Knee joint postoperative adaptive progressive rehabilitation training method based on pain detection

Abstract

The invention relates to the technical field of knee joint rehabilitation, in particular to a knee joint postoperative adaptive progressive rehabilitation training method based on pain detection, which comprises the following steps: initializing a knee joint rehabilitation machine, and enabling a patient to wear myoelectricity acquisition equipment and the knee joint rehabilitation machine; the patient drives the rehabilitation machine to conduct active knee joint flexion, and knee joint active movement angle data are recorded; the rehabilitation machine conducts passive knee joint flexion motion, and training data needed by the pain detection model are collected; preprocessing and feature extraction are carried out, and a classifier is trained to obtain a pain detection model; selecting a rehabilitation training mode to train the patient; after the patient finishes all training, the knee joint flexion is actively performed again, and active movement angle data of the knee joint are recorded. According to the application, pain detection is carried out by using the surface electromyogram signals of the patient, automatic identification of the knee joint movement range is realized, multi-mode training is carried out according to the training condition of the patient, and the problem of resource shortage of rehabilitation physicians is relieved.

Description

Technical Field

[0001] The present application relates to the technical field of knee joint rehabilitation for patients with periarticular fractures of the knee, and in particular to an adaptive progressive rehabilitation training method for knee joint surgery based on pain detection. Background Art

[0002] Traffic accidents, work-related injuries, and the increasing incidence of osteoporosis caused by an aging population have led to a large number of fracture patients in my country every year. The three basic links of fracture treatment are reduction, fixation and rehabilitation. Reduction and fixation are usually completed in hospitals through surgery, with good completion and controllability. Compared with reduction and fixation, the resources of clinical rehabilitation therapists in my country are relatively tight. Most patients cannot obtain timely and effective rehabilitation training, or the wrong concept of rest after fracture leads to problems such as joint adhesion and swelling, which seriously limits the joint mobility and brings great obstacles to the patient's postoperative rehabilitation. In recent years, the development of rehabilitation robots has provided a new way to alleviate the problem of fracture patients missing the best time for rehabilitation training due to the lack of rehabilitation therapists. The advantages of robot motion stability and repeatability enable it to partially replace rehabilitation therapists and assist patients in high-intensity, repetitive exercise training, thereby helping patients achieve better rehabilitation training results.

[0003] In clinical rehabilitation training, especially for patients with problems such as joint adhesion and swelling who are in urgent need of rehabilitation treatment, the maximum range of motion of the knee joint should be trained to cause slight pain. At this time, the adhesion tissue can be properly stretched to achieve the purpose of gradually expanding the range of joint motion. At present, clinical confirmation requires subjective expression of patients and the hand feel experience of rehabilitation physicians, and objective quantification is not possible.

[0004] However, there is currently little research on rehabilitation robots for the needs of postoperative rehabilitation training for fractures. Existing postoperative rehabilitation machines for fractures have simple functions and cumbersome operations. In particular, existing rehabilitation machines can only set the range of motion of the knee joint in advance, and cannot adjust the range of motion in time according to the patient's own conditions because they cannot sense and detect the patient's pain. Rehabilitation physicians are required to perform real-time operations, which does not alleviate the problem of tight resources for rehabilitation physicians. Therefore, in order to meet the postoperative rehabilitation needs of patients with peri-knee fractures, especially the needs of early motor function rehabilitation training, there is an urgent need for a rehabilitation training method that can autonomously sense the patient's current optimal range of motion of the knee joint and adaptively control multi-modal training. Summary of the invention

[0005] The embodiment of the present application provides an adaptive progressive rehabilitation training method for knee joint surgery based on pain detection. By utilizing the patient's surface electromyography signal for pain detection, automatic identification of the range of motion of the knee joint is achieved, and multi-modal training is performed according to the patient's training situation, alleviating the problem of tight rehabilitation physician resources.

[0006] In order to solve the above technical problems, an embodiment of the present application provides an adaptive progressive rehabilitation training method for knee joint surgery based on pain detection, comprising the following steps: first, the knee joint rehabilitation machine is initialized, and the patient wears the electromyography acquisition device and the knee joint rehabilitation machine; then, after the patient wears the electromyography acquisition device and the knee joint rehabilitation machine, the knee joint rehabilitation machine is driven to perform active knee flexion, and the active knee motion angle data of the patient before training is recorded; next, the patient follows the knee joint rehabilitation machine to perform passive knee flexion movement to collect the training data required for the pain detection model; then, the collected training data is preprocessed and feature extracted, a support vector machine is selected as a classifier, and the classifier is trained using the extracted two types of sample features to obtain a pain detection model; next, a rehabilitation training mode is selected to train the patient; the rehabilitation training modes include: passive motion training, pain adaptive passive training, confrontation training, and pain adaptive confrontation training; finally, after the patient completes all training, the knee joint rehabilitation machine is driven to perform active knee flexion again, and the active knee motion angle data of the patient after training is recorded.

[0007] In some exemplary embodiments, the patient wears the electromyography acquisition device and the knee joint rehabilitation machine, including: step 1, the patient wears the electromyography acquisition device, and the electrodes of the electromyography acquisition device are respectively attached to the rectus femoris, vastus medialis, long head of biceps femoris and semitendinosus of the thigh; the electromyography acquisition device is started to start surface electromyography signal data collection; step 2, the patient wears the knee joint rehabilitation machine, and when wearing it, ensure that the bionic joint connecting rod coincides with the rotation center of the knee joint, and fill the gap between the patient's affected limb and the knee joint rehabilitation machine through the airbag; step 3, fill in personal information on the system interface of the knee joint rehabilitation machine, and establish a personal training record file for the patient.

[0008] In some exemplary embodiments, the active motion angle data of the patient's knee joint before training is recorded, including: adjusting the knee joint rehabilitation machine to an unloading state so that the knee joint rehabilitation machine can follow the flexion movement of the affected limb; the patient actively flexes the knee joint and relaxes after reaching the maximum flexion angle of the patient's knee joint; the knee joint rehabilitation machine records the patient's maximum angle of the knee joint during the process of active knee flexion.

[0009] In some exemplary embodiments, the training data required for the pain detection model is collected, including: step 1, a knee rehabilitation machine drives the affected limb to move to an initial position, and gradually increases the knee joint angle from the initial position until the patient feels pain of 3 points in the pain assessment digital scale, and records the knee joint angle at this time; step 2, a trajectory curve is generated according to the recorded knee joint angle to perform knee flexion movement, and the knee joint is maintained at the maximum angle for 5 seconds; step 3, the knee flexion movement in step 2 is performed reciprocally 3 times, the patient's electromyographic signal during the knee flexion movement is recorded as a training signal for the pain detection model, and pain and non-pain labels are added to the electromyographic signal.

[0010] In some exemplary embodiments, the classifier is trained using the extracted two types of sample features to obtain a pain detection model, including: first, preprocessing the signal; then, extracting the features of the preprocessed electromyographic signal in a sliding window manner; finally, using a support vector machine as a classifier, and training the classifier using the extracted two types of sample features; optimizing the classifier hyperparameters using a cross-validation method and grid optimization; selecting the hyperparameter model with the highest evaluation index to complete the classifier training and establish a pain detection model; the classifier hyperparameters include cost and weight.

[0011] In some exemplary embodiments, the process of passive motion training includes: first setting parameters before starting passive motion training, generating a corresponding motion trajectory after the parameters are confirmed, and starting passive motion training; the knee joint rehabilitation machine drives the affected limb to perform passive motion according to the planned trajectory; when the knee joint rehabilitation machine reaches the set end angle, it maintains it for 10 seconds; after 10 seconds, the knee joint rehabilitation machine returns to the initial angle; multiple trainings are performed according to the set number of exercise parameters; after the training is completed, the data of this training process is saved in a folder.

[0012] In some exemplary embodiments, the process of pain adaptive passive training includes: first setting parameters before the start of pain adaptive passive training, generating the corresponding motion trajectory after the parameters are confirmed, and starting pain adaptive passive motion training; the knee joint rehabilitation machine drives the affected limb to perform passive motion according to the planned trajectory; if one of the following situations is met, the knee joint rehabilitation machine enters the holding stage and maintains the current angle for 10 seconds; in the first situation, the patient actively stops the motor movement due to excessive pain perception; in the second situation, the motor movement angle reaches the termination angle; in the third situation, the pain detection model outputs a judgment result of 1; after 10 seconds, the knee joint rehabilitation machine drives the affected limb to return to the initial angle; single rehabilitation training After completion, the movement frequency parameters will be updated according to the force-speed ratio and resistance change rate during the training process; multiple training will be performed according to the set movement number parameters; after each three flexion movements are completed, the movement range will be updated according to the number of times each condition enters the holding stage; when the condition for entering the holding stage is that the number of times the first situation is greater than or equal to 2, the termination angle will be reduced by 3°; when the condition for entering the holding stage is that the number of times the second situation is greater than or equal to 2, the termination angle will be increased by 3°; when the condition for entering the holding stage is that the number of times the third situation is greater than or equal to 2, the termination angle remains unchanged; continue training according to the updated movement parameters; after the training is completed, save the data of this training process in a folder.

[0013] In some exemplary embodiments, the process of antagonistic exercise training includes: first setting parameters before the start of antagonistic exercise training, generating a corresponding motion trajectory after the parameters are confirmed, and starting antagonistic exercise training; the knee joint rehabilitation machine drives the affected limb to perform passive movement according to the planned trajectory; after the knee joint rehabilitation machine reaches the set end angle, it maintains for 10 seconds and enters the impedance control mode, and the patient flexes and extends the knee joint for isometric contraction training; after 10 seconds, the knee joint rehabilitation machine drives the affected limb to return to the initial angle; multiple training sessions are performed according to the set number of exercise parameters; after the training is completed, the data of this training process is saved in a folder.

[0014] In some exemplary embodiments, the process of pain adaptive antagonism training includes: first setting parameters before the start of pain adaptive antagonism training, generating a corresponding motion trajectory after the parameters are confirmed, and starting pain adaptive antagonism motion training; the knee joint rehabilitation machine drives the affected limb to perform passive movement according to the planned trajectory; if one of the following situations is met, the device enters the holding stage, maintains the current angle for 10 seconds and enters the impedance control mode, and the patient flexes and extends the knee joint for isometric contraction training; the first situation: the patient actively stops the motor movement due to excessive pain perception; the second situation: the motor movement angle reaches the termination angle; the third situation: the pain detection model outputs a judgment result of 1; after 10 seconds, the knee joint rehabilitation machine drives the affected limb to return to the initial angle; after a single rehabilitation training is completed, it will be adjusted according to the training process The movement frequency parameters are updated according to the force-speed ratio and resistance change rate; the impedance control parameters are updated according to the maximum displacement difference, maximum speed difference and maximum electromyographic characteristic difference during the patient's impedance training process; multiple training is performed according to the set movement number parameters; after completing three flexion movements, the movement range is updated according to the number of times each condition enters the holding stage; when the condition for entering the holding stage is that the number of times the first situation is greater than or equal to 2, the termination angle is reduced by 3°; when the condition for entering the holding stage is that the number of times the second situation is greater than or equal to 2, the termination angle is increased by 3°; when the condition for entering the holding stage is that the number of times the third situation is greater than or equal to 2, the termination angle remains unchanged; continue training according to the updated movement parameters; after the training is completed, save the data of this training process in a folder.

[0015] In some exemplary embodiments, the active motion angle data of the patient's knee joint after training is recorded, including: adjusting the knee joint rehabilitation machine to an unloading state so that the knee joint rehabilitation machine can follow the flexion movement of the affected limb; the patient actively flexes the knee joint and relaxes after reaching the maximum flexion angle of the patient's knee joint; the knee joint rehabilitation machine records the patient's maximum angle of the knee joint during the process of active knee flexion.

[0016] The technical solution provided by the embodiments of the present application has at least the following advantages:

[0017] An embodiment of the present application provides an adaptive progressive rehabilitation training method for knee joint surgery based on pain detection, comprising the following steps: first, the knee joint rehabilitation machine is initialized, and the patient is made to wear the electromyography acquisition device and the knee joint rehabilitation machine; then, after the patient wears the electromyography acquisition device and the knee joint rehabilitation machine, the knee joint rehabilitation machine is driven to perform active knee flexion, and the active knee motion angle data of the patient before training is recorded; next, the patient follows the knee joint rehabilitation machine to perform passive knee flexion movement to collect the training data required for the pain detection model; then, the collected training data is preprocessed and feature extracted, a support vector machine is selected as a classifier, and the classifier is trained using the extracted two types of sample features to obtain a pain detection model; next, a rehabilitation training mode is selected to train the patient; the rehabilitation training modes include: passive motion training, pain adaptive passive training, confrontation training, and pain adaptive confrontation training; finally, after the patient completes all training, the knee joint rehabilitation machine is driven to perform active knee flexion again, and the active knee motion angle data of the patient after training is recorded.

[0018] The embodiment of the present application provides an adaptive progressive rehabilitation training method for knee joint surgery based on pain detection. On the one hand, the present application analyzes and processes the patient's electromyographic signals based on the physiological phenomena exhibited by the human body when feeling pain, thereby realizing the classification of knee pain or non-pain states without relying on the patient's active report and the doctor's experience, that is, autonomous detection of pain. At present, clinical rehabilitation can only judge whether the appropriate pain level has been reached based on the patient's feedback and the doctor's experience, and use this as the patient's knee joint limit range of motion, which is highly subjective. The pain state detection technology mentioned in the present application uses the patient's electromyographic signals as the analysis object, and can judge the patient's pain state more objectively, and perform rehabilitation exercises with an appropriate range of motion of the knee joint, thereby improving the effect of rehabilitation training.

[0019] On the other hand, the present application makes adaptive adjustments to the training termination angle according to the conditions of each entry into the holding phase during the rehabilitation training process to adapt to the changes of the patient. Since the affected part of the patient's knee joint is loosened during the rehabilitation training, the pain threshold is increased, and the range of motion of the knee joint is increased, it is necessary to adjust the rehabilitation machine according to the patient's condition during each training to cooperate with the patient's more effective rehabilitation training.

[0020] In addition, this application designs passive motion training, pain-adaptive passive training, antagonism training, and pain-adaptive antagonism training based on common clinical knee rehabilitation training techniques and combined with pain detection methods. This training method can meet the requirements of postoperative rehabilitation training for knee fractures, and can help patients stretch their joints to relieve joint adhesions, as well as help patients exercise their muscles and restore muscle strength. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplifications do not constitute limitations on the embodiments. Unless otherwise stated, the pictures in the drawings do not constitute proportional limitations.

[0022] Figure 1 A flowchart of a method for adaptive progressive rehabilitation training after knee surgery based on pain detection provided in an embodiment of the present application.

[0023] Figure 2 A flowchart of the knee joint rehabilitation machine provided in an embodiment of the present application for collecting training data required for the pain detection model.

[0024] Figure 3 A flowchart of pain detection model training provided in an embodiment of the present application.

[0025] Figure 4 A flowchart of rehabilitation training provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] As can be seen from the background technology, there is currently little research on rehabilitation robots targeting the need for post-fracture rehabilitation training, and existing post-fracture rehabilitation machines have simple functions and are complicated to operate.

[0027] In order to solve the above technical problems, an embodiment of the present application provides an adaptive progressive rehabilitation training method for knee joint surgery based on pain detection, comprising the following steps: first, the knee joint rehabilitation machine is initialized, and the patient wears the electromyography acquisition device and the knee joint rehabilitation machine; then, after the patient wears the electromyography acquisition device and the knee joint rehabilitation machine, the knee joint rehabilitation machine is driven to perform active knee flexion, and the active knee motion angle data of the patient before training is recorded; next, the patient follows the knee joint rehabilitation machine to perform passive knee flexion movement to collect the training data required for the pain detection model; then, the collected training data is preprocessed and feature extracted, a support vector machine is selected as a classifier, and the classifier is trained using the extracted two types of sample features to obtain a pain detection model; next, a rehabilitation training mode is selected to train the patient; the rehabilitation training modes include: passive motion training, pain adaptive passive training, confrontation training, and pain adaptive confrontation training; finally, after the patient completes all training, the knee joint rehabilitation machine is driven to perform active knee flexion again, and the active knee motion angle data of the patient after training is recorded. The embodiment of the present application provides an adaptive progressive rehabilitation training method for knee joint surgery based on pain detection. By utilizing the patient's surface electromyography signal for pain detection, automatic identification of the range of motion of the knee joint is achieved, and multi-modal training is performed according to the patient's training situation, alleviating the problem of tight rehabilitation physician resources.

[0028] The following will describe the various embodiments of the present application in detail with reference to the accompanying drawings. However, it will be appreciated by those skilled in the art that in the various embodiments of the present application, many technical details are provided in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solution claimed in the present application can be implemented.

[0029] See also Figure 1 The present application embodiment provides a method for adaptive progressive rehabilitation training after knee surgery based on pain detection, comprising the following steps:

[0030] Step S1, initialize the knee joint rehabilitation machine, and let the patient wear the electromyography acquisition device and the knee joint rehabilitation machine.

[0031] Step S2: After the patient puts on the electromyographic acquisition device and the knee rehabilitation machine, the patient drives the knee rehabilitation machine to perform active knee flexion and records the patient's knee active motion angle data before training.

[0032] Step S3: The patient follows the knee rehabilitation machine to perform passive knee flexion exercise to collect training data required for the pain detection model.

[0033] Step S4: preprocess and extract features of the collected training data, select a support vector machine as a classifier, and use the extracted two types of sample features to train the classifier to obtain a pain detection model.

[0034] Step S5, selecting a rehabilitation training mode to train the patient; the rehabilitation training modes include: passive movement training, pain adaptive passive training, confrontation training and pain adaptive confrontation training.

[0035] Step S6: After the patient completes all training, the patient drives the knee joint rehabilitation machine to perform active knee flexion again, and records the patient's knee joint active motion angle data after training.

[0036] The present application provides an adaptive progressive rehabilitation training method for knee joint surgery based on pain detection, which is used for patients undergoing knee joint surgery for rehabilitation, and the method includes: initializing the rehabilitation machine; the patient wears the rehabilitation equipment and fills in the patient information; recording the active motion angle of the knee joint before training; collecting the training data required for the pain detection model; preprocessing and feature extraction of the training data, selecting a support vector machine as a classifier for training, and obtaining a pain detection model; the patient selects a rehabilitation training mode for training; after the patient completes all training, the patient's knee joint active motion angle data after training is recorded. The present application utilizes a pain detection method based on electromyographic signals to design a multi-modal training method for a rehabilitation machine that can autonomously sense the range of motion of the knee joint, which enables patients to perform rehabilitation exercises with an appropriate range of motion of the knee joint, thereby improving the effect of rehabilitation training.

[0037] In some embodiments, in step S1, the patient is made to wear the electromyography acquisition device and the knee joint rehabilitation machine, including the following steps:

[0038] Step 1: The patient wears an electromyography acquisition device, and the electrodes of the electromyography acquisition device are respectively attached to the rectus femoris, vastus medialis, long head of biceps femoris and semitendinosus of the thigh; the electromyography acquisition device is started to start surface electromyography signal data collection.

[0039] Step 2: The patient wears the knee joint rehabilitation machine, ensuring that the rotation center of the bionic joint connecting rod coincides with the knee joint, and fills the gap between the patient's affected limb and the knee joint rehabilitation machine through the airbag.

[0040] Step 3: Fill in personal information on the system interface of the knee rehabilitation machine and create a personal training record file for the patient.

[0041] In some embodiments, step S2 records the patient's knee joint active motion angle data before training, including: adjusting the knee joint rehabilitation machine to an unloading state so that the knee joint rehabilitation machine can follow the affected limb to perform flexion movements; the patient actively flexes the knee joint and relaxes after reaching the patient's maximum knee flexion angle; the knee joint rehabilitation machine records the patient's maximum knee joint angle during active knee flexion.

[0042] Figure 2 A flowchart of the knee joint rehabilitation machine provided in the embodiment of the present application for collecting training data required for the pain detection model is shown. Figure 2 As shown, in some embodiments, collecting training data required for the pain detection model in step S3 includes the following steps:

[0043] Step 1: The knee joint rehabilitation machine drives the affected limb to move to the initial position, and gradually increases the knee joint angle from the initial position until the patient feels pain of 3 points in the pain assessment digital scale, and the knee joint angle at this time is recorded.

[0044] Step 2: Generate a trajectory curve based on the recorded knee joint angle to perform knee flexion exercise and maintain it at the maximum angle for 5 seconds.

[0045] Step 3: Repeat the knee flexion movement in step 2 three times, record the patient's electromyographic signal during the knee flexion movement as a training signal for the pain detection model, and add pain and non-pain labels to the electromyographic signal.

[0046] Figure 3 Figure 2 shows a flowchart of pain detection model training. Figure 3 As shown, in some embodiments, the classifier is trained using the extracted two types of sample features to obtain a pain detection model, including the following steps:

[0047] Step 1: Preprocess the signal.

[0048] Step 2: Extract the features of the preprocessed EMG signal using a sliding window.

[0049] Step three, use the support vector machine as a classifier, and use the extracted two types of sample features to train the classifier; use the cross-validation method and grid optimization to optimize the classifier hyperparameters; select the hyperparameter model with the highest evaluation index to complete the classifier training and establish a pain detection model; the classifier hyperparameters include cost and weight.

[0050] Specifically, the specific steps of signal preprocessing in step one include: performing 10Hz-500Hz bandpass filtering on the signal to remove 50Hz power frequency interference; according to the markers in the signal, removing useless data in the original data, and retaining the electromyographic signal from the beginning to the end of each rehabilitation training.

[0051] Specifically, step 2 is mainly feature extraction, which uses a sliding window method to extract the features of the preprocessed EMG signal. The extracted features include mean absolute value (MAV), root mean square (RMS), peak-to-peak value (PP), standard deviation (STD), wavelength (WL), number of zero crossings (ZC), mean frequency (MNF), median frequency (MDF), mean power (MNP) and approximate entropy (ApEn), and the extracted features are regularized.

[0052] Figure 4 A flowchart of rehabilitation training is shown. Figure 4As shown, in some embodiments, in step S5, a rehabilitation training mode is selected to train the patient, and the process of passive motion training includes: first setting parameters before starting passive motion training, generating a corresponding motion trajectory after the parameters are confirmed, and starting passive motion training; the knee joint rehabilitation machine drives the affected limb to perform passive motion according to the planned trajectory; when the knee joint rehabilitation machine reaches the set end angle, it maintains it for 10 seconds; after 10 seconds, the knee joint rehabilitation machine returns to the initial angle; multiple trainings are performed according to the set number of exercise parameters; after the training is completed, the data of this training process is saved in a folder.

[0053] In some embodiments, a rehabilitation training mode is selected in step S5 to train the patient, and the process of pain adaptive passive training includes: first setting parameters before the start of pain adaptive passive training, generating a corresponding motion trajectory after the parameters are confirmed, and starting pain adaptive passive motion training; the knee joint rehabilitation machine drives the affected limb to perform passive movement according to the planned trajectory; if one of the following conditions is met, the knee joint rehabilitation machine enters the holding stage and maintains the current angle for 10 seconds.

[0054] In the first case, the patient actively stops motor movement due to excessive pain perception.

[0055] In the second case, the motor movement angle reaches the terminal angle.

[0056] In the third case, the pain detection model outputs a judgment result of 1.

[0057] After 10 seconds, the knee joint rehabilitation machine drives the affected limb back to the initial angle. After a single rehabilitation training is completed, the exercise frequency parameters will be updated according to formula (1) based on the force-speed ratio and resistance change rate during the training process:

[0058]

[0059] Among them, r is the actual frequency of rehabilitation; k r1 ,k r2 is the compensation coefficient; r0 is the initial setting frequency of rehabilitation; F(t) is the human-machine interaction force; v(t) is the motor speed; The rate of change of human-computer interaction.

[0060] Perform multiple trainings according to the set number of exercise parameters; after completing three flexion exercises, update the range of motion according to the number of times each condition enters the holding phase.

[0061] When the condition for entering the holding phase is that the number of the first situation is greater than or equal to 2, the termination angle is reduced by 3°.

[0062] When the condition for entering the holding phase is that the number of times of the second situation is greater than or equal to 2, the termination angle increases by 3°.

[0063] When the condition for entering the holding phase is that the number of the third situation is greater than or equal to 2, the termination angle remains unchanged.

[0064] Continue training according to the updated motion parameters; after training, save the data of this training process in a folder.

[0065] In some embodiments, a rehabilitation training mode is selected in step S5 to train the patient, and the process of antagonistic exercise training includes: first setting parameters before the start of antagonistic exercise training, and after the parameters are confirmed, a corresponding motion trajectory will be generated to start antagonistic exercise training; the knee joint rehabilitation machine drives the affected limb to perform passive movement according to the planned trajectory; after the knee joint rehabilitation machine reaches the set end angle, it maintains for 10 seconds and enters the impedance control mode, and the patient flexes and extends the knee joint for isometric contraction training; after 10 seconds, the knee joint rehabilitation machine drives the affected limb to return to the initial angle; multiple trainings are performed according to the set number of exercise parameters; after the training is completed, the data of this training process is saved in a folder.

[0066] In some embodiments, a rehabilitation training mode is selected in step S5 to train the patient, and the process of pain adaptive antagonism training includes: first setting parameters before the start of pain adaptive antagonism training, generating a corresponding motion trajectory after the parameters are confirmed, and starting pain adaptive antagonism motion training; the knee joint rehabilitation machine drives the affected limb to perform passive movement according to the planned trajectory; if one of the following conditions is met, the device enters the holding stage, maintains the current angle for 10 seconds and enters the impedance control mode, and the patient flexes and extends the knee joint for isometric contraction training.

[0067] The first situation: the patient actively stops motor movement due to excessive pain perception.

[0068] The second situation: the motor movement angle reaches the terminal angle.

[0069] The third situation: the pain detection model outputs a judgment result of 1.

[0070] After 10 seconds, the knee rehabilitation machine drives the affected limb back to the initial angle; after a single rehabilitation training is completed, the movement frequency parameters will be updated according to the force-speed ratio and resistance change rate during the training process.

[0071] The impedance control parameters are updated according to formula (2) based on the maximum displacement difference, maximum velocity difference and maximum myoelectric characteristic difference during the patient's impedance training.

[0072]

[0073] Among them, k s ,k v ,k f ,k eis the compensation coefficient; K d ,B d ,T ff is the impedance control parameter; K d0 ,B d0 ,T ff0 To set the impedance control parameters initially; s0, v0, F0, RMS EMG0 is the maximum displacement, maximum velocity, maximum interaction force and maximum electromyographic RMS amplitude during the initial impedance training; s n ,v n ,F n ,RMS EMGn It is the maximum displacement, maximum velocity, maximum interaction force and maximum electromyographic RMS amplitude during the nth impedance training.

[0074] The fatigue degree estimation method is established by formula (3). ave is the average time of three consecutive training exercises, τ0 is the average time of the initial three training exercises, the fatigue level will be updated after every three training exercises, and the impedance training coefficient will be updated after each training.

[0075]

[0076] Perform multiple training sessions according to the set number of exercise parameters; after completing three flexion exercises, update the range of motion according to the number of times each condition enters the holding phase.

[0077] When the condition for entering the holding phase is that the number of the first situation is greater than or equal to 2, the termination angle is reduced by 3°.

[0078] When the condition for entering the holding phase is that the number of times of the second situation is greater than or equal to 2, the termination angle increases by 3°.

[0079] When the condition for entering the holding phase is that the number of the third situation is greater than or equal to 2, the termination angle remains unchanged.

[0080] Continue training according to the updated motion parameters; after training, save the data of this training process in a folder.

[0081] In some embodiments, step S6 records the patient's knee joint active motion angle data after training, including: adjusting the knee joint rehabilitation machine to an unloading state so that the knee joint rehabilitation machine can follow the affected limb to perform flexion movements; the patient actively flexes the knee joint, and relaxes after reaching the patient's maximum knee flexion angle; the knee joint rehabilitation machine records the patient's maximum knee joint angle during active knee flexion.

[0082] Based on the above technical scheme, the embodiment of the present application provides an adaptive progressive rehabilitation training method for knee joint surgery based on pain detection, including the following steps: first, the knee joint rehabilitation machine is initialized, and the patient wears the electromyography acquisition device and the knee joint rehabilitation machine; then, after the patient wears the electromyography acquisition device and the knee joint rehabilitation machine, the knee joint rehabilitation machine is driven to perform active knee flexion, and the active knee motion angle data of the patient before training is recorded; next, the patient follows the knee joint rehabilitation machine to perform passive knee flexion movement to collect the training data required for the pain detection model; then, the collected training data is preprocessed and feature extracted, a support vector machine is selected as a classifier, and the classifier is trained using the extracted two types of sample features to obtain a pain detection model; next, a rehabilitation training mode is selected to train the patient; the rehabilitation training mode includes: passive motion training, pain adaptive passive training, confrontation training and pain adaptive confrontation training; finally, after the patient completes all training, the knee joint rehabilitation machine is driven again to perform active knee flexion, and the active knee motion angle data of the patient after training is recorded.

[0083] The embodiment of the present application provides an adaptive progressive rehabilitation training method for knee joint surgery based on pain detection. On the one hand, the present application analyzes and processes the patient's electromyographic signals based on the physiological phenomena exhibited by the human body when feeling pain, thereby realizing the classification of knee pain or non-pain states without relying on the patient's active report and the doctor's experience, that is, autonomous detection of pain. At present, clinical rehabilitation can only judge whether the appropriate pain level has been reached based on the patient's feedback and the doctor's experience, and use this as the patient's knee joint limit range of motion, which is highly subjective. The pain state detection technology mentioned in the present application uses the patient's electromyographic signals as the analysis object, and can judge the patient's pain state more objectively, and perform rehabilitation exercises with an appropriate range of motion of the knee joint, thereby improving the effect of rehabilitation training.

[0084] On the other hand, the present application adaptively adjusts the training termination angle according to the conditions of entering the holding stage each time during the rehabilitation training process to adapt to the changes of the patient. Since the affected part of the patient's knee joint is loosened during the rehabilitation training, the pain threshold is increased, and the range of motion of the knee joint is increased, it is necessary to adjust the rehabilitation machine according to the patient's condition each time training to cooperate with the patient's more effective rehabilitation training. In addition, the present application designs passive motion training, pain-adaptive passive training, antagonism training, and pain-adaptive antagonism training based on the common knee rehabilitation training techniques in clinical practice and combined with the pain detection method. This training method can meet the requirements of postoperative rehabilitation training for knee fractures, which can not only help patients stretch their joints to relieve joint adhesions, but also help patients exercise their muscles and restore muscle strength.

[0085] Those skilled in the art can understand that the above-mentioned embodiments are specific examples for implementing the present application, and in practical applications, various changes can be made to them in form and detail without departing from the spirit and scope of the present application. Any person skilled in the art can make their own changes and modifications without departing from the spirit and scope of the present application, so the scope of protection of the present application shall be based on the scope defined in the claims.

Claims

1. A method for adaptive progressive rehabilitation training after knee surgery based on pain detection, characterized in that: The following steps are involved: Initialize the knee joint rehabilitation machine and let the patient wear the electromyography acquisition device and the knee joint rehabilitation machine; After the patient puts on the electromyography acquisition device and the knee joint rehabilitation machine, he drives the knee joint rehabilitation machine to actively flex the knee joint and record the patient's knee joint active motion angle data before training; The patient follows the knee rehabilitation machine to perform passive knee flexion movements to collect training data required for the pain detection model; The collected training data is preprocessed and features are extracted, a support vector machine is selected as a classifier, and the classifier is trained using the extracted two types of sample features to obtain a pain detection model; Select a rehabilitation training model to train the patient; The rehabilitation training modes include: passive movement training, pain adaptive passive training, confrontation training and pain adaptive confrontation training; After the patient completes all training, he / she drives the knee rehabilitation machine to perform active knee flexion again, and the patient's knee active motion angle data after training is recorded.

2. The method for adaptive progressive rehabilitation training after knee surgery based on pain detection according to claim 1 is characterized in that: The patient wears the electromyography acquisition device and knee joint rehabilitation machine, including: Step 1: The patient wears an electromyography acquisition device, and the electrodes of the electromyography acquisition device are respectively attached to the rectus femoris, vastus medialis, long head of biceps femoris and semitendinosus of the thigh; the electromyography acquisition device is started to start surface electromyography signal data collection; Step 2: The patient wears the knee joint rehabilitation machine, ensuring that the bionic joint connecting rod coincides with the rotation center of the knee joint, and the airbag fills the gap between the patient's affected limb and the knee joint rehabilitation machine; Step 3: Fill in personal information on the system interface of the knee rehabilitation machine and create a personal training record file for the patient.

3. The method for adaptive progressive rehabilitation training after knee surgery based on pain detection according to claim 1 is characterized in that: Record the patient's knee joint active motion angle data before training, including: Adjust the knee joint rehabilitation machine to the unloading state so that the knee joint rehabilitation machine can follow the flexion movement of the affected limb; The patient actively flexes the knee joint and relaxes after reaching the maximum flexion angle of the knee joint; The knee rehabilitation machine records the patient's maximum knee angle during active knee flexion.

4. The method for adaptive progressive rehabilitation training after knee surgery based on pain detection according to claim 1, characterized in that: Collect the training data required for the pain detection model, including: Step 1: The knee joint rehabilitation machine drives the affected limb to move to the initial position, and gradually increases the knee joint angle from the initial position until the patient feels pain of 3 points in the pain assessment digital scale, and the knee joint angle at this time is recorded; Step 2: Generate a trajectory curve based on the recorded knee joint angle to perform knee flexion exercise and maintain it at the maximum angle for 5 seconds; Step 3: Repeat the knee flexion movement in step 2 three times, record the patient's electromyographic signal during the knee flexion movement as a training signal for the pain detection model, and add pain and non-pain labels to the electromyographic signal.

5. The method for adaptive progressive rehabilitation training after knee surgery based on pain detection according to claim 1 is characterized in that: The classifier is trained using the extracted two types of sample features to obtain a pain detection model, including: Preprocess the signal; Extract the features of the preprocessed EMG signal using a sliding window method; A support vector machine is used as a classifier, and the extracted two types of sample features are used to train the classifier; the classifier hyperparameters are optimized and designed using a cross-validation method and grid optimization; the hyperparameter model with the highest evaluation index is selected to complete the classifier training and establish a pain detection model; the classifier hyperparameters include cost and weight.

6. The method for adaptive progressive rehabilitation training after knee surgery based on pain detection according to claim 1, characterized in that: The process of passive motion training includes: Before starting passive motion training, first set the parameters. After the parameters are confirmed, generate the corresponding motion trajectory and start passive motion training. The knee joint rehabilitation machine drives the affected limb to perform passive motion according to the planned trajectory. When the knee joint rehabilitation machine reaches the set end angle, keep it for 10 seconds. After 10 seconds, the knee joint rehabilitation machine returns to the initial angle. Perform multiple training according to the set number of exercise parameters. After the training is completed, save the data of this training process in a folder.

7. The method for adaptive progressive rehabilitation training after knee surgery based on pain detection according to claim 1, characterized in that: The process of pain adaptive passive training includes: Before the start of the pain adaptive passive training, the parameters are set first. After the parameters are confirmed, the corresponding motion trajectory is generated and the pain adaptive passive motion training begins; the knee joint rehabilitation machine drives the affected limb to perform passive motion according to the planned trajectory; if one of the following conditions is met, the knee joint rehabilitation machine enters the holding stage and maintains the current angle for 10 seconds; In the first case, the patient actively stops motor movement due to excessive pain perception; In the second case, the motor movement angle reaches the termination angle; In the third case, the pain detection model outputs a judgment result of 1; After 10 seconds, the knee joint rehabilitation machine drives the affected limb back to the initial angle; after a single rehabilitation training is completed, the exercise frequency parameters will be updated according to the force-speed ratio and resistance change rate during the training process; multiple trainings will be performed according to the set exercise number parameters; after each three flexion exercises are completed, the range of motion will be updated according to the number of times each condition is entered into the holding phase; When the condition for entering the holding phase is that the number of times of the first situation is greater than or equal to 2, the termination angle is reduced by 3°; When the condition for entering the holding phase is that the number of times of the second situation is greater than or equal to 2, the termination angle increases by 3°; When the condition for entering the holding phase is that the number of times of the third situation is greater than or equal to 2, the termination angle remains unchanged; Continue training according to the updated motion parameters; after training, save the data of this training process in a folder.

8. The method for adaptive progressive rehabilitation training after knee surgery based on pain detection according to claim 1, characterized in that: The process of resistance sports training includes: Before the start of antagonistic exercise training, the parameters are set first. After the parameters are confirmed, the corresponding motion trajectory will be generated and the antagonistic exercise training will begin; the knee joint rehabilitation machine drives the affected limb to perform passive movements according to the planned trajectory; after the knee joint rehabilitation machine reaches the set end angle, it will maintain for 10 seconds and enter the impedance control mode, and the patient flexes and extends the knee joint for isometric contraction training; after 10 seconds, the knee joint rehabilitation machine drives the affected limb to return to the initial angle; multiple training sessions are performed according to the set number of exercise parameters; after the training is completed, the data of this training process is saved in a folder.

9. The method for adaptive progressive rehabilitation training after knee surgery based on pain detection according to claim 1, characterized in that: The process of pain adaptive resistance training includes: Before the start of the pain adaptive confrontation training, the parameters are set first. After the parameters are confirmed, the corresponding motion trajectory will be generated to start the pain adaptive confrontation exercise training; the knee joint rehabilitation machine drives the affected limb to perform passive movements according to the planned trajectory; if one of the following conditions is met, the device enters the holding stage, maintains the current angle for 10 seconds and enters the impedance control mode, and the patient flexes and extends the knee joint for isometric contraction training; The first situation: the patient actively stops motor movement due to excessive pain perception; The second situation: the motor movement angle reaches the terminal angle; The third scenario: the pain detection model outputs a judgment result of 1; After 10 seconds, the knee joint rehabilitation machine drives the affected limb back to the initial angle; after a single rehabilitation training is completed, the exercise frequency parameters will be updated according to the force-speed ratio and resistance change rate during the training process; the impedance control parameters will be updated according to the maximum displacement difference, maximum speed difference and maximum electromyographic characteristic difference during the patient's impedance training process; multiple trainings will be performed according to the set exercise number parameters; after each three flexion exercises are completed, the range of motion will be updated according to the number of times each condition is entered into the holding phase; When the condition for entering the holding phase is that the number of times of the first situation is greater than or equal to 2, the termination angle is reduced by 3°; When the condition for entering the holding phase is that the number of times of the second situation is greater than or equal to 2, the termination angle increases by 3°; When the condition for entering the holding phase is that the number of times of the third situation is greater than or equal to 2, the termination angle remains unchanged; Continue training according to the updated motion parameters; after training, save the data of this training process in a folder.

10. The method for adaptive progressive rehabilitation training after knee surgery based on pain detection according to claim 1, characterized in that: Record the patient's knee joint active motion angle data after training, including: Adjust the knee joint rehabilitation machine to the unloading state so that the knee joint rehabilitation machine can follow the flexion movement of the affected limb; The patient actively flexes the knee joint and relaxes after reaching the maximum flexion angle of the knee joint; The knee rehabilitation machine records the patient's maximum knee angle during active knee flexion.

Images