Method for predicting risk of fracture in osteoporotic patients and predicting device

Abstract

The application discloses a kind of prediction method and prediction device of osteoporosis patient fracture risk.The prediction method includes: the individualized factor data and bone density data of batch osteoporosis patients are carried out multiple regression analysis, and multiple regression equation is established;Establish the lumbar finite element model of each osteoporosis patient;Simulation analysis each lumbar finite element model is biomechanics change when being stressed under several daily scenes, obtain the proportion of the vertebral cancellous bone unit microstrain of each lumbar finite element model exceeding threshold value;According to the proportion of the vertebral cancellous bone unit microstrain exceeding threshold value, the bone density corresponding to each lumbar finite element model is carried out correlation analysis, and obtains osteoporosis fracture risk prediction equation;According to the individualized factor data of to-be-predicted object, multiple regression equation and osteoporosis fracture risk prediction equation, fracture risk assessment result is obtained.The method considers the influence of individualized factor on bone density, and it is favorable to accurately carry out fracture risk prediction.

Description

Technical Field

[0001] This invention belongs to the field of electronic information technology, specifically, it relates to a method and device for predicting fracture risk in patients with osteoporosis. Background Technology

[0002] The most serious complication of osteoporosis is fracture, specifically a low-energy or non-violent fracture, also known as a fragility fracture. These fractures occur from minimal trauma, such as a fall while standing or walking on flat ground, and can result in fractures of the vertebrae, hip, proximal humerus, or distal radius. Osteoporotic fractures can cause pain and severe disability. The incidence of fractures in osteoporosis patients is approximately 20%, with the highest mortality and disability rates among fractures of the spine and hip. The incidence increases with age.

[0003] Bone strength is an important reference indicator for detecting and evaluating osteoporosis, but because it can only be obtained through destructive testing methods, it is difficult to directly assess the bone mechanical properties of osteoporosis patients in clinical practice. Bone mineral density (BMD), on the other hand, is closely related to bone strength and has the ability to diagnose osteoporosis and predict fracture risk. Currently, the main clinical methods for diagnosing osteoporosis rely on dual-energy X-ray absorptiometry (DEXA) and quantitative computed tomography (QCT) to measure bone mineral density.

[0004] Bone mineral density (BMD) measurements using techniques such as DEXA and QCT are widely used to diagnose osteoporosis. DEXA is economical, simple, and produces low radiation doses to patients, and was previously considered the "gold standard" for diagnosing osteoporosis. However, DEXA uses two-dimensional imaging technology, resulting in low measurement accuracy. Its projective scanning method cannot analyze the three-dimensional spatial structure of bone or differentiate mineral density changes between the cortex and trabeculae, providing only two-dimensional area BMD information. QCT, on the other hand, provides three-dimensional images of bone structure and the spatial distribution of bone minerals, making it more sensitive and accurate in detecting changes in bone mass compared to other methods.

[0005] However, many factors can lead to errors in fracture risk assessment. When measuring bone mineral density, the influence of factors such as weight, gender, age, and hormones must be considered to more accurately assess bone condition. Currently, there are no effective clinical methods for predicting the long-term fracture risk caused by osteoporosis. Summary of the Invention

[0006] (I) The technical problem to be solved by the present invention

[0007] The technical problem solved by this invention is: how to more accurately predict the fracture risk of osteoporosis patients.

[0008] (II) Technical Solution Adopted in this Invention

[0009] A method for predicting fracture risk in patients with osteoporosis, the prediction method comprising:

[0010] Multiple regression analysis was performed on personalized factor data and bone mineral density data of a batch of osteoporosis patients to establish a multiple regression equation between changes in bone mineral density and personalized factors;

[0011] A finite element model of the lumbar spine of each osteoporosis patient was established, and the material properties of the lumbar spine finite element model were set according to the bone density of the osteoporosis patient.

[0012] Simulation analysis was performed on the biomechanical changes of each lumbar finite element model under stress in several daily scenarios to obtain the proportion of micro-strain of the vertebral cancellous bone unit in each lumbar finite element model that exceeds the threshold.

[0013] Correlation analysis was performed on the proportion of vertebral cancellous bone units with microstrain exceeding the threshold and the bone density corresponding to each lumbar vertebra finite element model to obtain the osteoporotic fracture risk prediction equation.

[0014] The fracture risk prediction results for osteoporosis patients are obtained based on the individualized factor data of the subjects to be predicted, the multiple regression equation, and the osteoporosis fracture risk prediction equation.

[0015] Preferably, the personalized data includes at least gender, age, weight, height, exercise data, and smoking data.

[0016] Preferably, the method for establishing a finite element model of the lumbar spine of osteoporosis patients is as follows:

[0017] Bone mineral density samples were collected from the first and second lumbar vertebrae of osteoporosis patients to construct a three-dimensional mesh model from the first to the second lumbar vertebrae.

[0018] The average bone density of the first and second lumbar vertebrae and the three-dimensional mesh model are input into the finite element simulation analysis software to construct the lumbar vertebra finite element model.

[0019] Preferably, the threshold is 5000 με, and the proportion of vertebral cancellous bone units with microstrain exceeding the threshold is the ratio of the number of cancellous bone units with microstrain exceeding the threshold to the total number of vertebral cancellous bone units.

[0020] Preferably, the method for obtaining the fracture risk prediction result for osteoporosis patients based on the personalized data of the subject to be predicted, the multiple regression equation, and the osteoporosis fracture risk prediction equation includes:

[0021] The personalized factor data of the object to be predicted are substituted into the constructed multiple regression equation to obtain the predicted bone density value.

[0022] The predicted bone mineral density value is substituted into the constructed osteoporosis fracture risk prediction equation to obtain the fracture risk prediction result for the subject to be predicted.

[0023] Preferably, the fracture risk prediction result is a fracture risk level.

[0024] This application also discloses a device for predicting fracture risk in patients with osteoporosis, the device comprising:

[0025] The bone mineral density analysis unit is used to perform multiple regression analysis on personalized factor data and bone mineral density data of a batch of osteoporosis patients to obtain the multiple regression equation between bone mineral density and personalized factors.

[0026] The model building unit is used to build finite element models of the lumbar spine for each osteoporosis patient. The material properties of the lumbar spine finite element model are set according to the bone density of the osteoporosis patient.

[0027] The simulation unit is used to simulate and analyze the biomechanical changes of each lumbar finite element model under stress in several daily scenarios, and to obtain the proportion of micro-strain of the vertebral cancellous bone element in each lumbar finite element model that exceeds the threshold.

[0028] The risk analysis unit is used to perform correlation analysis based on the proportion of microstrain exceeding the threshold of vertebral cancellous bone units and the bone density corresponding to each lumbar finite element model, and to construct an osteoporotic fracture risk prediction equation.

[0029] The risk prediction unit is used to obtain the fracture risk prediction result of the osteoporosis patient to be predicted based on the personalized factor data of the subject to be predicted, the multiple regression equation, and the osteoporosis fracture risk prediction equation.

[0030] This application also provides a computer-readable storage medium storing a program for predicting the fracture risk of osteoporosis patients, which, when executed by a processor, implements the above-described method for predicting the fracture risk of osteoporosis patients.

[0031] This application also provides a computer device, the computer device including a computer-readable storage medium, a processor, and a program for predicting the fracture risk of osteoporosis patients stored in the computer-readable storage medium, wherein the program for predicting the fracture risk of osteoporosis patients, when executed by the processor, implements the above-described method for predicting the fracture risk of osteoporosis patients.

[0032] (III) Beneficial Effects

[0033] This invention discloses a method, device, storage medium, and equipment for predicting fracture risk in osteoporosis patients, which has the following technical advantages compared to the prior art:

[0034] This method takes into account the influence of individual factors on bone density, which is conducive to the accurate assessment of current fracture risk. At the same time, it can make predictions without the need for instrument measurement in practical applications, thus also being beneficial for long-term risk assessment. Attached Figure Description

[0035] Figure 1 This is a flowchart of a method for predicting fracture risk in osteoporosis patients according to Embodiment 1 of the present invention;

[0036] Figure 2 This is a schematic diagram of the fracture risk prediction device for osteoporosis patients according to Embodiment 2 of the present invention.

[0037] Figure 3 This is a schematic diagram of a computer device according to Embodiment 4 of the present invention. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0039] Before describing the various embodiments of this application in detail, the inventive concept of this application is first briefly described: Existing technologies typically obtain bone mineral density (BMD) of osteoporosis patients through direct measurement to predict fracture risk, without considering the influence of other individualized factors on BMD, thus failing to accurately assess fracture risk in osteoporosis patients. This application discloses a method for predicting fracture risk in osteoporosis patients, mainly comprising two parts: first, establishing a multiple regression equation between BMD and individualized factors through big data analysis; and second, establishing a fracture risk prediction equation correlated with BMD through simulation analysis. In practical application, the individualized factors and the multiple regression equation of the subject are first combined to predict the subject's BMD, and then the predicted BMD and the fracture risk prediction equation are combined to predict the fracture risk. This method comprehensively considers the influence of individualized factors on BMD, which is beneficial for accurate fracture risk assessment. Furthermore, in practical application, prediction can be performed without the need for instrumental measurement, thus also facilitating long-term risk assessment.

[0040] Specifically, such as Figure 1 As shown, the method for predicting fracture risk in osteoporosis patients in this embodiment includes the following steps:

[0041] Step S10: Perform multiple regression analysis on the personalized factor data and bone mineral density data of a batch of osteoporosis patients to establish a multiple regression equation between bone mineral density and personalized factors;

[0042] Step S20: Establish finite element models of the lumbar spine for each osteoporosis patient. The material properties of the lumbar spine finite element models are set according to the bone density of the osteoporosis patients.

[0043] Step S30: Simulate and analyze the biomechanical changes of each lumbar finite element model under stress in several daily scenarios, and obtain the proportion of micro-strain of the vertebral cancellous bone unit in each lumbar finite element model that exceeds the threshold.

[0044] Step S40: Based on the proportion of vertebral cancellous bone units with microstrain exceeding the threshold and the bone mineral density corresponding to each lumbar vertebra finite element model, a correlation analysis is performed to obtain the osteoporotic fracture risk prediction equation.

[0045] Step S50: Obtain the fracture risk prediction results for osteoporosis patients based on the individualized factor data, multiple regression equation, and osteoporosis fracture risk prediction equation of the subject to be predicted.

[0046] Specifically, in step S10, the personalized factor data includes at least gender, age, weight, height, exercise data, and smoking data. By performing multiple regression analysis on the personalized factor data and bone mineral density data of a batch of osteoporosis patients, a multiple regression equation between bone mineral density changes and personalized factors is established. Based on this multiple regression equation, the trend of bone mineral density changes with time (age) of the subject to be predicted under various personalized factor data can be realized.

[0047] Further, in step S20, a group of clinical osteoporosis patients are selected, and bone mineral density (BMD) is collected using a QCT device. The collection sites are the first to the second lumbar vertebrae. Based on the BMD of each pixel collected by the QCT device, the average BMD of the cancellous bone in the first and second lumbar vertebrae is calculated. A three-dimensional mesh model of the first to the second lumbar vertebrae of the osteoporosis patients is constructed. The three-dimensional mesh model includes models of cortical bone, cancellous bone, ligaments, etc. The three-dimensional mesh model is input into finite element simulation analysis software, and the material properties of the model are set based on the average BMD of the cancellous bone to obtain the finite element model of the lumbar vertebrae.

[0048] Further, in step S30, force boundary conditions are set for the lumbar spine finite element model, that is, the forces experienced by a person in daily life are simulated on the model, and the biomechanical changes of each lumbar spine finite element model under various daily scenarios are simulated and analyzed to obtain the proportion of vertebral cancellous bone units in each lumbar spine finite element model whose microstrain exceeds a threshold. For example, the threshold is 5000 με, and the proportion of vertebral cancellous bone units whose microstrain exceeds the threshold is the ratio of the number of cancellous bone units whose microstrain exceeds the threshold to the total number of cancellous bone units in the vertebral body. The higher the proportion of vertebral cancellous bone units whose microstrain exceeds the threshold, the greater the risk of fracture.

[0049] Furthermore, a correlation analysis was conducted based on the proportion of vertebral cancellous bone units with microstrain exceeding the threshold and the bone mineral density corresponding to each lumbar vertebra finite element model to obtain an osteoporotic fracture risk prediction equation. This osteoporotic fracture risk prediction equation reflects the relationship between bone mineral density and fracture risk.

[0050] After constructing the multiple regression equation and the osteoporosis fracture risk prediction equation, the personalized factor data of the subject to be predicted are substituted into the multiple regression equation to obtain the predicted bone mineral density (BMD) value. Then, the predicted BMD value is substituted into the osteoporosis fracture risk prediction equation to obtain the predicted fracture risk result for the subject. It should be noted that the fracture risk prediction result obtained here can be a prediction of the current state or a prediction of the future. For example, if the subject's current age is 45 years old, and other personalized factors are fixed, the BMD at age 45 can be predicted, thus predicting the current fracture risk. Alternatively, if the subject's age is changed to 46 years old, and other factors remain constant, the BMD at age 46 can be predicted, thus predicting the fracture risk one year later (at age 46). Similarly, any one factor in the personalized factor data can be changed while other factors remain constant to dynamically predict changes in BMD, thereby predicting the trend of fracture risk changes.

[0051] This second embodiment also discloses a device for predicting fracture risk in osteoporosis patients, such as... Figure 2As shown, the prediction device includes a bone density analysis unit 100, a model building unit 200, a simulation unit 300, a risk analysis unit 400, and a risk prediction unit 500. The bone mineral density analysis unit 100 is used to perform multiple regression analysis on personalized factor data and bone mineral density data of a batch of osteoporosis patients to obtain a multiple regression equation between bone mineral density and personalized factors; the model building unit 200 is used to build lumbar spine finite element models for each osteoporosis patient, and the material properties of the lumbar spine finite element models are set according to the bone mineral density of the osteoporosis patients; the simulation unit 300 is used to simulate and analyze the biomechanical changes of each lumbar spine finite element model under stress in several daily scenarios to obtain the proportion of vertebral cancellous bone units in each lumbar spine finite element model whose microstrain exceeds the threshold; the risk analysis unit 400 is used to perform correlation analysis based on the proportion of vertebral cancellous bone units whose microstrain exceeds the threshold and the bone mineral density corresponding to each lumbar spine finite element model to construct an osteoporosis fracture risk prediction equation; the risk prediction unit 500 is used to obtain the fracture risk prediction results of the osteoporosis patients to be predicted based on the personalized factor data of the subjects to be predicted, the multiple regression equation, and the osteoporosis fracture risk prediction equation. The specific working processes of the bone density analysis unit 100, model building unit 200, simulation unit 300, risk analysis unit 400, and risk prediction unit 500 are described in the relevant description in Example 1, and will not be repeated here.

[0052] Example 3 also discloses a computer-readable storage medium storing a program for predicting the fracture risk of osteoporosis patients. When the program for predicting the fracture risk of osteoporosis patients is executed by a processor, it implements the above-described method for predicting the fracture risk of osteoporosis patients.

[0053] Furthermore, Embodiment 4 also discloses a computer device, at the hardware level, such as Figure 3 As shown, the computer device includes a processor 12, an internal bus 13, a network interface 14, and a computer-readable storage medium 11. The processor 12 reads the corresponding computer program from the computer-readable storage medium and runs it, forming a request processing device at the logical level. Of course, in addition to the software implementation, one or more embodiments of this specification do not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices. The computer-readable storage medium 11 stores a program for predicting the fracture risk of osteoporosis patients. When the processor executes the program for predicting the fracture risk of osteoporosis patients, it implements the above-described method for predicting the fracture risk of osteoporosis patients.

[0054] Computer-readable storage media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0055] The specific embodiments of the present invention have been described in detail above. Although some embodiments have been shown and described, those skilled in the art should understand that modifications and improvements can be made to these embodiments without departing from the principles and spirit of the present invention as defined by the claims and their equivalents, and such modifications and improvements should also be within the protection scope of the present invention.

Claims

1. A method for predicting fracture risk in patients with osteoporosis, characterized in that, The prediction method includes: Multiple regression analysis was performed on personalized factor data and bone mineral density data of a batch of osteoporosis patients to establish a multiple regression equation between changes in bone mineral density and personalized factors; A finite element model of the lumbar spine of each osteoporosis patient was established, and the material properties of the lumbar spine finite element model were set according to the bone density of the osteoporosis patient. Simulation analysis was performed on the biomechanical changes of each lumbar finite element model under stress in several daily scenarios to obtain the proportion of micro-strain of the vertebral cancellous bone unit in each lumbar finite element model that exceeds the threshold. Correlation analysis was performed on the proportion of vertebral cancellous bone units with microstrain exceeding the threshold and the bone density corresponding to each lumbar vertebra finite element model to obtain the osteoporotic fracture risk prediction equation. The fracture risk prediction results for osteoporosis patients are obtained based on the personalized factor data of the subjects to be predicted, the multiple regression equation, and the osteoporosis fracture risk prediction equation. The method for establishing a finite element model of the lumbar spine in patients with osteoporosis is as follows: Bone mineral density samples were collected from the first and second lumbar vertebrae of osteoporosis patients to construct a three-dimensional mesh model from the first to the second lumbar vertebrae. The average bone density of the first and second lumbar vertebrae and the three-dimensional mesh model are input into the finite element simulation analysis software to construct the lumbar vertebra finite element model.

2. The method for predicting fracture risk in osteoporosis patients according to claim 1, characterized in that, The personalized data includes at least gender, age, weight, height, exercise data, and smoking data.

3. The method for predicting fracture risk in osteoporosis patients according to claim 2, characterized in that, The threshold is 5000με, and the proportion of vertebral cancellous bone units whose microstrain exceeds the threshold is the ratio of the number of cancellous bone units whose microstrain exceeds the threshold to the total number of cancellous bone units in the vertebral body.

4. The method for predicting fracture risk in osteoporosis patients according to claim 1, characterized in that, The method for obtaining the fracture risk prediction result for osteoporosis patients based on the personalized data of the subjects to be predicted, the multiple regression equation, and the osteoporosis fracture risk prediction equation includes: The personalized factor data of the object to be predicted are substituted into the constructed multiple regression equation to obtain the predicted bone density value. The predicted bone mineral density value is substituted into the constructed osteoporosis fracture risk prediction equation to obtain the fracture risk prediction result for the subject to be predicted.

5. The method for predicting fracture risk in osteoporosis patients according to claim 4, characterized in that, The fracture risk prediction result is the fracture risk level.

6. A device for predicting fracture risk in patients with osteoporosis, characterized in that, The prediction device includes: The bone mineral density analysis unit is used to perform multiple regression analysis on personalized factor data and bone mineral density data of a batch of osteoporosis patients to obtain the multiple regression equation between bone mineral density and personalized factors. The model building unit is used to build finite element models of the lumbar spine for each osteoporosis patient. The material properties of the lumbar spine finite element model are set according to the bone density of the osteoporosis patient. The simulation unit is used to simulate and analyze the biomechanical changes of each lumbar finite element model under stress in several daily scenarios, and to obtain the proportion of micro-strain of the vertebral cancellous bone element in each lumbar finite element model that exceeds the threshold. The risk analysis unit is used to perform correlation analysis based on the proportion of microstrain exceeding the threshold of vertebral cancellous bone units and the bone density corresponding to each lumbar finite element model, and to construct an osteoporotic fracture risk prediction equation. The risk prediction unit is used to obtain the fracture risk prediction result of the osteoporosis patient to be predicted based on the personalized factor data of the subject to be predicted, the multiple regression equation, and the osteoporosis fracture risk prediction equation. The method for establishing a finite element model of the lumbar spine in patients with osteoporosis is as follows: Bone mineral density samples were collected from the first and second lumbar vertebrae of osteoporosis patients to construct a three-dimensional mesh model from the first to the second lumbar vertebrae. The average bone density of the first and second lumbar vertebrae and the three-dimensional mesh model are input into the finite element simulation analysis software to construct the lumbar vertebra finite element model.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for predicting the risk of fracture in osteoporosis patients, which, when executed by a processor, implements the method for predicting the risk of fracture in osteoporosis patients according to any one of claims 1 to 5.

8. A computer device, characterized in that, The computer device includes a computer-readable storage medium, a processor, and a program for predicting the risk of fracture in osteoporosis patients stored in the computer-readable storage medium, wherein the program for predicting the risk of fracture in osteoporosis patients, when executed by the processor, implements the method for predicting the risk of fracture in osteoporosis patients according to any one of claims 1 to 5.

Images