Orthopedic trauma patient VTE risk prediction model establishment method and device based on column diagram

Abstract

The invention relates to the related technical field of the orthopedics department, in particular to an orthopedics department trauma patient VTE risk prediction model establishing method and device based on a column diagram. The method comprises the steps that original data of an orthopedic trauma patient are collected, and the original data comprise VTE risk factors and outcome indexes; based on the original data, a Logistic regression method is adopted, an outcome index is used as a prediction result, VTE risk factors are used as prediction variables, and a risk prediction model is constructed; a bootstrap resampling method is used to carry out internal verification on the risk prediction model, Spiegelhalter Z test and Hosmer-Lemeshop test are carried out, and the fitting degree of the prediction probability and the real probability distribution is judged; performing decision curve analysis, checking the net income range of the model, and constructing a dynamic column graph; acquiring current patient information and an adjustment intervention strategy for the patient; and displaying a corresponding prediction result under the current patient information and a corresponding prediction result under the adjustment intervention strategy based on the dynamic column graph.

Description

Technical Field

[0001] The present application relates to the technical field related to orthopedics, and specifically to a method and device for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram. Background Art

[0002] Venous thromboembolism (VTE), including deep vein thrombosis (DVT) and pulmonary embolism (PE), is a common complication of hospitalized patients and a preventable hospital-acquired adverse event recognized both at home and abroad. Orthopedic trauma patients are at high risk of VTE, but accurate prediction of VTE in orthopedic trauma patients has not yet been achieved, and there is a lack of effective prediction models for assessing VTE risk in orthopedic trauma patients. Existing VTE risk assessment in orthopedic trauma patients is mainly based on scale assessment, which lacks the ability to accurately predict risk probability. Summary of the invention

[0003] In view of this, the embodiments of the present application are directed to providing a method and device for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram.

[0004] The present application provides a method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram, comprising: Collect the original data of orthopedic trauma patients, including: VTE risk factors and outcome indicators; Based on the original data, a risk prediction model was constructed using the Logistic regression method, with the outcome index as the prediction result and the VTE risk factor as the prediction variable; The risk prediction model was internally validated using the bootstrap resampling method, and the operating characteristic curve and calibration curve were drawn. The calibration curve was subjected to the Spiegelhalter Z test and the Hosmer-Lemeshow test to determine the degree of fit between the predicted probability and the true probability distribution; Conduct decision curve analysis to examine the range of net benefits of the model and illustrate the relationship between differences in the proportion of true-positive and false-positive results and harms for patients when the model is used at different threshold probabilities; Based on the risk prediction model, construct a dynamic nomogram; obtaining current patient information and tailored intervention strategies for said patients; Based on the dynamic nomogram, the prediction results corresponding to the current patient information and the prediction results corresponding to the adjusted intervention strategy are displayed.

[0005] In some embodiments, the dynamic nomogram includes a first region and a second region; The first area is used to enter predictor variables; The second area is used to display the prediction result.

[0006] In some embodiments, the second area uses different colors to display the prediction results corresponding to the current patient information and the prediction results corresponding to the adjusted intervention strategy.

[0007] In some embodiments, the VTE risk factors include: age, cerebrovascular disease, thrombotic drug prevention, ICU admission, lower limb fractures, multiple injuries, other types of surgery except internal and external fixation, operation duration and postoperative bed rest days.

[0008] In some embodiments, the prediction results include: a probability prediction value and upper and lower limits of a 95% confidence interval.

[0009] In some embodiments, the risk prediction model is internally validated and an operating characteristic curve is drawn, comprising: The performance of the risk prediction model was internally validated, and its AUC, optimal cutoff value, sensitivity, specificity, accuracy, and F1 score were calculated, and the receiver operating characteristic curve was plotted.

[0010] The present application also provides a device for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram, comprising: A collection module is used to collect original data of orthopedic trauma patients, wherein the original data includes: VTE risk factors and outcome indicators; A module is constructed, based on the original data, using the Logistic regression method, taking the outcome index as the prediction result and the VTE risk factor as the prediction variable, to construct a risk prediction model; using the bootstrap resampling method, the risk prediction model is internally verified, and the operating characteristic curve and calibration curve are drawn, and the calibration curve is subjected to the Spiegelhalter Z test and the Hosmer-Lemeshow test to determine the degree of fit between the predicted probability and the true probability distribution; a decision curve analysis is performed to check the net benefit range of the model, and to explain the difference in the proportion of true positive and false positive results of patients and the relationship between the harm when the model is used at different threshold probabilities; based on the risk prediction model, a dynamic nomogram is constructed; An acquisition module, used for acquiring current patient information and an adjustment intervention strategy for the patient; The prediction module is used to display the prediction results corresponding to the current patient information and the prediction results corresponding to the adjusted intervention strategy based on the dynamic nomogram.

[0011] The present application also provides electronic equipment, including: A processor, and a memory for storing a program executable by the processor; The processor is used to implement the above-mentioned method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram by running the program in the memory.

[0012] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes the method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram as described above.

[0013] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram as described above.

[0014] The present application provides a method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram, which collects original data of orthopedic trauma patients, wherein the original data includes: VTE risk factors and outcome indicators; based on the original data, a risk prediction model is constructed by using a Logistic regression method, with the outcome indicators as the prediction results and the VTE risk factors as the prediction variables; the risk prediction model is internally verified by using a bootstrap resampling method, and an operating characteristic curve and a calibration curve are plotted, and the calibration curve is subjected to a Spiegelhalter Z test and a Hosmer-Lemeshow test to determine the degree of fit between the predicted probability and the true probability distribution; a decision curve analysis is performed to view the net benefit range of the model, and to explain the difference in the proportion of true positive and false positive results of the patient and the relationship between the harm when the model is used at different threshold probabilities; based on the risk prediction model, a dynamic nomogram is constructed; current patient information and an adjustment intervention strategy for the patient are obtained; and based on the dynamic nomogram, the corresponding prediction results under the current patient information and the corresponding prediction results under the adjustment intervention strategy are displayed. With this setting, by collecting the original data of VTE risk factors and outcome indicators, a comprehensive risk prediction model can be constructed to improve the accuracy of predicting the risk of VTE in orthopedic trauma patients. Using the Logistic regression method, the impact of various risk factors on the occurrence of VTE can be quantified, providing clinicians with a scientific risk assessment tool. The bootstrap resampling method was used for internal validation to enhance the robustness and reliability of the model and ensure the generalization ability of the model on different samples; by drawing the operating characteristic curve (ROC curve) and calibration curve, the discrimination ability and prediction accuracy of the model can be intuitively evaluated. Based on the dynamic nomogram, the prediction results under different patient characteristics can be dynamically displayed to improve the clinical application value of the model. Obtaining current patient information and adjusting intervention strategies for patients can update the prediction results in real time, enabling doctors to adjust treatment plans based on the latest patient data. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 It is a flowchart of a method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram provided in an embodiment of the present application.

[0017] Figure 2It is a schematic diagram of a dynamic nomogram provided in one embodiment of the present application.

[0018] Figure 3 It is a schematic diagram of a dynamic nomogram provided in another embodiment of the present application.

[0019] Figure 4 It is a structural schematic diagram of a device for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram provided in one embodiment of the present application.

[0020] Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Venous thromboembolism (VTE) refers to abnormal coagulation of blood in veins, forming thrombi, leading to partial or complete blockage of blood vessels. It is a general term for deep vein thrombosis (DVT) and pulmonary embolism (PE). Anticoagulant treatment, recurrence and sequelae after VTE prolong the patient's hospitalization time, increase mortality, seriously affect the patient's quality of life, and cause a heavy economic burden.

[0023] Any factors that cause blood stasis, blood hypercoagulation or vascular endothelial damage may trigger the occurrence of VTE. It is generally believed that major surgery, trauma, plaster fixation and tumors are the most important influencing factors. Orthopedic trauma patients often have multiple influencing factors at the same time and are one of the most common VTE high-risk groups. Their VTE incidence rate ranks among the highest among hospitalized patients.

[0024] Orthopedic trauma patients may have a variety of VTE risk factors, such as fractures, plaster fixation, bed rest, vascular injury, injury severity, etc., which are different from the risk factors of the regular hospitalized population. However, the current risk assessment methods mostly use scales suitable for the general population, such as the Caprini and Padua scales. Clinical assessment takes a long time and is not very accurate. At present, there is still a lack of specific VTE risk assessment and prevention tools for orthopedic trauma patients. At the same time, after the scale assessment, patients are divided into low risk, medium risk or high risk only according to the scale assessment score, and the probability of VTE occurrence in patients cannot be accurately given. In addition, as the concept of VTE prevention and treatment is deeply rooted in the hearts of the people, clinical preventive measures for VTE high-risk patients, such as bed activities and antithrombotic drugs, may reduce the incidence of VTE, but the current scale does not take this into account. How to make simple, convenient and easy-to-understand risk prediction based on the specialty characteristics of orthopedic trauma patients in the current VTE risk assessment of orthopedic trauma patients is still a problem that needs to be solved.

[0025] The Caprini risk assessment scale was developed based on expert experience and evidence-based medicine, including risk factors such as the patient's general condition, comorbidities, trauma and surgery, medical history, and genetic factors. The corresponding risk factors are checked according to the patient's condition and the total score is calculated. According to the total score, the patient is divided into low risk, medium risk, or high risk of VTE. The items of Caprini 2005 and Caprini 2010 are similar, with a total of 39 items; while Caprini 2013 made major adjustments to the risk factors on this basis, with a total of 37 items. Different guidelines recommend different versions of the Caprini risk assessment scale, and there are also differences in the scores of high, medium, and low risks. When choosing the Caprini risk assessment scale, it is not clear which version and which risk stratification standard to use to guide practice; on the other hand, the nearly 40 assessment items of the Caprini scale make its assessment time-consuming, which is often complicated and error-prone in clinical work, and the assessment accuracy is poor.

[0026] The present invention provides a method and device for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram. Only 9 risk prediction factors can be used to achieve accurate assessment of VTE risk in the orthopedic trauma population and visual display of individual risk factors and probability predictions, providing an intuitive, convenient and accurate method for predicting VTE risk in orthopedic trauma.

[0027] After introducing the basic principles of the present application, various non-limiting embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0028] Figure 1 FIG. 1 is a flow chart of a method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram provided in one embodiment of the present application. Figure 1As shown, the method includes the following contents.

[0029] Step S110, collecting original data of orthopedic trauma patients, the original data including: VTE risk factors and outcome indicators; In this step, we need to collect detailed medical data of orthopedic trauma patients, including but not limited to the patients' VTE risk factors and outcome indicators. Risk factors may involve the patient's age, gender, medical history, medication use, type of surgery, etc., while the outcome indicator refers to whether the patient has a VTE event. These data will serve as the basis for the subsequent construction of a risk prediction model.

[0030] Step S120, based on the original data, a risk prediction model is constructed by using a Logistic regression method, with the outcome index as the prediction result and the VTE risk factor as the prediction variable; A risk prediction model is constructed based on the original data collected in step S110 using the Logistic regression method. In this model, the outcome indicator (whether VTE occurs) is used as the prediction result, and the VTE risk factors (such as age, medical history, etc.) are used as predictor variables. Logistic regression is a statistical method used to estimate the impact of one or more independent variables on a binary dependent variable.

[0031] Step S130, using the bootstrap resampling method to perform internal verification on the risk prediction model, and draw an operating characteristic curve and a calibration curve, and perform a Spiegelhalter Z test and a Hosmer-Lemeshow test on the calibration curve to determine the degree of fit between the predicted probability and the true probability distribution; The bootstrap resampling method was used to internally validate the constructed risk prediction model. Bootstrap is a resampling technique that estimates the stability and accuracy of the model by repeatedly sampling from the original sample. Next, the operating characteristic curve (ROC curve) and calibration curve were drawn to evaluate the performance of the model. The ROC curve shows the sensitivity and specificity of the model, while the calibration curve shows the consistency of the predicted probability with the actual results. In addition, the calibration curve was subjected to the Spiegelhalter Z test and the Hosmer-Lemeshow test to determine the degree of fit between the predicted probability and the true probability distribution.

[0032] Step S140, performing decision curve analysis to check the net benefit range of the model, and explaining the difference in the proportion of true positive and false positive results of patients and the relationship between harm when the model is used at different threshold probabilities; Step S150, constructing a dynamic nomogram based on the risk prediction model; A nomogram is a graphical tool used to show the impact of different risk factors on the probability of a patient outcome. Dynamic nomograms allow the user to input patient-specific data and calculate and display predictions in real time.

[0033] Step S160, obtaining current patient information and an adjustment intervention strategy for the patient; Step S170, displaying the prediction results corresponding to the current patient information and the prediction results corresponding to the adjusted intervention strategy based on the dynamic nomogram.

[0034] With this setting, the prediction results corresponding to the current patient information and the prediction results corresponding to different intervention strategies are displayed based on the dynamic nomogram. This provides doctors with an intuitive tool to evaluate the impact of different treatment decisions on patient prognosis, so as to make more personalized and accurate treatment decisions.

[0035] Specifically, the dynamic nomogram includes a first area and a second area; the first area is used to input prediction variables; the second area is used to display prediction results. The second area uses different colors to display the prediction results corresponding to the current patient information and the prediction results corresponding to the adjusted intervention strategy.

[0036] VTE risk factors include: age, cerebrovascular disease, thrombotic drug prevention, ICU admission, lower limb fracture, multiple injuries, other types of surgery except internal and external fixation, operation time and postoperative bed rest days. The prediction results include: probability prediction value and upper and lower limits of 95% confidence interval.

[0037] Based on the above embodiments, the steps of the solution provided by this application are as follows: First, hospitalized orthopedic trauma patients were included to collect their VTE risk factors and outcome indicators. The risk factors mainly included age, comorbid cerebrovascular disease, type of surgery, number of days in bed after surgery, duration of surgery, lower limb fractures, whether they were admitted to the ICU, multiple injuries, and drug prevention. The outcome indicator was the occurrence of VTE. Based on the patient's DVT and PE-related symptoms and the test results, the presence or absence of VTE events was confirmed.

[0038] The specific criteria for VTE events are: screening patients for DVT symptoms, and performing color Doppler ultrasonography of the limb veins when sudden limb swelling and pain, increased arm circumference, increased skin temperature, positive Homans sign and Neuhof sign, and cerulean femoris occur; performing CT pulmonary angiography when chest pain, shortness of breath, hemoptysis, decreased oxygen saturation, or proximal DVT is present and the risk of dislocation is highly suspected after evaluation by a clinician. Confirm whether VTE has occurred based on the examination results.

[0039] Using the Logistic regression method, with VTE events as the outcome indicator and VTE risk factors as the predictor variables, a risk prediction model was constructed. Logistic regression is a generalized linear regression analysis model, which is often used for binary classification problems in the fields of data mining, automatic disease diagnosis, economic forecasting, etc. It estimates the probability of an event based on a given independent variable data set. Since the result is a probability, the range of the dependent variable is between 0 and 1. In logistic regression, a Logit transformation is applied to the odds, that is, the probability of occurrence is divided by the probability of non-occurrence. This is also often called the logarithmic odds, or the natural logarithm of the odds.

[0040] The bootstrap resampling method was used and repeated 1000 times to internally verify the model performance, calculate its AUC, optimal cutoff value, sensitivity, specificity, accuracy and F1 score, and draw the receiver operating characteristic curve (ROC); draw the calibration curve, calculate the calibration slope and intercept, Brier score, and perform the Spiegelhalter Z test and Hosmer-Lemeshow test on the calibration curve to determine the degree of fit between the predicted probability and the true probability distribution. Decision curve analysis was performed to view the net benefit range of the model and explain the difference in the proportion of true positive and false positive results of patients and the relationship between harm when the model was used at different threshold probabilities.

[0041] Based on the parameters of the logistic fitting model, a dynamic nomogram is drawn to give an example of the relationship between individual characteristics and predicted probability.

[0042] The following is explained in conjunction with specific embodiments: Specifically, variable assignment is included as follows: Age: in years, use the original value to enter the model Combined cerebrovascular disease: yes = 1, no = 0 Surgery type: divided into internal fixation, external fixation, and other types of surgery, using one-hot encoding to enter the model, yes = 1, no = 0 Postoperative bed rest days: in days, use the original value to enter the model Surgery duration: in hours, use the original value to enter the model Lower limb fracture: yes = 1, no = 0 Whether admitted to ICU: Yes = 1, No = 0 Multiple injuries: yes = 1, no = 0 Drug prevention: Yes = 1, No = 0 Logistic regression model, the model formula is: Logit (P) = -6.104 + 0.056 × age + 2.060 × cerebrovascular disease + 1.686 × lower limb fracture + 1.123 × multiple injuries + 0.363 × other types of surgery + 0.313 × duration of surgery + 0.029 × postoperative bed rest days + 0.620 × ICU admission - 0.947 × drug prevention As can be seen from the above, drug prevention can reduce the risk of VTE; the influence of variables on VTE is cerebrovascular disease, multiple injuries, drug prevention, ICU admission, other types of surgery, operation duration, age, and postoperative bed rest days. The ROC curve of the Logistic regression model was obtained, and its discrimination index was calculated respectively.

[0043] The calibration curve was drawn, and the model calibration indicators Brier score, calibration intercept, calibration slope, Spiegelhalter Z test and Hosmer-Lemeshow test results were calculated.

[0044] Finally, a dynamic nomogram is constructed, such as Figure 2 As shown in the figure, select the variables that need to be entered into the model, including age (AGE), cerebrovascular disease (CVD), thrombotic drug prevention (CHEMOPROPHYLAXIS), whether to be admitted to the ICU (ICU), lower limb fracture (LE), multiple injuries (MULTIPLE_TRAUMA), other types of surgery except internal and external fixation (OTHER), length of surgery (LENGTH_OF_SURGERY, in hours) and postoperative bed rest days (POSTOPERATIVE BEDREST, in days). When VTE risk prediction is required, enter the required variables on the left side of the page, and then click "Predict", and the point estimate and confidence interval of the current predicted probability will be generated on the right side of the page.

[0045] Specifically, refer to Figure 3 When you click on the confidence interval on the right side of the page, the selected feature parameters, the specific probability prediction value and the upper and lower limits of the 95% confidence interval will appear, such as Figure 3 As shown: This graph can also display the probabilities of multiple patients, especially when used for comparison. For example, after entering the corresponding information of a patient, the patient's initial VTE risk probability can be calculated (the black line in the figure); further intervention factors can be adjusted, such as thrombus drug prevention, postoperative bed rest days, etc. Here, after checking "yes" for the same patient's intervenable factor "CHEMOPROPHYLAXIS", click "Predict" to generate the blue line in the figure, at this time, you can clearly see the estimated probability of the patient using drug prevention and not using drug prevention.

[0046] The device embodiments of the present application can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0047] Figure 4 FIG. 1 is a block diagram of a device for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram provided by an embodiment of the present application. Figure 4 As shown, the device comprises: The acquisition module 41 is used to collect the original data of orthopedic trauma patients, and the original data includes: VTE risk factors and outcome indicators; Constructing module 42, based on the original data, using the Logistic regression method, taking the outcome index as the prediction result and the VTE risk factor as the prediction variable, to construct a risk prediction model; using the bootstrap resampling method, internally verifying the risk prediction model, and drawing the operating characteristic curve and the calibration curve, performing the Spiegelhalter Z test and the Hosmer-Lemeshow test on the calibration curve to determine the degree of fit between the predicted probability and the true probability distribution; performing a decision curve analysis to check the net benefit range of the model, and explaining the difference in the proportion of true positive and false positive results of patients and the relationship between the harm when the model is used at different threshold probabilities; constructing a dynamic nomogram based on the risk prediction model; An acquisition module 43 is used to acquire current patient information and an adjustment intervention strategy for the patient; The prediction module 44 is used to display the prediction results corresponding to the current patient information and the prediction results corresponding to the adjusted intervention strategy based on the dynamic nomogram.

[0048] Below, reference Figure 5 To describe an electronic device according to an embodiment of the present application. Figure 5 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0049] like Figure 5 As shown, electronic device 500 includes one or more processors 510 and memory 520 .

[0050] The processor 510 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 500 to perform desired functions.

[0051] The memory 520 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 510 may run the program instructions to implement the above-described methods for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram and / or other desired functions of the various embodiments of the present application. Various contents such as category correspondences may also be stored in the computer-readable storage medium.

[0052] In one example, the electronic device 500 may further include: an input device 530 and an output device 540 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0053] In addition, the input device 530 may also include, for example, a keyboard, a mouse, an interface, etc. The output device 540 may output various information to the outside, including analysis results, etc. The output device 540 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0054] Of course, to simplify, Figure 5 Only some of the components in the electronic device related to the present application are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device may further include any other appropriate components according to specific application conditions.

[0055] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0056] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0057] In addition, an embodiment of the present application may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, causes the processor to execute the steps of the method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram according to various embodiments of the present application as described in the above “Exemplary Method” section of this specification.

[0058] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0059] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram, characterized in that: include: Collect the original data of orthopedic trauma patients, including: VTE risk factors and outcome indicators; Based on the original data, a risk prediction model was constructed using the Logistic regression method, with the outcome index as the prediction result and the VTE risk factor as the prediction variable; The risk prediction model was internally validated using the bootstrap resampling method, and the operating characteristic curve and calibration curve were drawn. The calibration curve was subjected to the Spiegelhalter Z test and the Hosmer-Lemeshow test to determine the degree of fit between the predicted probability and the true probability distribution; Conduct decision curve analysis to examine the range of net benefits of the model and illustrate the relationship between differences in the proportion of true-positive and false-positive results and harms for patients when the model is used at different threshold probabilities; Based on the risk prediction model, construct a dynamic nomogram; obtaining current patient information and tailored intervention strategies for said patients; Based on the dynamic nomogram, the prediction results corresponding to the current patient information and the prediction results corresponding to the adjusted intervention strategy are displayed.

2. The method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram according to claim 1, characterized in that: The dynamic nomogram includes a first region and a second region; The first area is used to enter predictor variables; The second area is used to display the prediction result.

3. The method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram according to claim 2, characterized in that: The second area uses different colors to display the prediction results corresponding to the current patient information and the prediction results corresponding to the adjusted intervention strategy.

4. The method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram according to claim 1, characterized in that: The VTE risk factors include: age, cerebrovascular disease, thrombotic drug prevention, ICU admission, lower limb fractures, multiple injuries, other types of surgery except internal and external fixation, operation duration and postoperative bed rest days.

5. The method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram according to claim 1, characterized in that: The prediction results include: probability prediction value and upper and lower limits of 95% confidence interval.

6. The method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram according to claim 1, characterized in that: The risk prediction model is internally validated and an operating characteristic curve is drawn, including: The performance of the risk prediction model was internally validated, and its AUC, optimal cutoff value, sensitivity, specificity, accuracy, and F1 score were calculated, and the receiver operating characteristic curve was plotted.

7. A device for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram, characterized in that: include: A collection module is used to collect original data of orthopedic trauma patients, wherein the original data includes: VTE risk factors and outcome indicators; A module is constructed, based on the original data, using the Logistic regression method, taking the outcome index as the prediction result and the VTE risk factor as the prediction variable, to construct a risk prediction model; using the bootstrap resampling method, the risk prediction model is internally verified, and the operating characteristic curve and calibration curve are drawn, and the calibration curve is subjected to the Spiegelhalter Z test and the Hosmer-Lemeshow test to determine the degree of fit between the predicted probability and the true probability distribution; a decision curve analysis is performed to check the net benefit range of the model, and to explain the difference in the proportion of true positive and false positive results of patients and the relationship between the harm when the model is used at different threshold probabilities; based on the risk prediction model, a dynamic nomogram is constructed; An acquisition module, used for acquiring current patient information and an adjustment intervention strategy for the patient; The prediction module is used to display the prediction results corresponding to the current patient information and the prediction results corresponding to the adjusted intervention strategy based on the dynamic nomogram.

8. An electronic device, characterized in that: include: A processor, and a memory for storing a program executable by the processor; The processor is used to implement the method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram as described in any one of claims 1 to 6 by running the program in the memory.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, enables the processor to execute the method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for establishing a VTE risk prediction model for orthopedic trauma patients based on a nomogram as described in any one of claims 1 to 6 is implemented.

Images