WO2023193462A1 - 骨质疏松患者骨折风险的预测方法及预测装置 - Google Patents

骨质疏松患者骨折风险的预测方法及预测装置 Download PDF

Info

Publication number
WO2023193462A1
WO2023193462A1 PCT/CN2022/137713 CN2022137713W WO2023193462A1 WO 2023193462 A1 WO2023193462 A1 WO 2023193462A1 CN 2022137713 W CN2022137713 W CN 2022137713W WO 2023193462 A1 WO2023193462 A1 WO 2023193462A1
Authority
WO
WIPO (PCT)
Prior art keywords
osteoporosis
fracture risk
finite element
patients
element model
Prior art date
Application number
PCT/CN2022/137713
Other languages
English (en)
French (fr)
Inventor
白雪岭
姚治东
Original Assignee
深圳先进技术研究院
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳先进技术研究院 filed Critical 深圳先进技术研究院
Publication of WO2023193462A1 publication Critical patent/WO2023193462A1/zh

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
    • A61B5/4504—Bones
    • A61B5/4509—Bone density determination
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7271—Specific aspects of physiological measurement analysis
    • A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment

Definitions

  • the invention belongs to the field of electronic information technology, and specifically relates to a method and device for predicting fracture risk in patients with osteoporosis.
  • Osteoporosis affects approximately 200 million people worldwide, and its incidence ranks sixth among common diseases. Osteoporosis is particularly common among Asians and whites. The incidence rate among people over 40 years old in my country is 19.7%, and the male to female ratio is about 1:2.
  • the most serious complication caused by osteoporosis is fracture, which is a low-energy or non-violent fracture, also known as a fragility fracture. It refers to the minimum amount of trauma in life caused by standing or falling on a flat road. Leading to fractures of the spinal vertebrae, hip bones, proximal humerus or distal radius. Osteoporotic fractures can cause pain and severe disability. Generally speaking, the incidence of fractures in osteoporosis patients is about 20%. Among them, fractures of the spine and hip cause the highest mortality and disability rates, and The incidence rate increases with age.
  • Bone strength is an important reference index for detecting and evaluating osteoporosis.
  • this index can only be obtained by destructive testing methods, so it is difficult to directly evaluate the bone mechanical properties of patients with osteoporosis clinically.
  • bone density Bone density (Bone Mineral density (BMD) is closely related to bone strength and has the ability to diagnose osteoporosis and predict fracture risk.
  • the clinical examination method for diagnosing osteoporosis mainly relies on dual-energy X-ray absorptiometry (Dual-energy X-ray absorptiometry (DEXA) and quantitative CT (Quantitative computed tomography (QCT) to measure bone density.
  • DEXA dual-energy X-ray absorptiometry
  • QCT Quantitative computed tomography
  • DEXA is economical, simple, and has low radiation absorbed dose for patients. It was previously considered the "gold standard" for diagnosing osteoporosis.
  • DEXA uses two-dimensional imaging technology, and its measurement accuracy is not high. Its projection scanning method cannot analyze the three-dimensional spatial structure of bone and distinguish the changes in mineral density between bone cortex and bone trabeculae. It can only provide two-dimensional Area bone density information.
  • QCT provides three-dimensional images of bone structure and the spatial distribution of bone minerals, and is more sensitive and accurate to changes in bone mass than other methods.
  • the technical problem solved by this invention is: how to predict the fracture risk of osteoporosis patients more accurately.
  • a method for predicting fracture risk in patients with osteoporosis includes:
  • the material properties of the lumbar vertebra finite element model are set according to the bone density of the osteoporosis patient;
  • the fracture risk prediction result of the osteoporosis patient to be predicted is obtained according to the personalized factor data of the object to be predicted, the multiple regression equation and the osteoporosis fracture risk prediction equation.
  • the personalized factor data includes at least gender, age, weight, height, exercise data and smoking data.
  • the method for establishing the finite element model of the lumbar spine of patients with osteoporosis is:
  • the average value of the bone density of the first lumbar vertebra and the second lumbar vertebra and the three-dimensional grid model are input into the finite element simulation analysis software to construct a lumbar vertebra finite element model.
  • the threshold is 5000 ⁇
  • the ratio of the microstrain of the cancellous bone units in the vertebral body exceeding the threshold is: the ratio of the number of cancellous bone units whose microstrain exceeds the threshold to the total amount of cancellous bone units in the vertebral body.
  • the method of obtaining the fracture risk prediction result of the osteoporosis patient to be predicted based on the personalized data of the object to be predicted, the multiple regression equation and the osteoporosis fracture risk prediction equation includes:
  • the predicted bone density value is substituted into the constructed osteoporosis fracture risk prediction equation to obtain the fracture risk prediction result of the subject to be predicted.
  • the fracture risk prediction result is a fracture risk level.
  • the prediction device includes:
  • the bone density analysis unit is used to perform multiple regression analysis on the personalized factor data and bone density data of batches of osteoporosis patients to obtain a multiple regression equation between bone density and personalized factors;
  • the simulation unit is used to simulate and analyze the biomechanical changes of each lumbar vertebra finite element model when it is stressed in several daily scenarios, and obtain the proportion of the microstrain of the vertebral cancellous bone unit in each lumbar vertebra finite element model that exceeds the threshold;
  • the risk analysis unit is used to perform correlation analysis based on the proportion of the microstrain of the vertebral cancellous bone unit exceeding the threshold and the bone density corresponding to each lumbar vertebra finite element model, and construct an osteoporotic fracture risk prediction equation;
  • a risk prediction unit is configured to obtain the fracture risk prediction result of the osteoporosis patient to be predicted based on the personalized factor data of the object to be predicted, the multiple regression equation and the osteoporosis fracture risk prediction equation.
  • This application also provides a computer-readable storage medium that stores a program for predicting fracture risk in osteoporosis patients.
  • the program for predicting fracture risk in osteoporosis patients is executed by a processor, the above-mentioned steps are implemented. Methods for predicting fracture risk in patients with osteoporosis.
  • the application also provides a computer device, which computer device includes a computer-readable storage medium, a processor, and a program for predicting fracture risk of osteoporosis patients stored in the computer-readable storage medium, and the osteoporosis patient
  • the program for predicting the patient's fracture risk is executed by the processor, the above-mentioned method for predicting the fracture risk of the osteoporosis patient is implemented.
  • the invention discloses a method, prediction device, storage medium and equipment for predicting fracture risk in patients with osteoporosis. Compared with the existing technology, it has the following technical effects:
  • This method comprehensively considers the impact of personalized factors on bone density, which is beneficial to accurately assess the current fracture risk. At the same time, it can be predicted without using instrument measurement in practical applications, so it is also beneficial to long-term risk assessment.
  • Figure 1 is a flow chart of a method for predicting fracture risk in osteoporosis patients according to Embodiment 1 of the present invention
  • Figure 2 is a functional block diagram of a fracture risk prediction device for osteoporosis patients according to Embodiment 2 of the present invention
  • Figure 3 is a schematic diagram of computer equipment according to Embodiment 4 of the present invention.
  • the existing technology usually obtains the bone density of osteoporosis patients through direct measurement, and then predicts the risk of fracture, without considering other personalized factors.
  • the impact on bone density makes it impossible to accurately assess fracture risk in patients with osteoporosis.
  • This application discloses a method for predicting fracture risk in patients with osteoporosis, which mainly includes two parts. One is to establish a multiple regression equation between bone density and personalized factors through big data analysis methods, and the other is to establish a relationship with bone density through simulation analysis.
  • the density-related fracture risk prediction equation first combines the individual factors of the subject and the multiple regression equation to predict the bone density of the subject, and then combines the predicted bone density and the fracture risk prediction equation to predict fractures. risk.
  • This method comprehensively considers the impact of personalized factors on bone density, which is beneficial to accurately assess fracture risk. At the same time, it can be predicted without using instrument measurement in practical applications, so it is also beneficial to long-term risk assessment.
  • the method for predicting fracture risk in osteoporosis patients in Embodiment 1 includes the following steps:
  • Step S10 Perform multiple regression analysis on the personalized factor data and bone density data of batches of osteoporosis patients, and establish a multiple regression equation between bone density and personalized factors;
  • Step S20 Establish a lumbar vertebra finite element model for each osteoporosis patient.
  • the material properties of the lumbar vertebra finite element model are set according to the bone density of the osteoporosis patient;
  • Step S30 Simulate and analyze the biomechanical changes of each lumbar vertebra finite element model when it is stressed in several daily scenarios, and obtain the proportion of the microstrain of the vertebral cancellous bone unit in each lumbar vertebra finite element model that exceeds the threshold;
  • Step S40 Perform correlation analysis based on the proportion of the microstrain of the vertebral cancellous bone unit exceeding the threshold and the bone density corresponding to each lumbar vertebra finite element model to obtain an osteoporotic fracture risk prediction equation;
  • Step S50 Obtain the fracture risk prediction result of the osteoporosis patient to be predicted based on the personalized factor data of the object to be predicted, the multiple regression equation and the osteoporosis fracture risk prediction equation.
  • the personalized factor data at least includes gender, age, weight, height, exercise data and smoking data, and multiple regression analysis is performed on the personalized factor data and bone density data of batches of osteoporosis patients to establish Based on the multiple regression equation between bone density changes and personalized factors, the trend of bone density changes over time (age) of the subject to be predicted under each personalized factor data can be realized.
  • step S20 a batch of clinical osteoporosis patients are selected and QCT equipment is used to collect bone density.
  • the collection site is from the first lumbar vertebra to the second lumbar vertebra.
  • the average cancellous bone density of the first lumbar vertebra and the second lumbar vertebra is calculated.
  • the three-dimensional mesh model includes cortical bone, cancellous bone, ligament and other models.
  • the three-dimensional mesh model was input into the finite element simulation analysis software, and the material properties of the model were set based on the average bone density of cancellous bone to obtain a finite element model of the lumbar spine.
  • step S30 the force boundary conditions of the lumbar vertebra finite element model are set, that is, the force experienced by people in daily scenes is simulated on the model, and the biomechanical changes of each lumbar vertebra finite element model when it is stressed in several daily scenes are simulated and analyzed. , to obtain the proportion of the microstrain of the vertebral cancellous bone unit exceeding the threshold in each lumbar vertebra finite element model.
  • the threshold is 5000 ⁇
  • the ratio of the microstrain of the cancellous bone unit in the vertebral body exceeding the threshold is: the ratio of the number of cancellous bone units whose microstrain exceeds the threshold to the total amount of cancellous bone units in the vertebral body, where the cancellous bone unit in the vertebral body is The greater the proportion of bone unit microstrain exceeding the threshold, the greater the risk of fracture.
  • osteoporotic fracture risk prediction equation reflects The relationship between bone density and fracture risk.
  • the personalized factor data of the subject to be predicted is substituted into the multiple regression equation to obtain the predicted bone density value, and then the predicted bone density value is substituted into the osteoporotic fracture
  • the fracture risk prediction results of the object to be predicted are obtained.
  • the fracture risk prediction results obtained here can be prediction results of the current state or future prediction results.
  • the current age of the subject to be predicted is 45 years old.
  • the bone density at the age of 45 can be predicted, and then the current fracture risk can be predicted.
  • the age of the subject to be predicted can also be changed to 46 years old.
  • the bone density at the age of 46 can be predicted, and then the fracture risk one year later (at the age of 46) can be predicted.
  • the second embodiment also discloses a device for predicting fracture risk in patients with osteoporosis.
  • the prediction device includes a bone density analysis unit 100, a model construction unit 200, a simulation unit 300, a risk analysis unit 400 and Risk prediction unit 500.
  • the bone density analysis unit 100 is used to perform multiple regression analysis on the personalized factor data and bone density data of batches of osteoporosis patients to obtain a multiple regression equation between bone density and personalized factors;
  • the model building unit 200 is used to establish each bone density Finite element model of the lumbar vertebrae of patients with osteoporosis.
  • the material properties of the finite element model of the lumbar vertebrae are set according to the bone density of the patients with osteoporosis.
  • the simulation unit 300 is used to simulate and analyze when each lumbar vertebrae finite element model is stressed in several daily scenarios.
  • the biomechanical changes in each lumbar vertebra finite element model are used to obtain the proportion of the micro-strain of the vertebral cancellous bone unit exceeding the threshold value;
  • the risk analysis unit 400 is used to obtain the proportion of the micro-strain of the vertebral body cancellous bone unit exceeding the threshold value in each lumbar vertebra finite element model.
  • Correlation analysis is performed on the corresponding bone density to construct an osteoporosis fracture risk prediction equation;
  • the risk prediction unit 500 is used to obtain The prediction results of fracture risk in patients with osteoporosis are to be predicted.
  • the bone density analysis unit 100, the model construction unit 200, the simulation unit 300, the risk analysis unit 400 and the risk prediction unit 500 please refer to the relevant description of Embodiment 1 and will not be described again here.
  • Embodiment 3 also discloses a computer-readable storage medium.
  • the computer-readable storage medium stores a program for predicting the fracture risk of osteoporosis patients.
  • the program for predicting the fracture risk of osteoporosis patients is executed by a processor, the above-mentioned bone quality prediction program is implemented. Methods for predicting fracture risk in patients with rheumatoid arthritis.
  • Embodiment 4 also discloses a computer device.
  • 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 then runs it, forming a request processing device at the logical level.
  • one or more embodiments of this specification do not exclude other implementations, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each A logic unit can also be a hardware or logic device.
  • the computer-readable storage medium 11 stores a program for predicting the fracture risk of osteoporosis patients. When the program for predicting the fracture risk of osteoporosis patients is executed by the processor, the above-mentioned method for predicting the fracture risk of osteoporosis patients is implemented.
  • Computer-readable storage media includes permanent and non-transitory, removable and non-removable media and may be implemented by any method or technology to store information. Information may be computer-readable instructions, data structures, modules of programs, 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 memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage , magnetic tape cartridges, magnetic disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmission medium, can be used to store information that can be accessed by a computing device.
  • PRAM phase change memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • RAM random access memory
  • ROM read-only memory memory
  • EEPROM electrically era

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Analysis (AREA)
  • Software Systems (AREA)
  • Geometry (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computer Graphics (AREA)
  • Algebra (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)

Abstract

本发明公开了一种骨质疏松患者骨折风险的预测方法及预测装置。该预测方法包括：对批量骨质疏松患者的个性化因素数据和骨密度数据进行多元回归分析，建立多元回归方程；建立各个骨质疏松患者的腰椎有限元模型；仿真分析各个腰椎有限元模型在若干日常场景下受力时的生物力学变化，获得各个腰椎有限元模型中椎体松质骨单元微应变超过阈值的比例；根据椎体松质骨单元微应变超过阈值的比例、各个腰椎有限元模型对应的骨密度进行相关性分析，获得骨质疏松骨折风险预测方程；根据待预测对象的个性化因素数据、多元回归方程和骨质疏松骨折风险预测方程得到骨折风险评估结果。该方法考虑了个性化因素对骨密度的影响，有利于精确地进行骨折风险的预测。

Description

骨质疏松患者骨折风险的预测方法及预测装置 技术领域
本发明属于电子信息技术领域，具体地讲，涉及一种骨质疏松患者骨折风险的预测方法及预测装置。
 背景技术
骨质疏松在全球范围内有约2亿患者，而其发病率位列常见疾病的第六位。骨质疏松在亚洲人与白人中尤其普遍，我国40岁以上人群的发病率为19.7%，其中男女比例约为1:2。骨质疏松症导致的最严重的并发症是骨折，为低能量或非暴力骨折，也称为脆性骨折，指在生活中受到不超过站立或是走平路跌倒造成的最低限度的外伤即可导致脊柱椎体、髋骨、肱骨近端或桡骨远端等部位的骨折。骨质疏松性骨折可造成疼痛和重度伤残，一般而言骨折在骨质疏松患者中的发生率约为20%，其中以脊椎和髋部发生骨折造成的死亡率与病残率最高，且发病率会随年龄增加而提升。
骨强度是发现和评价骨质疏松重要的参考指标，但限于该指标只能由破坏性的检测方式获得，故临床上难以对骨质疏松患者的骨力学性能做出直接评估。而骨密度（Bone mineral density，BMD）与骨强度密切相关，具有诊断骨质疏松症及预测骨折风险的能力。目前临床上诊断骨质疏松的检查方法主要依靠双能X线吸收测量仪（Dual-energy X-ray absorptiometry，DEXA）和定量CT（Quantitative computed tomography，QCT）来测量骨密度。
通过DEXA及QCT等技术检测骨密度的方法诊断骨质疏松已广泛应用，DEXA经济、简便、病人放射线吸收剂量低，以往被认为是诊断骨质疏松的“金标准”。但DEXA应用二维影像技术，测量精确度不高，其投射性扫描的方式不能分析骨质的三维空间结构和区分在骨皮质与骨小梁之间矿物质密度变化，只能提供二维的面积骨密度信息。QCT提供了骨质结构的三维影像及骨矿物质的空间分布情况，相比其他方法对骨量的变化更为敏感和准确。
然而，很多因素可能导致骨折风险评估产生一定误差，测量骨密度时需考虑体重、性别、年龄、激素等因素可能带来的影响，以便更精确地评判骨骼状况。目前，对于骨质疏松症引起的远期骨折风险预测并无行之有效的临床手段。
 技术问题
本发明解决的技术问题是：如何更加精准地预测骨质疏松患者的骨折风险。
 技术解决方案
本发明所采用的技术方案
一种骨质疏松患者骨折风险的预测方法，所述预测方法包括：
对批量骨质疏松患者的个性化因素数据和骨密度数据进行多元回归分析，建立骨密度变化与个性化因素之间的多元回归方程；
建立各个骨质疏松患者的腰椎有限元模型，所述腰椎有限元模型的材料特性根据骨质疏松患者的骨密度进行设置；
仿真分析各个腰椎有限元模型在若干日常场景下受力时的生物力学变化，获得各个腰椎有限元模型中椎体松质骨单元微应变超过阈值的比例；
根据椎体松质骨单元微应变超过阈值的比例、各个腰椎有限元模型对应的骨密度进行相关性分析，获得骨质疏松骨折风险预测方程；
根据待预测对象的个性化因素数据、所述多元回归方程和所述骨质疏松骨折风险预测方程得到待预测骨质疏松患者的骨折风险预测结果。
优选地，所述个性化因素数据至少包括性别、年龄、体重、身高、运动数据和吸烟数据。
优选地，建立骨质疏松患者的腰椎有限元模型的方法为：
采集骨质疏松患者第一腰椎和第二腰椎的骨密度，构建第一腰椎至第二腰椎的三维网格模型；
将所述第一腰椎和第二腰椎的骨密度的平均值、所述三维网格模型输入到有限元仿真分析软件，构建得到腰椎有限元模型。
优选地，所述阈值为5000με，椎体松质骨单元微应变超过阈值的比例为：微应变超过阈值的松质骨单元的数量与椎体的松质骨单元总量的比值。
优选地，根据待预测对象的个性化数据、所述多元回归方程和所述骨质疏松骨折风险预测方程得到待预测骨质疏松患者的骨折风险预测结果的方法包括：
将待预测对象的个性化因素数据代入到已构建的所述多元回归方程中，得到骨密度预测值；
将所述骨密度预测值代入到已构建的所述骨质疏松骨折风险预测方程中，得到待预测对象的骨折风险预测结果。
优选地，所述骨折风险预测结果为骨折风险等级。
本申请还公开了一种骨质疏松患者骨折风险的预测装置，所述预测装置包括：
骨密度分析单元，用于对批量骨质疏松患者的个性化因素数据和骨密度数据进行多元回归分析，得到骨密度与个性化因素之间的多元回归方程；
模型构建单元，用于建立各个骨质疏松患者的腰椎有限元模型，所述腰椎有限元模型的材料特性根据骨质疏松患者的骨密度进行设置；
仿真模拟单元，用于仿真分析各个腰椎有限元模型在若干日常场景下受力时的生物力学变化，获得各个腰椎有限元模型中椎体松质骨单元微应变超过阈值的比例；
风险分析单元，用于根据椎体松质骨单元微应变超过阈值的比例、各个腰椎有限元模型对应的骨密度进行相关性分析，构建骨质疏松骨折风险预测方程；
风险预测单元，用于根据待预测对象的个性化因素数据、所述多元回归方程和所述骨质疏松骨折风险预测方程得到待预测骨质疏松患者的骨折风险预测结果。
本申请还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有骨质疏松患者骨折风险的预测程序，所述骨质疏松患者骨折风险的预测程序被处理器执行时实现上述的骨质疏松患者骨折风险的预测方法。
本申请还提供了一种计算机设备，所述计算机设备包括计算机可读存储介质、处理器和存储在所述计算机可读存储介质中的骨质疏松患者骨折风险的预测程序，所述骨质疏松患者骨折风险的预测程序被处理器执行时实现上述的骨质疏松患者骨折风险的预测方法。
 有益效果
本发明公开了一种骨质疏松患者骨折风险的预测方法、预测装置、存储介质和设备，相对于现有技术，具有如下技术效果：
该方法综合考虑了个性化因素对骨密度的影响，有利于精确地进行当前骨折风险的评估，同时在实际应用时无需采用仪器测量即可进行预测，因此也有利于进行远期的风险评估。
果值
 附图说明
图1为本发明的实施例一的骨质疏松患者骨折风险的预测方法的流程图；
图2为本发明的实施例二的骨质疏松患者骨折风险的预测装置的原理框图；
图3为本发明的实施例四的计算机设备示意图。
 本发明的实施方式
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
在详细描述本申请的各个实施例之前，首先简单描述本申请的发明构思：现有技术通常通过直接测量来获得骨质疏松患者的骨密度，进而预测骨折风险大小，并没有考虑其他个性化因素对骨密度的影响，因此也无法精确地进行骨质疏松患者骨折风险评估。本申请公开了一种骨质疏松患者骨折风险的预测方法，主要包括两部分，一是通过大数据分析方法建立骨密度与个性化因素之间的多元回归方程，二是通过仿真分析建立与骨密度关联的骨折风险预测方程，在实际应用时首先结合待测对象的个性化因素和多元回归方程来预测待测对象的骨密度，接着再结合预测到的骨密度和骨折风险预测方程来预测骨折风险。该方法综合考虑了个性化因素对骨密度的影响，有利于精确地进行骨折风险的评估，同时在实际应用时无需采用仪器测量即可进行预测，因此也有利于进行远期的风险评估。
具体地，如图1所示，本实施例一的骨质疏松患者骨折风险的预测方法包括如下步骤：
步骤S10：对批量骨质疏松患者的个性化因素数据和骨密度数据进行多元回归分析，建立骨密度与个性化因素之间的多元回归方程；
步骤S20：建立各个骨质疏松患者的腰椎有限元模型，腰椎有限元模型的材料特性根据骨质疏松患者的骨密度进行设置；
步骤S30：仿真分析各个腰椎有限元模型在若干日常场景下受力时的生物力学变化，获得各个腰椎有限元模型中椎体松质骨单元微应变超过阈值的比例；
步骤S40：根据椎体松质骨单元微应变超过阈值的比例、各个腰椎有限元模型对应的骨密度进行相关性分析，获得骨质疏松骨折风险预测方程；
步骤S50：根据待预测对象的个性化因素数据、多元回归方程和骨质疏松骨折风险预测方程得到待预测骨质疏松患者的骨折风险预测结果。
具体地，在步骤S10中，个性化因素数据至少包括性别、年龄、体重、身高、运动数据和吸烟数据，通过对批量骨质疏松患者的个性化因素数据和骨密度数据进行多元回归分析，建立骨密度变化与个性化因素之间的多元回归方程，基于该多元回归方程，可以实现待预测对象的骨密度在各个个性化因素数据下的随时间（年龄）变化的趋势。
进一步地，在步骤S20中，选取一批临床骨质疏松患者并采用QCT设备采集骨密度。采集部位为第一腰椎至第二腰椎，根据QCT设备采集到的各个像素的骨密度，计算第一腰椎和第二腰椎的松质骨骨密度平均值。构建骨质疏松患者的第一腰椎至第二腰椎的三维网格模型，三维网格模型包括皮质骨、松质骨、韧带等模型。将三维网格模型输入到有限元仿真分析软件，基于松质骨骨密度平均值对设置模型的材料特性，得到腰椎有限元模型。
进一步地，在步骤S30中，设置腰椎有限元模型的力边界条件，即在模型上模拟人在日常场景的受力，仿真分析各个腰椎有限元模型在若干日常场景下受力时的生物力学变化，获得各个腰椎有限元模型中椎体松质骨单元微应变超过阈值的比例。示例性地，阈值为5000με，椎体松质骨单元微应变超过阈值的比例为：微应变超过阈值的松质骨单元的数量与椎体的松质骨单元总量的比值，其中椎体松质骨单元微应变超过阈值的比例越大，意味着骨折风险越大。
进一步地，根据椎体松质骨单元微应变超过阈值的比例、各个腰椎有限元模型对应的骨密度进行相关性分析，获得骨质疏松骨折风险预测方程，该骨质疏松骨折风险预测方程反映了骨密度与骨折风险之间的关系。
在构建好多元回归方程和骨质疏松骨折风险预测方程之后，将待预测对象的个性化因素数据代入到多元回归方程中，得到骨密度预测值，接着将骨密度预测值代入到骨质疏松骨折风险预测方程中，得到待预测对象的骨折风险预测结果。需要说明的是，这里得到的骨折风险预测结果可以是当前状态的预测结果，也可以是未来的预测结果。例如待预测对象当前的年龄为45岁，在其他个性化因素确定的情况下，可以预测45岁时的骨密度，进而预测当前的骨折风险。还可以将待预测对象的年龄改为46岁，在保持其他因素不变的情况下，可以预测46岁时的骨密度，进而预测一年以后（46岁时）的骨折风险。类似地，还可以使得个性化因素数据中的任一种因素改变而保持其他因素不变，动态地预测骨密度变化，从而预测骨折风险的变化趋势。
本实施例二还公开了一种骨质疏松患者骨折风险的预测装置，如图2所示，该预测装置包括骨密度分析单元100、模型构建单元200、仿真模拟单元300、风险分析单元400和风险预测单元500。骨密度分析单元100用于对批量骨质疏松患者的个性化因素数据和骨密度数据进行多元回归分析，得到骨密度与个性化因素之间的多元回归方程；模型构建单元200用于建立各个骨质疏松患者的腰椎有限元模型，所述腰椎有限元模型的材料特性根据骨质疏松患者的骨密度进行设置；仿真模拟单元300用于仿真分析各个腰椎有限元模型在若干日常场景下受力时的生物力学变化，获得各个腰椎有限元模型中椎体松质骨单元微应变超过阈值的比例；风险分析单元400用于根据椎体松质骨单元微应变超过阈值的比例、各个腰椎有限元模型对应的骨密度进行相关性分析，构建骨质疏松骨折风险预测方程；风险预测单元500用于根据待预测对象的个性化因素数据、所述多元回归方程和所述骨质疏松骨折风险预测方程得到待预测骨质疏松患者的骨折风险预测结果。其中，骨密度分析单元100、模型构建单元200、仿真模拟单元300、风险分析单元400和风险预测单元500的具体工作过程参见实施例一的相关描述，在此不进行赘述。
实施例三还公开了一种计算机可读存储介质，计算机可读存储介质存储有骨质疏松患者骨折风险的预测程序，骨质疏松患者骨折风险的预测程序被处理器执行时实现上述的骨质疏松患者骨折风险的预测方法。
进一步地，实施例四还公开了一种计算机设备，在硬件层面，如图3所示，该计算机设备包括处理器12、内部总线13、网络接口14、计算机可读存储介质11。处理器12从计算机可读存储介质中读取对应的计算机程序然后运行，在逻辑层面上形成请求处理装置。当然，除了软件实现方式之外，本说明书一个或多个实施例并不排除其他实现方式，比如逻辑器件抑或软硬件结合的方式等等，也就是说以下处理流程的执行主体并不限定于各个逻辑单元，也可以是硬件或逻辑器件。计算机可读存储介质11上存储有骨质疏松患者骨折风险的预测程序，骨质疏松患者骨折风险的预测程序被处理器执行时实现上述的骨质疏松患者骨折风险的预测方法。
计算机可读存储介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机可读存储介质的例子包括，但不限于相变内存（PRAM）、静态随机存取存储器（SRAM）、动态随机存取存储器（DRAM）、其他类型的随机存取存储器（RAM）、只读存储器（ROM）、电可擦除可编程只读存储器（EEPROM）、快闪记忆体或其他内存技术、只读光盘只读存储器（CD-ROM）、数字多功能光盘（DVD）或其他光学存储、磁盒式磁带、磁盘存储、量子存储器、基于石墨烯的存储介质或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。
上面对本发明的具体实施方式进行了详细描述，虽然已表示和描述了一些实施例，但本领域技术人员应该理解，在不脱离由权利要求及其等同物限定其范围的本发明的原理和精神的情况下，可以对这些实施例进行修改和完善，这些修改和完善也应在本发明的保护范围内。

Claims (9)

  1. 一种骨质疏松患者骨折风险的预测方法，其特征在于，所述预测方法包括：
    对批量骨质疏松患者的个性化因素数据和骨密度数据进行多元回归分析，建立骨密度变化与个性化因素之间的多元回归方程；
    建立各个骨质疏松患者的腰椎有限元模型，所述腰椎有限元模型的材料特性根据骨质疏松患者的骨密度进行设置；
    仿真分析各个腰椎有限元模型在若干日常场景下受力时的生物力学变化，获得各个腰椎有限元模型中椎体松质骨单元微应变超过阈值的比例；
    根据椎体松质骨单元微应变超过阈值的比例、各个腰椎有限元模型对应的骨密度进行相关性分析，获得骨质疏松骨折风险预测方程；
    根据待预测对象的个性化因素数据、所述多元回归方程和所述骨质疏松骨折风险预测方程得到待预测骨质疏松患者的骨折风险预测结果。
  2. 根据权利要求1所述的骨质疏松患者骨折风险的预测方法，其特征在于，所述个性化因素数据至少包括性别、年龄、体重、身高、运动数据和吸烟数据。
  3. 根据权利要求2所述的骨质疏松患者骨折风险的预测方法，其特征在于，建立骨质疏松患者的腰椎有限元模型的方法为：
    采集骨质疏松患者第一腰椎和第二腰椎的骨密度，构建第一腰椎至第二腰椎的三维网格模型；
    将所述第一腰椎和第二腰椎的骨密度的平均值、所述三维网格模型输入到有限元仿真分析软件，构建得到腰椎有限元模型。
  4. 根据权利要求3所述的骨质疏松患者骨折风险的预测方法，其特征在于，所述阈值为5000με，椎体松质骨单元微应变超过阈值的比例为：微应变超过阈值的松质骨单元的数量与椎体的松质骨单元总量的比值。
  5. 根据权利要求1所述的骨质疏松患者骨折风险的预测方法，其特征在于，根据待预测对象的个性化数据、所述多元回归方程和所述骨质疏松骨折风险预测方程得到待预测骨质疏松患者的骨折风险预测结果的方法包括：
    将待预测对象的个性化因素数据代入到已构建的所述多元回归方程中，得到骨密度预测值；
    将所述骨密度预测值代入到已构建的所述骨质疏松骨折风险预测方程中，得到待预测对象的骨折风险预测结果。
  6. 根据权利要求5所述的骨质疏松患者骨折风险的预测方法，其特征在于，所述骨折风险预测结果为骨折风险等级。
  7. 一种骨质疏松患者骨折风险的预测装置，其特征在于，所述预测装置包括：
    骨密度分析单元，用于对批量骨质疏松患者的个性化因素数据和骨密度数据进行多元回归分析，得到骨密度与个性化因素之间的多元回归方程；
    模型构建单元，用于建立各个骨质疏松患者的腰椎有限元模型，所述腰椎有限元模型的材料特性根据骨质疏松患者的骨密度进行设置；
    仿真模拟单元，用于仿真分析各个腰椎有限元模型在若干日常场景下受力时的生物力学变化，获得各个腰椎有限元模型中椎体松质骨单元微应变超过阈值的比例；
    风险分析单元，用于根据椎体松质骨单元微应变超过阈值的比例、各个腰椎有限元模型对应的骨密度进行相关性分析，构建骨质疏松骨折风险预测方程；
    风险预测单元，用于根据待预测对象的个性化因素数据、所述多元回归方程和所述骨质疏松骨折风险预测方程得到待预测骨质疏松患者的骨折风险预测结果。
  8. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有骨质疏松患者骨折风险的预测程序，所述骨质疏松患者骨折风险的预测程序被处理器执行时实现权利要求1至6任一项所述的骨质疏松患者骨折风险的预测方法。
  9. 一种计算机设备，其特征在于，所述计算机设备包括计算机可读存储介质、处理器和存储在所述计算机可读存储介质中的骨质疏松患者骨折风险的预测程序，所述骨质疏松患者骨折风险的预测程序被处理器执行时实现权利要求1至6任一项所述的骨质疏松患者骨折风险的预测方法。
PCT/CN2022/137713 2022-04-08 2022-12-08 骨质疏松患者骨折风险的预测方法及预测装置 WO2023193462A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210368145.1 2022-04-08
CN202210368145.1A CN116936088A (zh) 2022-04-08 2022-04-08 骨质疏松患者骨折风险的预测方法及预测装置

Publications (1)

Publication Number Publication Date
WO2023193462A1 true WO2023193462A1 (zh) 2023-10-12

Family

ID=88243918

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/137713 WO2023193462A1 (zh) 2022-04-08 2022-12-08 骨质疏松患者骨折风险的预测方法及预测装置

Country Status (2)

Country Link
CN (1) CN116936088A (zh)
WO (1) WO2023193462A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5172695A (en) * 1990-09-10 1992-12-22 Cann Christopher E Method for improved prediction of bone fracture risk using bone mineral density in structural analysis
CN108305687A (zh) * 2017-12-21 2018-07-20 南京航空航天大学 一种快速诊断骨质疏松患者椎体承载能力的系统和方法
CN109256212A (zh) * 2018-08-17 2019-01-22 上海米因医疗器械科技有限公司 骨健康评估模型构建方法、装置、设备、介质及评估方法
CN113921140A (zh) * 2021-11-19 2022-01-11 中国中医科学院西苑医院 一种绝经后女性骨质疏松风险列线图预测系统及预测方法
CN114240848A (zh) * 2021-11-24 2022-03-25 慧影医疗科技(北京)股份有限公司 一种骨密度测量方法、系统、存储介质及电子设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5172695A (en) * 1990-09-10 1992-12-22 Cann Christopher E Method for improved prediction of bone fracture risk using bone mineral density in structural analysis
CN108305687A (zh) * 2017-12-21 2018-07-20 南京航空航天大学 一种快速诊断骨质疏松患者椎体承载能力的系统和方法
CN109256212A (zh) * 2018-08-17 2019-01-22 上海米因医疗器械科技有限公司 骨健康评估模型构建方法、装置、设备、介质及评估方法
CN113921140A (zh) * 2021-11-19 2022-01-11 中国中医科学院西苑医院 一种绝经后女性骨质疏松风险列线图预测系统及预测方法
CN114240848A (zh) * 2021-11-24 2022-03-25 慧影医疗科技(北京)股份有限公司 一种骨密度测量方法、系统、存储介质及电子设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZHU SHENG, ZHANG JIA: "The Application of Finite Element Model in Prediction And Evaluation of Osteoporotic Fracture", CHINESE JOURNAL OF BONE AND JOINT SURGERY, vol. 9, no. 3, 15 June 2016 (2016-06-15), pages 261 - 265, XP093097989, ISSN: 2095-9985, DOI: 10.3969/j.issn.2095-9958.2016.03-19 *

Also Published As

Publication number Publication date
CN116936088A (zh) 2023-10-24

Similar Documents

Publication Publication Date Title
Keaveny et al. Biomechanical Computed Tomography analysis (BCT) for clinical assessment of osteoporosis
Löffler et al. X-ray-based quantitative osteoporosis imaging at the spine
Johannesdottir et al. Fracture prediction by computed tomography and finite element analysis: current and future perspectives
Blake et al. An update on dual-energy x-ray absorptiometry
Engelke et al. FEA to measure bone strength: a review
Pauchard et al. Quality control for bone quality parameters affected by subject motion in high-resolution peripheral quantitative computed tomography
Schileo et al. Subject-specific finite element models implementing a maximum principal strain criterion are able to estimate failure risk and fracture location on human femurs tested in vitro
Giambini et al. The effect of quantitative computed tomography acquisition protocols on bone mineral density estimation
Gong et al. Relationships between femoral strength evaluated by nonlinear finite element analysis and BMD, material distribution and geometric morphology
Hsu et al. The assessment of trabecular bone parameters and cortical bone strength: a comparison of micro-CT and dental cone-beam CT
Hussein et al. The effect of intravertebral heterogeneity in microstructure on vertebral strength and failure patterns
Kim et al. Prediction of hand‐wrist maturation stages based on cervical vertebrae images using artificial intelligence
Langlais et al. Shear-wave elastography can evaluate annulus fibrosus alteration in adolescent scoliosis
Zymbal et al. Mediating effect of muscle on the relationship of physical activity and bone
Komeili et al. Correlation between a novel surface topography asymmetry analysis and radiographic data in scoliosis
EP3629902B1 (en) Systems and methods for patient specific modeling of the mechanical properties of bone
Michalski et al. The influence of reconstruction kernel on bone mineral and strength estimates using quantitative computed tomography and finite element analysis
Fleps et al. Finite element derived femoral strength is a better predictor of hip fracture risk than aBMD in the AGES Reykjavik study cohort
Yang et al. Association of incident hip fracture with the estimated femoral strength by finite element analysis of DXA scans in the Osteoporotic Fractures in Men (MrOS) study
US11202602B2 (en) Personalized assessment of bone health using imaging
Fleps et al. A review of CT-based fracture risk assessment with finite element modeling and machine learning
Czyz et al. The computed tomography-based fractal analysis of trabecular bone structure may help in detecting decreased quality of bone before urgent spinal procedures
Gulam et al. Bone mineral measurement of phalanges: comparison of radiographic absorptiometry and area dual X-ray absorptiometry
Jin et al. A novel mechanical parameter to quantify the microarchitecture effect on apparent modulus of trabecular bone: a computational analysis of ineffective bone mass
Muthuri et al. Associations between body mass index across adult life and hip shapes at age 60 to 64: evidence from the 1946 British birth cohort

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22936387

Country of ref document: EP

Kind code of ref document: A1