-making" to "data-driven decision-making";

[0088] In the embodiment of the present invention, the attending experience index of the current doctor can also be retrieved, and the display frequency of the blood vessel protection prompt is adjusted inversely according to the attending experience index of the previous doctor. Exemplarily, when the attending experience index of the doctor is low, the system determines that the doctor is a novice doctor, so the heat map update cycle is shortened from 5 seconds to 2 seconds to optimize the auxiliary effect on different doctors.

[0089] Embodiment 2

[0090] Please refer to Figure 2 and Figure 3 , based on the same inventive concept as Embodiment 1, the present invention provides a technical solution: a preoperative risk assessment system for urology, including:

[0091] Step decomposition module: used to parse historical surgical records and expert knowledge bases, split the surgical process into independent operation units, and generate a standardized unit list;

[0092] Risk assessment module: used to calculate the risk value of each operation unit according to historical data and the scoring rules of clinical experts, and classify it into low, medium, and high risk categories;

[0093] Simulation processing module: used to generate a dynamic interactive surgical simulation diagram based on the patient's imaging data, surgical process simulation, and mechanical analysis, and perform real-time monitoring and simulation on the operation steps;

[0094] Dynamic feedback module: It is used to provide real-time dynamic feedback based on the deviation between the real-time monitoring result and the historical ideal path, prompt the doctor to adjust the operation path, and automatically adjust the heat map update frequency and prompt intensity according to the doctor's skill level.

[0095] The simulation processing module further includes:

[0096] Low-risk text processor: It is used to call the text template library to generate natural language prompts;

[0097] Medium-risk heat renderer: It is used to generate a multi-dimensional heat map based on the patient's imaging data;

[0098] High-risk dynamic modeler: It uses finite element analysis to construct an interactive 3D anatomical model and simulate tissue deformation and risk animation;

[0099] In summary of the above embodiments, the present invention significantly improves the accuracy and practicability of preoperative risk assessment through refined step decomposition, scientific risk assessment, personalized simulation processing, and real-time dynamic feedback. The method first decomposes the complex surgical process into several independent operation units, making the risk of each unit quantifiable and the operation independent, providing a basis for subsequent risk assessment. Then, using historical data and clinical expert scoring rules, the risk of each operation unit is quantified and classified into low, medium, and high risk categories, realizing hierarchical risk management. In the simulation processing stage, according to the patient's imaging data and surgical process simulation, a dynamic interactive surgical simulation diagram is generated, providing intuitive visual and mechanical feedback for the doctor. At the same time, the system also monitors the doctor's operation trajectory in real time, compares it with the historical ideal path, provides real-time dynamic feedback, helps the doctor adjust the operation path, and reduces the surgical risk. In addition, the system can also automatically adjust the heat map update frequency and prompt intensity according to the doctor's skill level, realizing personalized assistance. Therefore, the comprehensive preoperative risk assessment method and system provided by the present invention not only improve the safety of the surgery, but also optimize the surgical process, provide more scientific, accurate, and practical decision-making support for the doctor, help improve the surgical success rate, reduce the complication rate, and have important significance for the development of urological surgery.

[0100] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0102] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0104] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit and scope protected by the claims of the present invention. These all fall within the protection scope of the present invention.

Claims

1. A method for preoperative risk assessment in urology, characterized in that: The following steps are involved: Step S1, dividing the urological surgery process into a number of operation units, each operation unit represents a key step in the surgery process; Step S2: Conduct a preliminary risk assessment on each operation unit based on historical data to determine its risk value, and classify the operation unit into three risk categories: low, medium, and high risk according to the risk value of the operation unit; Step S3: For low-risk operation units, directly call the text template in the historical database to generate standardized prompt information; Step S4: For medium-risk operation units, a multi-dimensional thermal rendering is constructed in combination with the patient's specific medical records and imaging data; Step S5: For high-risk operation units, a dynamic interactive anatomical model is constructed based on the generated thermal rendering, and detailed risk assessment results are output; Step S6: During the simulated surgery, the system monitors the doctor's operation trajectory in real time, calculates the deviation between the actual operation and the ideal path, and thus performs dynamic feedback and decision optimization.

2. A method for preoperative risk assessment in urology according to claim 1, characterized in that: The step S1 further comprises: Step S11, collecting historical urological surgery data, wherein the historical urological surgery data includes surgery records, doctor's notes, and patient feedback, and then analyzing the surgery process through a natural language processing (NLP) algorithm, and identifying the main steps in the surgery through keyword extraction technology; Step S12: Based on the common standard operating procedures during surgery, the surgical process is decomposed into several independent operation units. Among them, each unit must meet the requirements of operational independence and risk quantifiability.

3. A method for preoperative risk assessment in urology according to claim 1, characterized in that: The method for performing preliminary risk assessment on each operating unit based on historical data in step S2 is specifically as follows: Through the risk quantification model R i =α·P i +β·S i Calculate the risk value R for each unit i , where P i is the historical error probability, which is obtained based on the historical error rate of this step in the hospital database; S i is the severity of the consequence, obtained by the expert committee based on the clinical impact score. α and β are the weight coefficients of the historical error rate and the severity of the consequence, respectively, and α is slightly greater than β.

4. A method for preoperative risk assessment in urology according to claim 3, characterized in that: The specific method of classifying the operating units into three categories of low risk, medium risk and high risk according to their risk values ​​in step S2 includes: Set the first-level risk threshold f1 and the second-level risk threshold f2, where f1 <f2; When R i When ≤f1, it means that the historical error rate is extremely low and the consequences are controllable, and the target operation unit is classified as a low-risk operation unit; When f <R i When ≤f2, it means that there is a certain probability of complication risk, but it can be avoided through prejudgment, and the target operation unit is divided into a medium-risk operation unit; When R i When >f2, it indicates a step with high operational difficulty and serious consequences, and the target operation unit is classified as a high-risk operation unit.

5. A method for preoperative risk assessment in urology according to claim 1, characterized in that: The step S4 further comprises: Based on the patient's CT / MRI imaging data, a multi-dimensional thermal rendering is constructed to intuitively mark the risk areas; Calculate the thermal value H(x,y,z) of each voxel point, and its expression is as follows: Where D k is the quantitative value of the kth risk dimension in three-dimensional space, w k is the dimension weight, which is determined by expert experience and historical data statistics. Its logical expression is as follows: Among them, E k is the expert experience weighting coefficient, C k is the statistical weight coefficient of historical data; and 0.7 and 0.3 in the formula are the mixing coefficients; Finally, based on the calculated values, a heat map is superimposed on the patient's 3D anatomical model, and red highlighted areas indicate high risk.

6. A method for preoperative risk assessment in urology according to claim 1, characterized in that: The specific steps of constructing a dynamic interactive anatomical model and outputting detailed risk assessment results in step S5 are as follows: Model generation: Fusion of imaging data and biomechanical parameters, using finite element analysis to simulate tissue deformation; Risk animation simulation: When the simulated operation exceeds the safety threshold, the model automatically plays the pre-generated blood vessel rupture animation and gives a prompt; Multi-parameter fusion scoring: combining mechanical feedback and physiological parameters to generate a comprehensive risk index R 综合 , further helps doctors make accurate decisions in high-risk steps, and its expression is as follows: R 综合 =λ1·R 力 +λ2·R 生 , where λ1 and λ2 are clinical validation weight coefficients, R 力 Represents mechanical risk, R 生 Indicates physiological risk.

7. A method for preoperative risk assessment in urology according to claim 1, characterized in that: The step S6 further comprises: Compare the current instrument path with the ideal path and calculate the deviation value ΔY, which is expressed as: Among them, 实 represents the actual path coordinate sequence of the doctor's simulated operation, O 理 represents the ideal path coordinate sequence based on historical successful cases; ΔY is the deviation value, which quantifies the degree of deviation between the current operation and the ideal state; Get the risk dynamic warning threshold θ. When the calculated deviation value ΔY>θ, adjust the risk warning intensity of the heat map immediately.

8. A urology preoperative risk assessment system, used to execute a urology preoperative risk assessment method according to any one of claims 1 to 7, characterized in that: include: Step decomposition module: used to parse historical surgical records and expert knowledge base, split the surgical process into independent operation units, and generate a standardized unit list; Risk assessment module: used to calculate the risk value of each operation unit based on historical data and clinical experts' scoring rules, and divide it into low, medium and high risk categories; Simulation processing module: used to generate dynamic interactive surgical simulation diagrams based on the patient's image data, surgical process simulation and mechanical analysis, and to monitor and simulate the operation steps in real time; Dynamic feedback module: used to provide real-time dynamic feedback based on the deviation between the real-time monitoring results and the historical ideal path, prompting the doctor to adjust the operation path, and automatically adjust the heat map update frequency and prompt intensity according to the doctor's skill level.

9. A urology preoperative risk assessment system according to claim 8, characterized in that: The simulation processing module further comprises: Low-risk text processor: used to call the text template library to generate natural language prompts; Medium-risk thermal renderer: used to generate multi-dimensional heat maps based on patient imaging data; High-risk dynamic modeler: Use finite element analysis to build interactive 3D anatomical models to simulate tissue deformation and risk animation.

Images