An orthopedic patient rehabilitation state progress intelligent tracking method and system

Abstract

The application discloses an orthopedic patient rehabilitation state progress intelligent tracking method and system, and relates to the technical field of medical health; the application can accurately monitor the rehabilitation state of the patient and provide dynamic progress evaluation by integrating wearable devices, collecting and analyzing the vital signs, motion state and pressure distribution data of the patient in real time; based on the rehabilitation progress evaluation result, the system can automatically generate a personalized rehabilitation exercise program, adjust the exercise intensity, frequency and training plan according to the specific needs of each patient, and ensure the efficiency and safety of the rehabilitation process; through the analysis of vital sign fluctuations, motion accuracy and plantar pressure balance, the system can identify potential risk factors in real time, trigger an early warning in time, help the patient and nursing staff take necessary intervention measures, and ensure the smooth progress of the rehabilitation process.

Description

Technical Field

[0001] This invention relates to the field of medical and health technology, specifically to an intelligent tracking method and system for the rehabilitation progress of orthopedic patients. Background Technology

[0002] With advancements in medical technology and increased emphasis on health management, orthopedic diseases, particularly rehabilitation after fractures, have become a crucial area of ​​focus in the medical field. Traditional orthopedic patient rehabilitation management largely relies on manual monitoring and subjective assessment. This approach lacks real-time data support for the patient's recovery status and is prone to bias and delays in the assessment process. Consequently, it often fails to promptly identify problems during rehabilitation, leading to unsatisfactory outcomes and even issues such as excessive or insufficient exercise, uneven stress distribution, and negatively impacting the patient's recovery progress and quality of life.

[0003] Traditional rehabilitation methods rely on doctors' assessments or patients' subjective reports, failing to capture patients' physiological changes, movement status, and stress distribution in real time, which may lead to delays or inaccurate adjustments in the rehabilitation process.

[0004] Secondly, in traditional rehabilitation data management methods, data such as vital signs, movement status, and stress distribution are usually processed separately, lacking a unified digital platform for comprehensive analysis. This data fragmentation makes it difficult for doctors to fully and timely understand the patient's rehabilitation status.

[0005] To address the aforementioned issues, it is necessary to propose an intelligent tracking method and system for the rehabilitation progress of orthopedic patients. Summary of the Invention

[0006] The purpose of this invention is to solve the problems existing in the background art, and to propose an intelligent tracking method and system for the rehabilitation status of orthopedic patients.

[0007] The objective of this invention can be achieved through the following technical solutions:

[0008] A method and system for intelligently tracking the rehabilitation progress of orthopedic patients.

[0009] In a first aspect, the present invention provides an intelligent tracking method for the rehabilitation progress of orthopedic patients, comprising the following steps:

[0010] Step 1: Data Acquisition and Transmission;

[0011] At preset time intervals, the wearable device is accessed to collect various data from orthopedic patients in real time through accelerometers, gyroscopes, heart rate sensors, temperature sensors, pressure sensors, and blood pressure sensors, including vital signs data, motion status data, and pressure distribution data.

[0012] The vital signs data include heart rate (HR(t), blood pressure (BP(t), respiratory rate (RR(t)), and body temperature (BT(t)); where t is the time of data collection.

[0013] The motion state data includes the joint motion angle θ(t), frequency f(t), velocity v(t), and acceleration a(t) at the fracture site; where t is the data acquisition time.

[0014] The pressure distribution data includes the force data F of the joint at the fracture site and the plantar pressure distribution map.

[0015] In a preferred embodiment of the present invention, a vertical x-axis and y-axis are arranged in the plantar pressure distribution map to establish a Cartesian coordinate system, and the pressure P(x, y) at each coordinate point in the Cartesian coordinate system is obtained. The maximum pressure PLmax and PRmax of the left and right feet in the pressure distribution map are obtained respectively. Using PLmax / 6, 2PLmax / 6, 3PLmax / 6, 4PLmax / 6, and 5PLmax / 6 as dividing points, pressure contour lines are drawn in the plantar pressure distribution map of the left foot, and the areas enclosed by each pressure contour line are calculated, including the area SL1 enclosed by the 0 to 1PLmax / 6 contour line, the area SL2 enclosed by the PLmax / 6 contour line to the 2PLmax / 6 contour line, the area SL3 enclosed by the 2PLmax / 6 contour line to the 3PLmax / 6 contour line, the area SL4 enclosed by the 3PLmax / 6 contour line to the 4PLmax / 6 contour line, and the area SL5 enclosed by the 5PLmax / 6 contour line.

[0016] Similarly, obtain the area SR1 of the region enclosed by contour lines 0 to 1PRmax / 6, the area SR2 of the region enclosed by contour lines PRmax / 6 to 2PRmax / 6, the area SR3 of the region enclosed by contour lines 2PRmax / 6 to 3PRmax / 6, the area SR4 of the region enclosed by contour lines 3PRmax / 6 to 4PRmax / 6, and the area SR5 of the region enclosed by contour line 5PRmax / 6.

[0017] Extract the geometric centroids OL1(x,y) of the region enclosed by contour lines 0 to PLmax / 6, OL2(x,y) of the region enclosed by contour lines PLmax / 6 to 2PLmax / 6, OL3(x,y) of the region enclosed by contour lines 2PLmax / 6 to 3PLmax / 6, OL4(x,y) of the region enclosed by contour lines 3PLmax / 6 to 4PLmax / 6, and OL5(x,y) of the region enclosed by contour line 5PLmax / 6.

[0018] Similarly, obtain the geometric centroid OR1(x,y) of the portion enclosed by contour lines 0 to Pmax / 6, OR2(x,y) of the portion enclosed by contour lines PRmax / 6 to 2PRmax / 6, OR3(x,y) of the portion enclosed by contour lines 2PRmax / 6 to 3PRmax / 6, OR4(x,y) of the portion enclosed by contour lines 3PRmax / 6 to 4PRmax / 6, and OR5(x,y) of the portion enclosed by contour line 5PRmax / 6.

[0019] Step 2: Data cleaning and preprocessing;

[0020] The collected vital sign and movement data were cleaned and preprocessed to remove outliers and noise, ensuring data quality and providing a reliable foundation for subsequent analysis. The specific process is as follows:

[0021] Assuming that both vital sign data and motion status data are normally distributed random variables, outlier detection is performed using the pre-defined formula: E[xi(t)]=|xi(t)-μ[xi(t)]|-ασ[xi(t)], yielding the abnormal deviation characteristic value E[xi(t)] for each vital sign and motion status data. Here, xi(t) represents the specific vital sign or motion status data, and i is the data type identifier, representing data types including heart rate, blood pressure, respiratory rate, body temperature, and the motion angle, frequency, velocity, and acceleration of the fractured joint. μ[xi(t)] is the mean of xi(t), and σ[xi(t)] is the variance of xi; α is a pre-defined detection coefficient, with a value ranging from 1, 2, or 3.

[0022] Vital sign data or motion state data with positive abnormal deviation feature value E[xi(t)] are considered abnormal deviation data and are removed.

[0023] As a preferred embodiment of the present invention, for missing data, missing data detection and missing data imputation are performed, and the specific process is as follows:

[0024] Missing data detection is performed, and the acquisition time 't' of each data point in all vital sign and motion status data is extracted and denoted as the timestamp of that vital sign or motion status data. The difference between the timestamps of all vital sign and motion status data and the timestamp of the previously acquired data of the same type is calculated to obtain the timestamp interval between the two data points.

[0025] If it is detected that the timestamp interval between two data points xi(t1) and xi(t2) is greater than a preset time interval, it is determined that there is missing data between the two data points. A supplementary data point xi(t_new) is then added before the two data points, and the acquisition time t_new of the newly added supplementary data is set to the average of the timestamps of the two data points.

[0026] As a preferred embodiment of the present invention, the specific value of the newly added filler data is determined, and for each filler data xi(t_new), its specific value is set to the average of the two data xi(t1) and xi(t2).

[0027] For example, given existing heart rate data HR(t1) and HR(t2), the timestamp interval t2-t1 between the two data points is calculated. If t2-t1 is found to be greater than a preset time interval, a new heart rate data HR(t_new) is added between HR(t1) and HR(t2); where t_new = (t1+t2) / 2; and its specific value HR(t_new) = [HR(t1)+HR(t2)] / 2.

[0028] Step 3: Centralized Data Analysis and Judgment;

[0029] The analysis of collected vital signs and motor status data helps determine the patient's current physiological state and motor accuracy, providing a basis for developing a rehabilitation plan.

[0030] A preliminary analysis of vital sign data is performed, calculating the mean and standard deviation of fluctuations in heart rate (HR(t), blood pressure (BP(t), respiratory rate (RR(t)), and body temperature (BT(t)). If the mean of vital sign data exceeds a preset threshold, a level one warning signal is output; if the standard deviation of vital sign data exceeds a preset threshold, a level two warning signal is output.

[0031] As a preferred embodiment of the present invention, in-depth analysis of motion state data is performed, and an assessment value W(t) reflecting the fluctuation range of rehabilitation progress is obtained by calculating the motion angle, frequency, velocity, and acceleration of the joint at the fracture site. The specific process is as follows:

[0032] The maximum and minimum values ​​of the joint motion angle θ(t), frequency f(t), velocity v(t), and acceleration a(t) at the fracture site are obtained, and their differences are calculated, including the difference Δθ between the maximum and minimum values ​​of the motion angle, Δf between the maximum and minimum values ​​of the frequency, Δv between the maximum and minimum values ​​of the velocity, and Δa between the maximum and minimum values ​​of the acceleration. A weighted sum of Δθ, Δf, Δv, and Δa is then obtained to obtain the fluctuation range assessment value W(t) reflecting the rehabilitation progress.

[0033] In a preferred embodiment of the present invention, pressure distribution data is analyzed to calculate the changing trend of plantar pressure distribution and to analyze the degree of balance of pressure between the left and right feet, thereby assessing the plantar force distribution in patients with fractures. The specific process is as follows:

[0034] At preset time intervals, calculate the differences between SL1, SL2, SL3, SL4, and SL5 and the previous preset time interval to obtain the pressure distribution area differences of the left foot ΔSL1, ΔSL2, ΔSL3, ΔSL4, and ΔSL5; calculate the differences between SR1, SR2, SR3, SR4, and SR5 and the previous preset time interval to obtain the pressure distribution area differences of the right foot ΔSR1, ΔSR2, ΔSR3, ΔSR4, and ΔSR5.

[0035] By preset formula Calculate the pressure balance coefficient Ration for both feet. The closer the pressure balance coefficient Ration is to the surface level, the better the patient's lower limb recovery.

[0036] As a preferred embodiment of the present invention, the motion trajectories of OL1(x,y), OL2(x,y), OL3(x,y), OL4(x,y), OL5(x,y), OR1(x,y), OR2(x,y), OR3(x,y), OR4(x,y) and OR5(x,y) collected at each preset time interval are plotted as time progresses.

[0037] Step 4: Rehabilitation progress assessment and personalized plan generation;

[0038] Based on the patient's physiological status and motor precision analysis results, the rehabilitation progress is assessed, and a personalized rehabilitation exercise plan is generated based on the assessment results.

[0039] If a Level 1 warning signal is detected based on the analysis of vital sign data, it is determined that the patient's physiological state may be abnormal.

[0040] If a level 2 warning signal is detected, it indicates that the patient's physiological state is fluctuating too much and further examination is required.

[0041] As a preferred embodiment of the present invention, if the analysis results of the motion state data indicate that the fluctuation range assessment value continues to increase within T consecutive preset time intervals, it is determined that the patient's recovery progress is good within the T consecutive preset time intervals.

[0042] Otherwise, if the patient's recovery progress is deemed poor within the aforementioned T consecutive preset time intervals, the patient is advised to appropriately reduce the number of bodyweight exercises to avoid overtraining.

[0043] As a preferred embodiment of the present invention, based on the analysis results of the pressure distribution data, if it is identified that the pressure distribution area differences ΔSL1, ΔSL2, ΔSL3, ΔSL4 and ΔSL5 of the left foot remain decreasing within a continuous T preset time interval, it indicates that the force state of the left foot tends to be stable. If it is identified that the pressure distribution area differences ΔSR1, ΔSR2, ΔSR3, ΔSR4 and ΔSR5 of the right foot remain decreasing within a continuous T preset time interval, it indicates that the force state of the right foot tends to be stable.

[0044] Otherwise, it is determined that the force on the left and right soles is uneven, and specific gait correction exercises are added to the subsequent rehabilitation program.

[0045] Secondly, the present invention provides an intelligent tracking system for the rehabilitation progress of orthopedic patients, including a data acquisition and real-time transmission module, a data cleaning module, a rehabilitation status analysis module, a rehabilitation progress assessment module, and a feedback execution module.

[0046] The data acquisition and real-time transmission module is responsible for collecting various types of patient data in real time through wearable devices, including vital signs data, movement status data, and pressure distribution data, ensuring that all data is uploaded to the data processing platform at preset time intervals.

[0047] The data cleaning module cleans the collected raw data, removing noise, outliers, and missing data to ensure data quality. Statistical analysis methods based on outlier detection and missing data imputation are used to clean vital sign and motion status data, ensuring accuracy and reliability before subsequent analysis.

[0048] The rehabilitation status analysis module analyzes vital sign data, movement status data, and pressure distribution data after cleaning. It calculates the mean and standard deviation of physiological state fluctuations, determines whether they exceed preset thresholds, and outputs warning signals.

[0049] Calculate the assessment value of the range of motion fluctuations, and assess the patient's rehabilitation progress based on the changing trends of motion angle, frequency, speed, and acceleration.

[0050] The pressure balance of the left and right soles is analyzed. By calculating the area change of the pressure zone of the left and right feet, the force balance is evaluated, and the trend of the pressure distribution map of the left and right feet is generated.

[0051] The rehabilitation progress assessment module evaluates the patient's overall rehabilitation progress based on the analysis results, outputs early warning information for abnormal fluctuations in vital signs, changes in motor precision, or uneven pressure on the soles of the feet, and suggests adjustments to the rehabilitation plan.

[0052] The feedback execution module automatically generates personalized rehabilitation plans based on the patient's rehabilitation progress assessment, adjusting exercise intensity, frequency, and training schedule. It generates rehabilitation progress reports and provides real-time feedback to the patient and their caregivers, helping the patient understand their rehabilitation status and next steps.

[0053] Compared with the prior art, the beneficial effects of the present invention are:

[0054] 1. This invention integrates wearable devices to collect and analyze patients' vital signs, movement status, and pressure distribution data in real time, enabling precise monitoring of patients' rehabilitation status and providing dynamic progress assessment.

[0055] 2. Based on the rehabilitation progress assessment results, this system can automatically generate personalized rehabilitation exercise plans, adjusting the exercise intensity, frequency and training plan according to the specific needs of each patient, ensuring the efficiency and safety of the rehabilitation process.

[0056] 3. By analyzing fluctuations in vital signs, motor precision, and plantar pressure balance, the system can identify potential risk factors in real time and trigger early warnings in a timely manner, helping patients and their caregivers to take necessary intervention measures to ensure the smooth progress of the rehabilitation process. Attached Figure Description

[0057] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings:

[0058] Figure 1 This is a flowchart of the method of the present invention;

[0059] Figure 2 This is a plantar pressure distribution diagram presented in an embodiment of the present invention;

[0060] Figure 3 This is a system block diagram of the present invention. Detailed Implementation

[0061] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0062] Please see Figure 1 As shown, an intelligent tracking method for the rehabilitation progress of orthopedic patients includes the following steps:

[0063] Step 1: Data Acquisition and Transmission;

[0064] At preset time intervals, the wearable device is accessed to collect various data from orthopedic patients in real time through accelerometers, gyroscopes, heart rate sensors, temperature sensors, pressure sensors, and blood pressure sensors, including vital signs data, motion status data, and pressure distribution data.

[0065] The vital signs data include heart rate (HR(t), blood pressure (BP(t), respiratory rate (RR(t)), and body temperature (BT(t)); where t is the time of data collection.

[0066] The motion state data includes the joint motion angle θ(t), frequency f(t), velocity v(t), and acceleration a(t) at the fracture site; where t is the data acquisition time.

[0067] The pressure distribution data includes the force data F of the joint at the fracture site and the plantar pressure distribution map.

[0068] Please see Figure 2 As shown, in the plantar pressure distribution map, vertical x-axis and y-axis are arranged to establish a Cartesian coordinate system, and the pressure P(x, y) at each coordinate point in the Cartesian coordinate system is obtained. The maximum pressure PLmax and PRmax of the left and right feet in the pressure distribution map are obtained respectively. Using PLmax / 6, 2PLmax / 6, 3PLmax / 6, 4PLmax / 6, and 5PLmax / 6 as dividing points, pressure contour lines are drawn in the plantar pressure distribution map of the left foot. The areas enclosed by each pressure contour line are calculated, including the area SL1 enclosed by the contour line from 0 to 1PLmax / 6, the area SL2 enclosed by the contour line from PLmax / 6 to 2PLmax / 6, the area SL3 enclosed by the contour line from 2PLmax / 6 to 3PLmax / 6, the area SL4 enclosed by the contour line from 3PLmax / 6 to 4PLmax / 6, and the area SL5 enclosed by the contour line from 5PLmax / 6.

[0069] Similarly, obtain the area SR1 of the region enclosed by contour lines 0 to 1PRmax / 6, the area SR2 of the region enclosed by contour lines PRmax / 6 to 2PRmax / 6, the area SR3 of the region enclosed by contour lines 2PRmax / 6 to 3PRmax / 6, the area SR4 of the region enclosed by contour lines 3PRmax / 6 to 4PRmax / 6, and the area SR5 of the region enclosed by contour line 5PRmax / 6.

[0070] Extract the geometric centroids OL1(x,y) of the region enclosed by contour lines 0 to PLmax / 6, OL2(x,y) of the region enclosed by contour lines PLmax / 6 to 2PLmax / 6, OL3(x,y) of the region enclosed by contour lines 2PLmax / 6 to 3PLmax / 6, OL4(x,y) of the region enclosed by contour lines 3PLmax / 6 to 4PLmax / 6, and OL5(x,y) of the region enclosed by contour line 5PLmax / 6.

[0071] Similarly, obtain the geometric centroid OR1(x,y) of the portion enclosed by contour lines 0 to Pmax / 6, OR2(x,y) of the portion enclosed by contour lines PRmax / 6 to 2PRmax / 6, OR3(x,y) of the portion enclosed by contour lines 2PRmax / 6 to 3PRmax / 6, OR4(x,y) of the portion enclosed by contour lines 3PRmax / 6 to 4PRmax / 6, and OR5(x,y) of the portion enclosed by contour line 5PRmax / 6.

[0072] Step 2: Data cleaning and preprocessing;

[0073] The collected vital sign and movement data were cleaned and preprocessed to remove outliers and noise, ensuring data quality and providing a reliable foundation for subsequent analysis. The specific process is as follows:

[0074] Assuming that both vital sign data and motion status data are normally distributed random variables, outlier detection is performed using the pre-defined formula: E[xi(t)]=|xi(t)-μ[xi(t)]|-ασ[xi(t)], yielding the abnormal deviation characteristic value E[xi(t)] for each vital sign and motion status data. Here, xi(t) represents the specific vital sign or motion status data, and i is the data type identifier, representing data types including heart rate, blood pressure, respiratory rate, body temperature, and the motion angle, frequency, velocity, and acceleration of the fractured joint. μ[xi(t)] is the mean of xi(t), and σ[xi(t)] is the variance of xi; α is a pre-defined detection coefficient, with a value ranging from 1, 2, or 3.

[0075] Vital sign data or motion state data with positive abnormal deviation feature value E[xi(t)] are considered abnormal deviation data and are removed.

[0076] It should be noted that the abnormal deviation eigenvalue reflects the degree to which the data deviates from the mean. Under normal conditions, vital signs and motion data, including heart rate, blood pressure, respiratory rate, body temperature, and the angle, frequency, speed, and acceleration of joint movement at the fracture site, fluctuate around the mean within a certain range and will not produce a deviation greater than several times the variance. That is, the value of the abnormal deviation eigenvalue should be less than 0.

[0077] Furthermore, for missing data, missing data detection and missing data imputation are performed. The specific process is as follows:

[0078] Missing data detection is performed, and the acquisition time 't' of each data point in all vital sign and motion status data is extracted and denoted as the timestamp of that vital sign or motion status data. The difference between the timestamps of all vital sign and motion status data and the timestamp of the previously acquired data of the same type is calculated to obtain the timestamp interval between the two data points.

[0079] For example, given existing heart rate data HR(t1) and HR(t2), the timestamp interval t2-t1 between the two data points is calculated. If t2-t1 is found to be greater than a preset time interval, a supplementary heart rate data HR(t3) is added between HR(t1) and HR(t2); where t3 = (t1 + t2) / 2.

[0080] If it is detected that the timestamp interval between two data points xi(t1) and xi(t2) is greater than a preset time interval, it is determined that there is missing data between the two data points. A supplementary data point xi(t_new) is then added before the two data points, and the acquisition time t_new of the newly added supplementary data is set to the average of the timestamps of the two data points.

[0081] Furthermore, the specific values ​​of the newly added filler data are determined. For each filler data xi(t_new), its specific value is set to the average of the two data xi(t1) and xi(t2).

[0082] For example, given existing heart rate data HR(t1) and HR(t2), the timestamp interval t2-t1 between the two data points is calculated. If t2-t1 is found to be greater than a preset time interval, a new heart rate data HR(t_new) is added between HR(t1) and HR(t2); where t_new = (t1+t2) / 2; and its specific value HR(t_new) = [HR(t1)+HR(t2)] / 2.

[0083] Step 3: Centralized Data Analysis and Judgment;

[0084] The analysis of collected vital signs and motor status data helps determine the patient's current physiological state and motor accuracy, providing a basis for developing a rehabilitation plan.

[0085] A preliminary analysis of vital sign data is performed, calculating the mean and standard deviation of fluctuations in heart rate (HR(t), blood pressure (BP(t), respiratory rate (RR(t)), and body temperature (BT(t)). If the mean of vital sign data exceeds a preset threshold, a level one warning signal is output; if the standard deviation of vital sign data exceeds a preset threshold, a level two warning signal is output.

[0086] Furthermore, in-depth analysis of the motion data is performed. By calculating the motion angle, frequency, velocity, and acceleration of the joint at the fracture site, an assessment value W(t) reflecting the fluctuation range of rehabilitation progress is obtained. The specific process is as follows:

[0087] The maximum and minimum values ​​of the joint motion angle θ(t), frequency f(t), velocity v(t), and acceleration a(t) at the fracture site are obtained, and their differences are calculated, including the difference Δθ between the maximum and minimum values ​​of the motion angle, Δf between the maximum and minimum values ​​of the frequency, Δv between the maximum and minimum values ​​of the velocity, and Δa between the maximum and minimum values ​​of the acceleration. A weighted sum of Δθ, Δf, Δv, and Δa is then obtained to obtain the fluctuation range assessment value W(t) reflecting the rehabilitation progress.

[0088] It should be noted that during the rehabilitation process of orthopedic patients, as they gradually recover, the fluctuation range of motion data such as angle of motion, frequency, speed, and acceleration usually increases. This is because as rehabilitation progresses, the patient's range of motion and motor abilities gradually recover, leading to a corresponding increase in the magnitude of changes in motion data. Therefore, analyzing the fluctuation range and magnitude of these data can quantify the patient's rehabilitation progress.

[0089] Furthermore, the pressure distribution data is analyzed to calculate the changing trend of plantar pressure distribution and to analyze the degree of balance of pressure between the left and right feet, thus assessing the plantar force distribution in fracture patients. The specific process is as follows:

[0090] At preset time intervals, calculate the differences between SL1, SL2, SL3, SL4, and SL5 and the previous preset time interval to obtain the pressure distribution area differences of the left foot ΔSL1, ΔSL2, ΔSL3, ΔSL4, and ΔSL5; calculate the differences between SR1, SR2, SR3, SR4, and SR5 and the previous preset time interval to obtain the pressure distribution area differences of the right foot ΔSR1, ΔSR2, ΔSR3, ΔSR4, and ΔSR5.

[0091] By preset formula Calculate the pressure balance coefficient Ration for both feet. The closer the pressure balance coefficient Ration is to the surface level, the better the patient's lower limb recovery.

[0092] It should be noted that for patients with lower limb fractures, the balance of force on the sole of the foot can be assessed by calculating the changes in the area of ​​different pressure zones. As the patient recovers, the force on the left and right feet and the overall force on the sole of the foot will tend to be balanced, while the area of ​​the pressure concentration zone will gradually shrink.

[0093] Furthermore, the motion trajectories of OL1(x,y), OL2(x,y), OL3(x,y), OL4(x,y), OL5(x,y), OR1(x,y), OR2(x,y), OR3(x,y), OR4(x,y) and OR5(x,y) collected at each preset time interval are plotted as time progresses.

[0094] Step 4: Rehabilitation progress assessment and personalized plan generation;

[0095] Based on the patient's physiological status and motor precision analysis results, the rehabilitation progress is assessed, and a personalized rehabilitation exercise plan is generated based on the assessment results.

[0096] If a Level 1 warning signal is detected based on the analysis of vital sign data, it is determined that the patient's physiological state may be abnormal.

[0097] If a level 2 warning signal is detected, it indicates that the patient's physiological state is fluctuating too much and further examination is required.

[0098] Furthermore, based on the analysis results of the motion status data, if it is found that the fluctuation range assessment value continues to increase within T consecutive preset time intervals, it is determined that the patient's recovery progress is good within the T consecutive preset time intervals.

[0099] Otherwise, if the patient's recovery progress is deemed poor within the aforementioned T consecutive preset time intervals, the patient is advised to appropriately reduce the number of bodyweight exercises to avoid overtraining.

[0100] Furthermore, based on the analysis results of the pressure distribution data, if the pressure distribution area differences ΔSL1, ΔSL2, ΔSL3, ΔSL4, and ΔSL5 of the left foot are identified as decreasing over a continuous T preset time interval, it indicates that the force state of the left foot tends to be stable. Similarly, if the pressure distribution area differences ΔSR1, ΔSR2, ΔSR3, ΔSR4, and ΔSR5 of the right foot are identified as decreasing over a continuous T preset time interval, it indicates that the force state of the right foot tends to be stable.

[0101] Otherwise, it is determined that the force on the left and right soles is uneven, and specific gait correction exercises are added to the subsequent rehabilitation program.

[0102] Please see Figure 3 As shown, an intelligent tracking system for the rehabilitation progress of orthopedic patients includes a data acquisition and real-time transmission module, a data cleaning module, a rehabilitation status analysis module, a rehabilitation progress assessment module, and a feedback execution module.

[0103] The data acquisition and real-time transmission module is responsible for collecting various types of patient data in real time through wearable devices, including vital signs data, movement status data, and pressure distribution data, ensuring that all data is uploaded to the data processing platform at preset time intervals.

[0104] The data cleaning module cleans the collected raw data, removing noise, outliers, and missing data to ensure data quality. Statistical analysis methods based on outlier detection and missing data imputation are used to clean vital sign and motion status data, ensuring accuracy and reliability before subsequent analysis.

[0105] The rehabilitation status analysis module analyzes vital sign data, movement status data, and pressure distribution data after cleaning. It calculates the mean and standard deviation of physiological state fluctuations, determines whether they exceed preset thresholds, and outputs warning signals.

[0106] Calculate the assessment value of the range of motion fluctuations, and assess the patient's rehabilitation progress based on the changing trends of motion angle, frequency, speed, and acceleration.

[0107] The pressure balance of the left and right soles is analyzed. By calculating the area change of the pressure zone of the left and right feet, the force balance is evaluated, and the trend of the pressure distribution map of the left and right feet is generated.

[0108] The rehabilitation progress assessment module evaluates the patient's overall rehabilitation progress based on the analysis results, outputs early warning information for abnormal fluctuations in vital signs, changes in motor precision, or uneven pressure on the soles of the feet, and suggests adjustments to the rehabilitation plan.

[0109] The feedback execution module automatically generates personalized rehabilitation plans based on the patient's rehabilitation progress assessment, adjusting exercise intensity, frequency, and training schedule. It generates rehabilitation progress reports and provides real-time feedback to the patient and their caregivers, helping the patient understand their rehabilitation status and next steps.

[0110] It should be understood that the terms “comprising” and “including” used in this disclosure and claims indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0111] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the disclosure. As used in this disclosure and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this disclosure and claims means any combination and all possible combinations of one or more of the associated listed items, and includes such combinations;

[0112] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for intelligently tracking the rehabilitation progress of orthopedic patients, characterized in that, Includes the following steps: Step 1: Data Acquisition and Transmission; At preset time intervals, the wearable device is accessed to collect various data of orthopedic patients in real time through accelerometers, gyroscopes, heart rate sensors, temperature sensors, pressure sensors and blood pressure sensors, including vital signs data, motion status data and pressure distribution data. Step 2: Data cleaning and preprocessing; The collected vital signs and motion status data are cleaned and preprocessed to remove outliers and noise, fill in missing data, and ensure data quality. Step 3: Centralized Data Analysis and Judgment; Based on the analysis of collected vital signs and movement status data, the patient's current physiological state and movement accuracy are determined, providing a basis for developing a rehabilitation plan; the vital signs data are preliminarily analyzed, and their mean and standard deviation are calculated, and first-level and second-level warning signals are generated based on their specific values; the movement status data are analyzed in depth, and the fluctuation range assessment value reflecting the rehabilitation progress is obtained by calculating the movement angle, frequency, speed and acceleration of the joint at the fracture site. The maximum and minimum values ​​of the joint's motion angle, frequency, velocity, and acceleration at the fracture site are obtained. The differences in motion angle, frequency, velocity, and acceleration are calculated separately, and the differences are weighted and summed to obtain the fluctuation range evaluation value. The pressure distribution data were analyzed to calculate the changing trend of plantar pressure distribution and to analyze the degree of balance of pressure between the left and right feet, thus assessing the plantar force of patients with fractures. A Cartesian coordinate system is established on the plantar pressure distribution map to obtain the pressure at each coordinate point. The maximum pressure of the left and right feet is obtained separately. Multi-level pressure contour regions are established with the maximum pressure of the left and right feet divided into six equal parts as the dividing line. The area of ​​each pressure contour region is calculated and the corresponding geometric centroid is extracted. According to the preset time interval, the area of ​​each pressure contour region in the current time interval is compared with the area of ​​the corresponding pressure contour region in the previous time interval to obtain the difference of each pressure distribution region of the left and right feet. The pressure balance coefficient is calculated based on the area of ​​each pressure contour region of the left and right feet. At the same time, the movement trajectory over time is formed based on the geometric centroid of each pressure contour region in different preset time intervals. Step 4: Rehabilitation progress assessment and personalized plan generation; Based on the analysis results of the patient's physiological status and motor precision, the rehabilitation progress is assessed, and a personalized rehabilitation exercise plan is generated based on the assessment results. If the fluctuation range assessment value continues to increase within T consecutive preset time intervals, the patient is judged to have good recovery progress within the T consecutive preset time intervals; otherwise, the patient is judged to have poor recovery progress and a suggestion is made to reduce the number of bodyweight exercises. If the difference in pressure distribution areas of the left foot and the difference in pressure distribution areas of the right foot continue to decrease within T consecutive preset time intervals, the corresponding foot plantar force state is judged to be stable; otherwise, the left and right foot plantar force is judged to be uneven, and gait correction exercises are added to the rehabilitation exercise program.

2. The intelligent tracking method for the rehabilitation progress of orthopedic patients according to claim 1, characterized in that, The vital signs data, movement status data, and stress distribution data include: Vital signs data include heart rate (HR) (t), blood pressure (BP) (t), respiratory rate (RR) (t), and body temperature (BT) (t); where t is the time of data collection. The motion data include the joint motion angle θ(t), frequency f(t), velocity v(t), and acceleration a(t) at the fracture site; where t is the time of data acquisition. The pressure distribution data includes the force data F of the joint at the fracture site and the plantar pressure distribution map; Data was extracted from the force data F of the joint at the fracture site and the plantar pressure distribution map.

3. The intelligent tracking method for the rehabilitation progress of orthopedic patients according to claim 2, characterized in that, The specific process for extracting data from the force data F of the joint at the fracture site and the plantar pressure distribution map is as follows: In the plantar pressure distribution map, vertical x-axis and y-axis are arranged to establish a plane rectangular coordinate system, and the pressure P(x,y) at each coordinate point in the plane rectangular coordinate system is obtained; the maximum pressure PLmax and PRmax of the left and right feet in the pressure distribution map are obtained respectively. Using PLmax / 6, 2PLmax / 6, 3PLmax / 6, 4PLmax / 6, and 5PLmax / 6 as dividing points, draw pressure contour lines on the plantar pressure distribution map of the left foot, and calculate the area enclosed by each pressure contour line, including the area SL1 enclosed by the 0 to 1PLmax / 6 contour line, the area SL2 enclosed by the PLmax / 6 contour line to the 2PLmax / 6 contour line, the area SL3 enclosed by the 2PLmax / 6 contour line to the 3PLmax / 6 contour line, the area SL4 enclosed by the 3PLmax / 6 contour line to the 4PLmax / 6 contour line, and the area SL5 enclosed by the 5PLmax / 6 contour line. Similarly, obtain the area SR1 of the region enclosed by contour lines 0 to 1PRmax / 6, the area SR2 of the region enclosed by contour lines PRmax / 6 to 2PRmax / 6, the area SR3 of the region enclosed by contour lines 2PRmax / 6 to 3PRmax / 6, the area SR4 of the region enclosed by contour lines 3PRmax / 6 to 4PRmax / 6, and the area SR5 of the region enclosed by contour line 5PRmax / 6. Extract the geometric centroids OL1(x,y) of the region bounded by contour lines 0 to PLmax / 6, OL2(x,y) of the region bounded by contour lines PLmax / 6 to 2PLmax / 6, OL3(x,y) of the region bounded by contour lines 2PLmax / 6 to 3PLmax / 6, OL4(x,y) of the region bounded by contour lines 3PLmax / 6 to 4PLmax / 6, and OL5(x,y) of the region bounded by contour line 5PLmax / 6. Similarly, obtain the geometric centroid OR1(x,y) of the portion enclosed by contour lines 0 to Pmax / 6, OR2(x,y) of the portion enclosed by contour lines PRmax / 6 to 2PRmax / 6, OR3(x,y) of the portion enclosed by contour lines 2PRmax / 6 to 3PRmax / 6, OR4(x,y) of the portion enclosed by contour lines 3PRmax / 6 to 4PRmax / 6, and OR5(x,y) of the portion enclosed by contour line 5PRmax / 6.

4. The intelligent tracking method for the rehabilitation progress of orthopedic patients according to claim 1, characterized in that, The specific process for removing outliers and noise is as follows: Assuming that both vital sign data and motion status data are random variables that conform to a normal distribution, the following formula is used: Outlier detection is performed to obtain the abnormal deviation feature value E[xi(t)] of each vital sign data and motion state data; where xi(t) is the specific vital sign data or motion state data, and i is the data type number symbol, representing data types including heart rate, blood pressure, respiratory rate, body temperature, and the motion angle, frequency, speed, and acceleration of the joint at the fracture site; where μ[xi(t)] is the mean of xi(t), and σ[xi(t)] is the variance of xi; where α is the preset detection coefficient, and the value of α is in the range of 1, 2, or 3; Vital sign data or motion state data with positive abnormal deviation feature value E[xi(t)] are considered abnormal deviation data and are removed.

5. The intelligent tracking method for the rehabilitation progress of orthopedic patients according to claim 1, characterized in that, The specific process of filling in missing data is as follows: For missing data, missing data detection and missing data imputation are performed. The specific process is as follows: Perform missing data detection, extract the collection time t of each data point from all vital signs data and motion status data, and record it as the timestamp of the vital signs data or motion status data; calculate the difference between the timestamps of all vital signs data and motion status data and the timestamp of the previously collected data of the same type to obtain the timestamp interval between the two data points. If it is found that the timestamp interval between two data xi(t1) and xi(t2) is greater than the preset time interval, it is determined that there is missing data between the two data; a supplementary data xi(t_new) is added before the two data, and the acquisition time t_new of the newly added supplementary data is the average of the timestamps of the two data. Determine the specific value of the newly added filler data. For each filler data xi(t_new), let its specific value be the average of the two data xi(t1) and xi(t2) before and after it.

6. The intelligent tracking method for the rehabilitation progress of orthopedic patients according to claim 1, characterized in that, The specific process for obtaining the assessment value reflecting the fluctuation range of rehabilitation progress by calculating the joint's movement angle, frequency, velocity, and acceleration at the fracture site is as follows: The maximum and minimum values ​​of the joint motion angle θ(t), frequency f(t), velocity v(t), and acceleration a(t) at the fracture site are obtained, and their differences are calculated, including the difference between the maximum and minimum values ​​of the motion angle Δθ, frequency Δf, velocity Δv, and acceleration Δa. The weighted sum of Δθ, Δf, Δv, and Δa is used to obtain the fluctuation range assessment value W(t) reflecting the rehabilitation progress.

7. The intelligent tracking method for the rehabilitation progress of orthopedic patients according to claim 3, characterized in that: The specific process for assessing the plantar force in a fracture patient is as follows: At preset time intervals, calculate the differences between SL1, SL2, SL3, SL4, and SL5 and the previous preset time interval to obtain the pressure distribution area differences of the left foot ΔSL1, ΔSL2, ΔSL3, ΔSL4, and ΔSL5; calculate the differences between SR1, SR2, SR3, SR4, and SR5 and the previous preset time interval to obtain the pressure distribution area differences of the right foot ΔSR1, ΔSR2, ΔSR3, ΔSR4, and ΔSR5. By preset formula Calculate the pressure balance coefficient Ration for the left and right feet; The closer the pressure balance coefficient Ration is to the surface level, the better the patient's lower limb recovery. Plot the motion trajectories of OL1(x,y), OL2(x,y), OL3(x,y), OL4(x,y), OL5(x,y), OR1(x,y), OR2(x,y), OR3(x,y), OR4(x,y) and OR5(x,y) collected at each preset time interval as time progresses.

8. The intelligent tracking method for the rehabilitation progress of orthopedic patients according to claim 7, characterized in that, The specific process of generating a personalized rehabilitation exercise plan based on the assessment results is as follows: If a Level 1 warning signal is detected based on the analysis of vital sign data, it is determined that the patient's physiological state may be abnormal. If a level 2 warning signal is detected, it indicates that the patient's physiological state is fluctuating too much and further examination is required. Based on the analysis results of the motion status data, if it is found that the fluctuation range assessment value continues to increase within T consecutive preset time intervals, it is determined that the patient's recovery progress is good within the T consecutive preset time intervals. Otherwise, if the patient's recovery progress is deemed poor within the aforementioned T consecutive preset time intervals, the patient is advised to appropriately reduce the number of bodyweight exercises to avoid overtraining. Based on the analysis results of the pressure distribution data, if the pressure distribution area differences of the left foot ΔSL1, ΔSL2, ΔSL3, ΔSL4 and ΔSL5 are found to decrease over a continuous T preset time interval, it indicates that the force state of the left foot tends to be stable. If the pressure distribution area differences of the right foot ΔSR1, ΔSR2, ΔSR3, ΔSR4 and ΔSR5 are found to decrease over a continuous T preset time interval, it indicates that the force state of the right foot tends to be stable. Otherwise, it is determined that the force is uneven on the left and right soles, and gait correction exercises are added to the subsequent rehabilitation program.

9. An intelligent tracking system for the rehabilitation progress of orthopedic patients, comprising a data acquisition and real-time transmission module, a data cleaning module, a rehabilitation status analysis module, a rehabilitation progress assessment module, and a feedback execution module, characterized in that, A method for intelligently tracking the rehabilitation progress of orthopedic patients as described in any one of claims 1 to 8; The data acquisition and real-time transmission module is responsible for collecting various types of patient data in real time through wearable devices, including vital signs data, movement status data, and pressure distribution data, ensuring that all data is uploaded to the data processing platform at preset time intervals; The data cleaning module cleans the collected raw data, removing noise, outliers, and missing data to ensure data quality. It uses statistical analysis methods based on outlier detection and missing data imputation to clean vital sign data and motion status data, ensuring that the data is accurate and reliable before subsequent analysis. The rehabilitation status analysis module analyzes vital sign data, movement status data, and pressure distribution data after cleaning; it calculates the mean and standard deviation of physiological state fluctuations, determines whether they exceed preset thresholds, and outputs warning signals. Calculate the assessment value of the range of motion fluctuations, and assess the patient's rehabilitation progress based on the changing trends of motion angle, frequency, speed, and acceleration; The pressure balance of the left and right soles is analyzed. By calculating the changes in the area of ​​the pressure zone of the left and right feet, the force balance is evaluated, and the trend of the pressure distribution map of the left and right feet is generated. The rehabilitation progress assessment module evaluates the patient's overall rehabilitation progress based on the analysis results, outputs early warning information for abnormal fluctuations in vital signs, changes in motor precision, or uneven pressure on the soles of the feet, and suggests adjustments to the rehabilitation plan. The feedback execution module automatically generates personalized rehabilitation plans based on the patient's rehabilitation progress assessment, and adjusts the exercise intensity, frequency and training plan. Generate rehabilitation progress reports and provide real-time feedback to patients and their caregivers to help patients understand their rehabilitation status and next steps.

Images