A Big Data-Based Method and System for Osteoporosis Risk Assessment

Abstract

This invention relates to the field of risk assessment technology, specifically to a big data-based method and system for osteoporosis risk assessment. The method includes the following steps: acquiring daily UVB intensity at various times and accumulating it with exposure duration to determine vitamin D synthesis conditions; statistically analyzing static work type and total exposure time to determine insufficient bone load stimulation; combining bone density decline to determine the risk of bone stress pathway degeneration; assessing whether annual weight changes disrupt bone support; and integrating the results to generate an osteoporosis risk level label. In this invention, by introducing the cumulative calculation of hourly UVB irradiation intensity and exposure time in an individual's residential area, it determines whether vitamin D synthesis meets the effective conditions required for bone metabolism. Combining static work behavior labels and total static work time, it identifies insufficient bone load conditions. Furthermore, it performs trend analysis on the decreasing changes in distal tibial bone density over consecutive weeks, achieving dynamic identification of bone stress pathway degeneration and improving the timeliness and reliability of risk assessment.

Description

Technical Field

[0001] This invention relates to the field of risk assessment technology, and in particular to a method and system for osteoporosis risk assessment based on big data. Background Technology

[0002] The field of risk assessment technology involves the quantitative or qualitative analysis and judgment of the probability of adverse events occurring in a specific object or system under given conditions. This field includes risk identification, risk quantification modeling, risk level classification, and the construction of assessment indicator systems, and is widely used in various industries such as healthcare, workplace safety, financial management, and environmental engineering. In healthcare, risk assessment often combines individual clinical parameters, physiological indicators, behavioral data, and past medical history, using statistical modeling or algorithmic tools to predict and assess the occurrence, development, and consequences of diseases, aiming to provide decision support for prevention, intervention, diagnosis, treatment, and resource allocation.

[0003] Osteoporosis risk assessment methods are used to evaluate an individual's likelihood of developing osteoporosis. These methods typically rely on multiple indicators, including bone mineral density (BMD), age, sex, weight, history of fractures, medication use history, and lifestyle. By constructing a risk prediction model, the probability of developing osteoporosis is estimated. Their primary use is for preclinical screening, classifying and categorizing the risk of different individuals to identify high-risk groups.

[0004] Traditional assessment methods fail to precisely quantify the actual intensity and duration of an individual's exposure to ultraviolet radiation, resulting in vitamin D synthesis levels often being roughly estimated based on lifestyle. The relationship between sedentary behavior and bone load has not been effectively quantified and integrated, making it impossible to promptly capture the risk of bone degeneration caused by prolonged low-load activities. In monitoring changes in bone mineral density, indicators are not linked to behavioral and environmental factors, making it difficult to form a trend-based early warning mechanism. When assessing weight factors, they are usually treated as static attributes, ignoring the potential perturbation effect of their changes over time on bone stability. This makes it difficult to identify high-risk conditions in their early stages, and risk grading lacks dynamic response and fine-grained judgment capabilities. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a big data-based method and system for osteoporosis risk assessment.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for osteoporosis risk assessment based on big data, comprising the following steps: S1: Obtain daily UVB irradiation intensity records for an individual's residential area, accumulate the UVB intensity at each hour with the corresponding exposure duration, compare it with the cumulative UVB irradiation baseline value required for bone metabolism, determine whether the daily exposure conditions constitute an effective exposure condition for vitamin D synthesis, and generate UV exposure deficiency information. S2: Based on the UV exposure deficiency information, obtain the daily recorded work activity type labels and corresponding durations of individuals, filter the static state labels, and determine whether there is insufficient bone load stimulation based on the total daily static time and static work type, and generate the identification result of static behavior-induced insufficient bone load. S3: Call the static behavior-induced bone load insufficiency identification results, calculate the bone density decrease value between two consecutive cycles, determine whether the decrease value exceeds the bone loss risk threshold, determine the bone stress pathway degeneration trend initiation state, and generate a bone stress pathway degeneration risk signal. S4: Based on the bone stress pathway degeneration risk signal, retrieve the weight sequence recorded by the target individual in the past two years, determine whether the annual weight change is greater than the bone stability interference threshold, identify the bone structure support state as disturbed, and obtain the weight change interference state identification result.

[0007] As a further aspect of the present invention, the missing ultraviolet exposure information includes the effective exposure time period of UVB radiation per day, the cumulative intensity value of UVB radiation, and the comparison results between the irradiation dose and the reference value of bone metabolism. The identification results of insufficient bone load induced by static behavior specifically include the duration of static work, the number of days of missing bone load stimulation, and the difference in the bone stress triggering benchmark. The bone stress pathway degeneration risk signal includes the bone density deceleration rate, the duration of the insufficient load state, and the level of bone deterioration trend. The identification results of the disturbance state of weight change specifically refer to the annual weight change amplitude value, the relationship level between weight change and bone density, and the disturbance indicator of bone support structure.

[0008] As a further aspect of the present invention, the step of obtaining the missing ultraviolet exposure information specifically comprises: S101: Obtain daily UVB irradiation intensity records for an individual's residential area, filter out hourly UVB intensity values ​​that match the activity time, calculate the sum of the products between the hourly UVB intensity and the corresponding exposure duration, and obtain the cumulative daily UVB irradiation dose information. S102: Based on the cumulative daily UVB irradiation dose information, according to the minimum ultraviolet dose benchmark value corresponding to the vitamin D synthesis effectiveness condition, the cumulative daily UVB irradiation dose and the dose benchmark value are calculated, and it is determined whether the difference is greater than zero, so as to obtain the vitamin D synthesis effectiveness judgment result. S103: Based on the results of the vitamin D synthesis effectiveness assessment, and in conjunction with the daily calendar date corresponding to the day sequence, encode the daily assessment value in the form of 0 or 1, and count the length of the cycle in which inefficient exposure occurs in consecutive days to generate UV exposure deficiency information.

[0009] As a further aspect of the present invention, the steps for obtaining the identification results of insufficient bone load induced by static behavior are specifically as follows: S201: Based on the UV exposure deficiency information, obtain the daily work activity type tags and corresponding durations of the individual, filter the static state work types, including office sitting posture, fixed standing and equipment monitoring, and calculate the daily duration of each static type to generate static work duration classification information. S202: Based on the static work duration classification information, extract the bone stimulation static tolerance threshold associated with the daily total static time and the work type label, call the threshold range of the work type, and calculate the daily bone stimulation offset value by combining the individual's age and bone density. S203: Based on the daily bone stimulation offset value, compare it with the bone load loss warning value. If the daily bone stimulation offset value is greater than the bone load loss warning value, record it as the bone stimulation loss trigger day. Calculate the cumulative number of trigger days on a weekly cycle, select periodic samples with consecutive trigger days exceeding the static bone load risk limit, and generate the static behavior-induced bone load insufficiency identification result.

[0010] As a further aspect of the present invention, the formula for calculating the daily bone stimulation offset value is specifically as follows: ; in, Indicates the first The daily duration of static jobs. Indicates the first The corresponding static tolerance threshold for bone stimulation for this type of task. Indicates the first The unit effect of a task in the bone load influences its weight. This represents the normalized value of an individual's age. This represents the normalized value of an individual's bone mineral density. This represents the daily bone stimulation offset value.

[0011] As a further aspect of the present invention, the step of obtaining the bone stress pathway degeneration risk signal specifically includes: S301: Call the static behavior-induced bone load insufficiency identification result, call the individual's distal tibial bone mineral density monitoring data in the same period, extract the corresponding bone mineral density measurement values ​​in two consecutive periods, calculate the difference between the measurement values ​​of the two periods in time order, and calculate the rate of change of bone mineral density per unit time to generate tibial bone mineral density deceleration rate information. S302: Based on the tibial bone density deceleration rate information, call the bone loss risk threshold, determine whether the deceleration rate is greater than the bone loss risk threshold, and if the condition is met, extract the number of days of static bone load loss state and calculate the bone reduction compliance index value. The formula for calculating the bone loss compliance index is as follows: ; in, This represents the normalized variation in bone mineral density of the distal tibia. Indicates the risk threshold for bone loss. This indicates the cumulative number of days of static bone load loss. Indicates the total duration of the evaluation period. This represents the normalized value of an individual's average daily calcium intake. This indicates the index value for compliance with bone loss criteria; S303: Based on the bone loss compliance index value, if the bone loss compliance index value exceeds the deviation warning standard value, it is determined that there is a degenerative trend in the bone stress transmission structure, and abnormal individuals are marked, statistically coded, and a record of abnormal bone stimulation pathway identification is established to generate a bone stress pathway degeneration risk signal.

[0012] As a further aspect of the present invention, the step of obtaining the weight change interference state identification result specifically includes: S401: Based on the bone stress pathway degeneration risk signal, retrieve the target individual's weight monitoring data for the past two years, extract the initial and final weight values ​​for each year, corresponding to the data recorded on the first and last days of the year, calculate the annual weight change range for each year in the two years, and generate annual weight change information. S402: Based on the annual weight change information, calculate the ratio of the annual weight change value to the weight value at the beginning of the year, obtain the annual relative change percentage, calculate the current weight fluctuation amplitude index, compare it with the bone stability interference threshold standard, if the fluctuation value is greater than the threshold, determine that the individual's bone support structure is disturbed, mark it as a risk exposure state, and generate a weight change interference state identification result.

[0013] As a further aspect of the present invention, the method further includes the following steps: S5: Call the information on missing ultraviolet exposure, risk signals of bone stress pathway degeneration, and identification results of weight change interference status, calculate the cumulative score of osteoporosis risk, perform interval classification judgment with the osteoporosis risk level division boundary value, assign a corresponding risk level label to each individual, and generate bone risk level identification results. The bone risk level identification results include risk level labels, composite risk group composition status, and level trigger condition configuration.

[0014] As a further aspect of the present invention, the steps for obtaining the bone risk level identification result are specifically as follows: S501: Call the information on missing ultraviolet exposure, risk signals of bone stress pathway degeneration, and identification results of weight change interference status, and combine them with the risk weight coefficient set according to the impact of each parameter on osteoporosis to perform weighted calculation and obtain the cumulative score of bone risk. S502: Based on the cumulative bone risk score, call the osteoporosis risk level division threshold range, determine the attribution of the cumulative score within each level range, determine the level position range number into which the score falls, bind the risk level label to the individual identification identifier, and generate the bone risk level identification result.

[0015] A big data-based osteoporosis risk assessment system, wherein the big data-based osteoporosis risk assessment system is used to implement the aforementioned big data-based osteoporosis risk assessment method, the system comprising: The UV deficiency analysis module obtains daily UVB irradiation intensity records for an individual's residential area, accumulates the UVB intensity at each hour with the corresponding exposure duration, compares it with the cumulative UVB irradiation baseline value required for bone metabolism, determines whether the daily exposure conditions constitute an effective exposure condition for vitamin D synthesis, and generates UV exposure deficiency information. The static impact analysis module, based on the UV exposure deficiency information, obtains the daily recorded work activity type labels and corresponding durations of individuals, filters the static state labels, and determines whether there is insufficient bone load stimulation based on the total daily static time and static work type, generating a static behavior-induced bone load insufficiency identification result. The bone degeneration analysis module calls the identification results of insufficient bone load induced by static behavior, calculates the decrease value of bone density between two consecutive cycles, determines whether the decrease value exceeds the risk threshold of bone loss, determines the initiation state of the bone stress pathway degeneration trend, and generates a bone stress pathway degeneration risk signal. The weight disturbance identification module retrieves the weight sequence of the target individual in the past two years based on the bone stress pathway degeneration risk signal, determines whether the annual weight change is greater than the bone stability disturbance threshold, identifies the bone structure support state as disturbed, and obtains the weight change disturbance state identification result. The bone risk classification module calls upon the information on missing ultraviolet exposure, risk signals of bone stress pathway degeneration, and identification results of weight change interference status to calculate the cumulative score of osteoporosis risk. It then performs interval classification judgment against the osteoporosis risk level classification boundary value, assigns a corresponding risk level label to each individual, and generates bone risk level identification results.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In this invention, by introducing the cumulative calculation of hourly UVB irradiation intensity and exposure duration in an individual's residential area, it is determined whether vitamin D synthesis has reached the effective exposure conditions required for bone metabolism. By combining the static work behavior label with the total static work time to compare with the bone load stimulation threshold, insufficient bone load can be identified. Trend analysis of the decreasing changes in distal tibial bone density over consecutive weeks is performed to achieve dynamic identification of bone stress pathway degradation. By comparing the annual variation in weight sequence with the bone stability interference threshold, the potential interference of weight changes on bone structure stability can be revealed. Based on multiple physiological and environmental influencing factors, risk level labels are assessed to accurately identify and provide early warning of osteoporosis trends, improving the timeliness and reliability of risk assessment. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the workflow of the present invention; Figure 2 This is a detailed flowchart of S1 of the present invention; Figure 3 This is a detailed flowchart of the S2 process of the present invention; Figure 4 This is a detailed flowchart of the S3 process of the present invention; Figure 5 This is a detailed flowchart of the S4 process of the present invention; Figure 6 This is a detailed flowchart of S5 of the present invention; Figure 7 This is a system flowchart of the present invention. Detailed Implementation

[0019] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0020] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0021] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0022] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0023] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0024] Please see Figure 1 This invention provides a technical solution: a method for osteoporosis risk assessment based on big data, comprising the following steps: S1: Obtain daily UVB irradiation intensity records for individual residential areas, extract UVB intensity values ​​for each hour, accumulate the UVB intensity for each hour with the corresponding exposure duration, compare with the cumulative UVB irradiation baseline value required for bone metabolism, determine whether the daily exposure conditions constitute effective exposure conditions for vitamin D synthesis, and generate UV exposure deficiency information. Minimum light dose is the lowest dose standard for measuring the skin erythema reaction after UVB exposure. It is used to estimate the minimum amount of ultraviolet radiation required for vitamin D synthesis and is widely used in ultraviolet exposure assessment and bone health research. S2: Based on the information on missing ultraviolet exposure, obtain the daily work activity type labels and corresponding durations of individuals, filter the static state labels, sum up the time occupied by each type of static work label, compare the total daily static time and static work type with the static tolerance threshold of bone stimulation, determine whether there is insufficient bone load stimulation, and generate the identification result of static behavior-induced insufficient bone load. S3: Call the results of static behavior-induced insufficient bone load identification, match the bone mineral density value of the distal tibia in the same period, calculate the bone mineral density decrease value between two consecutive periods, determine whether the decrease value exceeds the bone loss risk threshold, if the decrease rate meets the condition and the duration of the bone load deficiency state exceeds the target period, it is determined to be the start state of bone stress pathway degradation trend, and generate a bone stress pathway degradation risk signal. Distal tibial bone mineral density is a standard indicator for monitoring the bone mineral density of weight-bearing bones. It is often used to assess density changes caused by insufficient bone load. The bone loss risk threshold is a commonly used clinical standard for bone mineral density loss alarm threshold, which represents the critical deceleration rate at which the risk of fracture increases rapidly. S4: Based on the risk signal of bone stress pathway degeneration, retrieve the weight sequence recorded by the target individual in the past two years, obtain the annual weight change range, and determine whether the annual weight change range is greater than the bone stability interference threshold. If the condition is met, the bone structure support state is marked as disturbed, and the weight change interference state identification result is obtained. S5: Call the information on missing ultraviolet exposure, risk signals of bone stress pathway degeneration, and the identification results of interference from weight changes. Calculate the cumulative score of osteoporosis risk based on the corresponding weight of each item, and perform interval classification judgment with the osteoporosis risk level division boundary value. Assign a corresponding risk level label to each individual and generate bone risk level identification results. Missing UV exposure information includes the effective daily UVB radiation exposure period, cumulative UVB radiation intensity, and comparison results between the radiation dose and bone metabolism reference values. The identification results of static behavior-induced bone underloading specifically include the duration of static work, the number of days without bone load stimulation, and the difference in bone stress triggering benchmarks. Bone stress pathway degradation risk signals include bone density deceleration rate, duration of underloading state, and bone decline trend level. The identification results of weight change disturbance state specifically refer to the annual weight change amplitude, the relationship level between weight change and bone density, and the bone support structure disturbance indicator. The bone risk level identification results include risk level labels, composite risk group composition status, and level triggering condition configuration.

[0025] Please see Figure 2 The specific steps for obtaining missing information on ultraviolet exposure are as follows: S101: Obtain daily UVB irradiation intensity records for an individual's residential area, filter out hourly UVB intensity values ​​that match the activity time, calculate the sum of the products between the hourly UVB intensity and the corresponding exposure duration, and obtain the cumulative daily UVB irradiation dose information. Daily UVB radiation intensity records for an individual's residential area were obtained. Specifically, outdoor environmental monitoring equipment recorded on July 15, 2024, for an individual residing in Beijing, showed UVB radiation in the 290-320 nm wavelength range. This data was recorded hourly, and hourly UVB intensity values ​​matching the individual's midday outdoor walk between 12:00 and 13:00 were selected. Specifically, the UVB intensity value at 12:00 was found to be 1.5. The UVB intensity at 13:00 was 1.6. Then, the sum of the products of hourly UVB intensity and corresponding exposure duration for each time period is calculated. The exposure duration from 12:00 to 13:00 is 1 hour, or 3600 seconds. Therefore, the UVB radiation dose during this period is (1.5...). +1.6 ) / 2*3600 =5580 This is the cumulative UVB exposure dose information for this individual on July 15, 2024.

[0026] Table 1. UVB Hourly Intensity Record Table

[0027] As shown in Table 1, it displays UVB intensity monitoring records at certain times on specific dates, used to calculate the cumulative radiation dose during specific activity periods.

[0028] S102: Based on the cumulative dose information of daily UVB irradiation, according to the minimum ultraviolet dose benchmark value corresponding to the vitamin D synthesis effectiveness condition, the difference between the cumulative dose of daily UVB irradiation and the dose benchmark value is calculated, and it is determined whether the difference is greater than zero, so as to obtain the vitamin D synthesis effectiveness judgment result. Based on the cumulative daily UVB radiation dose information, specifically the 5580 obtained on July 15, 2024... The dose value was determined, and based on the minimum UV dose baseline corresponding to the conditions for vitamin D synthesis to take effect, the cumulative daily UVB irradiation dose was calculated by subtracting the dose baseline. This dose baseline was determined based on a multi-site UV irradiation experiment conducted on 1000 Asian skin-type subjects. The experiment recorded the lowest UVB dose at which serum 25-hydroxyvitamin D3 concentration began to rise significantly under different UVB doses. The dose values ​​of all subjects were statistically analyzed, and the 25th percentile was taken as the baseline value to ensure that the baseline value was applicable to most individuals. The calculated baseline value was 300. (Equivalent to 0.3 standard erythema dose), then the individual's daily cumulative UVB exposure dose was 5580. Compared with the baseline dose of 300 The difference is calculated to be 5580 - 300 = 5280. The difference was then determined to be greater than zero. Since 5280 > 0, the result of the vitamin D synthesis effectiveness assessment for that day was "effective".

[0029] S103: Based on the results of the vitamin D synthesis effectiveness assessment, combined with the daily calendar date and corresponding day sequence, the daily assessment value is encoded in the form of 0 or 1, and the length of the cycle in which inefficient exposure occurs in consecutive days is counted to generate UV exposure missing information. Based on the vitamin D synthesis effectiveness assessment result, i.e., the assessment result for July 15, 2024 is "effective", combined with the daily calendar date corresponding to the day sequence, for example, recording July 15, 2024 as the 196th day of the year, the daily assessment value is encoded in the form of 0 or 1, where "effective" is encoded as 1 and "ineffective" is encoded as 0. Therefore, the encoding value for the 196th day is 1. The length of the cycle ineffective exposure in consecutive days is counted. If in the subsequent records, the assessment result for 7 consecutive days from the 197th day to the 203rd day is "ineffective", and its encoding sequence is [0, 0, 0, 0, 0, 0, 0], then the system counts the length of this cycle in which 0 appears consecutively, and the count result is 7 days. This is an ineffective exposure cycle with a cycle length of 7. By identifying and counting the lengths of all such ineffective exposure cycles within an assessment cycle (e.g., 90 days), the ultraviolet exposure deficiency information is finally generated.

[0030] Please see Figure 3 The specific steps for obtaining the identification results of insufficient bone load induced by static behavior are as follows: S201: Based on missing UV exposure information, obtain the daily work activity type tags and corresponding durations of individuals, filter the static state work types, including office sitting posture, fixed standing and equipment monitoring, and calculate the daily duration for each static type to generate static work duration classification information. Based on missing UV exposure information, specifically multiple inefficient exposure cycles and their length records identified within a 90-day assessment period, we retrieved the activity type tags and corresponding durations recorded daily by the same individual via wearable devices or work logs within that assessment period. Specifically, we retrieved the individual's activity records for July 20, 2024 (the 201st day of the year). The records showed that the total activities for that day included 7.5 hours of "sitting office," 1 hour of "standing still" (meetings), 0.5 hours of "equipment monitoring," 0.8 hours of "walking," and 1 hour of "lunch." We then filtered out static work types, specifically "sitting office," "standing still," and "equipment monitoring," and calculated the corresponding duration for each static type for the day. The results showed that the duration of "sitting office" was 7.5 hours, "standing still" was 1 hour, and "equipment monitoring" was 0.5 hours. These data were combined to generate the static work duration classification information for that day.

[0031] S202: Based on the static work duration classification information, extract the bone stimulation static tolerance threshold associated with the daily total static time and the work type label, call the threshold range of the work type, and calculate the daily bone stimulation offset value by combining the individual's age and bone density. The specific formula for calculating the daily bone stimulation offset value is as follows: ; in, Indicates the first The daily duration of static-like tasks is based on data from individual daily task records. Indicates the first The static tolerance thresholds for bone stimulation corresponding to each type of task are set according to the standards of clinical bone metabolism behavior experiments. Indicates the first The weight of the unit effect of each type of task in the bone load is a constant value determined empirically. This represents the normalized value of an individual's age, calculated by dividing the actual age by the oldest age of the study subject. This represents the normalized value of an individual's bone mineral density, calculated as the ratio of actual bone mineral density to reference bone mineral density values ​​for sex and age groups. The data source is dual-energy X-ray absorptiometry (DEXA) measurements. This represents the daily bone stimulation offset value. The bone load loss warning value is set based on the daily bone stimulation offset value of the top 10% quantiles in the individual offset samples in the long-term bone loss study. It is used to identify individual behaviors that deviate abnormally from the bone stimulation input. Based on the classification information of static task duration, the bone stimulation static tolerance threshold associated with the total daily static task duration and task type label is extracted. Then, the threshold range for each task type is retrieved, and combined with individual age and bone mineral density, the following formula is used: ; Calculate and obtain the daily bone stimulation offset value; In the formula, Representing the daily bone stimulation offset value, it is a quantitative indicator that measures the degree of deviation from normal skeletal stimulation caused by daily static behavior. Indexes representing static job types, from 1 to (In this example) ), The symbol represents the summation of calculation results for all types of static tasks (office work, fixed standing, equipment monitoring), and the absolute value symbol is used. A logarithmic function is used to obtain the undirected deviation of the difference between the duration and the threshold. The square root function is used to represent the nonlinear effect of aging on the decline of skeletal adaptability. This reflects the regulatory role of basic bone mineral density on load-bearing capacity. The entire formula comprehensively assesses the risk of insufficient bone load stimulation caused by daily static behavior by integrating the over-threshold duration of different static tasks, the influence weight of task type, individual age, and bone mineral density status.

[0032] The advantage of the formula lies in the introduction of weighting coefficients. The study differentiated the effects of various static activities on bone load and considered age. and bone mineral density Two key physiological parameters were individually adjusted, allowing the assessment results to more accurately reflect the bone health risk of a specific individual under specific physiological conditions, rather than solely relying on the duration of the activity. The specific parameter acquisition and calculation process is as follows: Indicates the first The daily duration of static-like tasks, according to the records in S201, is as follows: [Data for the individual on July 20, 2024 is missing]. (Office sitting posture) = 7.5 hours (Standing still) = 1 hour (Equipment monitoring) = 0.5 hours. Indicates the first The static tolerance threshold for bone stimulation corresponding to each type of work is set based on a cohort study of 500 people who have been engaged in different static jobs for a long time. The study measured the relationship between the participants' daily static job duration and their median calcaneal bone mineral density, and set the 80th percentile value of the duration at which bone mineral density began to show a downward trend as the tolerance threshold. The specific values ​​are shown in the table below.

[0033] Table 2 Static Operation Parameters Table

[0034] Indicates the first The weight of the unit effect of the type of work on bone load is a constant value determined empirically. This weight is set based on biomechanical simulation experiments. The experiments simulate the stress on the tibia and femoral neck under different static postures. The "office sitting posture" is used as the benchmark (weight is 1.0). The relative stress values ​​of other postures are the corresponding weights, as shown in Table 2. This represents the normalized value of an individual's age. The individual's actual age is 45 years old, and the maximum age of the study subjects is set at 90 years old (based on the life expectancy statistics of the target population). . This represents the normalized bone mineral density value for an individual. The individual's L1-L4 lumbar spine bone mineral density value at the beginning of the assessment period, measured using dual-energy X-ray absorptiometry, was 1.050. According to the bone mineral density reference database, the mean reference bone mineral density for 45-year-old men in the same age group is 1.100. ,but .

[0035] Substitute the above parameter values ​​into the formula to calculate: ; The individual's daily bone stimulation offset value on July 20, 2024 was finally obtained. It is 0.4488.

[0036] S203: Based on the daily bone stimulation offset value, compare it with the bone load loss warning value. If the daily bone stimulation offset value is greater than the bone load loss warning value, it is recorded as the bone stimulation loss trigger day. The cumulative number of trigger days is counted on a weekly cycle. Periodic samples with consecutive trigger days exceeding the static bone load risk limit are selected to generate the static behavior-induced bone load insufficiency identification result. Based on the daily bone stimulation offset value, specifically the offset value calculated on July 20, 2024. Compared with the bone load loss warning value, this warning value was set based on a statistical analysis of daily bone stimulation offset values ​​from a long-term bone loss study cohort containing 2000 individuals. After sorting the sample data from low to high, the values ​​corresponding to the top 10% quantiles were taken as the warning value, calculated to be 0.40. If the daily bone stimulation offset value is greater than the bone load loss warning value, it is recorded as a bone stimulation loss trigger day. Since 0.4488 > 0.40, July 20, 2024, was recorded as the bone stimulation loss trigger day. The cumulative number of trigger days was calculated on a weekly cycle (Monday to Sunday), and a trigger date was set for a specific week. Within the period, the individual had 5 days recorded as trigger days. Subsequently, periodic samples with consecutive trigger days exceeding the static bone load risk threshold were screened. This threshold was determined by analyzing the behavioral data of individuals with significant bone density loss (annual decline rate exceeding 3%) in the 90 days prior to the onset of the decline, calculating the average number of bone stimulation loss trigger days per week, and setting the threshold at the 75th percentile value, resulting in a threshold of 4 days per week. Since the cumulative number of trigger days in this week was 5 days, exceeding the threshold of 4 days, this week was marked as a risk period sample. By identifying and summarizing such risk period samples within all assessment periods, the static behavior-induced bone load insufficiency identification results were generated.

[0037] Please see Figure 4 The specific steps for obtaining risk signals of bone stress pathway degeneration are as follows: S301: Call the results of static behavior-induced bone load insufficiency identification, call the individual's distal tibial bone mineral density monitoring data in the same observation period, extract the corresponding bone mineral density measurement values ​​in two consecutive periods, calculate the difference between the measurement values ​​of the two periods in chronological order, and calculate the rate of change of bone mineral density per unit time to generate tibial bone mineral density deceleration rate information. The system retrieves the results of static behavior-induced bone underloading identification, i.e., multiple risk period samples that have been identified, and retrieves the individual's distal tibial bone mineral density (TMD) monitoring data within the same observation period. This data is obtained periodically through high-resolution peripheral quantitative CT (HR-pQCT). The corresponding TMD values ​​from two consecutive periods are extracted. For example, the distal tibial TMD value measured at the beginning of the assessment period (April 1, 2024) is 350.0. The value was measured again at the end of the evaluation period (September 27, 2024), which was 6 months (180 days) later, and was 345.5. The difference between the measurements from the two periods is calculated in chronological order: 345.5 - 350.0 = -4.5. And calculate the rate of change of bone mineral density per unit time, i.e., (-4.5). ) / 180 days = -0.025 / day, thereby generating information on the rate of decrease in tibial bone mineral density.

[0038] S302: Based on the tibial bone density deceleration rate information, call the bone loss risk threshold to determine whether the deceleration rate is greater than the bone loss risk threshold. If the condition is met, extract the number of days of static bone load loss state and calculate the bone reduction compliance index value. The specific formula for calculating the bone loss compliance index value is as follows: ; in, This represents the normalized variation of bone mineral density in the distal tibia, calculated by dividing the difference between two consecutive periodic bone mineral density measurements by a reference bone mineral density value (obtained based on standard bone mineral density curves for gender and age group). The threshold for bone loss risk is represented by a ratio-based conversion of the daily allowable variation in bone mineral density, normalized to a reference bone mineral density. This represents the cumulative number of days of static bone load deficiency, derived from bone stimulation-triggered marker behavior analysis. This represents the total duration of the evaluation period, set as the number of consecutive days within a fixed period window. This represents the normalized value of an individual's average daily calcium intake, calculated by dividing the individual's total calcium intake by the recommended intake level. The value of the bone loss compliance index is used to measure the intensity of the degenerative trend of the bone stress system. The deviation warning standard value is the identification threshold value when the degree of bone loss and bone load imbalance reaches the risk state of structural deviation. It is set as the 75th percentile value of the distribution of bone loss compliance index values ​​in the statistical sample, and is used to identify the risk upper bound distribution sample group. Based on the tibial bone mineral density deceleration rate information, i.e. -0.025 / day, the bone loss risk threshold is called up, and it is determined whether the rate of decline exceeds the bone loss risk threshold. This threshold is set with reference to the clinical guidelines published by the International Osteoporosis Foundation (IOF). The guidelines state that an annual bone mineral density decline rate exceeding 2.5% is considered significant loss. This annual rate is converted to a daily rate and normalized based on a reference bone mineral density. The reference distal tibial bone mineral density for this individual's age group is set to 360. Therefore, the maximum allowable daily decrease is 360*(2.5% / 365) = 0.0247. Therefore, the danger threshold is set to -0.0247. / day, due to the actual deceleration rate of -0.025 If the absolute value of the number of days is greater than the threshold (i.e., |-0.025|>|-0.0247|), the condition is met. Therefore, the number of days of static bone load loss is extracted. Based on the results of S203, a total of 95 bone stimulation loss trigger days were identified within the 180-day evaluation period. The formula used is: ; The calculation yields the bone loss conformity index value; In the formula, This represents an index of conformity to bone loss, used to quantify the strength of the association between the trend of declining bone mineral density and resting behavioral imbalance. It is a normalized value of bone mineral density variation. It is a normalized risk threshold for bone loss; the ratio reflects how many times the rate of bone loss exceeds the risk benchmark. Some studies use the square root of the percentage of risky days to reflect the persistent impact of imbalanced behavior, among which... For risk days, Total number of days, logarithmic term This will affect the individual's calcium intake level. Taking it into consideration as a corrective factor, the logic of the entire formula lies in the severity of bone loss ( and The ratio is affected by the duration of the adverse behavior ( ) and nutritional support level ( The formula is beneficial because it does not view the rate of bone mineral density loss in isolation, but rather through the combined regulation of [various factors]. This item directly correlates it with quantifiable behavioral indicators (days of static bone load loss), and also through... This study introduces nutritional factors as moderating variables, making the assessment model more comprehensive and accurate. The specific parameter acquisition and calculation process is as follows: This represents the normalized variation in bone mineral density (BMD) of the distal tibia, calculated as the difference between two consecutive BMD measurements (-4.5). Divide by the reference bone mineral density value (360) ),Right now . The threshold for bone loss risk is defined as a ratio-based conversion of the upper limit of daily bone mineral density variation, normalized to a reference bone mineral density. . This represents the cumulative number of days in a static bone load loss state, derived from the bone stimulation triggering marker behavior analysis of S203, with a value of 95 days. This indicates the total duration of the evaluation period, which is set to the number of consecutive days within a fixed period window; in this example, it is 180 days. This represents the normalized value of an individual's average daily calcium intake. Based on a dietary survey questionnaire, the individual's average daily calcium intake during the assessment period was assessed at 800 mg. Referring to the "Chinese Dietary Reference Intakes," the recommended intake for their age group is 1000 mg / day. Substitute the above parameter values ​​into the formula to calculate: ; The final calculated value of the bone loss compliance index was obtained. It is 77.78.

[0039] S303: Based on the bone loss compliance index value, if the bone loss compliance index value exceeds the deviation warning standard value, it is determined that there is a degenerative trend in the bone stress transmission structure, and abnormal individuals are marked, statistically coded, and a record of abnormal bone stimulation pathway identification is established to generate a bone stress pathway degeneration risk signal. Based on the bone loss compliance index value, i.e., the calculated This was compared to a deviation warning standard value, which was set by analyzing a sample of 500 people already diagnosed with osteopenia. The index value is calculated, and the numerical distribution of the results is statistically analyzed. The 75th percentile value of this distribution is taken as the warning standard, which is calculated to be 65.0. If the bone loss compliance index value exceeds the deviation warning standard value, it is determined that there is a degenerative trend in the bone stress transmission structure. Since 77.78 > 65.0, the judgment is valid, and the individual is marked as an abnormal individual and statistically coded. For example, an identification code "SRP-01" for "abnormal bone stress path" is assigned to it. The identification code, individual ID, assessment period, index value 77.78 and other information are stored in the database to establish a bone stimulation path abnormal identification record. This record is the generated bone stress pathway degeneration risk signal.

[0040] Please see Figure 5 The specific steps for obtaining the results of weight change interference state identification are as follows: S401: Based on the risk signal of bone stress pathway degeneration, retrieve the target individual's weight monitoring data for the past two years, extract the initial and final weight values ​​for each year, corresponding to the data recorded on the first and last days of the year, calculate the annual weight change range for each year in the two years, and generate annual weight change information. Based on the bone stress pathway degeneration risk signal, specifically for individuals marked "SRP-01", the weight monitoring data of the target individual for the past two years is retrieved. The data comes from their annual physical examination reports. The initial and final weight values ​​for each year are extracted, corresponding to the data recorded on the first day (e.g., January 1st) and the last day (e.g., December 31st) of that year. Specifically, the initial weight for the first year (2023) is 76.0 kg, and the final weight is 78.5 kg; the initial weight for the second year (2024) is 78.5 kg, and the final weight is 82.0 kg. Then, the annual weight change for each year in the two years is calculated. The change for the first year is 78.5 - 76.0 = +2.5 kg, and the change for the second year is 82.0 - 78.5 = +3.5 kg, thus generating annual weight change information.

[0041] S402: Based on the annual weight change information, calculate the ratio of the annual weight change value to the weight value at the beginning of the year, obtain the annual relative change percentage, calculate the current weight fluctuation amplitude index, compare it with the bone stability interference threshold standard, if the fluctuation value is greater than the threshold, it is determined that the individual's bone support structure is disturbed, marked as a risk exposure state, and generate the weight change interference state identification result. Based on the annual weight change information, i.e., a change of +2.5kg in the first year and +3.5kg in the second year, calculate the ratio of the annual weight change to the initial weight to obtain the annual relative percentage change. The relative percentage change for the first year is (+2.5kg / 76.0kg)*100%≈+3.29%, and the relative percentage change for the second year is (+3.5kg / 78.5kg)*100%≈+4.46%. Then, calculate the current weight fluctuation index, which is the absolute value of the most recent year's relative percentage change. The threshold was set at 4.46%, and compared with the bone stability interference threshold standard. This threshold was set based on a retrospective analysis of weight change data of fracture patients and healthy controls over the past 5 years. The analysis found that individuals with an absolute annual weight change of more than 4% had an odds ratio (OddsRatio) of 2.1 for the risk of fragility fracture in the next two years. Therefore, the threshold was set at 4%. Since the fluctuation value of 4.46% is greater than the threshold of 4%, it was determined that the individual's bone support structure was disturbed by the rapid increase in weight, and he / she was marked as a risk exposure state, generating a weight change interference state identification result.

[0042] Please see Figure 6 The specific steps for obtaining the bone risk level identification results are as follows: S501: Call the results of UV exposure loss information, bone stress pathway degeneration risk signal and weight change interference status identification, and combine them with the risk weight coefficient set according to the impact of each parameter on osteoporosis to perform weighted calculation and obtain the cumulative bone risk score. The system retrieves information on missing UV exposure, risk signals for bone stress pathway degeneration, and identification results of interference from weight changes. First, these qualitative results are quantified and encoded. For missing UV exposure information, if there is any inefficient exposure period of 7 days or longer within the assessment period, it is recorded as 1; otherwise, it is 0. Since this condition exists for this individual, it is encoded as 1. For risk signals for bone stress pathway degeneration, it has been determined to exist, so it is encoded as 1. For identification results of interference from weight changes, it has been determined to exist, so it is encoded as 1. Then, a weighted calculation is performed based on the risk weight coefficients set for the impact of each parameter on osteoporosis. These weight coefficients were determined through two rounds of anonymous scoring by 10 orthopedic and endocrinology experts using the Delphi method. The experts assigned weights based on the strength of the pathophysiological correlation between each indicator and the occurrence of osteoporosis. The final average value was taken and normalized. The specific weights are shown in the table below.

[0043] Table 3 Bone Risk Weighting Coefficients

[0044] Then, a weighted calculation was performed, and the cumulative score of bone risk was calculated as follows: (UV exposure deficiency code * 0.25) + (bone stress pathway degeneration code * 0.50) + (weight change interference code * 0.25) = (1 * 0.25) + (1 * 0.50) + (1 * 0.25) = 1.0, resulting in a cumulative score of 1.0 for bone risk.

[0045] S502: Based on the cumulative bone risk score, call the osteoporosis risk level division threshold range, determine the classification of the cumulative score within each level range, determine the level position range number where the score falls, bind the risk level label to the individual identification identifier, and generate the bone risk level identification result. Based on the cumulative bone risk score of 1.0, the osteoporosis risk level classification threshold range is used. This range is based on the risk scoring calculation of a community cohort of 5,000 people, combined with their DXA bone mineral density measurement results (T-score). The optimal cut-off point is determined through ROC curve analysis, and the risk level is divided into three levels: low risk, medium risk, and high risk. The specific correspondence between the score value and the level range is as follows: the cumulative score value in the range [0, 0.30] is low risk (level 1), in the range (0.30, 0.70) is medium risk (level 2), and in the range (0.70, 1.00) is high risk (level 3). Then, the cumulative score value of 1.0 is assigned to each level range. The level range number where the score value of 1.0 falls is determined to be 3, which is the high risk level. Finally, the risk level label "high risk" is bound to the identification identifier (such as ID-001) of the individual's electronic health record to generate the individual's bone risk level identification result.

[0046] Please see Figure 7 A big data-based osteoporosis risk assessment system, used to execute the aforementioned big data-based osteoporosis risk assessment method, the system comprising: The UV deficiency analysis module obtains daily UVB irradiation intensity records for an individual's residential area, accumulates the UVB intensity at each hour with the corresponding exposure duration, compares it with the cumulative UVB irradiation baseline value required for bone metabolism, determines whether the daily exposure conditions constitute an effective exposure condition for vitamin D synthesis, and generates UV exposure deficiency information. The static impact analysis module, based on the information on missing ultraviolet exposure, obtains the daily recorded work activity type labels and corresponding durations of individuals, filters the static state labels, and determines whether there is insufficient bone load stimulation based on the total daily static time and static work type, generating the identification results of static behavior-induced insufficient bone load. The bone degeneration analysis module calls the results of static behavior-induced insufficient bone load identification, calculates the decrease in bone density between two consecutive cycles, determines whether the decrease value exceeds the risk threshold of bone loss, determines the initiation status of the bone stress pathway degeneration trend, and generates a bone stress pathway degeneration risk signal. The weight disturbance identification module retrieves the weight sequence recorded by the target individual in the past two years based on the bone stress pathway degeneration risk signal, determines whether the annual weight change is greater than the bone stability disturbance threshold, identifies the bone structure support state as disturbed, and obtains the weight change disturbance state identification result. The bone risk classification module calls upon information on missing ultraviolet exposure, risk signals of bone stress pathway degeneration, and identification results of interference from weight changes to calculate the cumulative score of osteoporosis risk. It then performs interval classification judgment against the osteoporosis risk level classification boundary value, assigns a corresponding risk level label to each individual, and generates bone risk level identification results.

[0047] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0048] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0049] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0050] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0051] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0052] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0053] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0054] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0055] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0056] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for osteoporosis risk assessment based on big data, characterized in that, Includes the following steps: S1: Obtain daily UVB irradiation intensity records for an individual's residential area, accumulate the UVB intensity at each hour with the corresponding exposure duration, compare it with the cumulative UVB irradiation baseline value required for bone metabolism, determine whether the daily exposure conditions constitute an effective exposure condition for vitamin D synthesis, and generate UV exposure deficiency information. S2: Based on the UV exposure deficiency information, obtain the daily recorded work activity type labels and corresponding durations of individuals, filter the static state labels, and determine whether there is insufficient bone load stimulation based on the total daily static time and static work type, and generate the identification result of static behavior-induced insufficient bone load. S3: Call the static behavior-induced bone load insufficiency identification results, calculate the bone density decrease value between two consecutive cycles, determine whether the decrease value exceeds the bone loss risk threshold, determine the bone stress pathway degeneration trend initiation state, and generate a bone stress pathway degeneration risk signal. S4: Based on the bone stress pathway degeneration risk signal, retrieve the weight sequence recorded by the target individual in the past two years, determine whether the annual weight change is greater than the bone stability interference threshold, identify the bone structure support state as disturbed, and obtain the weight change interference state identification result.

2. The osteoporosis risk assessment method based on big data according to claim 1, characterized in that, The missing UV exposure information includes the effective exposure time period of UVB radiation per day, the cumulative intensity value of UVB radiation, and the comparison results between the radiation dose and the bone metabolism reference value. The identification results of static behavior-induced bone underloading specifically include the duration of static work, the number of days of missing bone load stimulation, and the difference in the bone stress triggering benchmark. The bone stress pathway degradation risk signals include the bone density deceleration rate, the duration of underloading state, and the level of bone deterioration trend. The identification results of weight change disturbance state specifically refer to the annual weight change amplitude value, the relationship level between weight change and bone density, and the bone support structure disturbance indicator.

3. The osteoporosis risk assessment method based on big data according to claim 2, characterized in that, The specific steps for obtaining the missing ultraviolet exposure information are as follows: S101: Obtain daily UVB irradiation intensity records for an individual's residential area, filter out hourly UVB intensity values ​​that match the activity time, calculate the sum of the products between the hourly UVB intensity and the corresponding exposure duration, and obtain the cumulative daily UVB irradiation dose information. S102: Based on the cumulative daily UVB irradiation dose information, according to the minimum ultraviolet dose benchmark value corresponding to the vitamin D synthesis effectiveness condition, the cumulative daily UVB irradiation dose and the dose benchmark value are calculated, and it is determined whether the difference is greater than zero, so as to obtain the vitamin D synthesis effectiveness judgment result. S103: Based on the results of the vitamin D synthesis effectiveness assessment, and in conjunction with the daily calendar date corresponding to the day sequence, encode the daily assessment value in the form of 0 or 1, and count the length of the cycle in which inefficient exposure occurs in consecutive days to generate UV exposure deficiency information.

4. The osteoporosis risk assessment method based on big data according to claim 3, characterized in that, The specific steps for obtaining the identification results of insufficient bone load induced by static behavior are as follows: S201: Based on the UV exposure deficiency information, obtain the daily work activity type tags and corresponding durations of the individual, filter the static state work types, including office sitting posture, fixed standing and equipment monitoring, and calculate the daily duration of each static type to generate static work duration classification information. S202: Based on the static work duration classification information, extract the bone stimulation static tolerance threshold associated with the daily total static time and the work type label, call the threshold range of the work type, and calculate the daily bone stimulation offset value by combining the individual's age and bone density. S203: Based on the daily bone stimulation offset value, compare it with the bone load loss warning value. If the daily bone stimulation offset value is greater than the bone load loss warning value, record it as the bone stimulation loss trigger day. Calculate the cumulative number of trigger days on a weekly cycle, select periodic samples with consecutive trigger days exceeding the static bone load risk limit, and generate the static behavior-induced bone load insufficiency identification result.

5. The osteoporosis risk assessment method based on big data according to claim 4, characterized in that, The formula for calculating the daily bone stimulation offset value is as follows: ； in, Indicates the first The daily duration of static jobs. Indicates the first The corresponding static tolerance threshold for bone stimulation for this type of task. Indicates the first The unit effect of a task in the bone load influences its weight. This represents the normalized value of an individual's age. This represents the normalized value of an individual's bone mineral density. This represents the daily bone stimulation offset value.

6. The osteoporosis risk assessment method based on big data according to claim 5, characterized in that, The specific steps for obtaining the bone stress pathway degeneration risk signal are as follows: S301: Call the static behavior-induced bone load insufficiency identification result, call the individual's distal tibial bone mineral density monitoring data in the same period, extract the corresponding bone mineral density measurement values ​​in two consecutive periods, calculate the difference between the measurement values ​​of the two periods in time order, and calculate the rate of change of bone mineral density per unit time to generate tibial bone mineral density deceleration rate information. S302: Based on the tibial bone density deceleration rate information, call the bone loss risk threshold, determine whether the deceleration rate is greater than the bone loss risk threshold, and if the condition is met, extract the number of days of static bone load loss state and calculate the bone reduction compliance index value. The formula for calculating the bone loss compliance index is as follows: ； in, This represents the normalized variation in bone mineral density of the distal tibia. Indicates the risk threshold for bone loss. This indicates the cumulative number of days of static bone load loss. Indicates the total duration of the evaluation period. This represents the normalized value of an individual's average daily calcium intake. This indicates the index value for compliance with bone loss criteria; S303: Based on the bone loss compliance index value, if the bone loss compliance index value exceeds the deviation warning standard value, it is determined that there is a degenerative trend in the bone stress transmission structure, and abnormal individuals are marked, statistically coded, and a record of abnormal bone stimulation pathway identification is established to generate a bone stress pathway degeneration risk signal.

7. The osteoporosis risk assessment method based on big data according to claim 6, characterized in that, The specific steps for obtaining the weight change interference state identification result are as follows: S401: Based on the bone stress pathway degeneration risk signal, retrieve the target individual's weight monitoring data for the past two years, extract the initial and final weight values ​​for each year, corresponding to the data recorded on the first and last days of the year, calculate the annual weight change range for each year in the two years, and generate annual weight change information. S402: Based on the annual weight change information, calculate the ratio of the annual weight change value to the weight value at the beginning of the year, obtain the annual relative change percentage, calculate the current weight fluctuation amplitude index, compare it with the bone stability interference threshold standard, if the fluctuation value is greater than the threshold, determine that the individual's bone support structure is disturbed, mark it as a risk exposure state, and generate a weight change interference state identification result.

8. The osteoporosis risk assessment method based on big data according to claim 7, characterized in that, The method further includes the following steps: S5: Call the information on missing ultraviolet exposure, risk signals of bone stress pathway degeneration, and identification results of weight change interference status, calculate the cumulative score of osteoporosis risk, perform interval classification judgment with the osteoporosis risk level division boundary value, assign a corresponding risk level label to each individual, and generate bone risk level identification results. The bone risk level identification results include risk level labels, composite risk group composition status, and level trigger condition configuration.

9. The osteoporosis risk assessment method based on big data according to claim 8, characterized in that, The specific steps for obtaining the bone risk level identification results are as follows: S501: Call the information on missing ultraviolet exposure, risk signals of bone stress pathway degeneration, and identification results of weight change interference status, and combine them with the risk weight coefficient set according to the impact of each parameter on osteoporosis to perform weighted calculation and obtain the cumulative score of bone risk. S502: Based on the cumulative bone risk score, call the osteoporosis risk level division threshold range, determine the attribution of the cumulative score within each level range, determine the level position range number into which the score falls, bind the risk level label to the individual identification identifier, and generate the bone risk level identification result.

10. A big data-based osteoporosis risk assessment system, characterized in that, The system is used to implement the osteoporosis risk assessment method based on big data as described in any one of claims 1-9, and the system comprises: The UV deficiency analysis module obtains daily UVB irradiation intensity records for an individual's residential area, accumulates the UVB intensity at each hour with the corresponding exposure duration, compares it with the cumulative UVB irradiation baseline value required for bone metabolism, determines whether the daily exposure conditions constitute an effective exposure condition for vitamin D synthesis, and generates UV exposure deficiency information. The static impact analysis module, based on the UV exposure deficiency information, obtains the daily recorded work activity type labels and corresponding durations of individuals, filters the static state labels, and determines whether there is insufficient bone load stimulation based on the total daily static time and static work type, generating a static behavior-induced bone load insufficiency identification result. The bone degeneration analysis module calls the identification results of insufficient bone load induced by static behavior, calculates the decrease value of bone density between two consecutive cycles, determines whether the decrease value exceeds the risk threshold of bone loss, determines the initiation state of the bone stress pathway degeneration trend, and generates a bone stress pathway degeneration risk signal. The weight disturbance identification module retrieves the weight sequence of the target individual in the past two years based on the bone stress pathway degeneration risk signal, determines whether the annual weight change is greater than the bone stability disturbance threshold, identifies the bone structure support state as disturbed, and obtains the weight change disturbance state identification result. The bone risk classification module calls upon the information on missing ultraviolet exposure, risk signals of bone stress pathway degeneration, and identification results of weight change interference status to calculate the cumulative score of osteoporosis risk. It then performs interval classification judgment against the osteoporosis risk level classification boundary value, assigns a corresponding risk level label to each individual, and generates bone risk level identification results.

Images