Knee osteoarthritis traditional Chinese medicine treatment scheme optimization method based on big data analysis

Abstract

The invention relates to the technical field of medical informatics, in particular to a knee osteoarthritis traditional Chinese medicine treatment scheme optimization method based on big data analysis, and the method comprises the following steps: based on knee joint load distribution data, collecting knee joint shear stress data, monitoring cartilage stress gradient data, and calculating a stress peak value in a gait cycle; and obtaining a knee joint biomechanical load balance value. According to the method, by combining shear stress, cartilage stress gradient and gait cycle stress peak value calculation, individual biomechanical characteristics are accurately described, patellar tendon stretching and quadriceps femoris tendon displacement data are analyzed, the instantaneous elastic modulus is recognized, tendon adaptability adjustment measurement precision is improved, soft tissue elastic change is reflected, and by means of individualized stress characteristic data, the stability of the muscle tendon is improved. Abnormal data are eliminated, illness state analysis is optimized, the curative effect evaluation accuracy is improved, the rehabilitation training intensity is dynamically optimized according to the curative effect offset degree, the therapeutic scheme is more adaptive, and the curative effect predictability and the personalized level are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical informatics, and in particular to a method for optimizing a traditional Chinese medicine treatment plan for knee osteoarthritis based on big data analysis. Background Art

[0002] The technical field of medical informatics includes technologies for collecting, storing, managing, analyzing and applying medical-related information based on computers and data analysis technologies. The core content of this technical field includes electronic health records, medical image processing, clinical decision support, medical data mining and other directions to improve the efficiency and accuracy of medical data utilization. Medical informatics involves the collection and integration of patient health data, including medical history information, diagnostic results, treatment plans, etc., and combines statistical analysis, machine learning, natural language processing and other methods to extract medical knowledge and assist in decision-making. This technical field is widely used in disease diagnosis, treatment plan optimization, health management, telemedicine and other aspects, aiming to improve the accuracy and efficiency of medical services.

[0003] Among them, the method for optimizing the TCM treatment plan for knee osteoarthritis refers to a method of using large-scale medical data analysis technology to optimize the TCM treatment process for patients with knee osteoarthritis. The patent subject covers the collection of symptom data, TCM syndrome differentiation information, historical treatment plans and efficacy data of patients with knee osteoarthritis, and uses pattern recognition, data mining and statistical analysis to study the correlation between different treatment plans. By constructing a TCM treatment data set for knee osteoarthritis, matching analysis is performed on treatment plans for different types of patients, and optimization strategies for individualized treatment plans are explored.

[0004] In the optimization of TCM treatment plans for knee osteoarthritis, the existing technology has problems such as insufficient data collection dimensions, limited accuracy of individualized analysis, and insufficient dynamic adjustment capabilities of rehabilitation plans. Current data collection mainly relies on medical records, diagnostic information, and feedback on treatment effects, and fails to fully cover key biomechanical indicators such as joint load, shear stress, and tendon flexibility, resulting in a lack of refined data support for individual evaluation. Due to the lack of real-time biomechanical data analysis for individuals, the evaluation of disease progression mainly relies on historical data speculation, and it is difficult to accurately predict the trend of patients' condition changes, resulting in a lag in program matching. The adjustment of rehabilitation plans is mainly based on fixed cycles or doctors' experience judgments, rather than optimization based on patients' real-time biomechanical feedback, which affects the timeliness and pertinence of interventions. Due to limited data quality, abnormal data is difficult to effectively eliminate, further reducing the reliability of treatment plans. The efficacy evaluation method is single, and the trend of efficacy changes cannot be dynamically monitored in combination with biomechanical parameters, resulting in short-term efficacy fluctuations that are difficult to accurately identify, affecting the adjustment and optimization of subsequent treatment plans. The existing technology is insufficient in individualized data collection, disease prediction accuracy, and rehabilitation plan optimization, which limits the accuracy and adaptability of TCM treatment plans and affects the stability and continuous optimization capabilities of the overall treatment effect. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a method for optimizing the TCM treatment plan for knee osteoarthritis based on big data analysis.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: a method for optimizing a traditional Chinese medicine treatment plan for knee osteoarthritis based on big data analysis, comprising the following steps: S1: Based on the knee joint load distribution data, collect knee joint shear stress data, monitor cartilage force gradient data, calculate the peak force during the gait cycle, and obtain the knee joint biomechanical load balance value; S2: calling the knee joint biomechanical load balancing value, detecting the patellar tendon stretching data and the quadriceps tendon displacement data, identifying the instantaneous elastic modulus, screening the tendon flexibility recovery characteristic data, and obtaining the knee joint tendon flexibility change coefficient; S3: calling the knee tendon flexibility change coefficient, screening individualized knee joint force characteristic data, analyzing the joint force change rate in the differentiated time window, comparing the cartilage wear trend parameters, determining the shear force distribution change characteristics, eliminating abnormal data, and obtaining an individualized disease progression trend data set; S4: calling the individualized disease progression trend data set, analyzing the therapeutic effect change rate of the differentiated cycle, extracting the short-term therapeutic effect growth rate data, setting the therapeutic effect deviation threshold, judging the therapeutic effect change trend, and combining the expert feedback mechanism to obtain the individualized therapeutic effect deviation degree; S5: Based on the individualized efficacy deviation, optimize the rehabilitation training intensity distribution, combine expert experience to adjust the individualized rehabilitation training, and obtain an optimized individual treatment plan for knee osteoarthritis.

[0007] As a further scheme of the present invention, the knee joint biomechanical load balance value includes knee joint load distribution parameters, shear stress parameters, cartilage force gradient parameters and gait cycle force peak parameters, the knee joint tendon flexibility change coefficient includes patellar tendon stretching parameters, quadriceps tendon displacement parameters, instantaneous elastic modulus and tendon flexibility recovery characteristic parameters, the individualized disease progression trend data set includes knee joint force characteristic parameters, joint force change rate parameters, cartilage wear trend parameters and shear force distribution change characteristic parameters, the individualized efficacy deviation includes efficacy change rate, short-term efficacy growth rate data, efficacy deviation threshold and efficacy change trend, and the optimized individual treatment plan for knee osteoarthritis includes treatment intervention adjustment range, rehabilitation training intensity distribution and individualized rehabilitation training adjustment results.

[0008] As a further solution of the present invention, the step of obtaining the knee joint biomechanical load balance value is specifically as follows: S111: Based on the knee joint load distribution data, collect knee joint shear stress data, record the shear stress change trend during the gait cycle, screen the interval with large rate change, and obtain the key shear stress change interval; S112: calling the shear stress key change interval, combining the monitored cartilage force gradient data, calculating the force gradient change rate in the key interval, analyzing the gait phase force gradient distribution, and obtaining the force gradient dynamic change value; S113: Call the dynamic change value of the force gradient to identify the degree of force difference within the gait cycle, and analyze it in combination with the gait stability parameter using the formula: ; Obtain the biomechanical load balance value of the knee joint; in, Represents the biomechanical load balance value of the knee joint. Representative Cartilage force value at each moment, Representative Shear stress value at time Represents the dynamic change value of the force gradient, represents the gait stability parameter, is the total number of gait cycle data points.

[0009] As a further solution of the present invention, the step of obtaining the knee joint tendon flexibility variation coefficient is specifically as follows: S211: calling the knee joint biomechanical load balancing value, extracting patellar tendon stretching data and quadriceps tendon displacement data, analyzing the patellar tendon stretching degree and the corresponding displacement ratio of the quadriceps tendon, comparing the change amplitude under the differentiated load state, and obtaining the instantaneous elastic modulus; S212: Based on the instantaneous elastic modulus, analyzing the change trend at the differentiated time points, screening the characteristic data of tendon flexibility recovery, identifying the fluctuation range, and obtaining the tendon flexibility recovery trend; S213: calling the tendon flexibility recovery trend, analyzing the change rate of adjacent time points, normalizing the change value of each time period, and using the formula: ; Calculate and obtain the knee joint tendon flexibility variation coefficient; in, represents the coefficient of change of knee tendon flexibility, represents the tendon flexibility recovery value at the t-th time point, Represents the tendon flexibility recovery value at the previous time point, Represents the total number of time points, represents the mean value at the time point.

[0010] As a further solution of the present invention, the steps of obtaining the individualized disease progression trend data set are specifically: S311: calling the knee tendon flexibility variation coefficient, screening individualized knee joint force characteristic data, calculating the force balance coefficient of the joint differentiation area, and obtaining individualized knee joint force distribution data; S312: Based on the individualized knee joint force distribution data, analyze the joint force change rate in the differentiated time window, and analyze the force change degree in the differentiated time window, using the formula: ; Calculate the joint force fluctuation index, identify abnormal force fluctuation areas, and obtain individualized joint force dynamic change data; in, Represents the joint force fluctuation index, represents the joint force value in the jth time window, Represents the joint force value in the previous time window, represents the mean joint force in the time window, Represents the number of time windows; S313: According to the individualized joint force dynamic change data, the shear force distribution change characteristics are identified, abnormal areas are screened and abnormal force data are removed to obtain an individualized disease progression trend data set.

[0011] As a further solution of the present invention, the steps for obtaining the individualized therapeutic effect deviation degree are specifically as follows: S411: calling the individualized disease progression trend data set, extracting the therapeutic effect change rate, comparing the differentiated cycle data, screening the differentiated time periods, and obtaining the differentiated cycle therapeutic effect change rate; S412: Based on the differentiated periodic efficacy change rate, analyze the short-term growth rate change using the formula: ; Calculate the short-term efficacy growth rate data, compare it with the efficacy deviation threshold, and obtain the efficacy growth rate deviation ratio; in, Represents the short-term efficacy growth rate data, Represents the rate of change of efficacy in the xth time period, Represents the highest rate of change in efficacy in a short period of time. Represents the minimum rate of change in efficacy in the short term. represents the stability factor, Indicates the total number of time periods; S413: calling the therapeutic effect growth rate deviation ratio, determining the change trend of the corresponding threshold, identifying the change direction of the individualized therapeutic effect according to the deviation direction and amplitude, and obtaining the individualized therapeutic effect deviation degree.

[0012] As a further solution of the present invention, the steps for obtaining the optimized individual treatment plan for knee osteoarthritis are specifically as follows: S511: Based on the individualized efficacy deviation, the adjustment range of the treatment intervention is evaluated, individual physiological parameters, lesion area characteristic values, and efficacy data are called, and the change rate of the current treatment intervention on the individual is analyzed to obtain an adjustment range correction coefficient; S512: Calling the adjustment amplitude correction coefficient to optimize the rehabilitation training intensity distribution, using the formula: ; Calculate the optimized intensity distribution value, analyze the individual rehabilitation training suitability, and obtain the optimized training parameter weights; in, represents the optimized intensity distribution value, represents the training load, represents the training frequency, represents the training duration, Represents individual basic recovery ability, Represents the target recovery progress, are the factors affecting training load, frequency, and duration. The factors affecting individual basic recovery ability and target recovery progress; S513: Based on the optimized training parameter weights and combined with expert experience, individualized rehabilitation training is adjusted to adjust the dynamic training cycle, training mode, and training load balance to obtain an optimized individual treatment plan for knee osteoarthritis.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by collecting knee joint load distribution data, combined with the calculation of shear stress, cartilage force gradient and force peak value in the gait cycle, the biomechanical characteristics of individuals in different motion states can be accurately portrayed, and the patellar tendon stretch and quadriceps tendon displacement data are further analyzed to identify the instantaneous elastic modulus, so that the measurement of tendon adaptive adjustment is more accurate, and the elastic changes of knee joint soft tissues during rehabilitation can be effectively reflected. The individualized knee joint force characteristic data are used to compare the joint force change rate, cartilage wear trend and shear force distribution characteristics, and the data quality is optimized while eliminating abnormal data, so that the disease analysis is more targeted, the efficacy change rate of different cycles is analyzed, and the efficacy deviation threshold is set to improve the accuracy of short-term efficacy evaluation. According to the individualized efficacy deviation, the adjustment range of the treatment intervention method is accurately calculated, and the rehabilitation training intensity is dynamically optimized, so that the rehabilitation plan is more in line with individual needs, and the overall rehabilitation effect is improved, so that the individualized treatment plan for knee osteoarthritis is established on the basis of accurate measurement, dynamic adjustment and data-driven optimization, the adaptability and efficacy predictability of the treatment plan are enhanced, and the scientificity and personalization of rehabilitation intervention are effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic diagram of the main steps of the present invention; Figure 2 A flowchart for obtaining the biomechanical load balancing value of the knee joint in the present invention; Figure 3 is a flow chart for obtaining the knee tendon flexibility variation coefficient in the present invention; Figure 4 A flowchart for obtaining an individualized disease progression trend data set in the present invention; Figure 5 The flowchart of obtaining the individualized therapeutic effect deviation degree in the present invention is as follows; Figure 6 The flowchart of the present invention is for obtaining the optimized individual treatment plan for knee osteoarthritis. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0016] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0017] Embodiment 1 See also Figure 1 The present invention provides a technical solution: a method for optimizing a traditional Chinese medicine treatment plan for knee osteoarthritis based on big data analysis, comprising the following steps: S1: Based on the knee joint load distribution data, collect knee joint shear stress data, monitor cartilage force gradient data, calculate the peak force during the gait cycle, and obtain the knee joint biomechanical load balance value; S2: Call the biomechanical load balancing value of the knee joint, detect the patellar tendon stretching data and quadriceps tendon displacement data, identify the instantaneous elastic modulus, screen the tendon flexibility recovery characteristic data, and obtain the knee joint tendon flexibility change coefficient; S3: Call the knee tendon flexibility change coefficient, screen the individualized knee force characteristic data, analyze the joint force change rate in the differentiated time window, compare the cartilage wear trend parameters, determine the shear force distribution change characteristics, eliminate abnormal data, and obtain the individualized disease progression trend data set; S4: Call the individualized disease progression trend data set, analyze the efficacy change rate of the differentiated cycle, extract the short-term efficacy growth rate data, set the efficacy deviation threshold, judge the efficacy change trend, and combine the expert feedback mechanism to obtain the individualized efficacy deviation degree; S5: Based on the individualized efficacy deviation, calculate the adjustment range of the treatment intervention method, optimize the distribution of rehabilitation training intensity, and adjust the individualized rehabilitation training based on expert experience to obtain the optimized individual treatment plan for knee osteoarthritis.

[0018] The biomechanical load balance values ​​of the knee joint include knee joint load distribution parameters, shear stress parameters, cartilage force gradient parameters and gait cycle force peak parameters. The knee tendon flexibility change coefficient includes patellar tendon stretch parameters, quadriceps tendon displacement parameters, instantaneous elastic modulus and tendon flexibility recovery characteristic parameters. The individualized disease progression trend data set includes knee joint force characteristic parameters, joint force change rate parameters, cartilage wear trend parameters and shear force distribution change characteristic parameters. The individualized efficacy deviation includes efficacy change rate, short-term efficacy growth rate data, efficacy deviation threshold and efficacy change trend. The optimized individual treatment plan for knee osteoarthritis includes the treatment intervention adjustment range, rehabilitation training intensity distribution and individualized rehabilitation training adjustment results.

[0019] See also Figure 2 ,The specific steps for obtaining the biomechanical load balance value of the knee joint are: S111: Based on the knee joint load distribution data, collect knee joint shear stress data, record the shear stress change trend during the gait cycle, screen the interval with large rate change, and obtain the key shear stress change interval; By using pressure sensors to collect shear stress data of the knee joint in different gait cycles, the sensors are installed at the knee joints of the subjects and can record in real time the mechanical changes of the knee joints during walking, running or activities. This data collection process involves not only data recording, but also monitoring and preliminary processing of data quality, such as removing abnormal data caused by sensor position offset, and analyzing the rate of change of shear stress in each gait cycle, selecting the interval with significantly increased rate of change as the key research area. For example, when walking uphill, the shear stress on the knee joint will increase significantly. The selection of the interval is based on the changing trend of the shear stress and the comparative analysis with the previous and subsequent data to obtain the key change interval of shear stress. The results are of great significance for understanding the biomechanical behavior of the knee joint under different motion states.

[0020] S112: calling the key change interval of shear stress, combining the monitored cartilage force gradient data, calculating the force gradient change rate in the key interval, analyzing the force gradient distribution in the gait phase, and obtaining the dynamic change value of the force gradient; Combined with real-time monitoring of cartilage force gradient data, the cartilage force gradient is measured by a group of micro sensors installed on the surface of the cartilage. The sensor can accurately measure the change in force on the cartilage during knee bending or extension. Through detailed calculation of the force gradient in the key change range, the force gradient distribution in different phases of the gait cycle (such as the stance phase and the swing phase) can be analyzed. This analysis helps to identify the area with the largest force change, which is the location where the cartilage damage or disease is most serious, and obtain the dynamic change value of the force gradient.

[0021] S113: Call the dynamic change value of the force gradient, identify the degree of force difference within the gait cycle, and analyze it in combination with the gait stability parameter using the formula: ; Obtain the biomechanical load balance value of the knee joint; in, Represents the biomechanical load balance value of the knee joint. Representative Cartilage force value at each moment, Representative Shear stress value at time Represents the dynamic change value of the force gradient, represents the gait stability parameter, is the total number of gait cycle data points; This embodiment uses five key data points in the gait cycle as the basis for calculation, namely, ; In the actual test, it is assumed that the collected data is as follows (unit: N, Newton): , , , , ; , , , , ; , , , , ; , , , , ; First, calculate the molecular part : ; Then, calculate the denominator: ; ; ; ; ; The final calculated biomechanical load balance value of the knee joint , the force balance of the knee joint during the gait cycle. If the value is too high, it means that the force on the knee joint is unbalanced during movement, leading to cartilage damage or biomechanical problems. If the value is close to a certain set benchmark value (such as the average value of healthy individuals measured clinically), The value is between 3.5 and 5.0), indicating that the biomechanical load of the subject's knee joint is within the normal range. , indicating that the force balance of the individual's knee joint is relatively stable, but it is still necessary to further evaluate whether there is a potential risk of injury based on the individual's movement status, age, etc.

[0022] See also Figure 3 , the specific steps for obtaining the knee tendon flexibility variation coefficient are: S211: calling the biomechanical load balancing value of the knee joint, extracting the patellar tendon stretching data and the quadriceps tendon displacement data, analyzing the patellar tendon stretching degree and the corresponding displacement ratio of the quadriceps tendon, comparing the change amplitude under the differentiated load state, and obtaining the instantaneous elastic modulus; By obtaining patellar tendon stretching data and quadriceps tendon displacement data, the patient's progress in the rehabilitation process can be monitored and evaluated. For example, during daily rehabilitation training, the patellar tendon stretching data of the patient's knee joint under different loads is measured by a sensor device, and the quadriceps tendon displacement data is also obtained in a similar manner. The data will be used to calculate the degree of patellar tendon stretching and the corresponding displacement ratio of the quadriceps tendon. By performing set operations on the data, the amplitude of changes under different load states can be compared to identify the instantaneous elastic modulus. This process can help doctors judge the patient's tendon and muscle recovery, thereby adjusting the rehabilitation plan. Through precise data analysis, the instantaneous elastic modulus can be obtained as a basis for subsequent adjustments to the treatment plan.

[0023] S212: Based on the instantaneous elastic modulus, analyze the change trend at the differentiated time points, screen the characteristic data of tendon flexibility recovery, identify the fluctuation range, and obtain the tendon flexibility recovery trend; It provides an important indicator for evaluating tendon flexibility. Based on the instantaneous elastic modulus, the characteristic data of the patient's tendon flexibility recovery can be analyzed. By regularly measuring the patient's tendon flexibility in the early stage of rehabilitation, the data change trend at different time points is monitored based on this data, so as to screen out the characteristic data of tendon flexibility recovery during the recovery process. For example, using data processing software, the collected time series data is screened and calculated to find data points that meet the rehabilitation standards, calculate the fluctuation range, and judge whether the flexibility change range is within the recovery range based on the data. Finally, the tendon flexibility recovery trend is obtained. The trend can help doctors evaluate the speed and effect of patients' rehabilitation and provide data support for further treatment.

[0024] S213: Call the tendon flexibility recovery trend, analyze the change rate of adjacent time points, normalize the change value of each time period, and use the formula: ; Calculate and obtain the knee joint tendon flexibility variation coefficient; in, represents the coefficient of change of knee tendon flexibility, represents the tendon flexibility recovery value at the t-th time point, Represents the tendon flexibility recovery value at the previous time point, Represents the total number of time points, represents the mean value at a time point; First, the tendon flexibility recovery trend is called. By comparing the tendon flexibility changes at different time points, the change rate between adjacent time points is calculated, and the change values ​​in different time periods are normalized to calculate the overall change coefficient. This process can be done by regularly collecting data through medical monitoring equipment. For example, during five consecutive days of rehabilitation training, the tendon flexibility values ​​are recorded at the end of each day. Assume that the tendon flexibility recovery values ​​of a patient during the training period are: 2.1, 2.3, 2.6, 2.4, and 2.5 respectively; is the coefficient of variation of knee tendon flexibility; Representative The tendon flexibility recovery values ​​at the time points are {2.1, 2.3, 2.6, 2.4, 2.5}; Represents the tendon flexibility recovery value at the previous time point; (total number of time points); Represents the mean value at all time points and is calculated as follows: ; Part 1: Calculating the mean of the rate of change ; ; ; Part 2: Calculating the square of the standard deviation ; ; ; Final calculation: ; Therefore, the calculated knee tendon flexibility variation coefficient The value is 0.0275, which indicates that the patient's tendon flexibility changed relatively smoothly during the five-day training period, with a low fluctuation range. This provides doctors with information on the stability of tendon recovery. Subsequent data can be used to compare the effects of different recovery plans on tendon flexibility and further adjust the rhythm of rehabilitation training.

[0025] See also Figure 4 ,The specific steps for obtaining the individualized disease progression trend dataset are: S311: calling the knee tendon flexibility variation coefficient, screening the individualized knee joint force characteristic data, calculating the force balance coefficient of the joint differentiation area, and obtaining the individualized knee joint force distribution data; Tendon flexibility testing equipment was used to perform non-invasive measurements of the subjects' knee joints and collect flexibility data. The tendon reaction index after different activities was recorded in each experiment. The data was obtained by comparing the difference in tendon tension before and after exercise. Numerical analysis showed that tendon flexibility has an obvious trend of change for different movement forms. The data was classified and processed through a screening algorithm to obtain tendon flexibility characteristics for different movements and individuals. The data was used to further calculate the balance of joint force. Based on the tendon flexibility and joint force data, the individualized knee joint force distribution data was calculated. The data helped medical personnel better understand the force situation of the knee joint and provide customized rehabilitation suggestions for clinical practice.

[0026] S312: Based on the individualized knee joint force distribution data, analyze the joint force change rate in the differentiated time window, and analyze the force change degree in the differentiated time window, using the formula: ; Calculate the joint force fluctuation index, identify the abnormal force fluctuation area, and obtain individualized joint force dynamic change data; in, Represents the joint force fluctuation index, represents the joint force value in the jth time window, Represents the joint force value in the previous time window, represents the mean joint force in the time window, Represents the number of time windows; Extract the joint force data of the experimental subjects from the database. The data comes from the real-time records of the dynamic gait analyzer or pressure sensor. The subjects collect force data in multiple time windows under different gait conditions (such as normal walking, running, and weight-bearing walking). The interval of each window is set to 0.5 seconds. During this time interval, the sensor collects force data points and calculates the average value as the force value of the window. In the data preprocessing stage, the acquired force data is first denoised to remove abnormal data caused by environmental interference factors. Then, the time window is divided. Each window contains force data at a series of time points, and the force mean of the window is calculated to form a time series data set. In the process of time series data analysis, the force fluctuation is quantified by calculating the force change in adjacent time windows. Assume that the joint force data of 5 time windows are collected, as follows (unit: N): ; Calculate the force change in each adjacent time window: ; ; ; ; Calculate the mean force: ; Calculate the denominator: ; ; ; Calculate the final force fluctuation index: ; The calculation shows that the joint force fluctuation index of the current subject in different time windows is 1.25. The result is used to evaluate the stability of joint force. If the M value is large (such as greater than 2.0), it means that the joint force fluctuates violently and there are abnormal force conditions, such as abnormal gait or increased risk of articular cartilage wear. If the M value is small (such as lower than 0.8), it means that the force is relatively stable and cartilage damage is not likely to occur. The joint force fluctuation index is obtained by calculation, abnormal force fluctuation areas are identified, and individualized joint force dynamic change data are obtained.

[0027] S313: According to the individualized joint force dynamic change data, identify the shear force distribution change characteristics, screen abnormal areas and remove abnormal force data, and obtain an individualized disease progression trend data set; Advanced mechanical simulation software is used to simulate the shear force distribution of the data, analyze the shear force characteristics of each area, identify and eliminate data areas that are beyond the normal range, and the shear force distribution pattern reveals potential cartilage damage areas. The data is further processed by algorithms to eliminate abnormal data caused by equipment errors or non-pathological changes, and ultimately generate an individualized disease progression trend data set. The data set provides dynamic monitoring information on knee joint lesions, allowing medical experts to observe the progression trend of the disease and adjust treatment plans accordingly to ensure that treatment measures are synchronized with changes in the disease and optimize the rehabilitation process.

[0028] See also Figure 5 , the specific steps for obtaining the individualized efficacy deviation are as follows: S411: calling the individualized disease progression trend data set, extracting the efficacy change rate, comparing the differentiated cycle data, screening the differentiated time periods, and obtaining the differentiated cycle efficacy change rate; First, it is necessary to obtain the rate of change of efficacy in each time period by calling the individualized disease progression trend data set. By comparing the efficacy data in different time periods, the periods with significant differences can be screened out. The process involves the set operation and comparison of a large amount of historical efficacy data. For example, in a clinical trial on knee osteoarthritis, by comparing the efficacy data of patients in different months before and after receiving traditional Chinese medicine treatment, it is determined which months show a significant improvement in efficacy, and then the months are screened as key research cycles. Such analysis can help researchers more accurately evaluate the effectiveness of treatment plans and obtain differentiated periodic efficacy change rates.

[0029] S412: Based on the differential cycle efficacy change rate, analyze the short-term growth rate change using the formula: ; Calculate the short-term efficacy growth rate data, compare it with the efficacy deviation threshold, and obtain the efficacy growth rate deviation ratio; in, Represents the short-term efficacy growth rate data, Represents the rate of change of efficacy in the xth time period, Represents the highest rate of change in efficacy in a short period of time. Represents the minimum rate of change in efficacy in the short term. represents the stability factor, Indicates the total number of time periods; To evaluate the effect of the treatment on patients with knee osteoarthritis, the efficacy change rate in different time periods was extracted, that is, the degree of improvement in efficacy within each period. The efficacy change rate can be calculated by indicators such as the patient's functional score change rate and pain relief index. Assuming that in a clinical trial, the efficacy change rate for three months is , , , indicating the improvement of patients at different stages; Represents the rate of change of therapeutic effect over a certain period of time; and They represent the maximum and minimum rates of change of therapeutic efficacy in the short term, respectively; represents the stability factor, which is used to measure the fluctuation of the growth rate of therapeutic effect; In the current situation, , ; Calculate the numerator part: ; Calculate the denominator, assuming : ; Final calculation: ; The result shows that the short-term efficacy growth rate data is -0.1253, indicating that the patient's efficacy has shown a downward trend in the near future. By comparing with the set efficacy deviation threshold (such as ±0.1), it is determined whether the treatment plan needs to be adjusted and the efficacy growth rate deviation ratio is obtained for subsequent individualized analysis.

[0030] S413: calling the therapeutic effect growth rate deviation ratio, judging the change trend of the corresponding threshold, identifying the change direction of the individualized therapeutic effect according to the deviation direction and amplitude, and obtaining the individualized therapeutic effect deviation degree; The efficacy growth rate deviation ratio is used to determine the changing trend of the efficacy, and the individualized efficacy deviation degree is calculated based on the deviation direction and amplitude. The process involves further analysis and calculation of the efficacy growth rate deviation ratio. The specific execution actions include comparing the measured efficacy data with the threshold to determine whether it exceeds the normal range of variation. For example, in a certain treatment trial, if a patient's efficacy deviation ratio exceeds the preset 5% threshold, this indicates that the trend of his or her efficacy change is different from the conventional treatment response and further personalized adjustment is required. In this way, researchers can accurately control and adjust the treatment plan to ensure that each patient receives the treatment that best suits his or her condition, thereby obtaining an individualized efficacy deviation degree.

[0031] See also Figure 6 The specific steps for obtaining the optimized individual treatment plan for knee osteoarthritis are as follows: S511: Based on the individualized efficacy deviation, the adjustment range of the treatment intervention method is evaluated, individual physiological parameters, lesion area characteristic values, and efficacy data are called, the change rate of the current treatment intervention on the individual is analyzed, and the adjustment range correction coefficient is obtained; First, we call up individual physiological parameters such as weight, age, and characteristic values ​​of the lesion area, such as the degree of joint wear and inflammatory indicators, as well as historical efficacy data including the responsiveness and recovery rate of past treatments, and conduct a comprehensive analysis of the data to determine the difference between the current treatment plan and the actual needs of the individual. We further calculate the adjustment amplitude correction coefficient of the therapeutic intervention. This coefficient is the result of adjustment based on the progression rate of the disease and individual differences. For example, for a 45-year-old patient with chronic knee arthritis, the adjustment amplitude correction coefficient is calculated based on his disease course and previous treatment response, indicating the need to increase the frequency and intensity of physical therapy.

[0032] S512: Calling the adjustment amplitude correction coefficient to optimize the rehabilitation training intensity distribution, using the formula: ; Calculate the optimized intensity distribution value, analyze the individual rehabilitation training suitability, and obtain the optimized training parameter weights; in, represents the optimized intensity distribution value, represents the training load, represents the training frequency, represents the training duration, Represents individual basic recovery ability, Represents the target recovery progress, are the factors affecting training load, frequency, and duration. The factors affecting individual basic recovery ability and target recovery progress; The training load, training frequency and training duration were calculated to ensure that the training intensity of the patient met his or her individual needs. The patient's individual physiological data was collected, such as weight 80 kg, age 55 years, characteristic values ​​of the lesion area (joint gap 2.5 mm, inflammation score 4.2), and historical efficacy data (exercise recovery rate of 75% in the past 3 months). The basic recovery capacity was then calculated based on the data. and target recovery progress , where the basic recovery capacity can be determined by the results of the exercise tolerance test. Assuming that the patient's knee joint exercise tolerance score is 3.8 (out of 5), the target recovery progress is determined by the rehabilitation goal set by the doctor, assuming it is 4.5 (out of 5), and the training load is calculated. (Daily walking distance), training frequency (Number of training sessions per week), duration of training (Duration of each training session), the patient's training load is set to walk 3.5 km each time, the training frequency is 5 times a week, and the duration of each training session is 40 minutes; Substitute the specific values ​​into the calculation, assuming that the training load affects the factor , training frequency influencing factor , training duration influence factor , factors affecting individual basic recovery ability , target recovery progress influencing factors , then the calculation is as follows: ; ; ; ; The final calculation results in the optimized training intensity distribution value. , this value indicates that the patient's current training load, training frequency and training duration have been optimized and adjusted, making the training plan more in line with their individual needs, thereby further improving the adaptability of rehabilitation training. Based on this value, the individual rehabilitation training adaptability is calculated, and the training parameters are adjusted accordingly to obtain the optimized training parameter weights.

[0033] S513: Based on the optimization of training parameter weights and combined with expert experience, individualized rehabilitation training is adjusted to adjust the dynamic training cycle, training mode, and training load balance to obtain an optimized individual treatment plan for knee osteoarthritis; Adjust the dynamic training cycle, training mode and training load balance, analyze and optimize the intensity distribution value. If the optimized intensity distribution value indicates that the current training frequency is too high, reduce the frequency while increasing the duration of each training to adapt to the patient's actual recovery ability. Through such adjustments, the load of each training cycle can be accurately controlled, and ultimately generate or obtain an optimized individual treatment plan for knee osteoarthritis. For example, an individualized treatment plan designed for a patient with acute symptoms will emphasize reducing exercise intensity in the short term to relieve symptoms and prevent further joint damage.

[0034] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for optimizing TCM treatment plans for knee osteoarthritis based on big data analysis, characterized in that: The following steps are involved: S1: Based on the knee joint load distribution data, collect knee joint shear stress data, monitor cartilage force gradient data, calculate the peak force during the gait cycle, and obtain the knee joint biomechanical load balance value; S2: calling the knee joint biomechanical load balancing value, detecting the patellar tendon stretching data and the quadriceps tendon displacement data, identifying the instantaneous elastic modulus, screening the tendon flexibility recovery characteristic data, and obtaining the knee joint tendon flexibility change coefficient; S3: calling the knee tendon flexibility change coefficient, screening individualized knee joint force characteristic data, analyzing the joint force change rate in the differentiated time window, comparing the cartilage wear trend parameters, determining the shear force distribution change characteristics, eliminating abnormal data, and obtaining an individualized disease progression trend data set; S4: calling the individualized disease progression trend data set, analyzing the therapeutic effect change rate of the differentiated cycle, extracting the short-term therapeutic effect growth rate data, setting the therapeutic effect deviation threshold, judging the therapeutic effect change trend, and combining the expert feedback mechanism to obtain the individualized therapeutic effect deviation degree; S5: Based on the individualized efficacy deviation, optimize the rehabilitation training intensity distribution, combine expert experience to adjust the individualized rehabilitation training, and obtain an optimized individual treatment plan for knee osteoarthritis.

2. The method for optimizing TCM treatment plans for knee osteoarthritis based on big data analysis according to claim 1, characterized in that: The knee joint biomechanical load balance value includes knee joint load distribution parameters, shear stress parameters, cartilage force gradient parameters and gait cycle force peak parameters; the knee joint tendon flexibility change coefficient includes patellar tendon stretch parameters, quadriceps tendon displacement parameters, instantaneous elastic modulus and tendon flexibility recovery characteristic parameters; the individualized disease progression trend data set includes knee joint force characteristic parameters, joint force change rate parameters, cartilage wear trend parameters and shear force distribution change characteristic parameters; the individualized efficacy deviation includes efficacy change rate, short-term efficacy growth rate data, efficacy deviation threshold and efficacy change trend; the optimized knee osteoarthritis individual treatment plan includes treatment intervention adjustment range, rehabilitation training intensity distribution and individualized rehabilitation training adjustment results.

3. The method for optimizing TCM treatment plans for knee osteoarthritis based on big data analysis according to claim 1, characterized in that: The steps for obtaining the knee joint biomechanical load balancing value are specifically as follows: S111: Based on the knee joint load distribution data, collect knee joint shear stress data, record the shear stress change trend during the gait cycle, screen the interval with large rate change, and obtain the key shear stress change interval; S112: calling the shear stress key change interval, combining the monitored cartilage force gradient data, calculating the force gradient change rate in the key interval, analyzing the gait phase force gradient distribution, and obtaining the force gradient dynamic change value; S113: Call the dynamic change value of the force gradient to identify the degree of force difference within the gait cycle, and analyze it in combination with the gait stability parameter using the formula: ； Obtain the biomechanical load balance value of the knee joint; in, Represents the biomechanical load balance value of the knee joint. Representative Cartilage force value at each moment, Representative Shear stress value at time Represents the dynamic change value of the force gradient, represents the gait stability parameter, is the total number of gait cycle data points.

4. The method for optimizing TCM treatment plans for knee osteoarthritis based on big data analysis according to claim 3, characterized in that: The steps for obtaining the knee joint tendon flexibility variation coefficient are specifically as follows: S211: calling the knee joint biomechanical load balancing value, extracting patellar tendon stretching data and quadriceps tendon displacement data, analyzing the patellar tendon stretching degree and the corresponding displacement ratio of the quadriceps tendon, comparing the change amplitude under the differentiated load state, and obtaining the instantaneous elastic modulus; S212: Based on the instantaneous elastic modulus, analyzing the change trend at the differentiated time points, screening the characteristic data of tendon flexibility recovery, identifying the fluctuation range, and obtaining the tendon flexibility recovery trend; S213: calling the tendon flexibility recovery trend, analyzing the change rate of adjacent time points, normalizing the change value of each time period, and using the formula: ； Calculate and obtain the knee joint tendon flexibility variation coefficient; in, represents the coefficient of change of knee tendon flexibility, represents the tendon flexibility recovery value at the tth time point, Represents the tendon flexibility recovery value at the previous time point, represents the total number of time points, represents the mean value at the time point.

5. The method for optimizing TCM treatment plans for knee osteoarthritis based on big data analysis according to claim 4, characterized in that: The steps for obtaining the individualized disease progression trend data set are specifically as follows: S311: calling the knee tendon flexibility variation coefficient, screening individualized knee joint force characteristic data, calculating the force balance coefficient of the joint differentiation area, and obtaining individualized knee joint force distribution data; S312: Based on the individualized knee joint force distribution data, analyze the joint force change rate in the differentiated time window, and analyze the force change degree in the differentiated time window, using the formula: ； Calculate the joint force fluctuation index, identify the abnormal force fluctuation area, and obtain individualized joint force dynamic change data; in, Represents the joint force fluctuation index, represents the joint force value in the jth time window, Represents the joint force value in the previous time window, represents the mean joint force in the time window, Represents the number of time windows; S313: According to the individualized joint force dynamic change data, the shear force distribution change characteristics are identified, abnormal areas are screened and abnormal force data are eliminated to obtain an individualized disease progression trend data set.

6. The method for optimizing TCM treatment plans for knee osteoarthritis based on big data analysis according to claim 5, characterized in that: The steps for obtaining the individualized therapeutic effect deviation degree are specifically as follows: S411: calling the individualized disease progression trend data set, extracting the therapeutic effect change rate, comparing the differentiated cycle data, screening the differentiated time periods, and obtaining the differentiated cycle therapeutic effect change rate; S412: Based on the differentiated periodic efficacy change rate, analyze the short-term growth rate change using the formula: ； Calculate the short-term efficacy growth rate data, compare it with the efficacy deviation threshold, and obtain the efficacy growth rate deviation ratio; in, Represents the short-term efficacy growth rate data, Represents the rate of change of efficacy in the xth time period, Represents the highest rate of change in efficacy in a short period of time. Represents the minimum rate of change in efficacy in the short term. represents the stability factor, Indicates the total number of time periods; S413: calling the therapeutic effect growth rate deviation ratio, determining the change trend of the corresponding threshold, identifying the change direction of the individualized therapeutic effect according to the deviation direction and amplitude, and obtaining the individualized therapeutic effect deviation degree.

7. The method for optimizing TCM treatment plans for knee osteoarthritis based on big data analysis according to claim 6, characterized in that: The steps for obtaining the optimized individual treatment plan for knee osteoarthritis are specifically as follows: S511: Based on the individualized efficacy deviation, the adjustment range of the treatment intervention is evaluated, individual physiological parameters, lesion area characteristic values, and efficacy data are called, and the change rate of the current treatment intervention on the individual is analyzed to obtain an adjustment range correction coefficient; S512: Calling the adjustment amplitude correction coefficient to optimize the rehabilitation training intensity distribution, using the formula: ； Calculate the optimized intensity distribution value, analyze the individual rehabilitation training suitability, and obtain the optimized training parameter weights; in, represents the optimized intensity distribution value, Represents training load, represents the training frequency, represents the duration of training, Represents individual basic recovery ability, Represents the target recovery progress, are the factors affecting training load, frequency, and duration. The factors affecting individual basic recovery ability and target recovery progress; S513: Based on the optimized training parameter weights and combined with expert experience, individualized rehabilitation training is adjusted to adjust the dynamic training cycle, training mode, and training load balance to obtain an optimized individual treatment plan for knee osteoarthritis.

Images