Device for assessing motor function in patients with diabetic foot

Abstract

The present application relates to the technical field of motion monitoring, and more particularly to a device for evaluating the motion function of a patient with diabetic foot, which is configured with a motion support, a plurality of visual collectors, a plurality of sensors and an evaluation server. In a single motion collection, the server controls the motion support to perform a motion action on the foot to be measured according to a target motion trajectory, the visual collector collects the motion action image and forms an actual motion trajectory, each sensor collects each position of the motion, the server determines the feedback interval of each sensor according to the motion trajectory, and confirms the feeling state of the foot to be measured according to the sensing state of the sensor, thereby realizing the objective and quantitative evaluation of multi-modal data fusion. The motion support, the visual collector and the sensor are matched, which effectively avoids the measurement error caused by the experience of the patient or the doctor, and effectively improves the reliability of the evaluation result.

Description

Technical Field

[0001] This invention relates to the field of motion monitoring technology, and in particular to a device for assessing the motor function of patients with diabetic foot. Background Technology

[0002] The detection and exercise assessment of diabetic foot have a crucial impact on the rehabilitation of diabetic foot. Existing assessment methods usually start with basic neurological and vascular examinations, such as vibration sense, tactile sense examinations, and ankle-brachial index measurement.

[0003] The above tests rely heavily on the doctor's experience, and patients may consciously resist the assessment, making it difficult to achieve the desired results.

[0004] Chinese Patent Announcement No. CN115363553B discloses a method for detecting diabetic foot, belonging to the field of diabetes. It achieves home-based monitoring of diabetic foot disease progression in a low-cost manner by inputting vital signs parameters, collecting and analyzing blood flow data of the foot using photoelectric sensors, collecting and analyzing body motion signals using triaxial accelerometers, conducting comprehensive analysis, and reminding patients to seek medical attention. By measuring the hemodynamics of the sole of the foot, it quantifies the health status of the sole and provides appropriate intervention to slow the progression of the disease.

[0005] However, the above methods have the following problems: they cannot determine the development of diabetic foot based on the patient's own feedback, and they cannot effectively determine the patient's feedback on rehabilitation movements. Summary of the Invention

[0006] Therefore, this invention provides a method to overcome the problems in existing technologies where the development of diabetic foot cannot be determined based on the patient's own feedback, and where the patient's feedback on rehabilitation movements cannot be effectively determined, leading to decreased detection accuracy.

[0007] To achieve the above objectives, the present invention provides a device for assessing motor function in patients with diabetic foot, comprising: Sports braces used to assist in exercise; Several visual acquisition devices used to monitor movement; Several sensors used to monitor the patient's movement trends; An evaluation server used to control the motion support and vision sensors, and connected to each sensor; For a single user, the sensor is fixed to the surface of the foot to be measured; In a single motion acquisition, the server controls the motion support to perform motion actions on the foot to be tested according to the target motion trajectory, and the vision acquisition device acquires motion action images and forms the actual motion trajectory; Each sensor collects data at various positions of this motion, among which, The server determines the feedback range of each sensor based on the motion trajectory, and confirms the sensory state of the foot to be tested based on the sensor's sensing state, including... If the response sensor fails to reach the feedback range, the server determines that the sensor at that location is faulty. If the response sensor exceeds the feedback range, the server determines that the sensation at that location is abnormal; or, In response to the actual motion trajectory misalignment, the server performs a secondary confirmation based on the feedback range of each sensor corresponding to the motion trajectory; Wherein, the sensing state is the feedback state of the foot to be tested in response to the execution of the motion trajectory; The sensing state is the feedback generated by the sensor to the movement of the foot being measured.

[0008] Furthermore, for a single user, the evaluation server controls the motion support to perform a motion action according to the target motion trajectory; The visual acquisition device determines the actual motion trajectory corresponding to the motion action based on the motion trajectory of each joint of the support corresponding to the motion action. The evaluation server sets each sensor as the primary sensor based on the target motion trajectory; If the sensor is located at a joint of the target motion trajectory or on the extension line of the motion trajectory, the server will set that sensor as the primary sensor.

[0009] Furthermore, for a single movement action, the server responds that the misalignment between the actual movement trajectory and the target movement trajectory is less than a preset misalignment threshold, and... Determine whether the sensing state of each active sensor is within its feedback range in order to determine the sensing state of each sensor at its corresponding location. If the misalignment between the actual motion trajectory and the target motion trajectory is not less than the preset misalignment threshold, the server determines to perform a secondary confirmation, and based on the feedback intervals of each position corresponding to the target motion trajectory, and... Determine whether the sensing state collected by each sensor during the movement conforms to the feedback range of the corresponding position, in order to determine the sensing state of each sensor at the corresponding position; The preset misalignment threshold is positively correlated with the area where the user can move freely, and the larger the range of free movement, the larger the preset misalignment threshold.

[0010] Furthermore, the feedback interval is the corresponding feedback data collected by each sensor when the healthy foot performs a movement action according to the target movement trajectory; or, Settings are configured based on sensor data from an individual user's historical evaluation records; The sensing data refers to the change curve of sensor data corresponding to the user at the target's motion trajectory, which is a sensor data curve at the corresponding location.

[0011] Furthermore, for a single sensor, the sensing state at its corresponding location is the corresponding state of the sensor signal strength changing with time or spatial location, including at least one of the rate of change and fluctuation frequency of the sensor signal waveform.

[0012] Furthermore, the evaluation server also calculates the signal characteristic curve of any sensor based on the signal strength of each sensor changing over time during a single motion acquisition. Compare the similarity between the signal characteristic curve of any sensor and the standard sensing data curve at the corresponding location; If the similarity is lower than the preset similarity threshold, the sensing state of the corresponding location of the sensor is determined to be abnormal or malfunctioning. The similarity threshold is related to the preset misalignment threshold.

[0013] Furthermore, when the sensing state of any adjacent sensor is determined to be abnormal and / or malfunctioning, the foot region formed by the corresponding positions of the at least two sensors is acquired. Based on the actual movement trajectory and the signal change trends of each sensor in the area, the abnormal range of the foot area is determined.

[0014] Furthermore, the evaluation server pre-stores a rehabilitation movement database. When it is determined that the sensory state of the foot under test is abnormal or ineffective under a certain target movement trajectory, The server matches and recommends at least one rehabilitation training exercise from the rehabilitation exercise database to improve the function of the trajectory movement.

[0015] Furthermore, the evaluation server determines the abnormal area of ​​the foot to be tested based on the misalignment between the actual motion trajectory and the target motion trajectory, as well as the sensing state of each sensor.

[0016] Furthermore, if the sensing status of a certain sensor is continuously missing, the evaluation server determines that the data corresponding to that sensor is invalid and re-executes the target motion trajectory.

[0017] Compared with the prior art, the beneficial effect of the present invention is that by setting up a motion support, several visual acquisition devices, several sensors and an evaluation server, the objective and quantitative evaluation of multimodal data fusion is realized. The mechanical assisted motion, i.e., the motion support, the kinematic capture, i.e. the visual acquisition device, and the physiological signal perception, i.e. the foot sensor, are fused together. This effectively avoids measurement errors caused by the experience of patients or doctors and effectively improves the reliability of the evaluation results.

[0018] Furthermore, by driving the foot with a preset target motion trajectory, the actual motion trajectory and the sensing status of the foot sensor are collected simultaneously, quantifying foot perception. At the same time, by detecting spatial trajectory data and time series signals, an objective and multi-dimensional data foundation is provided for motor function assessment, thereby further improving the reliability of the assessment results.

[0019] Furthermore, by setting feedback intervals, the abnormality types of patients' feet can be distinguished. This avoids the binary judgment of "sense presence" or "sense absence" that traditional assessments often only make. By comparing and distinguishing the feedback intervals formed by sensor signals and health benchmarks or individual historical data, more accurate data can be obtained, thereby further improving the reliability of the assessment results.

[0020] Furthermore, by introducing trajectory and perception analysis and a secondary confirmation mechanism, the robustness of the evaluation system is significantly improved. When the vision system detects a significant misalignment between the actual motion trajectory and the target trajectory, the system does not simply judge it as an execution error, but instead initiates a secondary confirmation mechanism to backtrack and analyze whether the signals of each position sensor under the abnormal trajectory still conform to their preset feedback range. This effectively avoids misjudgment caused by a single data anomaly and further improves the reliability of the evaluation results.

[0021] Furthermore, by monitoring sensor signals during continuous movement, the dynamic assessment of foot perception and motor coordination during movement is achieved. Through correlation analysis of abnormal states of adjacent sensors, the abnormal range of the foot region is determined, thereby further improving the reliability of the assessment results.

[0022] Furthermore, by setting corresponding feedback interval benchmarks based on the historical assessment records of individual users, the monitoring can dynamically reflect changes in the patient's condition. At the same time, the design of a preset misalignment threshold that is positively correlated with the user's ability to move freely, as well as the fault-tolerant design that can identify sensor failures and retest them, makes it suitable for long-term follow-up of patients. This provides an ideal tool for early warning of diseases and evaluation of intervention effects, thereby further improving the reliability of the assessment results. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the structure of the diabetic foot patient motor function assessment device of the present invention; Figure 2 This is a schematic diagram of the motion trajectory in an embodiment of the present invention; Figure 3 This is a schematic diagram of sensor deployment according to an embodiment of the present invention; Figure 4 This is a flowchart of the diabetic foot exercise assessment according to an embodiment of the present invention; The components are: 1. Foot support; 2. Straps; 3. Sensors; 4. The foot to be tested. Detailed Implementation

[0024] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0025] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0026] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0027] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0028] Please see Figure 1 As shown, it is a schematic diagram of the structure of the diabetic foot patient motor function assessment device of the present invention, including: Sports braces used to assist in exercise; Several visual acquisition devices used to monitor movement; Several sensors used to monitor the patient's movement trends; An evaluation server used to control motion supports and vision sensors, and connected to each sensor; Please see Figure 2 As shown, it is a schematic diagram of the motion trajectory in an embodiment of the present invention. For a single user, the sensor is fixed on the surface of the foot to be measured. In a single motion acquisition, the server controls the motion support to perform motion actions on the foot under test according to the target motion trajectory, and the vision acquisition device acquires motion action images and forms the actual motion trajectory; Each sensor collects data at various positions of this motion, among which, The server determines the feedback range of each sensor based on the motion trajectory, and confirms the sensor's sensing state of the foot being measured based on the sensor's sensing status, including... If the response sensor fails to reach the feedback range, the server determines that the sensor at that location is faulty. If the response sensor exceeds the feedback range, the server determines that the sensation at that location is abnormal; or, In response to a misalignment in the actual motion trajectory, the server performs a secondary confirmation based on the feedback range of each sensor corresponding to that motion trajectory. Among them, the sensing state is the feedback state of the foot to be tested in response to the executed movement trajectory; The sensing state is the feedback generated by the sensor on the movement of the foot being measured.

[0029] By using a motion support, several visual acquisition devices, several sensors, and an evaluation server, objectivity and quantitative evaluation of multimodal data fusion were achieved. By fusing the motion support, visual acquisition devices, and sensors, measurement errors caused by patient or doctor experience were effectively avoided, while the reliability of the evaluation results was significantly improved.

[0030] Example 1: Assessment of dorsiflexion function of foot in patients with diabetic foot 1. Equipment Setup and Preparation Exercise support: The device uses a programmable electric ankle joint rehabilitation training device, whose foot pedals can drive the patient's foot to perform dorsiflexion-plantarflexion movements in the sagittal plane.

[0031] Visual acquisition device: Two high-definition infrared motion capture cameras are placed on the side and diagonally above the patient's foot, respectively, and a three-dimensional coordinate system is established after calibration.

[0032] Sensors: Three flexible pressure sensors (FSRs) and one nine-axis inertial measurement unit (IMU) were selected. The pressure sensors were attached to the first metatarsal head, the center of the arch, and the heel of the foot being tested, respectively; the IMU was fixed to the dorsum of the foot.

[0033] Evaluation server: An industrial control computer that integrates motion control, data acquisition and processing algorithms, and communicates with motion support, cameras and sensors.

[0034] 2. Testing Process The patient sits with the foot to be tested fixed to the pedal of the exercise support, with the lower leg and foot forming an initial angle of 90°.

[0035] The evaluation server sets the target motion trajectory: within 5 seconds, the foot pedal drives the foot to move at a constant speed from 0° dorsiflexion to the target dorsiflexion angle of 20°, holds for 2 seconds, and then returns to the initial position.

[0036] Startup test: The server synchronously sends instructions to control the motion support to execute the above trajectory, and triggers the vision acquisition unit and sensors to start collecting data.

[0037] 3. Data Acquisition and Processing The visual acquisition device captures motion images of foot markers at a frequency of 60Hz, and generates the actual movement trajectory of the foot through three-dimensional reconstruction.

[0038] Pressure sensors collect pressure values ​​at various points on the sole of the foot in real time, while IMUs collect the angular velocity and acceleration of the foot.

[0039] 4. Sensitive State Determination Based on the target's motion trajectory, the server pre-calculates the feedback intervals of each sensor: Pressure sensor 1 (first metatarsal head): It is expected that the pressure will increase due to plantar stretching in the dorsiflexion range of 10°-18°. The normal feedback range is an increase in pressure value of 15%-30%.

[0040] IMU (Angular Velocity Z-axis): The expected angular velocity is positive during the dorsiflexion phase, with a normal range of 3-6° / s.

[0041] at this time: If the pressure sensor 1 only increases the pressure value by 5% when dorsiflexed to 15° (not reaching the feedback range), the server determines that there is a sensory failure at that position (indicating reduced plantar pressure sensation).

[0042] If the IMU measures an angular velocity of 9° / s during the uniform dorsiflexion phase (exceeding the feedback range), the server determines that the sensation is abnormal (indicating that there may be involuntary muscle spasms or compensatory movements).

[0043] If the visual acquisition device shows that the actual movement trajectory pauses or jerks (trajectory misalignment) in the middle of dorsiflexion, the server retrieves the corresponding pressure sensor and IMU data for that time period: if the pressure sensor shows a sudden increase in pressure at the heel and the disappearance of pressure at the arch, and the IMU detects foot inversion, then it is confirmed a second time that the patient is compensating for foot inversion due to sensory abnormalities.

[0044] Please see Figure 3 As shown, it is a schematic diagram of the sensor layout in an embodiment of the present invention. In the figure, the sole of the foot to be tested 4 contacts the foot support 1 in the motion support and moves through the motion support. A strap 2 is set on the foot to be tested 4 to fix the sensor 3 at the corresponding position. Several sensors 3 are also set at the contact position between the foot support 1 and the foot to be tested 4. In practice, the sensor 3 should be installed at least at the corresponding positions on the heel, arch, and front of the sole.

[0045] Specifically, for a single user, the evaluation server controls the motion support to perform a single motion action according to the target motion trajectory; The vision acquisition device determines the actual motion trajectory corresponding to the motion action based on the motion trajectory of each joint of the support corresponding to the motion action. The evaluation server sets each sensor as the primary sensor based on the target's motion trajectory; If the sensor is located at a joint of the target motion trajectory or on the extension line of the motion trajectory, the server will set that sensor as the primary sensor.

[0046] By driving the foot with a preset target motion trajectory, the actual motion trajectory and the sensing status of the foot sensor are collected simultaneously, and the foot perception is quantified. At the same time, by detecting spatial trajectory data and time series signals, an objective and multi-dimensional data foundation is provided for motor function assessment, thereby further improving the reliability of the assessment results.

[0047] Example 2: The difference from Example 1 is as follows: 4. Main sensor settings Target motion trajectory analysis: The server analyzes the kinematic characteristics based on the preset ankle dorsiflexion movement (0°→20°→0°) to determine the ankle joint as the trajectory execution joint, and the foot rotates around the ankle joint to form an arc trajectory.

[0048] Key sensor determination: An inertial measurement unit (IMU) is fixed to the dorsum of the foot, located near the center of ankle rotation, with its measurement axis parallel to the ankle rotation axis. It is situated on the joint of the target motion trajectory and is set as the primary sensor.

[0049] The attachment points of pressure sensor 1 (first metatarsal head) and pressure sensor 3 (heel) are located on the extension line of the ankle joint rotation center in the sagittal plane (i.e., on the foot rotation arc line), and are therefore set as the main sensors.

[0050] Pressure sensor 2 (foot arch center) is offset from the rotation arc and is set as an auxiliary sensor.

[0051] 5. Sensitive State Determination Based on the target's motion trajectory, the server pre-calculates the feedback intervals of each sensor (distinguishing between primary and secondary sensors): Main sensor 1 (IMU - angular velocity Z-axis): normal range 3-6° / s.

[0052] Main sensor 2 (pressure sensor 1 - first metatarsal head): pressure rises within the normal range of 15%-30%.

[0053] Main sensor 3 (pressure sensor 3 - heel): Pressure drop within the normal range of 10%-25%.

[0054] Auxiliary sensor (pressure sensor 2 - arch center): pressure change reference range ±5%.

[0055] at this time: If the IMU reaches an angular velocity of 9° / s during the uniform backflexion phase (exceeding the feedback range), the server determines that the sensation at that location is abnormal (indicating motor control disorder).

[0056] If the pressure sensor 1 only increases the pressure value by 5% when dorsiflexed to 15° (not reaching the feedback range), it is determined to be a sensor failure (indicating reduced protective sensation).

[0057] Secondary confirmation in case of trajectory misalignment: If the vision acquisition device shows an unexpected eversion at 10° dorsiflexion, the server: Retrieve data from the main sensors (IMU, pressure sensors 1 and 3) corresponding to this location; Analysis revealed that the IMU detected an abnormal increase in angular velocity around the Y-axis (foot eversion), while the pressure of pressure sensor 3 (heel) dropped beyond the range, and the pressure of pressure sensor 1 did not reach the range. Based on the abnormal feedback from the main sensors, it was confirmed a second time that the patient's compensatory eversion movement was caused by loss of heel pressure sensation.

[0058] Specifically, for a single motion action, the server response indicates that the misalignment between the actual motion trajectory and the target motion trajectory is less than a preset misalignment threshold, and... Determine whether the sensing state of each active sensor is within its feedback range in order to determine the sensing state of each sensor at its corresponding location. If the misalignment between the actual motion trajectory and the target motion trajectory is not less than a preset misalignment threshold, the server will perform a secondary confirmation, based on the feedback intervals of each position corresponding to the target motion trajectory, and... Determine whether the sensing state collected by each sensor during the movement conforms to the feedback range of the corresponding position, in order to determine the sensing state of each sensor at the corresponding position; The preset misalignment threshold is positively correlated with the area where the user can move freely, and the larger the range of free movement, the larger the preset misalignment threshold.

[0059] By setting feedback intervals, the abnormalities in the patient's foot can be differentiated. This avoids the binary judgment of "sense presence" or "sense absence" that traditional assessments often make. By comparing and distinguishing the feedback intervals formed by sensor signals and health benchmarks or individual historical data, more accurate data can be obtained, thereby further improving the reliability of the assessment results.

[0060] Example 3: The difference from Example 2 is as follows: 5. Setting the preset misalignment threshold Before the test begins, the server performs an assessment of areas where the patient can move freely: The patient actively performs the maximum range of ankle dorsiflexion and plantarflexion without wearing a brace.

[0061] The visual acquisition device records the active range of motion and calculates the range of motion of the ankle joint in the sagittal plane (e.g., 10° dorsiflexion to 30° plantarflexion, total range of motion 40°).

[0062] The server sets a preset misalignment threshold according to the following rules: The baseline misalignment threshold is 10% of the target trajectory amplitude (in this example, the target backbend is 20°, and the baseline threshold is 2°).

[0063] Dynamic adjustments are made based on the active range of motion: if the patient's active range of motion is ≥40°, the misalignment threshold increases by 0.5° for every 10° increase in range of motion.

[0064] In this case, the patient's active range of motion was 40°, which met the basic requirements, and the final preset misalignment threshold was set to 2°.

[0065] Specifically, the feedback interval is the corresponding feedback data collected by each sensor when the healthy foot performs a movement action according to the target movement trajectory; or, Settings are configured based on sensor data from an individual user's historical evaluation records; Among them, the sensing data is the curve of the change of sensor data corresponding to the user at the corresponding position under the target's movement trajectory.

[0066] Specifically, for a single sensor, the sensing state at its corresponding location is the corresponding state of the sensor signal strength changing with time or spatial location, including at least one of the rate of change and fluctuation frequency of the sensor signal waveform.

[0067] Specifically, the evaluation server also calculates the signal characteristic curve of any sensor based on the signal strength of each sensor changing over time during a single motion acquisition. Compare the similarity between the signal characteristic curve of any sensor and the standard sensing data curve at the corresponding location; If the similarity is lower than the preset similarity threshold, the sensing state of the corresponding location of the sensor is determined to be abnormal or malfunctioning. The similarity threshold is related to the preset misalignment threshold.

[0068] By introducing trajectory and perception analysis and a secondary confirmation mechanism, the robustness of the evaluation system is significantly improved. When the vision system detects a significant misalignment between the actual motion trajectory and the target trajectory, the system does not simply judge it as an execution error, but instead initiates a secondary confirmation mechanism to backtrack and analyze whether the signals of each position sensor under the abnormal trajectory still conform to their preset feedback range. This effectively avoids misjudgment caused by a single data anomaly and further improves the reliability of the evaluation results.

[0069] Specifically, when the sensing state of any adjacent sensor is determined to be abnormal and / or malfunctioning, the foot region formed by the corresponding positions of at least two sensors is acquired. Based on the actual movement trajectory and the signal change trends of each sensor in the area, the abnormal range of the foot area is determined.

[0070] Specifically, the assessment server contains a pre-stored database of rehabilitation movements. When it is determined that the sensory state of the foot under test is abnormal or ineffective under a certain target movement trajectory, The server matches and recommends at least one rehabilitation training exercise from the rehabilitation exercise database to improve the function of the movement in that trajectory.

[0071] Specifically, the evaluation server determines the abnormal area of ​​the foot to be tested based on the misalignment between the actual motion trajectory and the target motion trajectory, as well as the sensing state of each sensor.

[0072] By monitoring sensor signals during continuous movement, the dynamic assessment of foot perception and motor coordination during movement is achieved. Through correlation analysis of abnormal states of adjacent sensors, the abnormal range of the foot region is determined, thereby further improving the reliability of the assessment results.

[0073] Example 4: The difference from Example 1 is as follows: 2. Test Process Expansion The target movement trajectory is set as a compound movement: ① Back flexion 0° → 20° (3 seconds); ② Maintain 20° back flexion and inversion 0° → 10° (2 seconds); ③ Return to neutral position (2 seconds).

[0074] The visual acquisition device and the sensor acquire data synchronously.

[0075] 3. Signal Characteristic Curve Analysis The server extracts the signals from each sensor over time and generates signal characteristic curves. Pressure sensor 1 (first metatarsal head): pressure-time curve (P1-t); IMU (Angular Velocity Z-axis): Angular velocity-time curve (ωz-t); IMU (Angular velocity Y-axis): Angular velocity-time curve (ωy-t); Comparison with standard induction data curves (standard curves are derived from a database of healthy individuals moving along the same trajectory): Calculate the dynamic time warping (DTW) distance between the P1-t curve and the standard pressure curve, and set the similarity threshold to 0.85 (linearly correlated with the preset misalignment threshold of 2°: for every 0.5° increase in the misalignment threshold, the similarity threshold decreases by 0.05).

[0076] If the similarity of the P1-t curve is 0.72 (<0.85), the location is considered to be sensory abnormal.

[0077] 4. Secondary confirmation and determination of the range of regional anomalies Actual motion trajectory analysis: The vision system detected an abnormal outward deviation in the trajectory during stage ② (inversion movement), with a misalignment of 3° (≥ threshold 2°), triggering a secondary confirmation.

[0078] Sensor data corresponding to server backtracking phase ②: Pressure sensor 1 (first metatarsal head): Insufficient pressure rise (similarity 0.72, abnormal); Pressure sensor 3 (heel): Delayed pressure drop (similarity 0.70, anomalous); IMU(ωy): Inversion velocity is low (similarity 0.68, anomaly); Determination of abnormal areas in adjacent sensors: Abnormalities were found in the sensor / calculation points of pressure sensor 1 (metastatic head), pressure sensor 3 (heel), and the plantar area between them (covering the middle of the metatarsal bone).

[0079] Based on the signal change trends at various points during the actual trajectory deviation period (interruption of pressure transmission, abnormal angular velocity), the server determined the abnormal area of ​​the foot to be the "fractured area of ​​the pressure sensing chain from the forefoot to the heel", and the abnormal range was marked as the anterior 2 / 3 area of ​​the longitudinal arch of the foot.

[0080] 5. Rehabilitation Exercise Matching and Recommendations The server's pre-stored rehabilitation exercise database contains: Action code A01: Foot rolling massage (for reduced sensation in the soles of the feet); Action code A02: Ankle proprioception training (closed-eye ankle pump); Action code A03: Toe gripping towel training (activates plantar muscle groups); Motion code B01: Resisted inversion training (for inversion control inadequacy); When it is determined that the patient has a broken plantar sensory chain under the inversion trajectory, accompanied by abnormal inversion control: The server matches the associated actions: A01 (improves plantar sensation), A02 (enhances proprioception), and B01 (strengthens inversion control). The recommended training plan is as follows: daily training A01 (5 minutes) → A02 (10 minutes) → B01 (10 minutes), emphasizing attention to changes in plantar pressure distribution during training; Specifically, if the sensing status of a certain sensor is continuously missing, the evaluation server determines that the data corresponding to that sensor is invalid and re-executes the target motion trajectory.

[0081] By setting corresponding feedback interval benchmarks based on the historical assessment records of individual users, the monitoring can dynamically reflect changes in the patient's condition. At the same time, the design of a preset misalignment threshold that is positively correlated with the user's ability to move freely, as well as the fault-tolerant design that can identify sensor failures and retest them, makes it suitable for long-term follow-up of patients. This provides an ideal tool for early warning of diseases and evaluation of intervention effects, thereby further improving the reliability of the assessment results.

[0082] Please see Figure 4 As shown, it is a flowchart of the diabetic foot exercise assessment according to an embodiment of the present invention, including: Step S1: Position the sensor and complete the equipment calibration; Step S2: The patient's foot is guided by the exercise frame to complete a standard target movement; Step S3: Record the actual movement trajectory of the foot and the real-time signals from each sensor; Step S4: Compare the actual motion trajectory with the preset target trajectory; Step S5: Compare the signals of each sensor with the standard feedback range to determine whether the sensing status of each position on the foot is normal, ineffective, or abnormal. Step S6: Locate the specific abnormal area of ​​the foot and automatically match and recommend a personalized rehabilitation training plan; Step S7: Record the evaluation data for subsequent tracking and analysis.

[0083] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0084] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A device for assessing motor function in patients with diabetic foot, comprising: Sports braces used to assist in exercise; Several visual acquisition devices used to monitor movement; Several sensors used to monitor the patient's movement trends; An evaluation server used to control the motion support and vision sensors, and connected to each sensor; Its characteristic is that, for a single user, the sensor is fixed to the surface of the foot to be measured; In a single motion acquisition, the server controls the motion support to perform motion actions on the foot to be tested according to the target motion trajectory, and the vision acquisition device acquires motion action images and forms the actual motion trajectory; Each sensor collects data at various positions of this motion, among which, The server determines the feedback range of each sensor based on the motion trajectory, and confirms the sensory state of the foot to be tested based on the sensor's sensing state, including... If the response sensor fails to reach the feedback range, the server determines that the sensor at that location is faulty. If the response sensor exceeds the feedback range, the server determines that the sensation at that location is abnormal; or, In response to the actual motion trajectory misalignment, the server performs a secondary confirmation based on the feedback range of each sensor corresponding to the motion trajectory; Wherein, the sensing state is the feedback state of the foot to be tested in response to the execution of the motion trajectory; The sensing state is the feedback generated by the sensor to the movement of the foot being measured.

2. The device for assessing motor function in diabetic foot patients according to claim 1, characterized in that, For a single user, the evaluation server controls the motion support to perform a motion action according to the target motion trajectory; The visual acquisition device determines the actual motion trajectory corresponding to the motion action based on the motion trajectory of each joint of the support corresponding to the motion action. The evaluation server sets each sensor as the primary sensor based on the target motion trajectory; If the sensor is located at a joint of the target motion trajectory or on the extension line of the motion trajectory, the server will set that sensor as the primary sensor.

3. The diabetic foot patient motor function assessment device according to claim 2, characterized in that, For a single movement action, the server responds that the misalignment between the actual movement trajectory and the target movement trajectory is less than a preset misalignment threshold, and... Determine whether the sensing state of each active sensor is within its feedback range in order to determine the sensing state of each sensor at its corresponding location. If the misalignment between the actual motion trajectory and the target motion trajectory is not less than the preset misalignment threshold, the server determines to perform a secondary confirmation, and based on the feedback intervals of each position corresponding to the target motion trajectory, and... Determine whether the sensing state collected by each sensor during the movement conforms to the feedback range of the corresponding position, in order to determine the sensing state of each sensor at the corresponding position; The preset misalignment threshold is positively correlated with the area where the user can move freely, and the larger the range of free movement, the larger the preset misalignment threshold.

4. The diabetic foot patient motor function assessment device according to claim 3, characterized in that, The feedback interval is the corresponding feedback data collected by each sensor when the healthy foot performs a movement action according to the target movement trajectory; or, Settings are configured based on sensor data from an individual user's historical evaluation records; The sensing data refers to the change curve of sensor data corresponding to the user at the target's motion trajectory, which is a sensor data curve at the corresponding location.

5. The diabetic foot patient motor function assessment device according to claim 4, characterized in that, For a single sensor, the sensing state at its corresponding location is the corresponding state of the sensor signal strength changing with time or spatial location, including at least one of the rate of change and fluctuation frequency of the sensor signal waveform.

6. The diabetic foot patient motor function assessment device according to claim 5, characterized in that, The evaluation server also calculates the signal characteristic curve of any sensor based on the signal strength of each sensor changing over time during a single motion acquisition. Compare the similarity between the signal characteristic curve of any sensor and the standard sensing data curve at the corresponding location; If the similarity is lower than the preset similarity threshold, the sensing state of the corresponding location of the sensor is determined to be abnormal or malfunctioning. The similarity threshold is related to the preset misalignment threshold.

7. The diabetic foot patient motor function assessment device according to claim 6, characterized in that, When the sensing state of any adjacent sensor is determined to be abnormal and / or malfunctioning, the foot region formed by the corresponding positions of the at least two sensors is acquired; Based on the actual movement trajectory and the signal change trends of each sensor in the area, the abnormal range of the foot area is determined.

8. The device for assessing motor function in diabetic foot patients according to claim 6 or 7, characterized in that, The assessment server contains a pre-stored database of rehabilitation movements. When it is determined that the sensory state of the foot under test is abnormal or ineffective under a certain target movement trajectory, The server matches and recommends at least one rehabilitation training exercise from the rehabilitation exercise database to improve the function of the trajectory movement.

9. The device for assessing motor function in diabetic foot patients according to claim 8, characterized in that, The evaluation server determines the abnormal area of ​​the foot to be tested based on the misalignment between the actual motion trajectory and the target motion trajectory, as well as the sensing state of each sensor.

10. The device for assessing motor function in diabetic foot patients according to claim 9, characterized in that, If the sensing status of a certain sensor is continuously missing, the evaluation server determines that the data corresponding to that sensor is invalid and re-executes the target motion trajectory.

Images