Female osteoporosis risk prediction method, device, equipment, medium and product

Abstract

The invention discloses a female osteoporosis risk prediction method and device, equipment, a medium and a product, and relates to the technical field of osteoporosis detection.The method comprises the steps that related data of a to-be-detected user is input into a multiple logistic regression model to obtain a first prediction probability, the related data is input into a support vector machine regression model to obtain a second prediction probability, and the first prediction probability is obtained; inputting the related data into a Bayesian prediction model to obtain a third prediction probability; the related data comprises a detection result of anti-mullerian hormone in serum; the multiple logistic regression model, the support vector machine regression model and the Bayesian prediction model are obtained through training of a training set; and performing weighted summation on the first prediction probability, the second prediction probability and the third prediction probability to obtain the osteoporosis risk prediction probability of the to-be-detected user. The accuracy of osteoporosis risk prediction can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of osteoporosis detection, and in particular to a method, device, equipment, medium and product for predicting the risk of osteoporosis in women. Background Art

[0002] Osteoporosis (OP) is the most common bone disease. It is a systemic bone disease characterized by low bone mass, destruction of bone tissue microstructure, increased bone brittleness, and susceptibility to osteoporotic fractures. Osteoporotic fractures refer to fractures that occur after minor trauma or during daily activities. It is one of the main causes of disability and even death in the elderly. Osteoporosis patients usually have no obvious symptoms and signs in the early stages of the disease. How to identify osteoporosis early has become an urgent problem to be solved in this field.

[0003] Osteoporosis is an age-related bone disease. Elderly women are at high risk of osteoporotic fractures (incidence rate is about 40%), and 28% of patients will lose their ability to take care of themselves after fractures, which seriously affects their quality of life and brings huge health expenses. Studies have shown that the number of hospital bed occupancy days caused by osteoporotic hip fractures in women over 45 years old is higher than that of diabetes, chronic obstructive pulmonary disease (COPD), cardiovascular disease and breast cancer. The perimenopausal period is a critical period for preventing osteoporosis. Due to changes in hormone levels, women will experience rapid and large bone loss during the perimenopausal period (from about 45 years old to within 12 months after menopause), losing about 40% of their peak bone mass. Therefore, early identification of high-risk osteoporosis populations during the perimenopausal period is helpful for timely intervention or treatment of this population, alleviating the large loss of bone density, and has important clinical significance for reducing the risk of osteoporotic fractures.

[0004] At present, many osteoporosis screening tools have been established, among which the more mature tools include: the International Osteoporosis Foundation (IOF) one-minute osteoporosis risk test, the Asian osteoporosis self-screening tool (OSTA), the simplified osteoporosis risk factor evaluation questionnaire (SCORE), the osteoporosis risk assessment tool (ORAI), the osteoporosis risk index (OSIRIS) and the osteoporosis preliminary assessment tool (OPERA).

[0005] Although commonly used osteoporosis screening tools have high sensitivity, their specificity is low and the overall accuracy of screening is not high. Summary of the invention

[0006] The purpose of this application is to provide a method, device, equipment, medium and product for predicting osteoporosis risk in women, which can improve the accuracy of osteoporosis risk prediction.

[0007] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a method for predicting osteoporosis risk in women, the method comprising: Inputting relevant data of the user to be detected into a multiple logistic regression model to obtain a first prediction probability, inputting the relevant data into a support vector machine regression model to obtain a second prediction probability, and inputting the relevant data into a Bayesian prediction model to obtain a third prediction probability; the relevant data includes a test result of anti-Mullerian hormone in serum; the multiple logistic regression model, the support vector machine regression model and the Bayesian prediction model are all obtained by training with a training set; The first predicted probability, the second predicted probability and the third predicted probability are weightedly summed to obtain the osteoporosis risk predicted probability of the user to be detected.

[0008] Optionally, the relevant data also includes age, height, weight, lifestyle, menstrual history, reproductive history, family history of disease, past illness, current medical history and medication use.

[0009] Optionally, the training set includes relevant data and bone density test results of multiple users; The multiple logistic regression model is obtained by performing logistic regression analysis based on the training set with relevant data as independent variables and bone density test results as dependent variables; The support vector machine regression model is obtained by training the support vector machine structure based on the training set with relevant data as input and osteoporosis risk probability as output; the osteoporosis risk probability is determined according to the bone density test result; The Bayesian prediction model is obtained by training the Bayesian model based on the training set with relevant data as input and osteoporosis risk probability as output.

[0010] Optionally, the lifestyle includes whether one smokes, drinks alcohol, drinks caffeinated beverages, and takes calcium supplements.

[0011] Optionally, the drug usage includes the usage of antihypertensive drugs, hypoglycemic drugs, glucocorticoids, aromatase inhibitors, gonadotropin-releasing hormone drugs and proton pump inhibitors.

[0012] Optionally, performing weighted summation on the first prediction probability, the second prediction probability and the third prediction probability to obtain the osteoporosis risk prediction probability of the user to be detected specifically includes: According to the formula Obtaining a predicted probability of osteoporosis risk of the user to be detected; in, represents the osteoporosis risk prediction probability of the user to be detected, is the first predicted probability, for The weight of is the second predicted probability, for The weight of is the third predicted probability, for The weight of .

[0013] In a third aspect, the present application provides a perimenopausal female osteoporosis risk prediction device, the perimenopausal female osteoporosis risk prediction device comprising: A multi-model prediction module, used for inputting relevant data of the user to be detected into a multiple logistic regression model to obtain a first prediction probability, inputting the relevant data into a support vector machine regression model to obtain a second prediction probability, and inputting the relevant data into a Bayesian prediction model to obtain a third prediction probability; the relevant data includes the anti-Mullerian hormone test result in serum; the multiple logistic regression model, the support vector machine regression model and the Bayesian prediction model are all obtained by training with a training set; The prediction probability fusion module is used to perform weighted summation on the first prediction probability, the second prediction probability and the third prediction probability to obtain the osteoporosis risk prediction probability of the user to be detected.

[0014] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above-described methods for predicting osteoporosis risk in women.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned methods for predicting osteoporosis risk in women.

[0016] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for predicting osteoporosis risk in women.

[0017] According to the specific embodiments provided in this application, this application discloses the following technical effects: The present application provides a method, device, equipment, medium and product for predicting osteoporosis risk in women. By taking the anti-Müllerian hormone (AMH) test results as the prediction input, the influence of ovarian reserve function on osteoporosis in perimenopausal women is taken into consideration, thereby improving the accuracy of risk prediction. In addition, three prediction models are used for prediction separately and then fused, thereby further improving the accuracy of risk prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 This is an application environment diagram of a method for predicting osteoporosis risk in women in one embodiment of the present application.

[0020] Figure 2 A flowchart of a method for predicting osteoporosis risk in women provided in one embodiment of the present application.

[0021] Figure 3 A schematic diagram of the support vector machine (SVM) structure provided in one embodiment of the present application.

[0022] Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0025] The present invention provides a method for predicting osteoporosis risk in women, which can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the relevant data of the user to be detected to the server 104. After the server 104 receives the relevant data of the user to be detected, for the relevant data of the user to be detected, the server 104 inputs the relevant data of the user to be detected into a multiple logistic regression model to obtain a first prediction probability, inputs the relevant data into a support vector machine regression model to obtain a second prediction probability, and inputs the relevant data into a Bayesian prediction model to obtain a third prediction probability; the relevant data includes the anti-Mullerian hormone test results in serum; the multiple logistic regression model, the support vector machine regression model and the Bayesian prediction model are all obtained through training with a training set; the first prediction probability, the second prediction probability and the third prediction probability are weighted and summed to obtain the osteoporosis risk prediction probability of the user to be detected. The server 104 can feedback the obtained osteoporosis risk prediction probability to the terminal 102. In addition, in some embodiments, the method for predicting osteoporosis risk in women can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly predict the osteoporosis risk in women based on the relevant data of the user to be detected, or the server 104 can obtain the relevant data of the user to be detected from the data storage system and predict the osteoporosis risk in women based on the relevant data of the user to be detected.

[0026] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0027] In an exemplary embodiment, Figure 2 As shown, a method for predicting the risk of osteoporosis in women is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 201 to 202.

[0028] Step 201: inputting the relevant data of the user to be tested into a multiple logistic regression model to obtain a first prediction probability, inputting the relevant data into a support vector machine regression model to obtain a second prediction probability, and inputting the relevant data into a Bayesian prediction model to obtain a third prediction probability; the relevant data include the anti-Mullerian hormone test result in serum; the multiple logistic regression model, the support vector machine regression model and the Bayesian prediction model are all obtained through training with a training set.

[0029] Step 202: performing weighted summation on the first prediction probability, the second prediction probability and the third prediction probability to obtain the osteoporosis risk prediction probability of the user to be detected.

[0030] The relevant data also include age, height, weight, education level, lifestyle, menstrual history, reproductive history, family history of disease, past illness, current medical history and medication use.

[0031] The lifestyle includes whether one smokes, drinks alcohol, drinks caffeinated beverages, and takes calcium supplements.

[0032] The drug usage includes the use of antihypertensive drugs, hypoglycemic drugs, glucocorticoids, aromatase inhibitors, gonadotropin-releasing hormone drugs and proton pump inhibitors, and the usage status is used or not used.

[0033] The training set includes relevant data and bone density test results of multiple users, one sample corresponds to relevant data and bone density test results of one user, and the users serving as samples are the population of subjects to be tested, specifically perimenopausal women.

[0034] The bone density test results were obtained through dual-energy X-ray absorptiometry (DXA).

[0035] The multiple logistic regression model is obtained by performing logistic regression analysis based on the training set with relevant data as independent variables and bone density test results as dependent variables.

[0036] The multiple logistic regression model is expressed as: .

[0037] in, is the first predicted probability, is the jth independent variable, is a constant, for The coefficient of , m is the number of independent variables, that is, the number of parameters in the relevant data.

[0038] This application uses the Maximum Likelihood Estimation (MLE) method to fit the model parameters of the multiple logistic regression model. Here the model parameters are and .

[0039] Construct the likelihood function using maximum likelihood estimation (MLE) and take the logarithmic form of the likelihood function: .

[0040] in, L is the likelihood function value, is the observed value of the i-th sample, i.e., the relevant data, is the predicted probability of the ith sample.

[0041] The Newton-Raphson iterative method is used to maximize the log-likelihood function. At this time, the value of the parameter b 0 , b 1 , b 2 , ...., b m That is β 0 , β 1 , β 2 , ..., β m The maximum likelihood estimate of the parameter estimate was obtained, and the variance-covariance matrix of the parameter estimate was obtained. The consistency index (C-index) was used to judge the goodness of fit of the model. The value range of C-index was 0-1, and the closer to 1, the better the goodness of fit. The boot package of R software was used to perform K-fold cross validation of the regression model.

[0042] The support vector machine regression model is obtained by training the support vector machine structure based on the training set with relevant data as input and osteoporosis prediction probability as output; the osteoporosis risk probability is determined based on the bone density test results, and there is a known nonlinear relationship between the osteoporosis risk probability and the bone density test results.

[0043] For a given training set ,in, is the influencing factor, i.e., the relevant data, For the predicted value, i.e. the predicted probability of osteoporosis risk, we seek an optimal function relationship y=f(x) that reflects the sample data, where x is the input of the optimal function and y is the output of the optimal function. In the construction of the support vector machine regression model, are the index values ​​of various factors affecting osteoporosis, and Represents the prediction of bone density value. The main principle of this algorithm is to train the hyperplane f(x)=w T +b is the predicted value, w is the normal vector of the hyperplane, which determines the direction of the hyperplane, b is the distance from the hyperplane to the origin, and the support vector regression assumes that it can tolerate a maximum deviation of ε between f(x) and y, where ε is a constant, that is, it requires that the distance from all sample points to the desired hyperplane is no greater than e , then the problem of seeking the optimal regression hyperplane is transformed into solving the following quadratic convex programming problem: , the constraints are: , and are slack variables.

[0044] When the distance from an individual sample point to the desired hyperplane is greater than e hour, e- The insensitivity function makes the deviation beyond x i This is equivalent to the slack variable introduced in the support vector machine classification. By introducing the fault-tolerant penalty coefficient C, the quadratic convex programming problem of seeking the optimal regression hyperplane becomes: .

[0045] , and The parameters of the optimal hyperplane are determined by constraints, in which the kernel function can be introduced to realize nonlinear regression and transform the points in the sample space into and Using the mapped image and Replace and apply You can get: Here x and x i They all represent the feature vectors of the data points.

[0046] The support vector machine calculation process is completed by R software, and the structure is as follows Figure 3 As shown, , , , …, Constitute the input vector, represents the kth input value, , represents the kernel function, n is the length of the input vector, and the kernel function is used to calculate the inner product. is the weight, For a nonlinear mapping, the decision rule for summing the symbol output is .

[0047] The calculation process of support vector machine is as follows: ① Construct a sample data set containing various predictors and outcome variables; ② Divide the data set into training samples and test samples in proportion; ③ Construct the SVM regression model in the training samples and perform ten-fold cross validation; ④ Test the SVM model in the test samples. If the test results are not ideal, return to redesign the model structure.

[0048] The Bayesian prediction model is obtained by training the Bayesian model based on the training set with relevant data as input and osteoporosis risk probability as output.

[0049] Bayesian theory treats any unknown parameter i are all considered as random variables. i Has its own probability distribution .assumed is a sample from a population whose density function is , For i In case of occurrence y The probability of occurrence, , Indicates t unknown value, , k is a constant, when given a set of observations y hour, i The conditional probability is: ,in, , is the probability of y occurring.

[0050] when y When given, remember i The likelihood function is ,at this time i The posterior distribution of can be expressed as , For y In case of occurrence i The probability of occurrence. m Group y Then every time a new sample is obtained, i The posterior distribution of is recalculated, and the final posterior distribution is updated as follows: , for In case of occurrence iThe probability of occurrence, for In case of occurrence i The probability of occurrence, For a given hour, i The likelihood function of .

[0051] The basis of Bayesian inference is the posterior distribution of the parameter, and inference is made using the mean, percentile, high-dimensional probability density function, etc. of the posterior distribution. π ( i ), especially for high-dimensional distribution with multiple parameters. Monte Carlo integration (MCMC algorithm) based on Markov Chain is an effective solution to this problem, also known as MH algorithm. Gibbs sampling is also a type of MH algorithm. The construction of Bayesian prediction model is based on this type of algorithm, and its operation process can be realized through WinBUGS software.

[0052] This application intends to use the ideas of the Bayesian school to construct a Bayesian prediction model for osteoporosis, which is completed through WinBUGS1.4.3 software, using Gibbs sampling, combining prior information to estimate the posterior probability, and using the Bayesian Information Criterion (BIC) to judge the goodness of fit of the model. The specific calculation process is as follows: ① Construct a prior distribution based on literature data, and select non-informative priors for variables with little information; ② Establish a Bayesian prediction model, and calculate the posterior probability through the likelihood function and prior probability; ③ Observe the parameter trajectory diagram, autocorrelation diagram and kernel density diagram to judge the convergence of the model; ④ Perform Geweke diagnosis on the model to judge the stable distribution; ⑤ Calculate the posterior statistic.

[0053] The first prediction probability, the second prediction probability and the third prediction probability are weighted and summed to obtain the osteoporosis risk prediction probability of the user to be detected, specifically including: according to the formula Obtaining the osteoporosis risk prediction probability of the user to be detected.

[0054] in, represents the osteoporosis risk prediction probability of the user to be detected, is the first predicted probability, for The weight of is the second predicted probability, for The weight of is the third predicted probability, for The weight of .

[0055] Based on the same inventive concept, the embodiment of the present application also provides a female osteoporosis risk prediction device for implementing the female osteoporosis risk prediction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more female osteoporosis risk prediction device embodiments provided below can refer to the limitations of the female osteoporosis risk prediction method above, and will not be repeated here.

[0056] In an exemplary embodiment, the present application provides a female osteoporosis risk prediction device comprising: A multi-model prediction module is used to input the relevant data of the user to be detected into a multiple logistic regression model to obtain a first prediction probability, input the relevant data into a support vector machine regression model to obtain a second prediction probability, and input the relevant data into a Bayesian prediction model to obtain a third prediction probability; the relevant data includes the anti-Mullerian hormone test result in serum; the multiple logistic regression model, the support vector machine regression model and the Bayesian prediction model are all obtained through training with a training set.

[0057] The prediction probability fusion module is used to perform weighted summation on the first prediction probability, the second prediction probability and the third prediction probability to obtain the osteoporosis risk prediction probability of the user to be detected.

[0058] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store female osteoporosis risk prediction data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting female osteoporosis risk is implemented.

[0059] Those skilled in the art will understand that Figure 4The structure shown in the figure is only a block diagram of a part of the structure related to the present application scheme, and does not constitute a limitation on the computer device to which the present application scheme is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in the above-mentioned embodiments of the method for predicting the risk of osteoporosis in women are implemented.

[0060] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which, when executed by a processor, implements the steps in the above-mentioned embodiments of the method for predicting the risk of osteoporosis in women.

[0061] In an exemplary embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in the above-mentioned embodiments of the method for predicting the risk of osteoporosis in women.

[0062] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0063] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0064] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a data processing logic of a programmable logic device, etc., but is not limited thereto.

[0065] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0066] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for predicting osteoporosis risk in women, characterized in that: The method for predicting the risk of osteoporosis in women comprises: Inputting relevant data of the user to be detected into a multiple logistic regression model to obtain a first prediction probability, inputting the relevant data into a support vector machine regression model to obtain a second prediction probability, and inputting the relevant data into a Bayesian prediction model to obtain a third prediction probability; the relevant data includes a test result of anti-Mullerian hormone in serum; the multiple logistic regression model, the support vector machine regression model and the Bayesian prediction model are all obtained by training with a training set; The first predicted probability, the second predicted probability and the third predicted probability are weightedly summed to obtain the osteoporosis risk predicted probability of the user to be detected.

2. The method for predicting osteoporosis risk in women according to claim 1, characterized in that: The relevant data also include age, height, weight, lifestyle, menstrual history, reproductive history, family history of disease, past illness, current illness history and medication use.

3. The method for predicting osteoporosis risk in women according to claim 2, characterized in that: The training set includes relevant data and bone density test results of multiple users; The multiple logistic regression model is obtained by performing logistic regression analysis based on the training set with relevant data as independent variables and bone density test results as dependent variables; The support vector machine regression model is obtained by training the support vector machine structure based on the training set with relevant data as input and osteoporosis risk probability as output; the osteoporosis risk probability is determined according to the bone density test result; The Bayesian prediction model is obtained by training the Bayesian model based on the training set with relevant data as input and osteoporosis risk probability as output.

4. The method for predicting osteoporosis risk in women according to claim 2, characterized in that: The lifestyle includes whether one smokes, drinks alcohol, drinks caffeinated beverages, and takes calcium supplements.

5. The method for predicting osteoporosis risk in women according to claim 2, characterized in that: The drug usage includes the use of antihypertensive drugs, hypoglycemic drugs, glucocorticoids, aromatase inhibitors, gonadotropin-releasing hormone drugs and proton pump inhibitors.

6. The method for predicting osteoporosis risk in women according to claim 1, characterized in that: The first prediction probability, the second prediction probability and the third prediction probability are weighted and summed to obtain the osteoporosis risk prediction probability of the user to be detected, specifically including: According to the formula Obtaining a predicted probability of osteoporosis risk of the user to be detected; in, represents the osteoporosis risk prediction probability of the user to be detected, is the first predicted probability, for The weight of is the second predicted probability, for The weight of is the third predicted probability, for The weight of .

7. A perimenopausal female osteoporosis risk prediction device, characterized in that: The perimenopausal female osteoporosis risk prediction device uses the female osteoporosis risk prediction method according to any one of claims 1 to 6, and the perimenopausal female osteoporosis risk prediction device comprises: A multi-model prediction module, used for inputting relevant data of the user to be detected into a multiple logistic regression model to obtain a first prediction probability, inputting the relevant data into a support vector machine regression model to obtain a second prediction probability, and inputting the relevant data into a Bayesian prediction model to obtain a third prediction probability; the relevant data includes the anti-Mullerian hormone test result in serum; the multiple logistic regression model, the support vector machine regression model and the Bayesian prediction model are all obtained by training with a training set; The prediction probability fusion module is used to perform weighted summation on the first prediction probability, the second prediction probability and the third prediction probability to obtain the osteoporosis risk prediction probability of the user to be detected.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting osteoporosis risk in women according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting osteoporosis risk in women described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting osteoporosis risk in women described in any one of claims 1 to 6 is implemented.

Images