A method for evaluating joint range of motion for postoperative rehabilitation training of elderly patients

Abstract

The present application relates to the technical field of joint motion analysis, and in particular to a method for evaluating joint activity of postoperative rehabilitation training of elderly patients. The present application obtains joint correlation abnormality according to the abnormal degree of target joint motion at each time, and divides the motion cycle into similar sub-periods. The present application obtains motion lag factor according to the difference of activity angle change of the target joint and adjacent joint in the similar sub-period, and adjusts the change degree of the activity angle range of adjacent similar sub-periods to obtain joint rigidity coefficient. The present application adjusts the joint rigidity coefficient and joint correlation abnormality of the similar sub-period in the test period according to the correlation degree between the joint correlation abnormality and the joint rigidity coefficient, and obtains dysfunction coefficient. The present application evaluates the joint activity of postoperative rehabilitation training of elderly patients by using the dysfunction coefficient. The present application considers the joint dynamic cooperation mode and the time-space delay effect, and significantly improves the identification sensitivity of joint activity abnormality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of joint motion analysis, in particular to a method for evaluating joint range of motion in postoperative rehabilitation training of elderly patients. BACKGROUND

[0002] Joint range of motion refers to the range of motion that the joint can pass through when moving, which is an important indicator for evaluating the function of muscles, bones and nervous system, and not only reflects the flexibility of the joint, but also is an important basis for judging joint diseases and formulating rehabilitation plans, so the recovery of joint range of motion is crucial in the postoperative rehabilitation process of elderly patients.

[0003] The patent document with publication number CN116250831A discloses a shoulder joint range of motion calculation method based on visual recognition, which specifically obtains a front human body image of a tester completing a test action, extracts first coordinates of joint marker points of the tester from the image, calculates to obtain first and second length values, and then obtains arm forward stretching and lifting joint angle data to obtain a shoulder joint range of motion score. However, postoperative nerve edema causes delayed nerve signal conduction, which is manifested as a lag in the response of the distal joint after the issuance of the proximal joint motion instruction, and the increased collagen deposition between the joints after the operation increases the joint viscous resistance, resulting in a significant lack of recognition accuracy of subtle abnormalities in the postoperative rehabilitation process, and low accuracy in evaluating the joint range of motion in postoperative rehabilitation training of elderly patients. SUMMARY

[0004] In order to solve the technical problem of significant lack of recognition accuracy of subtle abnormalities in the postoperative rehabilitation process due to lack of analysis of the time and space delay effect induced by the biomechanical transmission efficiency of the movement chain and the change of joint stiffness, the purpose of the present application is to provide a method for evaluating the joint range of motion in postoperative rehabilitation training of elderly patients, and the technical solution adopted is as follows:

[0005] The present application provides a method for evaluating the joint range of motion in postoperative rehabilitation training of elderly patients, which comprises:

[0006] Obtaining the three-dimensional coordinates and activity angles of the target joint node and its adjacent joint nodes of the tester at each time point within the test period; the test period includes different action periods;

[0007] According to the abnormality degree of the target joint node motion at each time point within the test period, obtaining the joint correlation abnormality degree at each time point; based on the joint correlation abnormality degree, dividing each action period into similar sub-periods;

[0008] According to the difference between the activity angle change of the target joint and the activity angle change of the adjacent joint of the target joint in each similar sub-period, an activity lag factor of each similar sub-period is obtained; according to the change degree of the activity angle range of adjacent similar sub-periods in the test period, the activity lag factor is adjusted to obtain a joint rigidity coefficient of each similar sub-period;

[0009] According to the correlation degree between the joint correlation abnormality and the joint rigidity coefficient, the joint rigidity coefficient and the joint correlation abnormality of the similar sub-period in the test period are adjusted to obtain a dysfunction coefficient; and the dysfunction coefficient is used to evaluate the joint activity of the postoperative rehabilitation training of the elderly patient.

[0010] Further, the joint correlation abnormality at each time point is obtained by:

[0011] Two adjacent joints of the target joint are denoted as a first joint and a second joint respectively; a direction of the first joint pointing to the target joint is taken as a direction of a first vector, and a distance between the first joint and the target joint is taken as a size of the first vector; a direction of the target joint pointing to the second joint is taken as a direction of a second vector, and a distance between the second joint and the target joint is taken as a size of the second vector; an included angle between the first vector and the second vector at the same time point is obtained, denoted as an analysis angle at each time point; a change rate of the analysis angle at any two adjacent time points is calculated, denoted as a joint linkage fluctuation degree at the next time point;

[0012] According to the deviation degree of the joint linkage fluctuation degree at each time point relative to the joint linkage fluctuation degrees at all time points in the test period, a joint correlation abnormality at each time point is obtained.

[0013] Further, the similar sub-periods are divided for each action cycle based on the joint correlation abnormality, including:

[0014] For each action cycle, an initial pending time period is formed by a first time point in the action cycle, the first time point in the action cycle is denoted as an initial pending time point, when a difference between the joint correlation abnormalities of the pending time point and an adjacent next time point is less than a preset threshold, an adjacent next time point of the pending time point is added to the pending time period, the pending time period is updated, and a next time point of the pending time point is denoted as a new pending time point;

[0015] When the difference between the joint correlation abnormalities of the pending time point and the adjacent next time point is greater than or equal to the preset threshold, the pending time period is denoted as a similar sub-period, the adjacent next time point of the pending time point is denoted as the new pending time point, and a new pending time period is formed by the new pending time point; whether the difference between the joint correlation abnormalities of the new pending time point and the adjacent next time point is less than the preset threshold is judged; all time points in the action cycle are traversed, and the action cycle is divided into different similar sub-periods.

[0016] Further, the motion lag factor of each similar sub-period is obtained by:

[0017] The proximal joint of the two adjacent joints of the target joint is recorded as an analysis joint together with the target joint; for each similar sub-period, the activity angle of the analysis joint at all time points in the similar sub-period is curve-fitted, and the second derivative of the fitted function is obtained to obtain an angular acceleration function; the absolute value of the difference between the angular velocity functions of the two analysis joints is obtained to obtain a response efficiency function;

[0018] The autocorrelation function peak point of the response efficiency function in the time delay range from the beginning to the middle of the similar sub-period is obtained, and the value of the time delay corresponding to the peak point is taken as a conduction time delay coefficient;

[0019] The motion lag factor of the similar sub-period is obtained according to the activity angle at the first time point in the similar sub-period and the conduction time delay coefficient.

[0020] Further, the joint stiffness coefficient of each similar sub-period is obtained by:

[0021] The range of the activity angle of the target joint at all time points in each similar sub-period is recorded as an activity range scale;

[0022] The activity range scales of all similar sub-periods in the test period are arranged in time sequence to obtain a scale sequence; the difference between each two adjacent activity range scales in the scale sequence is calculated, and the average of all the differences is obtained to obtain a joint activity attenuation coefficient;

[0023] The joint stiffness coefficient of each similar sub-period is obtained according to the joint activity attenuation coefficient and the motion lag factor of each similar sub-period.

[0024] Further, the dysfunction coefficient is obtained by:

[0025] The average of the joint correlation abnormality at all time points in the similar sub-period is calculated and recorded as the overall smoothness; the overall smoothness of all similar sub-periods in the test period and the joint stiffness coefficient are arranged in time sequence respectively to obtain a smooth sequence and a stiffness sequence in turn;

[0026] The sum of the correlation coefficient between the smooth sequence and the stiffness sequence and the constant 1 is used to weight the sum of the overall smoothness and the joint stiffness coefficient of the similar sub-period to obtain a local obstacle coefficient; the average of the local obstacle coefficient of all similar sub-periods in the test period is normalized to obtain a dysfunction coefficient.

[0027] Further, the joint correlation abnormality at each time point is obtained by:

[0028] The mean and standard deviation of the joint linkage fluctuation degree at all time points in the test period are calculated respectively, the joint linkage fluctuation degree at each time point is taken as a numerator, and the ratio of the sum of the mean and twice the standard deviation to the denominator is normalized to obtain the joint linkage abnormality degree at each time point.

[0029] Further, the method for curve fitting of the activity angles of the analysis joint at all time points in the similar sub-period is a least square method.

[0030] Further, the joint activity attenuation coefficient and the motion lag factor are positively correlated with the joint rigidity coefficient.

[0031] Further, the correlation coefficient is a Pearson correlation coefficient.

[0032] The present application has the following beneficial effects:

[0033] In the embodiment of the present application, the motion state fluctuation of the target joint at adjacent time points reflects the out-of-sync situation of the motion direction of adjacent joints, and the sudden break of adjacent joint linkage beyond the normal fluctuation range of the patient himself will cause the sudden break of adjacent joint linkage, the linkage mutation degree between adjacent joints during the motion process can be analyzed, the joint linkage abnormality degree is obtained, and the similar sub-period is divided by using the same, the local micro-abnormality and phase lag can be captured, the early warning and accurate positioning of joint linkage abnormality are realized; the nerve signal conduction is delayed due to postoperative nerve edema, the response efficiency of the instantaneous motion of the distal joint to the proximal joint is analyzed through the difference between the activity angle changes of the target joint and the adjacent joint in the similar sub-period, the motion lag factor is obtained, the change degree of the activity angle range of the adjacent similar sub-period covers the spatial pathological characteristics of joint motion, the spatial abnormality in the motion maintenance stage is quantified, the joint rigidity coefficient is constructed by integrating the two factors, and the time and space delay effect of joint motion is considered; when the joint stiffness and cooperative fracture are coupled in a certain angle range, it is indicated that there is pathological motion chain failure, the actual joint activity loss is significantly underestimated, the joint linkage abnormality degree and the joint rigidity coefficient reflect the abnormal degree of adjacent joint linkage and the time and space delay effect in the motion process in sequence, the correlation degree of the two presents the possibility of joint pathological motion chain failure, and adjustment is performed by using the same, the joint dynamic cooperative mode and the time and space delay effect are considered, the recognition sensitivity of joint activity abnormality is significantly improved, the accuracy of the evaluation of joint activity degree of the elderly patient in postoperative rehabilitation training is improved, the rehabilitation scheme is optimized, and the risk of missed detection is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description only constitute some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0035] Figure 1 A step flow chart of a joint range of motion evaluation method for postoperative rehabilitation training of elderly patients provided by an embodiment of the present application;

[0036] Figure 2 A flow chart of a joint correlation abnormality acquisition method provided by an embodiment of the present application;

[0037] Figure 3 A flow chart of a motion hysteresis factor acquisition method provided by an embodiment of the present application;

[0038] Figure 4 A computer device schematic diagram of a joint range of motion evaluation device for postoperative rehabilitation training of elderly patients provided by an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purposes, the specific embodiments, structures, features and effects of a joint range of motion evaluation method for postoperative rehabilitation training of elderly patients according to the present application are described in detail as follows in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0041] The specific scheme of a joint range of motion evaluation method for postoperative rehabilitation training of elderly patients provided by the present application is specifically described below in combination with the drawings.

[0042] Embodiment 1:

[0043] The present application proposes a joint range of motion evaluation method for postoperative rehabilitation training of elderly patients, please refer to Figure 1 which shows a step flow chart of a joint range of motion evaluation method for postoperative rehabilitation training of elderly patients provided by an embodiment of the present application. The method comprises:

[0044] Step S1: Obtain the three-dimensional coordinates of the target joint of the tester and its adjacent joints at each time point in the test period; the test period includes different action cycles.

[0045] The depth camera is directed at the tester at a distance of 1.5 to 3 meters to ensure that the whole body is within the field of view, and the height of the camera is fixed to be level with the pelvis of the tester to reduce perspective distortion. Reflective marker points are attached to the positions of the target joint of the tester and its adjacent joints, and the depth camera is used to collect human body images during the process of the tester completing the preset test action. The above process needs to ensure that the target joint and its adjacent joints are always visible; the time period corresponding to the execution of the preset test action by the tester is recorded as the test period, and human body images at each time point in the test period are obtained. The depth camera with a built-in bone tracking algorithm is used in this scheme, which can directly provide the three-dimensional coordinates of the reflective points, i.e., the target joint and its adjacent joints, in each frame of human body image. It should be noted that the three-dimensional coordinates are determined based on a depth map.

[0046] It should be noted that this scheme takes the elbow joint as an example to evaluate the joint range of motion of the elbow joint in postoperative rehabilitation training, the target joint is the elbow joint, the two adjacent joints of the elbow joint are the shoulder joint and the wrist joint, and the preset test action is to perform 5 elbow flexion movements from 0 degrees to 90 degrees starting from unilateral upper limb 90 degree forward horizontal lifting. The time period corresponding to each elbow flexion movement is an action cycle.

[0047] In one implementation manner of the embodiment of the application, the frame rate of the depth camera is set to 120 frames per second.

[0048] Step S2: Obtain the joint correlation abnormality degree of each time point according to the abnormal degree of the motion state fluctuation of the target joint at adjacent time points in the test period; and divide each action cycle into similar sub-periods based on the joint correlation abnormality degree.

[0049] Postoperative joint stiffness of elderly patients can destroy the coordination of multi-joint movement, leading to desynchronization of the movement direction of adjacent joints. The motion state fluctuation of the target joint at adjacent time points is analyzed. Postoperative joint stiffness of elderly patients occurs intermittently, and when the patient has significant synovial adhesion of the joint, which leads to a decrease in joint range of motion, the sudden mutation of the linkage between adjacent joints will exceed the normal fluctuation range of the patient himself, and the linkage between adjacent joints may suddenly break. Therefore, the degree of linkage mutation between adjacent joints during the movement can be analyzed based on the abnormal degree of the motion state fluctuation of the target joint at adjacent time points, and the joint correlation abnormality degree is obtained.

[0050] The adjacent joints are normally linked under closed-loop neural control, but joint adhesion or pain leads to open-loop control, i.e. the patient's movement chain suddenly "stutters" at a certain angle, causing pathological disruption of the linkage of adjacent joints. The time periods can be classified when the abnormality degree of joint linkage is similar, and the similar sub-periods can be obtained, which can capture the slight local abnormality and phase lag, and realize early warning and accurate positioning of joint linkage abnormality.

[0051] Step S3: According to the lag degree of motion transmission of the target joint node in each similar sub-period, obtain the motion lag factor of each similar sub-period; adjust the motion lag factor according to the change degree of the range of motion angles of adjacent similar sub-periods in the test period, and obtain the joint stiffness coefficient of each similar sub-period.

[0052] Postoperative nerve edema causes delay of nerve signal transmission, which is manifested as a response lag of the distal joint after the proximal joint motion instruction is issued. In order to capture the start-up lag of joint motion, the response efficiency of instantaneous motion of the distal joint to the proximal joint is analyzed through the difference in the change of the range of motion angles of the target joint node and its adjacent joint nodes in each similar sub-period, the start-up lag degree of the target joint node in the motion process in the similar sub-period is reflected, and the motion lag factor is obtained. The motion lag factor can directly reflect the delay of neuromuscular control or joint structural abnormality, and can be used as an early warning index of joint linkage disruption risk.

[0053] Under normal circumstances, the increase of collagen deposition between joints of elderly patients after surgery increases the viscous resistance of joints, resulting in a decrease in the range of joint motion. The motion lag factor quantifies the time abnormality in the start-up stage of joint motion, and the change degree of the range of motion angles of adjacent similar sub-periods in the test period covers the spatial pathological characteristics of joint motion. By analyzing the change degree of the range of motion angles of adjacent similar sub-periods in the test period, the spatial abnormality in the motion maintenance stage is quantified. The joint stiffness coefficient is constructed by integrating the change degree of the range of motion angles of adjacent similar sub-periods and the motion lag factor, considering the time and space delay effect of joint motion.

[0054] Step S4: According to the correlation between the joint linkage abnormality degree and the joint stiffness coefficient, adjust the joint stiffness coefficient and the joint linkage abnormality degree of the similar sub-period in the test period, and obtain the dysfunction coefficient; use the dysfunction coefficient to evaluate the range of motion of the joint of the elderly patient after rehabilitation training.

[0055] When the joint stiffness and the synergistic fracture are coupled in a certain angular range, it indicates that there is a pathological motion chain failure, i.e., a structural biomechanical dysfunction. The traditional static range of motion calibration method cannot capture such dynamic coupling, and significantly underestimates the actual loss of joint range of motion. The joint correlation abnormality reflects the abnormal degree of linkage between adjacent joint nodes during movement, and the joint stiffness coefficient reflects the time-space delay effect of joint movement. The correlation between the joint correlation abnormality and the joint stiffness coefficient shows the possibility of joint pathological motion chain failure. By adjusting the joint stiffness coefficient and the joint correlation abnormality, considering the joint dynamic synergy mode and the time-space delay effect, the sensitivity of joint activity abnormality recognition is significantly improved, and high-precision and full-cycle joint range of motion calibration results are provided to optimize the rehabilitation scheme and reduce the risk of missed detection.

[0056] Preferably, in some possible implementation manners of the embodiment of the present application, the joint correlation abnormality acquisition method can refer to Figure 2 The figure shows a joint correlation abnormality acquisition method flowchart provided by an embodiment of the present application. The method comprises the following steps:

[0057] Step S211: two adjacent joint nodes of the target joint node are respectively denoted as a first joint node and a second joint node; the direction of the first joint node pointing to the target joint node is taken as the direction of a first vector, and the distance between the first joint node and the target joint node is taken as the size of the first vector; the direction of the target joint node pointing to the second joint node is taken as the direction of a second vector, and the distance between the second joint node and the target joint node is taken as the size of the second vector; the included angle of the first vector and the second vector at the same time is obtained, denoted as the analysis angle at each time; the change rate of the analysis angle at any two adjacent times is calculated, denoted as the joint linkage fluctuation degree at the next time.

[0058] It should be noted that in the present scheme, the patient holds the upper limb horizontally at 90 degrees before elbow flexion, i.e., the analysis angle is 0 degrees before elbow flexion. The analysis angle reflects the consistency of the movement direction of the joint node. The ratio of the absolute value of the difference between the analysis angle at the next time and the analysis angle at the previous time to the time interval is taken as the change rate, which quantifies the instantaneous rate of change of the movement direction of the adjacent joint, and reflects the severity of the movement direction desynchronization of the adjacent joint. The greater the joint linkage fluctuation degree at each time, the more unsmooth the linkage between the elbow and shoulder joint structure and the elbow and wrist joint structure, and the more serious the movement joint stiffness or abnormality of the patient at that time. In the present embodiment, the joint linkage fluctuation degree at the first time in the test period is directly set to a constant 0.

[0059] Step S212: according to the deviation of the joint linkage fluctuation degree at each time relative to the joint linkage fluctuation degree at all times in the test period, the joint correlation abnormality at each time is obtained.

[0060] Preferably, in some possible implementation manners of the embodiment of the present application, the method for obtaining the joint correlation abnormality degree comprises: calculating the mean value and the standard deviation of the joint linkage fluctuation degree at all time points in the test period respectively, normalizing the ratio obtained by taking the joint linkage fluctuation degree at each time point as the numerator and the sum of the mean value and twice the standard deviation as the denominator, to obtain the joint correlation abnormality degree at each time point. It should be noted that the joint correlation abnormality degree measures the abnormality degree of the joint linkage fluctuation degree at each time point by analyzing the deviation of the joint linkage fluctuation degree at each time point from the overall distribution of the joint linkage fluctuation degree. If the joint linkage fluctuation degree at each time point is larger, but the overall joint linkage fluctuation degree in the test period is smaller and more stable, it indicates that the structural linkage mutation of the target joint node and its adjacent joint nodes at each time point exceeds the normal fluctuation range of the patient itself, and the possibility of sudden breakage of the joint linkage is larger, such as the jam caused by synovial adhesion.

[0061] In the embodiment of the present application, the normalization processing is performed using the maximum-minimum normalization, and the normalization methods such as Sigmoid function, function transformation, etc. can also be selected, which are not limited herein.

[0062] It should be noted that, since the target joint node of the patient continuously moves in the test period, the mean value and the standard deviation of the joint linkage fluctuation degree at all time points cannot be zero at the same time.

[0063] In other embodiments of the present application, the Z-score of the joint linkage fluctuation degree at each time point in the test period can also be obtained, which is denoted as the joint correlation abnormality degree.

[0064] Preferably, in some possible implementation manners of the embodiment of the present application, the method for dividing the similar sub-periods comprises: for each action cycle, constructing an initial pending period by the first time point in the action cycle, taking the first time point in the action cycle as the initial pending time point, when the difference between the joint correlation abnormality degrees of the pending time point and the adjacent next time point is less than a preset threshold, adding the adjacent next time point of the pending time point to the pending period, updating the pending period, and taking the next time point of the pending time point as a new pending time point; when the difference between the joint correlation abnormality degrees of the pending time point and the adjacent next time point is greater than or equal to the preset threshold, taking the pending period as a similar sub-period, taking the adjacent next time point of the pending time point as a new pending time point, and constructing a new pending period by the new pending time point, judging whether the difference between the joint correlation abnormality degrees of the new pending time point and the adjacent next time point is less than the preset threshold, and traversing all time points in the action cycle to divide the action cycle into different similar sub-periods. The difference refers to the absolute value of the difference.

[0065] It should be noted that, if the difference between the joint association abnormality of the to-be-determined time and the adjacent next time is greater, it indicates that the possibility of abnormality of the adjacent joint linkage is greater, and the instantaneous motion is stalled. The absolute value of the difference between the joint association abnormality of the adjacent two times in the same similar sub-period is less than the preset threshold value.

[0066] In one implementation manner of the embodiment of the present application, the preset threshold value is set to 0.3.

[0067] Preferably, in some possible implementation manners of the embodiment of the present application, the method for acquiring the motion lag factor can refer to Figure 3 which shows a flow chart of a method for acquiring a motion lag factor provided by one embodiment of the present application, and the method comprises the following steps:

[0068] Step S221: record the proximal joint of the two adjacent joints of the target joint and the target joint as analysis joints; for each similar sub-period, perform curve fitting on the activity angle of the analysis joints at all times in the similar sub-period, perform second-order derivation on the fitting function obtained by the fitting, and obtain an angular acceleration function; take the absolute value of the difference between the angular velocity functions of the two analysis joints to obtain a response efficiency function.

[0069] Based on the theory of dynamic chain, the proximal joint needs to be activated to provide a stable motion basis for the distal joint. The shoulder joint is the proximal joint among the shoulder joint and the wrist joint, and the stability of the shoulder joint directly affects the motion efficiency of the elbow joint. The activity angle of the two analysis joints is measured by using an electronic protractor. Taking the elbow joint and the shoulder joint as an example, when measuring the activity angle of the shoulder joint, the protractor axis is aligned with the humeral head, and the fixed arm is parallel to the sagittal plane of the trunk; when measuring the activity angle of the elbow joint, the protractor axis is placed on the lateral epicondyle of the humerus, and the moving arm moves with the forearm; the activity angle of the analysis joint at each time is measured by using the protractor within the test period.

[0070] It should be noted that the least square method is used for curve fitting in this embodiment, and other methods such as cubic spline interpolation can also be used. Because natural joint movements such as elbow flexion usually involve variable acceleration, the angular acceleration function is determined. The motion response function of the distal joint and the proximal joint is constructed by using the angular acceleration functions of the two analysis joints. The smaller the absolute value of the difference between the two angular acceleration functions is, the higher the response efficiency of the instantaneous motion of the distal joint, i.e. the elbow joint, to the proximal joint, i.e. the shoulder joint.

[0071] Step S222: obtain the autocorrelation function peak point of the response efficiency function in the range of the start time to the middle time of the similar sub-period, and take the value of the time delay corresponding to the peak point as the conduction time delay coefficient.

[0072] It should be noted that the detailed acquisition step of the autocorrelation function peak point is: acquiring the autocorrelation function of the response efficiency function in the similar sub-period, and the value range of the time delay is the starting moment to the middle moment of the similar sub-period; all values of the autocorrelation function in the value range are calculated, and the moment corresponding to the maximum value is selected as the conduction time delay coefficient. The greater the conduction time delay coefficient, the more significant the joint start-up lag in the similar sub-period, and the joint range of motion of the patient in the similar sub-period is abnormal; on the contrary, the better the two joint synergies, the more accurate the joint range of motion of the patient in the similar sub-period. The expression of the autocorrelation function is known to those skilled in the art, and will not be described here.

[0073] In the embodiment of the application, by constraining the time delay range to be the first 50% of the similar sub-period, edge effect interference is avoided, and the maximum autocorrelation time delay is used to represent the dominant dynamic mode of the system response.

[0074] Step S223: acquiring a motion lag factor of the similar sub-period according to the activity angle at the first moment in the similar sub-period and the conduction time delay coefficient.

[0075] Considering that the tendon pre-tension increases at a large angle, additional time is needed to overcome the static friction, and the lag increases with the increase of the initial angle, the activity angle at the first moment in the similar sub-period is introduced to analyze the joint motion start-up lag capture, and the angle is compensated; the greater the activity angle, the greater the tendon pre-tension, which leads to more serious joint start-up lag; the greater the conduction time delay coefficient, the more significant the joint start-up lag in the similar sub-period. Therefore, the activity angle at the first moment in the similar sub-period and the conduction time delay coefficient are both positively correlated with the motion lag factor. In the embodiment of the application, the product of the sine value of the activity angle at the first moment in the similar sub-period and the conduction time delay coefficient is normalized to obtain the motion lag factor of the similar sub-period. The motion lag factor reflects the start-up lag degree of the joint during the motion process in the similar sub-period, and the greater the motion lag factor means that the motion coordination of the joint of the patient during the postoperative rehabilitation period is worse, and there is more significant delay in the motion start-up and the motion process.

[0076] It should be noted that the value range of the activity angle is 0 degrees to 90 degrees.

[0077] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the joint stiffness coefficient includes: recording the range of the activity angles of the target joint point at all times within each similar sub-time period as the activity range scale; arranging the activity range scales of all similar sub-time periods within the test period in chronological order to obtain a scale sequence; calculating the difference between every two adjacent activity range scales in the scale sequence, averaging all differences to obtain the joint activity attenuation coefficient; and obtaining the joint stiffness coefficient of each similar sub-time period based on the joint activity attenuation coefficient and the motion hysteresis factor of each similar sub-time period. Wherein, the difference between two adjacent activity range scales in the sequence is equal to the difference between the preceding and following activity range scales.

[0078] It should be noted that a larger joint mobility attenuation coefficient indicates a faster decline in joint mobility within similar sub-time periods, and a more pronounced spatial abnormality in joint movement. This is due to the increased nonlinearity of viscous resistance caused by increased collagen deposition, which exacerbates the impact on joint mobility. When both the motion lag factor and the joint mobility attenuation coefficient are larger within similar sub-time periods, it indicates more severe biomechanical dysfunction of the joint caused by the combined effects of delayed nerve conduction and viscous resistance, resulting in a larger joint stiffness coefficient. Therefore, both the motion lag factor and the joint mobility attenuation coefficient are positively correlated with the joint stiffness coefficient. In this embodiment of the invention, the product of the motion lag factor and the joint mobility attenuation coefficient for each similar sub-time period is normalized to obtain the joint stiffness coefficient.

[0079] In this embodiment of the invention, the Sigmoid function is used for normalization. Other normalization methods such as function transformation and max-min normalization can also be selected, and no limitation is made here.

[0080] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the functional impairment coefficient includes:

[0081] The mean of joint correlation anomaly degree at all times within similar sub-time periods is calculated and recorded as the overall smoothness. The overall smoothness and joint stiffness coefficients of all similar sub-time periods within the test period are arranged in chronological order to obtain the smooth sequence and the stiff sequence. The sum of the correlation coefficient between the smooth sequence and the stiff sequence and the constant 1 is used to weight the sum of the overall smoothness and joint stiffness coefficients of similar sub-time periods to obtain the local impairment coefficient. The mean of the local impairment coefficients of all similar sub-time periods within the test period is normalized to obtain the functional impairment coefficient.

[0082] It should be noted that when joint stiffness and synergistic fracture are spatiotemporally coupled within a specific angular range—that is, when the degree of joint correlation anomaly and the joint stiffness coefficient are greater—the more abnormal the linkage between adjacent joint points during the test subject's movement and the more pronounced the spatiotemporal delay effect of joint movement. This indicates the presence of pathological kinetic chain failure in similar sub-time periods, i.e., structural biomechanical dysfunction. The correlation between joint correlation anomaly and the joint stiffness coefficient reveals the possibility of pathological kinetic chain failure in the joint. Adjusting this correlation can further improve the accuracy of structural biomechanical dysfunction analysis.

[0083] In the embodiments of the present invention, the overall smoothness, joint stiffness coefficient, correlation coefficient between smooth sequences and stiff sequences, and functional impairment coefficient can also be constructed through other basic mathematical operations, which are not limited or elaborated here.

[0084] In one implementation of this invention, the correlation coefficient is the Pearson correlation coefficient, but it can also be the Spearman correlation coefficient, Kendall rank correlation coefficient, canonical correlation coefficient, etc.

[0085] In this embodiment of the invention, an inertial measurement unit (IMU) is used to collect the range of motion of the elbow joint during each elbow flexion movement, and the average range of motion of all elbow flexion movements is recorded as the final range of motion. The functional impairment coefficient of the test subject is input into a pre-trained machine learning model, and multimodal features are fused through a multilayer perceptron branch to output the final range of motion. The model establishes a mapping relationship between the functional impairment coefficient and the range of motion through supervised learning, resulting in a trained machine learning model. The functional impairment coefficient of elderly patients is obtained and input into the trained machine learning model, which outputs an estimated value of the range of motion of the elbow joint of the elderly patients. It should be noted that the machine learning module can be a gradient boosting decision tree, a temporal convolutional network, or a neural network, etc. At the same time, rehabilitation stage parameters of elderly patients are obtained as auxiliary features. These rehabilitation stage parameters include postoperative days, pain index, and muscle strength level, etc., to further improve the reliability of the range of motion of the elbow joint of elderly patients.

[0086] The joint mobility data in this solution is based on objective feature annotations generated from big data analysis. It does not provide a direct diagnostic conclusion, but rather provides doctors with objective quantitative data for reference. This allows doctors to focus more quickly on the pathological features of the target joint and improves their efficiency in judging joint mobility during postoperative rehabilitation training. The final medical judgment still needs to be made by a professional doctor.

[0087] This invention is now complete.

[0088] Example 2:

[0089] This invention also provides a schematic diagram of a computer device for assessing joint mobility during postoperative rehabilitation training in elderly patients. Please refer to [link / reference].Figure 4 The computer device includes a memory 501, a processor 502, and a computer program 503 stored in the memory 501 and running on the processor 502. When the processor 502 executes the computer program 503, the computer device can perform any of the aforementioned methods for assessing joint mobility in postoperative rehabilitation training for elderly patients.

[0090] Furthermore, embodiments of this application also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to perform a method for assessing joint mobility in postoperative rehabilitation training for elderly patients provided in embodiments of this application.

[0091] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0092] When each module is divided according to its function, the device may also include a communication module, a signal analysis module, a complexity analysis module, and a positioning module. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0093] It should be understood that the device provided in this embodiment is used to perform the above-described method for assessing joint range of motion in postoperative rehabilitation training for elderly patients, and therefore can achieve the same effect as the above-described implementation method.

[0094] When using integrated units, the device may include a processing module and a storage module. When applied to a workpiece, the processing module can be used to control and manage the workpiece's operations. The storage module can be used to support the execution of program code by the workpiece.

[0095] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits contained in conjunction with the disclosure of this application. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0096] Example 3:

[0097] This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the above-described related method steps to implement the method for assessing joint mobility in postoperative rehabilitation training for elderly patients provided in the above embodiment.

[0098] Example 4:

[0099] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement the method for assessing joint mobility during postoperative rehabilitation training for elderly patients provided in the above embodiment.

[0100] In this embodiment, the apparatus, computer-readable storage medium, or computer program product chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0101] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0102] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0103] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for assessing joint range of motion during postoperative rehabilitation training in elderly patients, characterized in that, The method includes: The tester obtains the three-dimensional coordinates and movement angles of the target joint and its adjacent joints at each moment during the test period; the test period includes different motion cycles. Based on the degree of abnormality of the target joint movement at each moment within the test period, the joint correlation anomaly degree at each moment is obtained; based on the joint correlation anomaly degree, each action cycle is divided into similar sub-time periods; Based on the difference in the change of the activity angle between the target joint and its adjacent joints in each similar sub-time period, the motion hysteresis factor of each similar sub-time period is obtained; based on the degree of change in the range of activity angle between adjacent similar sub-time periods in the test period, the motion hysteresis factor is adjusted to obtain the joint stiffness coefficient of each similar sub-time period. Based on the correlation between the joint correlation abnormality and the joint stiffness coefficient, the joint stiffness coefficient and joint correlation abnormality of similar sub-time periods within the test period are adjusted to obtain the functional impairment coefficient; the functional impairment coefficient is used to evaluate the joint mobility of elderly patients during postoperative rehabilitation training. The process of obtaining the motion lag factor for each similar sub-time period includes: The proximal joint of two adjacent joints of the target joint is denoted as the analysis joint. For each similar sub-time period, the activity angle of the analysis joint at all times within the similar sub-time period is curve-fitted. The second derivative of the fitted function is obtained to get the angular acceleration function. The absolute value of the difference between the angular acceleration functions of the two analysis joints is taken to obtain the response efficiency function. Obtain the peak point of the autocorrelation function of the response efficiency function within the range from the beginning to the middle of a similar sub-period time delay, and use the value of the time delay corresponding to the peak point as the propagation delay coefficient; Based on the activity angle at the first moment within the similar sub-period and the transmission delay coefficient, the motion lag factor of the similar sub-period is obtained.

2. The method for assessing joint range of motion in postoperative rehabilitation training of elderly patients according to claim 1, characterized in that, The process of obtaining the joint correlation anomaly degree at each time step includes: Two adjacent joints of the target joint are designated as the first joint and the second joint, respectively. The direction from the first joint to the target joint is taken as the direction of the first vector, and the distance between the first joint and the target joint is taken as the magnitude of the first vector. The direction from the target joint to the second joint is taken as the direction of the second vector, and the distance between the second joint and the target joint is taken as the magnitude of the second vector. The angle between the first and second vectors at the same moment is obtained and recorded as the analysis angle at each moment. The rate of change of the analysis angle between any two adjacent moments is calculated and recorded as the joint linkage fluctuation at the next moment. The joint correlation anomaly degree at each moment is obtained based on the degree of deviation of the joint linkage fluctuation degree at each moment within the test period relative to the joint linkage fluctuation degree at all moments.

3. The method for assessing joint range of motion in postoperative rehabilitation training of elderly patients according to claim 1, characterized in that, The process of dividing each motion cycle into similar sub-time periods based on the joint correlation anomaly degree includes: For each action cycle, the first moment in the action cycle constitutes the initial undetermined time period. The first moment in the action cycle is recorded as the initial undetermined moment. When the difference between the joint correlation abnormality degree between the undetermined moment and the next adjacent moment is less than a preset threshold, the next adjacent moment of the undetermined moment is added to the undetermined time period, the undetermined time period is updated, and the next moment of the undetermined moment is recorded as the new undetermined moment. When the difference between the joint correlation anomaly degree of the pending time and the next adjacent time is greater than or equal to the preset threshold, the pending time period is recorded as a similar sub-time period, the next adjacent time of the pending time is recorded as a new pending time, and the new pending time constitutes a new pending time period. It is then determined whether the difference between the joint correlation anomaly degree of the new pending time and the next adjacent time is less than the preset threshold. All times within the action cycle are traversed, and the action cycle is divided into different similar sub-time periods.

4. The method for assessing joint range of motion in postoperative rehabilitation training of elderly patients according to claim 1, characterized in that, The process of obtaining the joint stiffness coefficient for each similar sub-time period includes: The range of the activity angles of the target key point at all times within each similar sub-time period is denoted as the activity range scale. Arrange the activity range scales of all similar sub-time periods within the test period in chronological order to obtain a scale sequence; calculate the difference between every two adjacent activity range scales in the scale sequence, and average all differences to obtain the joint activity attenuation coefficient; The joint stiffness coefficient for each similar sub-time period is obtained based on the joint activity attenuation coefficient and the motion hysteresis factor for each similar sub-time period.

5. The method for assessing joint range of motion in postoperative rehabilitation training of elderly patients according to claim 1, characterized in that, The acquisition of the functional impairment coefficient includes: The mean of the joint association anomaly degree at all times within the similar sub-time periods is calculated and recorded as the overall smoothness; the overall smoothness of all similar sub-time periods within the test period and the joint stiffness coefficient are arranged in time sequence to obtain the smooth sequence and the stiffness sequence in turn; Using the sum of the correlation coefficient between the smooth sequence and the rigid sequence and the constant 1, the sum of the overall smoothness and the joint rigidity coefficient of similar sub-time periods is weighted to obtain the local obstacle coefficient; the mean of the local obstacle coefficients of all similar sub-time periods within the test period is normalized to obtain the functional impairment coefficient.

6. The method for assessing joint range of motion in postoperative rehabilitation training of elderly patients according to claim 2, characterized in that, The process of obtaining the joint correlation anomaly degree at each time step includes: The mean and standard deviation of the joint linkage fluctuation at all times during the test period are calculated respectively. The ratio of the joint linkage fluctuation at each time point as the numerator and the sum of the mean and twice the standard deviation as the denominator is normalized to obtain the joint linkage anomaly degree at each time point.

7. The method for assessing joint range of motion in postoperative rehabilitation training of elderly patients according to claim 1, characterized in that, The method for curve fitting the activity angles of the analysis joints at all times within similar sub-time periods is the least squares method.

8. The method for assessing joint range of motion in postoperative rehabilitation training of elderly patients according to claim 4, characterized in that, The joint motion attenuation coefficient and the motion hysteresis factor are both positively correlated with the joint stiffness coefficient.

9. The method for assessing joint range of motion in postoperative rehabilitation training of elderly patients according to claim 5, characterized in that, The correlation coefficient mentioned is the Pearson correlation coefficient.

Images