A method, equipment, media, and program product for constructing a bleeding risk prediction model after percutaneous renal biopsy.

Abstract

The embodiment of the specification provides a method, device, medium and program product for constructing a post-percutaneous renal biopsy hemorrhage risk prediction model, and relates to the field of intelligent medical treatment. The method comprises the following steps: obtaining preoperative target parameters of training set samples, obtaining postoperative imaging data of the training set samples subjected to percutaneous renal biopsy, and extracting an outcome index for evaluating the hemorrhage risk from the postoperative imaging data, wherein the outcome index comprises (hematoma long diameter+hematoma short diameter) / 2; taking the outcome index as a verification standard, evaluating the prediction ability of the preoperative target parameters on the postoperative hemorrhage risk, and obtaining an evaluation result; and constructing a hemorrhage risk prediction model based on the preoperative target parameters according to the evaluation result. The application adjusts the outcome index for judging whether to hemorrhage and the hemorrhage risk after operation, proposes a new hemorrhage risk definition, and is used for precise prediction, real-time prediction and individualized prediction on patients who are about to perform percutaneous renal biopsy.

Description

Technical Field

[0001] This invention relates to the field of intelligent healthcare, and more specifically, to a method, device, medium, and program product for constructing a bleeding risk prediction model after percutaneous renal biopsy. Background Technology

[0002] Percutaneous renal biopsy (PRB) is the gold standard for diagnosing kidney disease. Postoperative bleeding is its most common and serious complication, with gross hematuria occurring in 5-10% of cases, perirenal hematoma in 15-30%, and severe bleeding requiring intervention in 1-3% of cases. Clinically, severe bleeding can lead to anemia, shock, and deterioration of renal function, and may even necessitate blood transfusions, vascular interventions, or surgery. Currently, the commonly used clinical standard for assessing postoperative bleeding and its risk is the circumference of the hematoma, observed immediately after the percutaneous renal biopsy under ultrasound guidance.

[0003] However, how can we predict the risk of postoperative bleeding in patients before performing percutaneous nephrolithotomy using their preoperative parameters? Current assessments rely on the physician's personal experience, are highly subjective, lack objective quantitative tools, resulting in low prediction accuracy, have poor real-time performance (unable to provide rapid quantitative risk assessments preoperatively), and lack individualization (lacking precise stratification for different patient characteristics to provide personalized postoperative management measures). Summary of the Invention

[0004] This invention aims to at least solve one of the technical problems existing in the prior art. To this end, this invention provides a method, device, medium, and program product for constructing a bleeding risk prediction model after percutaneous nephrolithotomy (PCNL). The method of this invention proposes a new definition of bleeding risk by adjusting the outcome indicators for determining postoperative bleeding and bleeding risk, so as to provide accurate, real-time, and individualized prediction for patients about to undergo PCNL.

[0005] The first aspect of this application discloses a method for constructing a bleeding risk prediction model after percutaneous renal biopsy, the method comprising: The preoperative target parameters of the training set samples are obtained. The preoperative target parameters include: age, glomerular filtration rate, platelet count, albumin concentration, presence of hypertension, whether sleeping pills were used the day before surgery, whether hemostatic injections were given, and whether blood transfusions were given. Among them, whether hypertension is present is determined by measuring blood pressure again before surgery after blood pressure management has been implemented to keep blood pressure at a normal level. Postoperative imaging data of percutaneous renal biopsy performed on training set samples were obtained, and outcome indicators for assessing bleeding risk were extracted from the postoperative imaging data, wherein the outcome indicators included: (hematoma long diameter + hematoma short diameter) / 2; The outcome indicators were used as validation criteria to evaluate the predictive ability of the preoperative target parameters for postoperative bleeding risk, and the evaluation results were obtained. Based on the assessment results, a bleeding risk prediction model based on the preoperative target parameters is constructed.

[0006] The second aspect of this application discloses a method for preoperative prediction of bleeding risk after percutaneous renal biopsy, the method comprising: Obtain the preoperative target parameters of the collected test samples, in which percutaneous renal biopsy was not performed; The preoperative target parameters are input into the bleeding risk prediction model disclosed in the first aspect of this application to calculate the risk value; The risk score is used to predict the postoperative bleeding risk of the sample undergoing percutaneous nephrolithotomy. When the risk score is greater than the first threshold, an auxiliary prediction result indicating a high risk of bleeding for the sample is output; when the prediction score is less than the first threshold, an auxiliary prediction result indicating a low risk of bleeding for the sample is output. A third aspect of this application discloses a computer device, comprising: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to implement the steps of the above-described method.

[0007] The fourth aspect of this application discloses a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0008] The fifth aspect of this application discloses a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method.

[0009] This application has the following beneficial effects: This application innovatively proposes a new definition of bleeding risk, changing the outcome indicators for determining postoperative bleeding and bleeding risk from hematoma circumference to (hematoma long diameter + hematoma short diameter) / 2 and / or hematoma area and / or ellipse circumference 2*3.14. At the same time, through the above-mentioned new outcome indicators, the accuracy of multiple preoperative target parameters in predicting whether bleeding will occur is proposed and verified, so as to be used for accurate, real-time and individualized prediction for patients who are about to undergo percutaneous nephrolithotomy. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1This is a schematic diagram of the method flow provided in the first aspect of the present invention; Figure 2 This is a schematic diagram of the method flow provided in the second aspect of the present invention; Figure 3 This is a schematic diagram of a computer device provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the architecture of an exemplary computing device provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the storage medium provided in an embodiment of the present invention; Figure 6 This invention provides a method for constructing a nomogram based on preoperative target parameters. Figure 7 This is the ROC curve of the bleeding risk prediction model constructed based on preoperative target parameters provided in this embodiment of the invention; Figure 8 These are the model performance results of the bleeding risk model provided in the embodiments of the present invention; Figure 9 These are ROC curves for different outcome indicators provided in the embodiments of the present invention; Figure 10 This is a schematic diagram of the results of different outcome indicators provided in the embodiments of the present invention. Detailed Implementation

[0012] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0013] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] Figure 2 This is a schematic flowchart of a preoperative prediction method for bleeding risk after percutaneous renal biopsy provided by an embodiment of the present invention. Specifically, the preoperative prediction method includes the following steps: S201: Obtain the preoperative target parameters of the collected test sample, wherein the test sample did not undergo percutaneous renal biopsy; In some embodiments, the preoperative target parameters include: age, glomerular filtration rate, platelet count, albumin concentration, presence of hypertension, use of sleeping pills the day before surgery, administration of hemostatic injections, and blood transfusions. Regarding the use of sleeping pills: insomnia increases inflammatory factors in the body, inhibits platelet aggregation efficiency, delays hematoma absorption and hemostasis, while quality sleep maintains normal platelet metabolism. Fragmented sleep can lead to abnormal expression of platelet receptors. Whether the patient used sleeping pills the day before surgery and whether the patient has sleep disorders increases the risk of bleeding. Postoperative use of hemostatic injections: clinically, if a patient shows signs of active bleeding immediately after a renal biopsy under ultrasound guidance, doctors routinely administer hemostatic injections for bleeding prevention. Studies have found that the use of hemostatic injections after renal biopsy reflects, to some extent, the occurrence of hematomas after the renal biopsy.

[0016] In some embodiments, the terms “subject” or “test subject” or “sample to be tested” as used herein refer to any animal (e.g., a mammal), including but not limited to humans, non-human primates, rodents, etc., which will become the recipient of a particular treatment. Generally, the terms “subject” and “patient” are used interchangeably herein when referring to human subjects. Preferably, the subject is a human. In some embodiments, the sample to be tested is a patient clinically used for prognostic assessment.

[0017] S202: Input the preoperative target parameters into the bleeding risk prediction model disclosed in the first aspect of this application, and calculate the risk value; In some embodiments, such as Figure 1 As shown, the method for constructing the bleeding risk prediction model is as follows: Obtain the preoperative target parameters of the training set samples. The preoperative target parameters include: age, glomerular filtration rate, platelet count, albumin concentration, presence of hypertension, use of sleeping pills the day before surgery, administration of hemostatic injections, and blood transfusions. In some more specific embodiments, age is divided into three segments: under 40 years old, between 40 and 60 years old, and over 60 years old; platelet count is divided into three segments: less than 150 × 10⁻⁶. 9 / L, located at (150-216)×10 9 Between / L, greater than 216×10 9 / L; albumin concentration was divided into two segments with a threshold of 30 g / L (≤30 g / L, 30-55 g / L); whether hypertension was present was determined by a systolic blood pressure of 140 mmHg. Hypertension was defined as the blood pressure measured before a kidney biopsy, specifically the systolic blood pressure. A blood pressure of 140 mmHg increases the risk of bleeding. Patients with a history of hypertension or those with hypertension (as a comorbidity) were not included in this model (due to statistically insignificant results). Generally, for hypertensive patients undergoing renal biopsy, doctors manage blood pressure preoperatively to maintain it at a normal level; therefore, this did not show statistical significance in this model. Even after preoperative blood pressure control, some patients may still experience preoperative blood pressure fluctuations and elevations due to anxiety, tension, etc., which is a significant factor in the preoperative systolic blood pressure reading in this model. The actual clinical significance of 140 mmHg. Whether or not sleeping pills were used refers to whether the patient took estazolam or zolpidem the night before the kidney biopsy due to difficulty falling asleep or anxiety. Whether or not hemostatic agents were used refers to whether the patient used medication to prevent bleeding after the kidney biopsy; in this case, sulfadiazine powder was used for injection. Whether or not blood transfusion was required refers to whether the patient received a red blood cell transfusion after the kidney biopsy.

[0018] In some more specific embodiments, the preoperative target parameters are obtained by screening using the following methods: Data collection: ① General information (name, age, ethnicity, marital status, gender, place of residence, education level, smoking, drinking, and medical expense methods), etc.; ② Clinical data (comorbidities (hypertension, coronary heart disease, diabetes, others), infectious diseases (hepatitis A, hepatitis B, hepatitis C, etc.), hematuria, body mass index, alanine aminotransferase level, urea level, creatinine level, glomerular filtration rate (eGFR), platelet count, prothrombin time, albumin concentration, hemoglobin concentration, blood pressure before puncture, whether temporary antihypertensive drugs were used before puncture, whether sedatives were used, whether anticoagulant injections were used before the procedure, whether anticoagulant drugs were used, whether there was proteinuria, whether hemodialysis was performed, etc.).

[0019] Please note that anticoagulant injections and hemostatic injections are not the same thing. Anticoagulant injections are routinely given to nephrology patients with hypoproteinemia, which increases the risk of thrombosis. Guidelines recommend discontinuing anticoagulant injections or anticoagulant medications 24 hours before a kidney biopsy or one week before. In this model, hemostatic injections are used post-operatively, depending on whether an immediate hematoma occurred during the biopsy (in this study, this refers to the use of sulfadiazine powder for injection).

[0020] ③ Post-renal biopsy (whether hemostasis measures were used, whether gross hematuria occurred, whether blood transfusion was performed, whether interventional hemostasis was performed, whether catheterization was performed, the size of the hematoma after the patient's renal biopsy, and the pathological type).

[0021] Postoperative imaging data of percutaneous renal biopsy patients in the training set were obtained. Outcome indicators for assessing bleeding risk were extracted from these data, including: (hematoma long diameter + hematoma short diameter) / 2; glomerular filtration rate (GFR) values ​​were divided into three segments: less than 30, between 30 and 60, and greater than 60; optionally, postoperative bleeding after renal biopsy was defined as a hematoma area ≥5 cm² on ultrasound. 2 .

[0022] Definition of bleeding indicators: The outcome event of this study was hemorrhage. Patients underwent routine ultrasound examination on the second postoperative day to assess bleeding and record the size of the hematoma following renal biopsy. Referring to the definition by Manno et al., bleeding complications were categorized into three degrees: mild, moderate, and severe: Mild bleeding: small subcapsular hematoma with a diameter <5 cm as seen on ultrasound, which may resolve spontaneously without special intervention; Moderate bleeding: gross hematuria and / or subcapsular hematoma with a diameter ≥5 cm as seen on ultrasound, requiring prolonged hospitalization for observation; Severe bleeding: hypotension and decreased hemoglobin (a decrease in hematocrit of 10% or more compared to pre-biopsy levels, indicating true hemorrhage) after renal biopsy, requiring blood transfusion, interventional hemostasis, or even nephrectomy and death. In this study, bleeding was defined as a hematoma area ≥5 cm² as seen on ultrasound. 2 Defined as bleeding after a kidney biopsy.

[0023] The deformation parameter used to define the hemorrhage outcome is (long axis plus short axis) / 2 of the hematoma, with a threshold of 4.275. The clinically commonly used diagnostic criteria for hemorrhage are a long axis greater than 5 cm and a hematoma area greater than 10 cm². 2 As diagnostic criteria, deformation parameters and predictive indicators were screened, and the results are as follows: Figure 9 and Figure 10 As shown.

[0024] In some more specific embodiments, the threshold value of (hematoma long diameter + hematoma short diameter) / 2 is between 4 and 1.5, preferably 4.275.

[0025] The screening process using statistical methods is as follows: (1) Descriptive analysis SPSS 24.0 was used for data cleaning and descriptive analysis. Qualitative data were expressed as number of cases (proportions), and chi-square tests were used for comparisons between groups. Baseline data are shown in Table 1.

[0026] (2) Screening of factors affecting post-renal biopsy bleeding When building a logistic regression model, selecting appropriate variables is crucial. Traditional variable selection methods, such as the optimal subset method and stepwise selection, primarily find the best-fit model by minimizing the sum of squared residuals. The lasso method, however, was developed to address this issue, providing a novel variable selection algorithm that effectively solves the problem of collinearity. Choosing appropriate adjustment parameters to balance goodness of fit and complexity can result in a streamlined model with a good fit. This study uses 10-fold cross-validation to evaluate lasso regression. The study population was randomly divided into 10 groups, with 9 groups used as training data and the remaining group as validation data. This process was repeated 10 times to maximize the area under the curve (AUC) of the model.

[0027] This process is implemented using the `cv.glmnet` function, which returns the adjustment parameter `λ.min` that minimizes the deviation between cross-validation and actual data, and the adjustment parameter `λ.1se` that achieves the highest degree of regularization (i.e., the highest penalty for variable coefficients and the most streamlined model) within one standard error range. `λ.1se` is selected as the adjustment parameter for lasso regression to screen the final influencing factors. Multivariate logistic regression is performed on the final influencing factors, and parameter estimation is performed for each factor. The results of univariate and multivariate analysis are shown in Table 2, and the lasso coefficient screening results are shown in Table 3.

[0028] Table 1 Baseline Data

[0029] Table 2 Univariate and Multivariate Analysis

[0030] Table 2. Results of Lasso coefficient selection

[0031] In some embodiments, the outcome indicators further include: hematoma area and / or ellipse circumference 2*3.14.

[0032] The outcome indicators were used as validation criteria to evaluate the predictive ability of the preoperative target parameters for postoperative bleeding risk, and the evaluation results were obtained. In some embodiments, such as Figure 9 and Figure 10 As shown, this application studies multiple outcome indicators, including the two indicators mentioned above, as well as ellipse area, presence or absence of intramuscular thrombosis, ellipse circumference 2*3.14, area / circumference, circumference / area, and ellipse area / ellipse circumference. The results show that (hematoma long axis + hematoma short axis) / 2, hematoma area, and ellipse circumference 2*3.14 have better predictive ability than other outcome indicators when used as validation criteria.

[0033] In some embodiments, assessing the predictive ability of the preoperative target parameter for postoperative bleeding risk includes: It is recommended to use a statistical or machine learning model with at least one of the preoperative target parameters as independent variables and the outcome index as the dependent variable, and to quantify the predictive ability using the area under the receiver operating characteristic curve, precision, or recall.

[0034] Based on the assessment results, a bleeding risk prediction model based on the preoperative target parameters is constructed.

[0035] In some more specific embodiments, currently, patients undergoing renal biopsy are required to have absolute bed rest for 6 hours post-surgery, or strict bed rest for 24 hours. This study aims to screen patients with a high risk of bleeding to guide postoperative care practices. Low-risk patients can engage in early mobilization and shorten their bed rest time, while high-risk patients will have a longer bed rest period. Hematoma area greater than 10 cm² is also considered. 2 The bed rest period needs to be extended beyond the initial 24 hours. Postoperative bleeding is defined as severe, clinically significant bleeding requiring blood transfusion, surgery, or interventional hemostasis. Postoperative bleeding is assessed based on the hematoma size; most studies use 1 cm as a baseline. 2 3cm 2 5cm 2 The sections were divided into 5cm sections. 2 The aim is to help clinical medical staff screen patients at low risk of postoperative bleeding, guide them in early postoperative mobilization, reduce the waste of medical resources, and ensure patient safety. The bleeding risk prediction model in this application is: Y=ax1+bx2+cx3+dx4+ex5+fx6+gx7+hx8, where a, b, c, d, e, f, g, and h are weights, and x1-x8 are the preoperative target parameters. In this embodiment, the bleeding risk prediction model is visualized as a nomogram, as shown in the figure below. Figure 6 As shown, the ROC curve of the bleeding risk prediction model is as follows: Figure 7 As shown, the model effect is as follows Figure 8 As shown.

[0036] S203: Based on the risk value, predict the postoperative bleeding risk of the test sample undergoing percutaneous nephrolithotomy. When the risk value is greater than the first threshold, output an auxiliary prediction result indicating a high risk of bleeding for the test sample; when the prediction score is less than the first threshold, output an auxiliary prediction result indicating a low risk of bleeding for the test sample. The auxiliary prediction results output based on the risk value include, but are not limited to, paper or electronic reports. This result is only obtained by the intelligent machine based on the relevant data of the test subject and is only used as a reference for medical staff, and is not used as the final diagnosis result of the test subject.

[0037] The following is an example of how to use this column chart: For example, to predict the postoperative bleeding risk of a patient after a renal biopsy based on the nomogram of this bleeding risk prediction model, the preoperative target parameters of the patient are first obtained: age 50 years (corresponding to 2 in the nomogram), glomerular filtration rate (eGFR) 45 (corresponding to 2 in the nomogram), platelet count 200 (corresponding to 2 in the nomogram), albumin 40 (corresponding to 2 in the nomogram), systolic blood pressure 130 (corresponding to 1 in the nomogram), no use of sleeping pills (corresponding to 0 in the nomogram), no hemostatic injection (corresponding to 0 in the nomogram), and no blood transfusion (corresponding to 0 in the nomogram). The individual scores of each predictive indicator are as follows: age score 32.5, glomerular filtration rate (eGFR) score 27.5, platelet count score 17.5, albumin score 0, systolic blood pressure score 0, no use of sleeping pills score 0, no hemostatic injection score 0, and no blood transfusion score 0. The total score of all predictive indicators is 77.5. Finally, the bleeding risk corresponding to this patient is obtained as follows: A score of 0.2 indicates that the patient has a low risk of bleeding after a kidney biopsy.

[0038] In some embodiments, the first threshold is obtained through training on training set samples. It can be a specific threshold or an interval range. The specific form is not specifically limited in this embodiment.

[0039] In some embodiments, the method further includes: generating postoperative bed rest time or postoperative care measures for the sample to be tested based on the risk value.

[0040] Figure 3 This is a schematic diagram of a computer device provided in an embodiment of the present invention, such as... Figure 3 As shown, the device 2000 may include: one or more processors 2010 and one or more memories 2020; wherein the memories store computer-readable code that, when run by the one or more processors, can perform the methods described above.

[0041] The processor in this embodiment can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, operations, and logic block diagrams disclosed in this embodiment. The general-purpose processor can be a microprocessor or any conventional processor, and can be based on an x86 or ARM architecture.

[0042] In general, the various exemplary embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. When aspects of embodiments of this disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0043] For example, the method or apparatus according to embodiments of this disclosure can also be used by means of Figure 4 The architecture of the computing device 3000 shown is used for implementation. For example... Figure 4 As shown, the computing device 3000 may include a bus 3010, one or more CPUs 3020, a read-only memory (ROM) 3030, a random access memory (RAM) 3040, a communication port 3050 connected to a network, an input / output component 3060, a hard disk 3070, etc. The storage devices in the computing device 3000, such as the ROM 3030 or the hard disk 3070, may store various data or files used for processing and / or communication of the methods provided in this disclosure, as well as program instructions executed by the CPU. The computing device 3000 may also include a user interface 3080. Of course, Figure 4 The architecture shown is merely exemplary and can be omitted as needed when implementing different devices. Figure 4 One or more components in the computing device shown.

[0044] This invention also includes a computer-readable storage medium, such as... Figure 5The diagram illustrates a storage medium 4000 provided in an embodiment of the present invention. The computer storage medium 4020 stores computer-readable instructions 4010. When the computer-readable instructions 4010 are executed by a processor, the method described above according to embodiments of the present disclosure can be performed. The computer-readable storage medium in the embodiments of the present disclosure may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Synchronous Link Dynamic Random Access Memory (SLDRAM), and Direct Memory Bus Random Access Memory (DRRAM). It should be noted that the memory used in the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0045] This disclosure also provides a computer program product or system, including a computer program that, when executed by a processor, implements the steps of the above-described method. The computer program product or system is used to execute a system for constructing a percutaneous renal biopsy postoperative bleeding risk prediction model. The system includes: The training set data acquisition module is used or configured to acquire preoperative target parameters of the training set samples, including: age, glomerular filtration rate, platelet count, albumin concentration, presence of hypertension, use of sleeping pills the day before surgery, administration of hemostatic injections, and blood transfusions. An outcome indicator extraction module is used or configured to acquire postoperative imaging data of percutaneous renal biopsy performed on training set samples, and extract outcome indicators for assessing bleeding risk from the postoperative imaging data, wherein the outcome indicators include: (hematoma long diameter + hematoma short diameter) / 2; The outcome evaluation module is used or configured to use the outcome indicators as validation criteria to evaluate the predictive ability of the preoperative target parameters for postoperative bleeding risk and obtain evaluation results. A model training module is used or configured to construct a bleeding risk prediction model based on the preoperative target parameters according to the evaluation results.

[0046] In some embodiments, this embodiment also discloses a preoperative prediction system for the risk of bleeding after percutaneous renal biopsy, the system comprising: The preoperative target parameter acquisition module is used or configured to acquire the preoperative target parameters of the collected sample to be tested, wherein the sample to be tested has not undergone percutaneous renal biopsy. A risk value calculation module is used or configured to input the preoperative target parameters into the bleeding risk prediction model disclosed in the first aspect of this application to calculate the risk value; The result prediction module is used or configured to predict the postoperative bleeding risk of a test sample undergoing percutaneous renal biopsy based on the risk value. When the risk value is greater than a first threshold, it outputs an auxiliary prediction result indicating a high risk of bleeding for the test sample; when the prediction score is less than the first threshold, it outputs an auxiliary prediction result indicating a low risk of bleeding for the test sample.

[0047] It should be noted that 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 this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated 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 operation, or using a combination of dedicated hardware and computer instructions.

[0048] In general, the various exemplary embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. When aspects of embodiments of this disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0049] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0050] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0051] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0052] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0053] The exemplary embodiments of this disclosure described in detail above are merely illustrative and not restrictive. Those skilled in the art will understand that various modifications and combinations of these embodiments or their features can be made without departing from the principles and spirit of this disclosure, and such modifications should fall within the scope of this disclosure.

Claims

1. A method for constructing a predictive model for postoperative bleeding risk after percutaneous renal biopsy, characterized in that, The method includes: Obtain the preoperative target parameters of the training set samples. The preoperative target parameters include: age, glomerular filtration rate, platelet count, albumin concentration, presence of hypertension, whether sleeping pills were used the day before surgery, whether hemostatic injections were given, and whether blood transfusions were given. Among them, whether hypertension is present is determined by measuring blood pressure again before surgery after blood pressure management has been implemented to keep blood pressure at a normal level. Postoperative imaging data of percutaneous renal biopsy performed on training set samples were obtained, and outcome indicators for assessing bleeding risk were extracted from the postoperative imaging data, wherein the outcome indicators included: (hematoma long diameter + hematoma short diameter) / 2; The outcome indicators were used as validation criteria to evaluate the predictive ability of the preoperative target parameters for postoperative bleeding risk, and the evaluation results were obtained. Based on the assessment results, a bleeding risk prediction model based on the preoperative target parameters is constructed.

2. The method for constructing a bleeding risk prediction model after percutaneous renal biopsy according to claim 1, characterized in that, The bleeding risk prediction model is: Y=ax1+bx2+cx3+dx4+ex5+fx6+gx7+hx8, where a, b, c, d, e, f, g and h are weights, and x1-x8 are the preoperative target parameters; Optionally, post-renal biopsy bleeding is defined as a hematoma area ≥5 cm² on ultrasound. 2 .

3. The method for constructing a bleeding risk prediction model after percutaneous renal biopsy according to claim 1, characterized in that, The threshold value of (hematoma long diameter + hematoma short diameter) / 2 is between 4 and 1.5, preferably 4.

275.

4. The method for constructing a bleeding risk prediction model after percutaneous renal biopsy according to claim 1, characterized in that, The assessment of the predictive ability of the preoperative target parameters for postoperative bleeding risk includes: It is recommended to use a statistical or machine learning model with at least one of the preoperative target parameters as independent variables and the outcome index as the dependent variable, and to quantify the predictive ability using the area under the receiver operating characteristic curve, precision, or recall.

5. The method for constructing a bleeding risk prediction model after percutaneous renal biopsy according to claim 1, characterized in that, The outcome indicators also include: hematoma area and / or ellipse circumference 2*3.

14.

6. A method for preoperative prediction of bleeding risk after percutaneous renal biopsy, characterized in that, The method includes: Obtain the preoperative target parameters of the collected test samples, in which percutaneous renal biopsy was not performed; Input the preoperative target parameters into the bleeding risk prediction model according to any one of claims 1-5, and calculate the risk value; The risk score is used to predict the postoperative bleeding risk of the sample undergoing percutaneous nephrolithotomy. When the risk score is greater than the first threshold, an auxiliary prediction result indicating a high risk of bleeding for the sample is output; when the prediction score is less than the first threshold, an auxiliary prediction result indicating a low risk of bleeding for the sample is output. Optionally, the method further includes: generating postoperative bed rest time or postoperative care measures for the sample to be tested based on the risk value.

7. The method for preoperative prediction of bleeding risk after percutaneous renal biopsy according to claim 6, characterized in that, The preoperative target parameters include: age, glomerular filtration rate, platelet count, albumin concentration, presence of hypertension, use of sleeping pills the day before surgery, administration of hemostatic injections, and blood transfusions. Among these, the presence of hypertension is determined by measuring blood pressure again before surgery after blood pressure management has been implemented to maintain normal blood pressure levels.

8. A computer device, characterized in that, The device includes: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to implement the steps of the method according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the steps of the method as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method described in any one of claims 1-7.

Images