Evaluation training method and system based on hand joint continuous active and passive activity instrument
By monitoring and calculating patients' active and passive training data in real time, the training methods and duration are automatically adjusted, solving the safety risks and inefficiencies caused by reliance on the subjective judgment of medical staff in existing technologies, and achieving safer and more efficient rehabilitation training.
Patent Information
- Application Number
- CN202511719845.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-21
- Publication Date
- 2026-02-17
AI Technical Summary
In existing technologies, the training methods of continuous active and passive hand joint movement devices rely on the subjective judgment of medical staff, which can lead to insufficient or excessive training intensity, posing safety risks and resulting in low training efficiency.
By monitoring the patient's active and passive training data in real time through a continuous active and passive hand joint movement device, the fitness level is calculated, and the training method and duration are automatically adjusted according to the fitness level to ensure that the training intensity matches the patient's physiological condition.
It enables dynamic adjustment of training methods and duration based on the patient's physiological condition, improving training safety and efficiency and reducing the risk of soft tissue injury.
Smart Images
Figure CN121545671A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of rehabilitation training technology. More specifically, this invention relates to an assessment and training method and system based on a continuous active and passive hand joint movement device. Background Technology
[0002] The continuous active and passive joint movement device for the hand allows patients to improve their joint range of motion through continuous passive joint movement. It is widely used in the rehabilitation of patients' limb functions.
[0003] Currently, routine clinical procedures rely heavily on the professional knowledge and experience of healthcare professionals for decision-making. Specifically, doctors or therapists manually determine whether a patient is suitable for active exercise or passive stretching by visually assessing the patient's range of hand movement, palpating muscle tension, and inquiring about the patient's subjective feelings. After determining the training method, healthcare professionals typically set a fixed training duration on the equipment (e.g., 5 minutes) and intermittently check on the patient during the training to confirm their condition.
[0004] However, because medical staff's judgment is subjective and cannot be monitored around the clock, they may not be able to accurately determine whether active or passive training is more suitable for a patient. This could result in insufficient training intensity when the patient is in good condition, or forced training when the patient resists, causing soft tissue damage. Therefore, there may be safety risks and low training efficiency during the rehabilitation training process. Summary of the Invention
[0005] To address the technical problems of potential safety risks and low training efficiency during the rehabilitation training of the aforementioned patients, this invention provides solutions in the following aspects.
[0006] In a first aspect, an assessment and training method based on a continuous active-passive hand joint motion analyzer includes: obtaining active training data and a first training duration for the patient's active training during one active training session using the continuous active-passive hand joint motion analyzer; obtaining passive training data and a second training duration for the patient's passive training during one passive training session using the same analyzer; wherein the active training data includes joint angles and joint torques at multiple moments, and the passive training data includes joint angles and joint torques at multiple moments; calculating active training fit and passive training fit, wherein the active training fit is related to the active training data. The active training fit is related to the passive training data; in response to the active training fit being greater than the passive training fit, it is determined that the patient is currently undergoing active training using the continuous active-passive hand joint movement device; the total duration of the patient's active training is determined, wherein both the active training fit and the first training duration are proportional to the total duration of the patient's active training; in response to the passive training fit being greater than the active training fit, it is determined that the patient is currently undergoing passive training using the continuous active-passive hand joint movement device; the total duration of the patient's passive training is determined, wherein both the passive training fit and the second training duration are proportional to the total duration of the patient's passive training.
[0007] Preferably, the formula for calculating the active training fit is: ; in A The active training fit, k The weighting coefficient is a preset size, and 0 < k <1, i 1,max The maximum value of the joint angles at all times in the active training data. i 2,max The minimum value of the joint angles at all times in the active training data. s 1 represents the standard deviation of the joint torque at all times in the active training data. m 1 represents the mean of joint torques at all times in the active training data, and exp() is an exponential function with base e. norm () is the standard normalization function. i ref The standard joint range of motion is set to a preset size.
[0008] Preferably, the formula for calculating the passive training fit is: ; in B For the passive training fit, i2,max The maximum value of the joint angles at all times in the passive training data. i 2,max The minimum joint angle at all times in the passive training data. s 2 represents the standard deviation of the joint torque at all times in the passive training data. m 2 represents the mean of joint torques at all times in the passive training data.
[0009] Preferably, determining the total duration of the patient's active training based on the active training fit includes: calculating a first correction coefficient based on the active training fit, wherein the first correction coefficient is proportional to the active training fit and is greater than or equal to -1 and less than or equal to 1; adjusting the first training duration based on the first correction coefficient to obtain the total duration of the patient's active training, wherein the formula for adjusting the first training duration is: ; in, t 1 represents the first training duration. T 1 represents the total duration of the patient's active training this time. l The gain coefficient is a preset value, and 0 < l <1, α 1 represents the first correction coefficient.
[0010] Preferably, the formula for calculating the first correction coefficient is: ; in, A Let be the active training fit, and 0 < A <1, s The sensitivity adjustment coefficient is a preset value, and s >1.
[0011] Preferably, determining the total duration of passive training for the patient based on the passive training fit includes: calculating a second correction coefficient based on the passive training fit, wherein the second correction coefficient is proportional to the passive training fit and is greater than or equal to -1 and less than or equal to 1; adjusting the second training duration based on the second correction coefficient to obtain the total duration of passive training for the patient, wherein the formula for adjusting the second training duration is: ; in, t 2 represents the second training duration. T 2 represents the total duration of the patient's passive training in this session. l The gain coefficient is a preset value, and 0 < l <1, α 2 is the second correction factor.
[0012] Preferably, the formula for calculating the second correction coefficient is: ; in, B The passive training fit is given, and 0 < B <1, s The sensitivity adjustment coefficient is a preset value, and s >1.
[0013] Preferably, the gain coefficient l The value is 0.69, and the sensitivity adjustment coefficient is... s The value is 2.
[0014] Preferably, an evaluation and training method based on a continuous active and passive hand joint movement device further includes: issuing an alarm in response to the active training fit and the passive training fit both being less than a preset fit threshold.
[0015] In a second aspect, an assessment and training system based on a continuous active and passive hand joint motion analyzer includes a processor and a memory, the memory storing a computer program, the processor executing the computer program to implement an assessment and training method based on a continuous active and passive hand joint motion analyzer as described in any of the above-described inventions.
[0016] The beneficial effects of this invention are as follows: This invention determines the patient's fitness level for active and passive training based on physiological data collected during each training session. The fitness level then determines the training method and duration for the next training session (i.e., the current training session). Furthermore, this invention extends the training time when the patient is in good condition (high fitness level) to consolidate the therapeutic effect, and shortens the training time when resistance or spasticity occurs (low fitness level) to prevent injury. Based on this, this invention solves the problems of potential safety risks and low training efficiency during rehabilitation training. Attached Figure Description
[0017] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent upon reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of the invention are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein: Figure 1 This is a schematic flowchart illustrating the steps of an assessment and training method based on a continuous active and passive hand joint movement device according to an embodiment of the present invention. Figure 2 This is a schematic block diagram illustrating the structure of an assessment and training system based on a continuous active and passive hand joint movement device according to this embodiment. Detailed Implementation
[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0019] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0020] Figure 1 This is a schematic flowchart illustrating the steps of an assessment and training method based on a continuous active and passive hand joint movement device according to an embodiment of the present invention.
[0021] like Figure 1 As shown, an assessment and training method based on a continuous active and passive hand joint movement device includes steps S1 to S4.
[0022] Step S1: Obtain active training data, first training duration, passive training data, and second training duration.
[0023] Specifically, when a patient performs one active training session using the continuous active and passive hand joint motion device, active training data and the first training duration of the active training session are obtained. When a patient performs one passive training session using the continuous active and passive hand joint motion device, passive training data and the second training duration of the passive training session are obtained.
[0024] The active training data includes the patient's joint angles and joint torques at multiple moments, while the passive training data also includes the patient's joint angles and joint torques at multiple moments. The joint angles refer to the angles of the hand joints, and the joint torques refer to the torques of the hand joints. In one embodiment, the hand joints are the finger joints.
[0025] It should be noted that joint angles directly reflect the kinematic characteristics of the patient's limbs, i.e., the patient's actual range of motion; while joint torque data reflects the dynamic characteristics of the patient's limbs, i.e., how much force the patient exerted during training. In active training, active training data reflects the patient's nervous system's control over muscles; while in the passive training phase, passive training data mainly reflects the viscoelasticity of soft tissues and joint stiffness.
[0026] Step S2: Calculate active training fitness and passive training fitness.
[0027] The active training fit is related to the active training data, and the active training fit is related to the passive training data.
[0028] In one embodiment, the formula for calculating the active training fit is: ; in A The active training fit, k The weighting coefficient is a preset size, and 0 < k <1, i 1,max The maximum value of the joint angles at all times in the active training data. i 2,max The minimum value of the joint angles at all times in the active training data. s 1 represents the standard deviation of the joint torque at all times in the active training data. m 1 represents the mean of joint torques at all times in the active training data, and exp() is an exponential function with base e. norm () is the standard normalization function. i ref The standard joint range of motion is set to a preset size.
[0029] The formula for calculating the passive training fit is: ; in B For the passive training fit, i 2,max The maximum value of the joint angles at all times in the passive training data. i 2,max The minimum joint angle at all times in the passive training data. s 2 represents the standard deviation of the joint torque at all times in the passive training data. m 2 represents the mean of joint torques at all times in the passive training data.
[0030] It should be noted that the calculation of active training fitness... A In the formula, the formula The representative represents the actual range of motion of the joints achieved during active training. The standard range of motion is the range of motion of a normal adult joint. Formula The higher the value, the more drastic the change in joint torque in the patient. Based on this, active training adaptation... A The larger, the more it means Calculate passive training fit B The formula is similar.
[0031] Step S3: In response to the active training fit being greater than the passive training fit, determine that the patient is performing active training using the continuous active and passive hand joint movement device, and determine the total duration of the patient's active training.
[0032] The active training fit and the first training duration are both proportional to the total duration of the patient's active training.
[0033] In one embodiment, determining the total duration of active training for the patient based on the active training fit includes: calculating a first correction coefficient based on the active training fit, wherein the first correction coefficient is proportional to the active training fit and is greater than or equal to -1 and less than or equal to 1; adjusting the first training duration based on the first correction coefficient to obtain the total duration of active training for the patient, wherein the formula for adjusting the first training duration is: ; in, t 1 represents the first training duration. T 1 represents the total duration of the patient's active training this time. l The gain coefficient is a preset value, and 0 < l <1, α 1 represents the first correction coefficient.
[0034] It should be noted that this scheme uses a formula to determine the first training duration. t 1. Perform nonlinear mapping. When the active training fit is high (the correction coefficient is positive), the exponential term (i.e., If the value is greater than 1, the total duration of the patient's active training in this session is calculated. T 1 will be greater than the first training duration. t 1. Determining that a patient's high-quality training reflects a good physiological condition allows for extended treatment courses to consolidate the current positive training status. Conversely, when active training fit is low (correction coefficient is negative), the initial training duration should be [not specified]. t 1 will be reduced. Based on this, if the patient engages in active training, the intensity of the training will be more in line with the patient's physiological condition.
[0035] In one embodiment, the formula for calculating the first correction coefficient is: ; in, A Let be the active training fit, and 0 < A <1, s The sensitivity adjustment coefficient is a preset value, and s >1.
[0036] It should be noted that the sensitivity adjustment coefficient s The steepness of the mapping curve was determined, which is the system's sensitivity to changes in fitness. s >1, formula The corresponding curve exhibits a Sigmoid characteristic, with gentle curves at both ends and a steep curve in the middle. For the fuzzy region where the active training fit is close to 0.5, the output changes rapidly, quickly classifying the state as either preferred or biased; however, for extreme active training fits… A Values (e.g., active training fit) A (The value of the input is close to 0 or 1), and the output tends to saturate. This design simulates the activation function mechanism of biological neurons, avoids the bland response caused by linear mapping, and ensures that a significant duration correction is applied only when the patient shows a clear "good" or "bad" tendency, thereby guaranteeing the robustness of the control strategy.
[0037] Step S4: In response to the passive training fit being greater than the active training fit, determine that the patient is undergoing passive training using the continuous active and passive hand joint movement device, and determine the total duration of the patient's passive training.
[0038] The passive training fit and the second training duration are both proportional to the total duration of the patient's passive training.
[0039] In one embodiment, determining the total duration of passive training for the patient based on the passive training fit includes: calculating a second correction coefficient based on the passive training fit, wherein the second correction coefficient is proportional to the passive training fit and is greater than or equal to -1 and less than or equal to 1; adjusting the second training duration based on the second correction coefficient to obtain the total duration of passive training for the patient, wherein the formula for adjusting the second training duration is: ; in, t 2 represents the second training duration. T 2 represents the total duration of the patient's passive training in this session. l The gain coefficient is a preset value, and 0 < l <1, α 2 is the second correction factor.
[0040] In one embodiment, the formula for calculating the second correction coefficient is: ; in, B The passive training fit is given, and 0 < B <1, s The sensitivity adjustment coefficient is a preset value, and s >1.
[0041] It should be noted that passive training adaptability B A higher value indicates that the patient's limbs show no significant resistance, the range of motion of the joints has reached the expected level, and the torque is stable (without spastic resistance). At this point, the formula passes through a positive second correction coefficient. α 2. Increase the duration of the second training session t 2. Determining that the patient's high-quality training reflects a good physiological condition allows for extending the training time of subsequent sessions to consolidate the current positive training status.
[0042] Conversely, if passive training fits... B A lower score usually indicates that the patient is exhibiting resistance behaviors (such as muscle tension or involuntary spasms in response to pain). In this case, although the machine runs for the same amount of time, the actual rehabilitation benefit is extremely low, and it may even cause injury to the patient. Therefore, the training time for subsequent passive training should be reduced.
[0043] In one embodiment, the gain coefficient l The value is 0.69, and the sensitivity adjustment coefficient is... s The value is 2.
[0044] In this embodiment, the gain coefficient l The value is 0.69, when the first correction factor... α When the value of 1 is close to 1, the first training duration is... t 1. The total duration of active training for the patient this time. T The value of 1 satisfies: When the first correction factor α When the value of 1 equals 0, the first training duration is... t 1. The total duration of active training for the patient this time. T The value of 1 satisfies: When the first correction factor α When the value of 1 is close to -1, the first training duration is... t 1. The total duration of active training for the patient this time. T The value of 1 satisfies: .
[0045] The present invention also includes: issuing an alarm in response to the fact that both the active training fit and the passive training fit are less than a preset fit threshold.
[0046] It should be noted that when actively training the fit... A Adaptability to passive training BSimultaneously, if the fit falls below a preset threshold, it excludes two normal training scenarios: the patient is either undergoing effective active training or good passive training. At this point, the patient may be in a stiff state, resulting in extremely limited joint mobility; or experiencing persistent spasticity, leading to a large torque standard deviation and unstable mean. To prevent patient injury, an alarm is triggered to notify medical staff, who can then terminate the patient's training and examine their condition.
[0047] Figure 2 This is a schematic block diagram illustrating the structure of an assessment and training system based on a continuous active and passive hand joint movement device according to this embodiment.
[0048] This invention also provides an assessment and training system based on a continuous active and passive hand joint movement device. For example... Figure 2 As shown, the system includes a processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement an assessment and training method based on a continuous active and passive hand joint movement device according to the first aspect of the present invention.
[0049] The system also includes other components well known to those skilled in the art, such as communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.
[0050] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented using computer-readable / executable instructions that can be stored or otherwise maintained by such a computer-readable medium.
[0051] In the description of this specification, "multiple" or "several" means at least two, such as two, three or more, unless otherwise explicitly specified.
[0052] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.
Claims
1. An evaluation training method based on a hand joint continuous passive motion device, characterized in that, The method comprises: obtaining active training data and a first training duration of active training of the patient when the patient performs active training through the hand joint continuous passive motion device, and obtaining passive training data and a second training duration of passive training of the patient when the patient performs passive training through the hand joint continuous passive motion device, wherein the active training data comprises joint angles and joint torques of the patient at multiple time points, and the passive training data comprises joint angles and joint torques of the patient at multiple time points; calculating an active training fitness and a passive training fitness, wherein the active training fitness is related to the active training data, and the passive training fitness is related to the passive training data; determining that the patient performs active training through the hand joint continuous passive motion device this time in response to the active training fitness being greater than the passive training fitness; determining a total duration of active training of the patient this time, wherein the active training fitness and the first training duration are both proportional to the total duration of active training of the patient this time; determining that the patient performs passive training through the hand joint continuous passive motion device this time in response to the passive training fitness being greater than the active training fitness; determining a total duration of passive training of the patient this time, wherein the passive training fitness and the second training duration are both proportional to the total duration of passive training of the patient this time.
2. The evaluation training method based on the continuous passive and active movement instrument for hand joints according to claim 1, characterized in that, The formula for calculating the active training fitness is: ； wherein A is the active training fitness, k is a preset size of the weight coefficient, and 0 k <1, θ 1,max is the maximum value of the joint angle in the active training data at all time points, θ 2,max is the minimum value of the joint angle in the active training data at all time points, σ 1is the standard deviation of the joint torque in the active training data at all time points, μ 1is the mean value of the joint torque in the active training data at all time points, and exp() is an exponential function with the real number e as the base, norm () is a standard normalization function, θ ref is a preset size of the standard joint movement angle.
3. The evaluation training method based on the continuous passive and active movement instrument for hand joints according to claim 2, characterized in that, The formula for calculating the passive training fitness is: ； wherein B is the maximum value of the joint angles in the passive training data, θ 2,max is the maximum value of the joint angles in the passive training data, θ 2,max is the minimum value of the joint angles in the passive training data, σ 2 is the standard deviation of the joint torques in the passive training data, μ 2 is the mean value of the joint torques in the passive training data.
4. The evaluation training method based on the continuous passive motion instrument for hand joints according to claim 1, characterized in that, The total duration of active training of the patient this time according to the active training fitness comprises: calculating a first correction coefficient according to the active training fitness, wherein the first correction coefficient is proportional to the active training fitness, and the first correction coefficient is greater than or equal to -1 and less than or equal to 1; correcting the first training duration according to the first correction coefficient to obtain the total duration of active training of the patient this time, wherein the formula for correcting the first training duration is: ； wherein, t 1 is the first training duration, T 1 is the total duration of the active training of the patient, λ is a preset gain coefficient, and 0 λ <1, α 1 is the first correction coefficient.
5. The evaluation training method based on the continuous passive and active motion instrument for hand joints according to claim 4, characterized in that, The formula for calculating the first correction coefficient is: ； wherein, A is the degree of adaptation of the active training, and 0 A <1, s is a preset size of a sensitivity adjustment coefficient, and s >1.
6. The evaluation training method based on the continuous passive and active movement instrument for hand joints according to claim 5, characterized in that, The total duration of passive training of the patient this time according to the passive training fitness comprises: calculating a second correction coefficient according to the passive training fitness, wherein the second correction coefficient is proportional to the passive training fitness, and the second correction coefficient is greater than or equal to -1 and less than or equal to 1; correcting the second training duration according to the second correction coefficient to obtain the total duration of passive training of the patient this time, wherein the formula for correcting the second training duration is: ； wherein, t 2 is the second training duration, T 2 is the total duration of the passive training of the patient, λ is a preset gain coefficient, and 0 λ <1, α 2 is the second correction coefficient.
7. The evaluation training method based on the continuous passive and active movement instrument of hand joints according to claim 6, characterized in that, The formula for calculating the second correction coefficient is: ； wherein, B is the degree of adaptation of the passive training, and 0 B <1, s is a preset size of a sensitivity adjustment coefficient, and s >1.
8. The evaluation training method based on the continuous passive and active movement instrument for hand joints according to claim 7, characterized in that, The gain coefficient λ has a value of 0.69, and the sensitivity adjustment coefficient s has a value of 2.
9. The evaluation training method based on the continuous passive motion instrument for hand joints according to claim 1, characterized in that, The method further comprises: performing an alarm in response to the active training fitness and the passive training fitness both being less than a preset fitness threshold.
10. An evaluation training system based on a hand joint continuous passive motion instrument, comprising a processor and a memory, characterized in that, The memory stores a computer program, and the processor executes the computer program to implement the evaluation training method based on the hand joint continuous passive motion device according to any one of claims 1-9.