Analysis method and system for osteoporosis prevention strategy

Abstract

The invention discloses an osteoporosis prevention strategy analysis method and system, and belongs to the technical field of health data analys.The osteoporosis prevention strategy analysis method specifically comprises the steps that the bone mineral density of a user is measured and preprocessed, a T value is calculated and compared with a preset osteoporosis threshold value, and the osteoporosis condition is judged; for the osteoporosis user, risk self-evaluation is carried out, risk grades are divided, a personalized treatment scheme is formulated, and the effect is monitored; for non-osteoporosis users, a risk prediction model is established through an osteoporosis prediction algorithm, and risk scores are calculated and graded; formulating a prevention strategy according to the risk level, evaluating an effect and adjusting an algorithm and the strategy; according to the invention, accurate prevention and treatment of osteoporosis are realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of health data analysis, and specifically relates to an osteoporosis prevention strategy analysis method and system. Background Art

[0002] Osteoporosis is a systemic bone disease characterized by decreased bone mass, changes in bone microstructure and increased risk of fractures. The pathogenesis of osteoporosis involves multiple aspects, mainly including abnormal endocrine metabolism, decreased bone mass, destruction of bone microstructure and decreased bone biomechanical properties. At present, the prevention strategies for osteoporosis mainly include the following aspects: 1) Adjusting the dietary structure: Increasing the intake of calcium and vitamin D is the basic measure to prevent osteoporosis; 2) Physical exercise: Moderate exercise can stimulate bone growth and enhance bone strength and toughness; 3) Correcting bad living habits: Bad living habits such as smoking, excessive drinking, and staying up late for a long time will have a negative impact on bone health; 4) Regular physical examinations and bone density testing: Physical examinations can timely detect and deal with diseases or factors that may cause osteoporosis, while bone density testing can assess the health of bones and provide a basis for prevention and treatment; 5) Drug treatment: Use calcium, vitamin D, bisphosphonates, and estrogen receptor modulators, which can increase bone mass, improve bone microstructure, and reduce the risk of fractures.

[0003] For example, the Chinese patent with publication number CN118609847A discloses a community online intelligent analysis system based on health big data, including: information collection module, analysis module, level determination module, decision-making module and dynamic adjustment module; the information collection module is responsible for collecting health indicators, lifestyle and environmental data of community members, and obtaining historical data; the analysis module predicts the disease risk index, calculates the green coverage rate, and analyzes the influence coefficient of environmental factors on the risk index; the level determination module calculates the risk score level based on this; the decision-making module formulates the initial prevention strategy according to the risk level; the dynamic adjustment module monitors health indicators and environmental data in real time, and adjusts the initial prevention strategy according to real-time data. This technical solution improves the accuracy of community health risk assessment and the effectiveness of response measures through intelligent analysis and management, which helps to improve the health level and disease prevention ability of community members.

[0004] For example, a Chinese patent with publication number CN118737447A discloses a diabetes risk assessment system, including: a group data integration module, an individual risk dynamic assessment module, a disease progression path analysis module and a risk rating module. By constructing a group health database, analyzing the patient's lifestyle and blood sugar level data, and calculating the transition probability between health states, the diabetes risk assessment is made more personalized and accurate, which can effectively predict the development trend of the disease, identify key health turning points, and provide a scientific basis for medical intervention. By adjusting the weights of diabetes risk factors, a quantitative rating of diabetes risk is achieved, the accuracy and practicality of risk assessment are optimized, the pertinence and effectiveness of preventive measures are improved, and support for patient health management is enhanced, making diabetes prevention strategies more targeted, and effectively improving patient management efficiency and prevention effects.

[0005] The above existing technologies all have the following problems: lack of in-depth analysis and precise prevention of specific diseases, such as osteoporosis, and are general but not precise; more resources and computing power are required to support their operation, resulting in uneven resource allocation; and there are limitations on the scope of diseases. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention proposes an osteoporosis prevention strategy analysis method and system, which measures the user's bone density and performs preprocessing, and calculates the T value and compares it with the preset osteoporosis threshold to determine the osteoporosis condition; for users with osteoporosis, self-assessment of risk is performed and risk levels are divided, and personalized treatment plans are formulated and the effects are monitored; for users without osteoporosis, a risk prediction model is established through an osteoporosis prediction algorithm, and risk scores are calculated and divided into levels; prevention strategies are formulated according to risk levels, the effects are evaluated and the algorithms and strategies are adjusted; the present invention achieves precise prevention and treatment of osteoporosis.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for analyzing osteoporosis prevention strategies, comprising:

[0009] Step S1: measuring the bone density of the user, obtaining the bone density value, and performing preprocessing;

[0010] Step S2: Calculate the T value according to the preprocessed bone density value, and compare the obtained T value with the preset osteoporosis threshold to determine whether the user has osteoporosis;

[0011] Step S3: If the user is determined to have osteoporosis, a risk self-assessment is performed, and the user is classified into a user risk level according to the risk self-assessment result, and a treatment plan is formulated according to the user risk level. At the same time, the treatment effect is regularly monitored;

[0012] Step S4: If it is determined that the user does not have osteoporosis, an osteoporosis risk prediction model is established using an osteoporosis prediction algorithm, and the user's bone density value and pre-acquired user health data are input into the osteoporosis risk prediction model to calculate the osteoporosis risk score. At the same time, the osteoporosis risk level is divided according to the osteoporosis risk score result;

[0013] Step S5: Formulate an osteoporosis prevention strategy based on the osteoporosis risk level. After implementing the osteoporosis prevention strategy, perform bone density testing on the user again to evaluate the effectiveness of the osteoporosis prevention strategy. Adjust the osteoporosis prediction algorithm parameters and the osteoporosis prevention strategy based on the evaluation results.

[0014] Specifically, the specific steps of step S4 include:

[0015] S4.1: Obtain the bone density value and the user health data from the user health file, integrate the bone density value and the user health data to generate the user bone density fusion data X = {x1,...,x N}, where x N Indicates the Nth bone density fusion data of the user, where N indicates the number of bone density fusion data of the user;

[0016] S4.2: Use the osteoporosis prediction algorithm to establish an osteoporosis risk prediction model, and use the pre-acquired historical user bone density fusion data to train the osteoporosis risk prediction model to obtain a pre-trained osteoporosis risk prediction model;

[0017] S4.3: X={x1,…,x N} Input the trained osteoporosis risk prediction model, and the osteoporosis risk prediction model outputs the user's osteoporosis risk score, the formula is:

[0018]

[0019] Among them, core represents the user's osteoporosis risk score, w i Indicates the contribution of the user's i-th bone density fusion data in the risk score, α i represents the adjustment factor of the user's i-th bone density fusion data, b represents the intercept, β j represents the jth correction factor, m represents the number of correction factors, and m∈[1,4], β1 is the age correction factor, β2 is the gender correction factor, β3 is the genetic factor correction factor, and β4 is the lifestyle correction factor;

[0020] S4.4: Set osteoporosis risk thresholds h1 and h2, and classify users into different osteoporosis risk levels according to the obtained osteoporosis risk scores;

[0021] If core≤h1, the osteoporosis risk belongs to the low risk interval, and level=1;

[0022] If h1<core≤h2, the osteoporosis risk belongs to the medium risk range, and level=2;

[0023] If core>h2, the osteoporosis risk belongs to the high risk interval, and level=3, where level=1 indicates that the osteoporosis risk level is low risk, level=2 indicates that the osteoporosis risk level is medium risk, and level=3 indicates that the osteoporosis risk level is high risk.

[0024] Specifically, the specific steps of S4.2 include:

[0025] S4.21: Obtain historical bone density values ​​and historical user health data, generate historical user bone density fusion data through integration, and perform feature extraction on the historical user bone density fusion data to obtain historical bone density feature data;

[0026] S4.22: Use historical bone density feature data as input and train with the random forest algorithm to obtain an initial osteoporosis risk prediction model, and evaluate the initial osteoporosis risk prediction model;

[0027] S4.23: Based on the evaluation results, the prediction performance of the initial osteoporosis risk prediction model is optimized by adjusting the parameters of the initial osteoporosis risk prediction model to obtain a trained osteoporosis risk prediction model.

[0028] Specifically, the specific steps of step S5 include:

[0029] S5.1: Obtain the osteoporosis risk level, formulate an osteoporosis prevention strategy based on the assessed osteoporosis risk level, and guide the user to implement the formulated osteoporosis prevention strategy;

[0030] S5.2: After the osteoporosis prevention strategy is implemented for a period of Δt, the user is again tested for bone density;

[0031] S5.3: Set a minimum error threshold h3, compare the bone density test results before and after the user implements the osteoporosis prevention strategy, and evaluate the effect of the osteoporosis prevention strategy;

[0032] If e=|g huan,1 -g huan,2 |≤h3, then the osteoporosis prevention strategy is ineffective;

[0033] If e=|g huan,1 -g huan,2|>h3, then the osteoporosis prevention strategy is effective, where e represents the bone density error before and after the user implements the osteoporosis prevention strategy, and g huan,1 Indicates the bone density value before the user implements the osteoporosis prevention strategy, g huan,2 Indicates the bone density value after the user implements the osteoporosis prevention strategy;

[0034] S5.4: Adjust the parameters of the osteoporosis prediction algorithm based on the effect evaluation results.

[0035] Specifically, the osteoporosis prevention strategy in step S5 includes diet adjustment, exercise training, lifestyle adjustment and drug treatment. The diet adjustment includes increasing the intake of foods rich in calcium and vitamin D; the exercise training includes aerobic exercise and muscle strengthening training; the lifestyle adjustment includes increasing exercise, improving diet, quitting smoking and limiting alcohol consumption.

[0036] Specifically, an osteoporosis prevention strategy analysis system includes: a data processing module, an osteoporosis judgment module, a risk level classification module, an osteoporosis risk prediction module, and a prevention strategy formulation module;

[0037] The data processing module is used to collect the user's bone density value and user health data and perform preprocessing;

[0038] The osteoporosis judgment module is used to judge whether the user is an osteoporosis patient by comparing the calculated T value with a preset osteoporosis threshold;

[0039] The risk level classification module is used to classify the risk level of users diagnosed with osteoporosis according to the risk self-assessment results and formulate a treatment plan;

[0040] The osteoporosis risk prediction module is used to obtain the osteoporosis risk level of a user who is not diagnosed as having osteoporosis through an osteoporosis risk prediction model;

[0041] The prevention strategy formulation module is used to formulate a personalized osteoporosis prevention strategy according to the user's osteoporosis risk level and evaluate the implementation effect of the osteoporosis prevention strategy.

[0042] Specifically, the osteoporosis judgment module includes: a T value calculation unit and an osteoporosis judgment unit;

[0043] The T value calculation unit is used to calculate the user's T value according to the preprocessed bone density value;

[0044] The osteoporosis judgment unit is used to compare the calculated T value with a preset osteoporosis threshold to judge whether the user is an osteoporosis patient.

[0045] Specifically, the osteoporosis risk prediction module includes: a model building unit, a risk score calculation unit, and an osteoporosis risk classification unit;

[0046] The model building unit is used to use the osteoporosis prediction algorithm to combine the user's bone density value and the user's health data to build an osteoporosis risk prediction model;

[0047] The risk score calculation unit is used to calculate the osteoporosis risk score according to the osteoporosis risk prediction model;

[0048] The osteoporosis risk classification unit is used to classify users into different osteoporosis risk levels according to the osteoporosis risk score results.

[0049] Specifically, the prevention strategy formulation module includes: a prevention strategy formulation unit, a prevention strategy execution unit, an effect evaluation unit, and a strategy adjustment unit;

[0050] The prevention strategy formulation unit is used to formulate a personalized prevention strategy according to the osteoporosis risk level of the user;

[0051] The prevention strategy execution unit is used to guide the user to execute the prevention strategy;

[0052] The effect evaluation unit is used to perform bone density testing on the user again after the prevention strategy is implemented to evaluate the effect of the prevention strategy;

[0053] The strategy adjustment unit is used to adjust the parameters of the osteoporosis prediction algorithm and the prevention strategy according to the effect evaluation result.

[0054] An electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of an osteoporosis prevention strategy analysis method when executing the computer program.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] 1. The present invention proposes an osteoporosis prevention strategy analysis system, and optimizes and improves the architecture, operation steps and processes. The system has the advantages of simple process, low investment and operation costs, and low production work costs.

[0057] 2. The present invention proposes an osteoporosis prevention strategy analysis method. For users who do not suffer from osteoporosis, the system uses an osteoporosis prediction algorithm to establish an osteoporosis risk prediction model, calculates a risk score based on the user's bone density value and health data, divides the risk level in advance, and formulates corresponding prevention strategies; by re-testing bone density to evaluate the prevention effect, the system can continuously optimize the prediction algorithm and prevention strategy to provide users with more effective osteoporosis prevention measures.

[0058] 3. The present invention proposes an osteoporosis prevention strategy analysis method, which can accurately determine whether the user suffers from osteoporosis through bone density measurement and T-value calculation, and provide personalized risk level classification and treatment plans for confirmed patients to achieve precision medicine. At the same time, the treatment effect is regularly monitored to ensure the effectiveness of the treatment and timely adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of an osteoporosis prevention strategy analysis method of the present invention;

[0060] Figure 2 This is a principle flow chart of an osteoporosis prevention strategy analysis method of the present invention;

[0061] Figure 3 A flowchart of osteoporosis risk level classification in an osteoporosis prevention strategy analysis method of the present invention;

[0062] Figure 4 This is an architecture diagram of an osteoporosis prevention strategy analysis system of the present invention. DETAILED DESCRIPTION

[0063] Example 1

[0064] See also Figure 1-Figure 3 , an embodiment provided by the present invention: a method for analyzing osteoporosis prevention strategies, comprising the following steps:

[0065] Step S1: measuring the bone density of the user, obtaining the bone density value, and performing preprocessing;

[0066] In the present invention, the dual-energy X-ray detection method is used to measure the bone density of the user, and the specific detection process includes:

[0067] (1) Body position: The patient needs to lie or sit on a special testing bed according to the requirements of the measurement site, so that part of the body is exposed under the scanner. For example, if the lumbar spine bone density is measured, the patient may need to lie on his side or prone; if the femoral neck bone density is measured, the patient may need to lie on his back and slightly raise his lower limbs;

[0068] (2) Scanning measurement: The scanner will emit X-rays, pass through body tissues and measure their absorption or reflection in bones. The patient needs to remain quiet and relaxed, avoid moving and breathing too deeply, so as not to affect the measurement results;

[0069] (3) After the measurement is completed, the doctor will interpret the bone density value based on the data output by the scanner and combined with factors such as the patient's age, gender, and weight, and judge the patient's bone health status. If the bone density value is low, it may be necessary to take measures such as calcium supplementation, increased exercise, and improved diet to increase bone density. If the bone density value is extremely low or there is a risk of fracture, further treatment and monitoring may be required.

[0070] Step S2: Calculate the T value according to the preprocessed bone density value, and compare the obtained T value with the preset osteoporosis threshold to determine whether the user has osteoporosis;

[0071] Furthermore, the specific steps of step S2 include:

[0072] S2.1: Obtain the pre-treated bone density value, compare the pre-treated bone density value with the average bone density of healthy young people of the same gender, and calculate the T value. The formula is:

[0073]

[0074] Among them, g huan Indicates the bone density value of the subject, g av represents the mean bone density of young people, g base represents the standard deviation of bone density in young people;

[0075] It should be noted that bone density values ​​are usually expressed as T value and Z value. The T value represents the degree of difference compared with the average bone density of healthy people of the same age, and the Z value represents the degree of difference compared with the average bone density of people of the same age, gender, and race. In the present invention, the T value representation method is selected.

[0076] It should be noted that the T value is a relative value that reflects the difference in bone density between the subject and young people. The T value is usually used clinically to determine whether the body's bone density is normal. It is also the most meaningful indicator for diagnosing primary osteoporosis.

[0077] S2.2: Set osteoporosis threshold;

[0078] If -1≤T<1, it means the user's bone density value is normal;

[0079] If -2.5<T<-1, it means that the bone mass is reduced, indicating bone loss;

[0080] If T≤-2.5, it means that the user has one or more fractures, indicating severe osteoporosis.

[0081] Step S3: If the user is determined to have osteoporosis, a risk self-assessment is performed, and the user is classified into a user risk level according to the risk self-assessment result, and a treatment plan is formulated according to the user risk level. At the same time, the treatment effect is regularly monitored;

[0082] Furthermore, the specific steps of step S3 include:

[0083] S3.1: Design a risk self-assessment questionnaire or scale that covers the patient's lifestyle, family medical history, previous fracture history, current health status, and medication. The lifestyle includes diet, exercise, smoking, and drinking.

[0084] S3.2: Patients fill out questionnaires or scales according to their own circumstances and complete self-assessment of risk. Based on the results of the self-assessment and combined with professional medical knowledge, patients are divided into different risk levels, such as low, medium and high risk. The risk level classification criteria should be based on comprehensive factors such as the severity of osteoporosis, fracture risk, patient age, gender, and physical condition;

[0085] S3.3: Develop a personalized treatment plan based on the patient's risk level, which includes drug therapy, such as anti-osteoporosis drugs, calcium supplements, and vitamin D; physical therapy, such as ultrasound therapy and magnetic therapy; and lifestyle adjustments, such as increasing exercise and improving diet;

[0086] S3.4: Develop a monitoring plan, including monitoring time and monitoring items, where monitoring items include bone density and bone metabolism markers;

[0087] S3.5: According to the monitoring plan, patients should be examined and evaluated regularly to understand the treatment effects, and treatment plans should be adjusted in a timely manner based on the monitoring results to ensure treatment effectiveness.

[0088] Step S4: If it is determined that the user does not have osteoporosis, an osteoporosis risk prediction model is established using an osteoporosis prediction algorithm, and the user's bone density value and pre-acquired user health data are input into the osteoporosis risk prediction model to calculate the osteoporosis risk score. At the same time, the osteoporosis risk level is divided according to the osteoporosis risk score result;

[0089] Step S5: Formulate an osteoporosis prevention strategy based on the osteoporosis risk level. After implementing the osteoporosis prevention strategy, perform bone density testing on the user again to evaluate the effectiveness of the osteoporosis prevention strategy. Adjust the osteoporosis prediction algorithm parameters and the osteoporosis prevention strategy based on the evaluation results.

[0090] The osteoporosis prevention strategies in S5 include dietary adjustment, physical exercise, lifestyle adjustment and drug treatment. The dietary adjustment includes increasing the intake of foods rich in calcium and vitamin D; the physical exercise includes aerobic exercise and muscle strengthening training; the lifestyle adjustment includes increasing exercise, improving diet, quitting smoking and limiting alcohol consumption.

[0091] The specific steps of step S4 include:

[0092] S4.1: Obtain the bone density value and the user health data from the user health file, integrate the bone density value and the user health data to generate the user bone density fusion data X = {x1,...,x N}, where x N Indicates the Nth bone density fusion data of the user, where N indicates the number of bone density fusion data of the user;

[0093] S4.2: Use the osteoporosis prediction algorithm to establish an osteoporosis risk prediction model, and use the pre-acquired historical user bone density fusion data to train the osteoporosis risk prediction model to obtain a pre-trained osteoporosis risk prediction model;

[0094] S4.3: X={x1,...,x N} Input the trained osteoporosis risk prediction model, and the osteoporosis risk prediction model outputs the user's osteoporosis risk score, the formula is:

[0095]

[0096] Among them, core represents the user's osteoporosis risk score, w i Indicates the contribution of the user's i-th bone density fusion data in the risk score, α i represents the adjustment factor of the user's i-th bone density fusion data, b represents the intercept, β j represents the jth correction factor, m represents the number of correction factors, and m∈[1,4], β1 is the age correction factor, β2 is the gender correction factor, β3 is the genetic factor correction factor, and β4 is the lifestyle correction factor;

[0097] Furthermore, the implementation process of the osteoporosis risk prediction model includes:

[0098] S4.31: Get X = {x1, ..., x N}, X={x1,…,x N}After the preprocessing layer of the osteoporosis risk prediction model, cleaning and standardization steps are performed to ensure data quality and consistency;

[0099] S4.32: The preprocessed data is fed into the algorithm core of the osteoporosis risk prediction model, where the algorithm uses the random forest algorithm;

[0100] S4.33: Random forest algorithm is based on X = {x1,…,x N} features, and performs complex calculations and analysis on the data through the weights and bias parameters learned during the training process;

[0101] S4.34: After the osteoporosis risk prediction model algorithm processes the input X={x1,...,x N}, a continuous osteoporosis risk score is output. This score is usually a value between 0 and 1, which is used to indicate the user's risk level of osteoporosis.

[0102] It should be noted that the higher the user's osteoporosis risk score, the greater the risk of osteoporosis. At the same time, doctors can develop personalized prevention and treatment plans based on the user's osteoporosis risk score and level, and users can also adjust their lifestyle and eating habits according to their risk score to reduce the risk of osteoporosis.

[0103] In summary, the osteoporosis risk prediction model receives the user's bone density fusion data as input, processes it through a complex algorithm, and finally outputs a continuous osteoporosis risk score. This score can help doctors and users better understand the risk level of osteoporosis and take corresponding preventive measures.

[0104] S4.4: Set osteoporosis risk thresholds h1 and h2, and classify users into different osteoporosis risk levels according to the obtained osteoporosis risk scores;

[0105] If core≤h1, the osteoporosis risk belongs to the low risk interval, and level=1;

[0106] If h1<core≤h2, the osteoporosis risk belongs to the medium risk range, and level=2;

[0107] If core>h2, the osteoporosis risk belongs to the high-risk interval, and level=3, among which, level=1 indicates that the osteoporosis risk level is low risk, that is, the probability of osteoporosis is very low, level=2 indicates that the osteoporosis risk level is medium risk, that is, the probability of osteoporosis is slightly higher than that of ordinary people, and level=3 indicates that the osteoporosis risk level is high risk, that is, the probability of osteoporosis is relatively high. In the present invention, h1=0.2, h2=0.8.

[0108] Among them, for each test sample, each decision tree in the random forest will give a prediction result, that is, the classification label. Then, these prediction results are voted and the classification label with the most votes is selected as the final prediction result.

[0109] The specific steps of S4.2 include:

[0110] S4.21: Obtain historical bone density values ​​and historical user health data, generate historical user bone density fusion data through integration, and perform feature extraction on the historical user bone density fusion data to obtain historical bone density feature data;

[0111] S4.22: taking the historical bone density characteristic data as input, combining it with the random forest algorithm for training, obtaining an initial osteoporosis risk prediction model, and evaluating the initial osteoporosis risk prediction model, wherein the random forest algorithm is the prior art content in this field, is not the inventive solution of the present application, and is not described in detail here;

[0112] Furthermore, the specific steps of obtaining the initial osteoporosis risk prediction model in S4.22 include:

[0113] (1) Obtain historical bone density characteristic data and perform preprocessing;

[0114] (2) dividing the preprocessed historical bone density characteristic data into 8:2 ratios;

[0115] (3) The random forest model was trained using the training set and the random forest algorithm, and the performance of the random forest model was optimized by adjusting the parameters of the random forest, such as the number of decision trees, the maximum depth, and the minimum number of samples, to obtain the initial osteoporosis risk prediction model.

[0116] S4.23: According to the evaluation results, the prediction performance of the initial osteoporosis risk prediction model is optimized by adjusting the initial osteoporosis risk prediction model parameters to obtain a trained osteoporosis risk prediction model. In the present invention, a grid search algorithm is used when adjusting the model parameters so that the optimized model should have higher accuracy, sensitivity and specificity, while maintaining low false positive and false negative rates. However, the grid search algorithm is a prior art in this field and is not an inventive solution of the present application, so it will not be described here. At the same time, after the optimization of the initial osteoporosis risk prediction model is completed, verification is required to ensure its effectiveness in practical applications. This usually includes evaluating the model using an independent verification data set and conducting pilot applications in actual scenarios. If the verification results meet expectations, the model can be deployed in a production environment to provide osteoporosis risk prediction services for clinicians and patients.

[0117] The specific steps of step S5 include:

[0118] S5.1: Obtain the osteoporosis risk level, formulate an osteoporosis prevention strategy based on the assessed osteoporosis risk level, and guide the user to implement the formulated osteoporosis prevention strategy;

[0119] S5.2: After the osteoporosis prevention strategy is implemented for a period of Δt, the user is again tested for bone density;

[0120] S5.3: Set a minimum error threshold h3, compare the bone density test results before and after the user implements the osteoporosis prevention strategy, and evaluate the effect of the osteoporosis prevention strategy;

[0121] If e=|g huan,1 -g huan,2 |≤h3, then the osteoporosis prevention strategy is ineffective;

[0122] If e=|g huan,1 -g huan,2 |>h3, then the osteoporosis prevention strategy is effective, where e represents the bone density error before and after the user implements the osteoporosis prevention strategy, and g huan,1 Indicates the bone density value before the user implements the osteoporosis prevention strategy, g huan,2 Indicates the bone density value after the user implements the osteoporosis prevention strategy;

[0123] S5.4: Adjust the parameters of the osteoporosis prediction algorithm based on the effect evaluation results.

[0124] Furthermore, the specific steps of S5.4 include:

[0125] S5.41: Use the test data set or validation data set to evaluate the effect of the osteoporosis prediction algorithm, where the evaluation index uses the accuracy index;

[0126] S5.42: Based on the evaluation results, determine whether the performance of the osteoporosis prediction algorithm meets the requirements and which parameters may need to be adjusted, including learning rate, number of iterations, regularization parameter, number of decision trees, maximum depth, and minimum number of samples;

[0127] S5.43: Develop a parameter adjustment strategy based on the evaluation results and algorithm characteristics. For example, if the accuracy is low, you can try to increase the number of iterations, adjust the learning rate, or increase the number of decision trees; if overfitting is serious, you can try to increase the regularization parameter or reduce the depth or number of decision trees;

[0128] S5.44: According to the adjustment strategy, adjust the parameters of the osteoporosis prediction algorithm one by one, and retrain the model after each adjustment, and use the test data set or validation data set to evaluate the effect. At the same time, record the evaluation results after each adjustment for comparison and analysis;

[0129] S5.45: Based on the results of multiple experiments, determine a set of optimal algorithm parameters, where this set of parameters should be able to achieve the best performance on the test data set or the validation data set;

[0130] S5.46: Retrain the model using the best parameters and perform a final optimization.

[0131] Example 2

[0132] See also Figure 4 Another embodiment provided by the present invention is an osteoporosis prevention strategy analysis system, comprising:

[0133] Data processing module, osteoporosis judgment module, risk level classification module, osteoporosis risk prediction module, prevention strategy formulation module;

[0134] The data processing module is used to collect the user's bone density value and user health data, and perform pre-processing to provide an accurate data basis for subsequent analysis and judgment;

[0135] The osteoporosis judgment module is used to judge whether the user is an osteoporosis patient by comparing the calculated T value with a preset osteoporosis threshold;

[0136] The risk level classification module is used to classify the risk level of users diagnosed with osteoporosis based on the risk self-assessment results and formulate treatment plans;

[0137] The osteoporosis risk prediction module is used to obtain the osteoporosis risk level of users who are not diagnosed as osteoporotic through the osteoporosis risk prediction model;

[0138] The prevention strategy formulation module is used to formulate a personalized osteoporosis prevention strategy based on the user's osteoporosis risk level and evaluate the implementation effect of the osteoporosis prevention strategy.

[0139] The data processing module includes: a bone density measurement unit and a preprocessing unit;

[0140] Bone density measurement unit, which measures the user's bone density using professional bone density measurement equipment to obtain the original bone density value;

[0141] The preprocessing unit is used to clean and standardize the collected bone density values ​​to ensure the accuracy and comparability of the data.

[0142] The osteoporosis judgment module includes: a T value calculation unit and an osteoporosis judgment unit;

[0143] A T value calculation unit, used to calculate the user's T value according to the preprocessed bone density value;

[0144] The osteoporosis judgment unit is used to compare the calculated T value with a preset osteoporosis threshold to determine whether the user is an osteoporosis patient.

[0145] The risk level classification module includes: risk self-assessment unit, risk level classification unit, treatment plan formulation unit, and effect monitoring unit;

[0146] The risk self-assessment unit is used to guide users to conduct risk self-assessment and collect risk self-assessment information;

[0147] The risk level classification unit is used to classify users into low risk, medium risk or high risk levels according to the risk self-assessment results;

[0148] A treatment plan formulation unit is used to formulate a personalized treatment plan based on the user's risk level;

[0149] The effect monitoring unit is used to regularly monitor the user's treatment effect and provide a basis for subsequent adjustments.

[0150] The osteoporosis risk prediction module includes: model building unit, risk score calculation unit, and osteoporosis risk classification unit;

[0151] A model building unit, used to use an osteoporosis prediction algorithm, combined with a user's bone density value and user health data, to build an osteoporosis risk prediction model;

[0152] A risk score calculation unit, used for calculating an osteoporosis risk score according to an osteoporosis risk prediction model;

[0153] The osteoporosis risk classification unit is used to classify users into different osteoporosis risk levels according to the osteoporosis risk score results.

[0154] The prevention strategy formulation module includes: prevention strategy formulation unit, prevention strategy execution unit, effect evaluation unit, and strategy adjustment unit;

[0155] A prevention strategy formulation unit, which is used to formulate personalized prevention strategies based on the user's osteoporosis risk level;

[0156] The prevention strategy execution unit is used to guide users to execute the prevention strategy and ensure the effective implementation of the strategy;

[0157] An effect evaluation unit, used to perform bone density testing on the user again after the prevention strategy has been implemented for a period of time, so as to evaluate the effect of the prevention strategy;

[0158] The strategy adjustment unit is used to adjust the parameters and prevention strategies of the osteoporosis prediction algorithm according to the effect evaluation results to improve the accuracy and effectiveness.

[0159] In the present invention, the osteoporosis prevention strategy analysis system can comprehensively and accurately analyze the osteoporosis risk of users, formulate personalized prevention and treatment strategies, and continuously optimize and adjust the strategies to improve the prevention and treatment effects of osteoporosis.

[0160] Example 3

[0161] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of an osteoporosis prevention strategy analysis method are implemented. For details, please refer to the above method embodiment, which will not be repeated here.

[0162] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention, and all of these are within the protection of the present invention.

[0163] If the disclosed technical solution involves personal information, the product using the disclosed technical solution has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the disclosed technical solution involves sensitive personal information, the product using the disclosed technical solution has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

Claims

1. A method for analyzing osteoporosis prevention strategies, characterized in that: include: Step S1: measuring the bone density of the user, obtaining the bone density value, and performing preprocessing; Step S2: Calculate the T value according to the preprocessed bone density value, and compare the obtained T value with the preset osteoporosis threshold to determine whether the user has osteoporosis; Step S3: If the user is determined to have osteoporosis, a risk self-assessment is performed, and the user is classified into a user risk level according to the risk self-assessment result, and a treatment plan is formulated according to the user risk level. At the same time, the treatment effect is regularly monitored; Step S4: If it is determined that the user does not have osteoporosis, an osteoporosis risk prediction model is established using an osteoporosis prediction algorithm, and the user's bone density value and pre-acquired user health data are input into the osteoporosis risk prediction model to calculate the osteoporosis risk score. At the same time, the osteoporosis risk level is divided according to the osteoporosis risk score result; Step S5: Formulate an osteoporosis prevention strategy based on the osteoporosis risk level. After implementing the osteoporosis prevention strategy, perform bone density testing on the user again to evaluate the effectiveness of the osteoporosis prevention strategy. Adjust the osteoporosis prediction algorithm parameters and the osteoporosis prevention strategy based on the evaluation results.

2. The osteoporosis prevention strategy analysis method according to claim 1, characterized in that: The specific steps of step S4 include: S4.1: Obtain the bone density value and the user health data from the user health file, integrate the bone density value and the user health data to generate the user bone density fusion data X = {x1,...,x N }, where x N Indicates the Nth bone density fusion data of the user, where N indicates the number of bone density fusion data of the user; S4.2: Use the osteoporosis prediction algorithm to establish an osteoporosis risk prediction model, and use the pre-acquired historical user bone density fusion data to train the osteoporosis risk prediction model to obtain a pre-trained osteoporosis risk prediction model; S4.3: X={x1,…,x N } Input the trained osteoporosis risk prediction model, and the osteoporosis risk prediction model outputs the user's osteoporosis risk score, the formula is: Among them, core represents the user's osteoporosis risk score, w i Indicates the contribution of the user's i-th bone density fusion data in the risk score, α i represents the adjustment factor of the user's i-th bone density fusion data, b represents the intercept, β j represents the jth correction factor, m represents the number of correction factors, and m∈[1,4], β1 is the age correction factor, β2 is the gender correction factor, β3 is the genetic factor correction factor, and β4 is the lifestyle correction factor; S4.4: Set osteoporosis risk thresholds h1 and h2, and classify users into different osteoporosis risk levels according to the obtained osteoporosis risk scores; If core≤h1, the osteoporosis risk belongs to the low risk range, and level=1; If h1<core≤h2, the osteoporosis risk belongs to the medium risk range, and level=2; If core>h2, the osteoporosis risk belongs to the high risk interval, and level=3, where level=1 indicates that the osteoporosis risk level is low risk, level=2 indicates that the osteoporosis risk level is medium risk, and level=3 indicates that the osteoporosis risk level is high risk.

3. The osteoporosis prevention strategy analysis method according to claim 2, characterized in that: The specific steps of S4.2 include: S4.21: Obtain historical bone density values ​​and historical user health data, generate historical user bone density fusion data through integration, and perform feature extraction on the historical user bone density fusion data to obtain historical bone density feature data; S4.22: Use historical bone density feature data as input and train with the random forest algorithm to obtain an initial osteoporosis risk prediction model, and evaluate the initial osteoporosis risk prediction model; S4.23: Based on the evaluation results, the prediction performance of the initial osteoporosis risk prediction model is optimized by adjusting the parameters of the initial osteoporosis risk prediction model to obtain a trained osteoporosis risk prediction model.

4. The osteoporosis prevention strategy analysis method according to claim 3, characterized in that: The specific steps of step S5 include: S5.1: Obtain the osteoporosis risk level, formulate an osteoporosis prevention strategy based on the assessed osteoporosis risk level, and guide the user to implement the formulated osteoporosis prevention strategy; S5.2: After the osteoporosis prevention strategy is implemented for a period of Δt, the user is again tested for bone density; S5.3: Set a minimum error threshold h3, compare the bone density test results before and after the user implements the osteoporosis prevention strategy, and evaluate the effect of the osteoporosis prevention strategy; If e=|g huan,1 -g huan,2 |≤h3, then the osteoporosis prevention strategy is ineffective; If e=|g huan,1 -g huan,2 |>h3, then the osteoporosis prevention strategy is effective, where e represents the bone density error before and after the user implements the osteoporosis prevention strategy, and g huan,1 Indicates the bone density value before the user implements the osteoporosis prevention strategy, g huan,2 Indicates the bone density value after the user implements the osteoporosis prevention strategy; S5.4: Adjust the parameters of the osteoporosis prediction algorithm based on the effect evaluation results.

5. The osteoporosis prevention strategy analysis method according to claim 4, characterized in that: The osteoporosis prevention strategy in step S5 includes diet adjustment, exercise training, lifestyle adjustment and drug treatment. The diet adjustment includes increasing the intake of foods rich in calcium and vitamin D; the exercise training includes aerobic exercise and muscle strengthening training; the lifestyle adjustment includes increasing exercise, improving diet, quitting smoking and limiting alcohol consumption.

6. An osteoporosis prevention strategy analysis system, which is used to implement an osteoporosis prevention strategy analysis method according to any one of claims 1 to 5, characterized in that: include: Data processing module, osteoporosis judgment module, risk level classification module, osteoporosis risk prediction module, prevention strategy formulation module; The data processing module is used to collect the user's bone density value and user health data and perform preprocessing; The osteoporosis judgment module is used to judge whether the user is an osteoporosis patient by comparing the calculated T value with a preset osteoporosis threshold; The risk level classification module is used to classify the risk level of users diagnosed with osteoporosis according to the risk self-assessment results and formulate a treatment plan; The osteoporosis risk prediction module is used to obtain the osteoporosis risk level of a user who is not diagnosed as having osteoporosis through an osteoporosis risk prediction model; The prevention strategy formulation module is used to formulate a personalized osteoporosis prevention strategy according to the user's osteoporosis risk level and evaluate the implementation effect of the osteoporosis prevention strategy.

7. The osteoporosis prevention strategy analysis system according to claim 6, characterized in that: The osteoporosis judgment module includes: a T value calculation unit and an osteoporosis judgment unit; The T value calculation unit is used to calculate the user's T value according to the preprocessed bone density value; The osteoporosis judgment unit is used to compare the calculated T value with a preset osteoporosis threshold to judge whether the user is an osteoporosis patient.

8. The osteoporosis prevention strategy analysis system according to claim 7, characterized in that: The osteoporosis risk prediction module includes: a model building unit, a risk score calculation unit, and an osteoporosis risk classification unit; The model building unit is used to use the osteoporosis prediction algorithm to combine the user's bone density value and the user's health data to build an osteoporosis risk prediction model; The risk score calculation unit is used to calculate the osteoporosis risk score according to the osteoporosis risk prediction model; The osteoporosis risk classification unit is used to classify users into different osteoporosis risk levels according to the osteoporosis risk score results.

9. The osteoporosis prevention strategy analysis system according to claim 8, characterized in that: The prevention strategy formulation module includes: a prevention strategy formulation unit, a prevention strategy execution unit, an effect evaluation unit, and a strategy adjustment unit; The prevention strategy formulation unit is used to formulate a personalized prevention strategy according to the osteoporosis risk level of the user; The prevention strategy execution unit is used to guide the user to execute the prevention strategy; The effect evaluation unit is used to perform bone density testing on the user again after the prevention strategy is implemented to evaluate the effect of the prevention strategy; The strategy adjustment unit is used to adjust the parameters of the osteoporosis prediction algorithm and the prevention strategy according to the effect evaluation result.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the osteoporosis prevention strategy analysis method according to any one of claims 1 to 5 are implemented.

Images