An individualized intelligent wrist joint orthosis system with multi-modal perception and closed-loop feedback

Abstract

The application relates to the fields of medical rehabilitation and intelligent wearable devices, and discloses a multi-modal sensing and closed-loop feedback individualized intelligent wrist joint brace system which comprises a brace body, a distributed wrist and forearm monitoring system, an individualized assessment and decision module, and a closed-loop adjustment and doctor-patient interaction module. The brace body is used for being worn on the forearm, wrist and palm of a patient and comprises a forearm fixing mechanism, a wrist transition mechanism, a palm fixing mechanism, an angle adjustment mechanism and a dynamic blocking and buffering assembly; the distributed wrist and forearm monitoring system is integrated in the brace body and is used for collecting wrist joint posture, local pressure, fixing tension and muscle activity data; the individualized assessment and decision module is used for receiving and fusing the monitoring data, combining patient individual information to construct an individualized assessment model, and outputting decision information including rehabilitation stage recognition results and parameter adjustment suggestions; and the application can be used for conservative treatment of wrist joints, postoperative fixation protection, functional training and remote rehabilitation management.

Description

Technical Field

[0001] This invention relates to the field of medical rehabilitation and smart wearable devices, and in particular to a personalized smart wrist joint brace system with multimodal sensing and closed-loop feedback. Background Technology

[0002] The wrist joint is one of the most complex and frequently used joints in the human body, playing a crucial role in grasping, holding objects, pushing, twisting, keyboard operation, and fine motor skills, including posture adjustment, load transfer, and motor coordination. Distal radius fractures, wrist ligament injuries, tenosynovitis, TFCC injuries, and chronic wrist pain are common in trauma orthopedics, hand surgery, and rehabilitation medicine. Existing patents for wrist fixation braces indicate that different types of wrist injuries often require different fixation angles, such as palmar flexion, dorsiflexion, neutral, ulnar deviation, or radial deviation. Traditional plaster casts or splints often fail to simultaneously meet the needs for precise angle fixation, comfortable wear, and subsequent functional recovery.

[0003] Traditional wrist braces primarily achieve external fixation through palmar splints, dorsal splints, forearm support plates, and Velcro straps. Their main function is to restrict abnormal wrist movements, maintain stability at fracture or soft tissue repair sites, and reduce pain and local traction load. In clinical practice, these braces are of significant value for early protection. However, wrist rehabilitation is not simply about fixation; it is a dynamic process involving palmar tilt / dorsiflexion reconstruction, ulnar / radial deviation control, forearm rotation adaptation, finger function recovery, and grasping ability reconstruction. Existing braces either prioritize fixation and lack mobility, or prioritize training and lack stability, making it difficult to provide continuous, precise, and individualized support across different diseases, surgical procedures, and rehabilitation stages.

[0004] Currently, the application of wrist braces mainly suffers from the following problems. First, there is a lack of continuous and objective rehabilitation monitoring capabilities. Clinically, the assessment of wrist fixation effectiveness and rehabilitation progress still relies primarily on outpatient follow-ups, X-ray examinations, and patient subjective descriptions, which cannot accurately reflect the patient's wrist posture, local stress, fixation tightness, and high-risk behaviors during home or daily activities. Second, monitoring indicators are limited. Although some wrist fracture precision fixation braces have introduced pressure sensors to assist in adjusting tightness, most solutions are still limited to single-point pressure or mechanical angle adjustment, making it difficult to comprehensively assess multi-dimensional characteristics such as wrist palmar tilt / dorsiflexion, ulnar / radial deviation, forearm pronation / supination trends, local contact pressure, and muscle activation status. Third, there is a lack of truly individualized decision-making capabilities for the wrist rehabilitation process. Existing devices mostly remain at the level of manual adjustment, fixed angle setting, or simple prompts, and cannot yet dynamically optimize the fixation angle, brace tension, training load, and support parameters based on the patient's age, body type, disease type, surgical procedure, postoperative time, pain feedback, and rehabilitation stage. Fourth, the lack of closed-loop adjustment and remote doctor-patient collaboration mechanisms means that even if abnormal pressure, excessive angle, or loose fit can be identified, it is difficult to promptly enhance support, trigger local buffering, or change parameters through the brace itself. As a result, wrist braces remain passive devices that are "fixable and recordable, but difficult to intervene in."

[0005] On the other hand, existing wrist braces have accumulated certain technological expertise in areas such as individualized fixation, dynamic assisted movement, protective cushioning, and intelligent adjustment, providing an important structural and functional foundation for the construction of new intelligent wrist rehabilitation systems. For example, individualized 3D-printed wrist braces propose a main structure consisting of multiple fixed pieces forming a fully enclosed placement space, combined with limiting components to achieve detachability and lightweight through-holes / reinforcing ribs; dynamic wrist braces propose a double torsion spring connection between the arm and palm sleeves, and a passive extension / active flexion training approach linked with the finger sleeve assembly; wearable dynamic protective braces propose a nested dynamic blocking structure around the wrist joint, maintaining freedom of movement during normal activities, while providing immediate stress transmission and palm cushioning in dangerous situations such as excessive movement or falls; and precise fixation braces for wrist fractures propose an approach based on pressure sensing and adjustable mechanisms to achieve palmar flexion / dorsiflexion and ulnar / radial deviation adjustment. These technologies address specific problems of wrist braces, but a unified, multimodal perception-driven closed-loop wrist rehabilitation platform is still lacking.

[0006] Therefore, there is an urgent need to construct an intelligent closed-loop feedback brace system for the entire process of conservative treatment and postoperative rehabilitation of the wrist joint. Based on the mechanical support of traditional wrist braces, this system should further integrate wrist and forearm posture monitoring, local pressure detection, muscle function assessment, individualized analysis, and active feedback technology. This would enable continuous perception of wrist joint palmar tilt / dorsiflexion, ulnar / radial deviation, pronation and supination trends, local force, and wearing status. Furthermore, it should dynamically optimize the brace support angle, fixation strength, dangerous movement threshold, and training suggestions based on the patient's individual characteristics and real-time rehabilitation status, ultimately forming a closed-loop rehabilitation management model. Summary of the Invention

[0007] To address the aforementioned technical problems, this invention provides a personalized intelligent wrist joint brace system with multimodal sensing and closed-loop feedback, comprising: The brace body is for wearing on the patient's forearm, wrist and palm, and includes a forearm fixation mechanism, a wrist transition mechanism, a palm fixation mechanism, and an angle adjustment mechanism and a dynamic blocking and cushioning component disposed on the brace body. A distributed wrist-forearm monitoring system, integrated into the brace body, includes at least a kinematic / posture sensing unit, a dynamics / contact sensing unit, and a muscle function sensing unit, for collecting wrist joint posture, local pressure, and muscle activity data while in use; The individualized assessment and decision-making module is communicatively connected to the distributed wrist and forearm monitoring system, receives and integrates the monitoring data, constructs an individualized assessment model based on the patient's individual information, and outputs decision information, including rehabilitation stage identification results, risk warning information, and parameter adjustment suggestions. The closed-loop adjustment and doctor-patient interaction module includes an actuator mounted on the brace body and a user interaction unit communicatively connected to the individualized assessment and decision-making module. The actuator drives the angle adjustment mechanism and / or the dynamic blocking and buffering components to perform actions based on the decision information in order to adjust the support state of the brace body.

[0008] Compared with the prior art, the beneficial effects of the present invention are as follows: Building upon the mechanical support of traditional wrist braces, this system adds continuous monitoring capabilities for wrist posture, local stress, fixation tightness, functional training status, and wearing environment. It provides more clinically interpretable quantitative indicators addressing the most critical clinical issues in wrist rehabilitation: excessive palmar flexion / dorsiflexion, excessive ulnar / radial deviation, abnormal local pressure, palmar impact risk, improper wearing, and insufficient training compliance. Through an individualized assessment model, it identifies rehabilitation stages, provides risk warnings, and generates wearing recommendations, upgrading the wrist brace from a passive fixation tool to an intelligent rehabilitation platform. A closed-loop feedback mechanism enables dynamic optimization of fixation angle, band tension, palmar cushioning, and dynamic blocking status, improving active protection capabilities while maintaining daily comfort. It achieves an integrated closed-loop system for home rehabilitation, remote follow-up, and collaborative doctor-patient management, enhancing the accuracy, safety, and long-term efficacy of conservative wrist treatment and postoperative rehabilitation. Attached Figure Description

[0009] Figure 1 This is a schematic diagram of the support body structure provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the arrangement of the distributed wrist-forearm monitoring system on the brace body according to an embodiment of the present invention; Figure 3 This is a diagram illustrating the multimodal sensing system and data acquisition and transmission architecture provided in an embodiment of the present invention. Figure 4 The flowchart of the individualized assessment and decision-making module provided in the embodiments of the present invention is shown.

[0010] The attached figures are labeled as follows: Forearm fixation mechanism 100, wrist transition mechanism 300, palm fixation mechanism 200 Forearm support plate 11; metacarpal support plate 21; thumb / metacarpal positioning component 22; functional training auxiliary component 23; radius and ulna contact plate 31; angle adjustment mechanism 32; dynamic blocking and buffering component 33; 8. Flexible padding layer; 9. Restraint strap; 10. Sensing / actuation module mounting position; Kinematic / Posture Sensing Unit 1; Dynamics / Contact Sensing Unit 2; Muscle Function Sensing Unit 3; Physiological and Local Microenvironment Sensing Unit 4; Auxiliary Abnormal Event Sensing Unit 5. Detailed Implementation

[0011] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” or “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0012] like Figures 1 to 4 A multimodal sensing and closed-loop feedback personalized intelligent wrist joint brace system, comprising: The brace body is for wearing on the patient's forearm, wrist and palm, and includes a forearm fixation mechanism, a wrist transition mechanism, a palm fixation mechanism, and an angle adjustment mechanism and a dynamic blocking and cushioning component disposed on the brace body. A distributed wrist-forearm monitoring system, integrated into the brace body, includes at least a kinematic / posture sensing unit, a dynamics / contact sensing unit, and a muscle function sensing unit, for collecting wrist joint posture, local pressure, and muscle activity data while in use; The individualized assessment and decision-making module is communicatively connected to the distributed wrist and forearm monitoring system, receives and integrates the monitoring data, constructs an individualized assessment model based on the patient's individual information, and outputs decision information, including rehabilitation stage identification results, risk warning information, and parameter adjustment suggestions. The closed-loop adjustment and doctor-patient interaction module includes an actuator mounted on the brace body and a user interaction unit communicatively connected to the individualized assessment and decision-making module. The actuator drives the angle adjustment mechanism and / or the dynamic blocking and buffering components to perform actions based on the decision information in order to adjust the support state of the brace body.

[0013] The brace body is formed by 3D printing based on the shape data of the patient's distal forearm, wrist, palm and thumb regions. The forearm fixation mechanism, wrist transition mechanism and palm fixation mechanism are integrated or modular splicing structures.

[0014] The kinematics / posture sensing unit includes multiple nine-axis IMU sensors, which are respectively fixed to the dorsal side of the palm fixation mechanism, the wrist transition area, and the proximal end of the forearm fixation mechanism. The IMU sensors output palmar flexion angle, dorsiflexion angle, ulnar deviation angle, radial deviation angle, and forearm rotation trend data of the wrist joint. The dynamics / contact sensing unit includes a multi-region distributed pressure sensing pad and a tension band sensor. The pressure sensing pad is set in the forearm area, palm area, and palm buffer zone to detect the contact pressure distribution between the brace and the limb. The tension band sensor is used to detect the tension of the fixation strap. The muscle function sensing unit is a surface electromyography (SEMG) module, which is arranged in at least one location in the forearm extensor and flexor muscle groups to collect electromyographic signals and extract muscle activation features.

[0015] When integrating the monitoring data, the individualized assessment and decision-making module extracts multimodal motion feature vectors and integrates information such as patient age, body type, disease type, surgical procedure, postoperative time, and rehabilitation stage to construct a patient-specific digital twin wrist joint support model. This model dynamically estimates the safe range of motion, recommends fixation tension and local pressure tolerance thresholds, and outputs the decision information accordingly.

[0016] The actuator includes at least one of a miniature winding motor, a partial tightening mechanism, a controllable locking element, a short-stroke angle adjustment actuator, and a palm cushioning trigger unit; the actuator responds to the decision information and actively adjusts the palmar flexion / dorsiflexion angle limitation, ulnar / radial deviation angle limitation, band tension, or palm cushioning state of the wrist joint.

[0017] The user interaction unit includes a patient-side application and a doctor-side platform. The patient-side application receives and displays training tasks, posture and stress statistics, and risk alerts. The doctor-side platform remotely acquires the patient's monitoring data and assessment results, and receives instructions from the doctor to adjust rehabilitation prescriptions and update brace parameter thresholds.

[0018] The distributed wrist-forearm monitoring system also includes a physiological and local microenvironment sensing unit, which includes a temperature sensor and a humidity sensor, arranged in a high-contact area inside the brace body to collect temperature and humidity data of the wearing environment; the individualized assessment and decision module also assesses wearing comfort and skin tolerance based on the temperature and humidity data.

[0019] The distributed wrist-forearm monitoring system also includes an auxiliary abnormal event sensing unit, which includes an impact detection module and / or a fall determination module, used to identify fall or palm-on impact events; when the event is detected, the closed-loop adjustment and doctor-patient interaction module triggers the dynamic blocking and buffering components to switch to a high protection state.

[0020] The brace body also includes a functional training auxiliary component, which includes a torsion spring, a telescopic strip, an elastic band, a finger sleeve assembly, and a thumb sleeve assembly, which are detachably connected between the palm fixation mechanism and the forearm fixation mechanism to provide passive or active training resistance in the mid-to-late stages of rehabilitation.

[0021] The inner side of the brace body is provided with a removable flexible padding layer. The padding layer has a locally thickened structure in the metacarpal head, radial styloid process, ulnar high pressure area and forearm near wrist contact area. The padding layer and the brace body are reserved with a space for embedding airbags, heating layers or massage blocks.

[0022] Specifically, the solution of the present invention is as follows: 1. Support body like Figure 1 The brace itself can be designed as a modular wrist rehabilitation brace, individually formed based on the patient's distal forearm, wrist, palm, and, if necessary, thumb region morphology data. The brace consists of a forearm fixation mechanism, a wrist transition mechanism, a palm fixation mechanism, a thumb / metacarpal positioning component, an angle adjustment mechanism, a dynamic blocking and cushioning component, a functional training auxiliary component, and a sensor / actuator mounting position. Its design goal is not to create a single, heavy plaster-like overall fixation, but rather to establish a stable, adjustable, and long-term wearable support and protection pathway between the forearm, wrist, and palm, enabling the brace to meet both early precise fixation and restrictions on dangerous movements, as well as the needs of mid-to-late-stage micro-motion recovery and functional training.

[0023] The forearm fixation mechanism 100 is preferably located at the distal end of the forearm. It can be formed by a forearm dorsal support plate 11, a forearm palmar support plate, and connecting pieces on both sides to create a semi-enclosed or fully enclosed structure. Alternatively, it can be formed by splicing together multiple individual 3D-printed fixation pieces to create a single main body. Its inner curvature preferably conforms to the curve of the user's distal forearm to improve fixation stability and reduce displacement. The forearm fixation mechanism can use a 3D-printed main body with multiple through holes and cross reinforcing ribs to reduce weight and improve breathability while maintaining strength.

[0024] The palm fixation mechanism 200 is preferably located in the palm and metacarpal region, including a metacarpal support plate 21 for supporting the metacarpals and providing directional support for the palm, metacarpals, and thumb base; and a thumb / metacarpal positioning component 22 located on the metacarpal support plate 21 for fixing the palm, metacarpals, and thumb base. The palm fixation mechanism preferably has two functions: first, to provide stable support for the metacarpals and wrist in the early fixation stage; and second, to preserve the necessary structural interface and movement space for grasping, pinching, and finger training in the recovery stage.

[0025] The wrist transition mechanism 300, located between the forearm fixation mechanism 100 and the palm fixation mechanism 200, is the core area for achieving multi-directional restriction and graded opening of the range of motion in this invention. Preferably, this area may employ a radius and ulna contact plate 31, an angle adjustment mechanism 32, and a dynamic blocking and buffering assembly 33. The radius and ulna contact plate 31 is used to wrap around the radius and ulna, and the wrist transition mechanism 300 enables the forearm segment and the palm segment to establish a multi-axis or quasi-multi-axis relative adjustment relationship around the wrist joint. The use of graded limiting and a lockable pivot axis allows the wrist to exhibit different activity boundaries in the acute, intermediate, and late stages.

[0026] The angle adjustment mechanism 32 is preferably used to adjust the palmar tilt / dorsiflexion angle, ulnar deviation / radial deviation angle, and, when necessary, the forearm rotation adaptation angle of the wrist joint. Preferably, this mechanism can be formed by an electric push rod, a movable disc, a connecting plate, a sleeve plate, and a palm rest to form a controllable adjustment mechanism. The angle adjustment mechanism preferably has the following characteristics: first, the adjustment axis is as consistent as possible with the main movement direction of the wrist joint to reduce the feeling of misalignment during the adjustment process; second, it is equipped with graded locking holes or controllable actuators so that different fixed angles can be switched at different stages; third, the adjustment structure should be compatible with the sensing system and the closed-loop execution module to facilitate subsequent real-time fine-tuning.

[0027] The dynamic blocking and cushioning component 33 is preferably located in the wrist transition area and palm area, and has a spring structure to preserve wrist joint flexibility within the normal range of motion, while providing additional restriction and cushioning in scenarios of excessive movement or fall impact. The dynamic blocking and cushioning component can preferably adopt a dual-mode design of "passive limiting + active cushioning", providing flexible restriction during daily wear and triggering stronger protection in cases of falls or high-risk excessive movements.

[0028] The functional training auxiliary component 23 can be optionally installed between the palm fixation mechanism 200 and the forearm fixation mechanism 100, preferably in the form of a torsion spring, telescopic strip, elastic band, finger sleeve assembly, or thumb sleeve assembly. This invention allows for modular installation of this component during the mid-to-late stages of rehabilitation, enabling a smooth transition from a fixed mode to a training mode without replacing the entire brace.

[0029] The inner side of the brace preferably features a removable flexible padding layer 8, approximately 3–8 mm thick, made of skin-friendly foam, antibacterial fabric, low-resilience cushioning layer, or porous elastic layer. Local thickening can be applied near the metacarpal heads, radial styloid process, ulnar high-pressure area, and the forearm near the wrist contact area to reduce tenderness and skin irritation caused by prolonged wear. To meet the needs of long-term wear and physiotherapy, space can be provided between the padding layer and the brace body for the installation of airbags, heating layers, or massage blocks. The restraint strap 9 is used to stabilize the palm, metacarpal region, or proximal finger region to reduce relative displacement of the wrist and palm, and can be used to restrict or release some finger movement depending on the stage of rehabilitation.

[0030] A sensor / actuator module mounting position 10 is provided on the forearm fixation mechanism 100. To meet the needs of subsequent intelligent integration, the brace body preferably has standardized mounting positions, flexible wiring channels or control compartments reserved in the forearm fixation mechanism, wrist transition mechanism, palm fixation mechanism and palm area for mounting IMU, pressure sensor, tension sensor, electromyography module, main control board, battery, micro actuator and necessary air / electrical connection parts.

[0031] 2. Distributed wrist-forearm monitoring system like Figure 2 The distributed wrist-forearm monitoring system can be embedded in the brace itself. It consists of a kinematic / posture sensing unit 1, a dynamics / contact sensing unit 2, a muscle function sensing unit 3, a physiological and local microenvironment sensing unit 4, and an auxiliary abnormal event sensing unit 5. It achieves real-time fusion of multi-source data through a unified clock synchronization and edge sampling module. The design goal of this system is not simply to increase the number of sensors, but to form a collaborative perception of wrist palm tilt / dorsiflexion, ulnar / radial deviation, forearm relative posture, local pressure, wearing tightness, and hand function training status within a wearable wrist brace platform. This provides continuous, stable, and clinically interpretable input data for subsequent individualized assessment, risk warning, and closed-loop feedback.

[0032] The kinematic / posture sensing unit preferably employs 3–5 miniature nine-axis IMUs, respectively positioned on the dorsal side of the palm fixation mechanism, the wrist transition zone, the proximal end of the forearm fixation mechanism, and, if necessary, the thumb or back of the hand area. Each IMU's sampling frequency can be set to 25–200 Hz, preferably 50–100 Hz, to continuously acquire wrist joint palmar flexion angle, dorsiflexion angle, ulnar deviation angle, radial deviation angle, rotational tendency, angular velocity, and angular acceleration, and can further estimate the relative posture relationship between the forearm and palm. During the acute fixation phase, the system focuses more on excessive palmar tilt / dorsiflexion and abnormal deviation; during the training phase, it focuses more on the range of motion, rhythm, and number of repetitions.

[0033] The dynamics / contact sensing unit is primarily used to reflect the force relationship, tightness, and local contact pressure distribution between the brace and the forearm, wrist, and palm. This unit may include a forearm pressure sensing pad, a palm pressure sensing pad, a palm buffer pressure sensor, a tensioning strap sensor, and a palm rest / connecting plate contact load detection element. Building upon this, the present invention further expands pressure monitoring from a single point to multi-area distributed monitoring and incorporates tension monitoring into a unified analysis framework to determine whether the brace is worn too loosely, too tightly, misaligned, or subject to localized overpressure.

[0034] The muscle function sensing unit preferably employs a 2–4 ​​channel surface electromyography (EMG) module, which can be selectively deployed in the forearm extensor and flexor muscles, and, where necessary, the thenar eminence or superficial areas related to the abductor pollicis brevis. The sampling frequency can be set to 1000–2000 Hz, preferably approximately 1500 Hz, and RMS, mean absolute value, median frequency, activation sequence, and fatigue-related characteristics are extracted through bandpass filtering, rectification, and smoothing. The main function of this module is to assess whether the patient exhibits problems such as acute-phase protective muscle inhibition, insufficient active recruitment during training, abnormal grasping compensation, or excessively rapid fatigue accumulation due to repetitive training.

[0035] The physiological and local microenvironment sensing unit may include a temperature sensor, a humidity / sweat sensor, and an optional blood flow / skin temperature module. The temperature and humidity sensors are preferably positioned in the high-contact area of ​​the forearm, the palm fixation area, and the palm buffer zone to assess local temperature rise, humidity, and skin tolerance after prolonged wear. If a skin temperature or blood flow assist module is included, it can serve as a reference indicator for determining whether local pressure is excessive and whether wear affects circulation. By incorporating temperature, humidity, skin temperature, or blood flow assist monitoring modules, the ability to monitor the local environment and assess wearing comfort during long-term wear can be further improved.

[0036] The auxiliary abnormal event sensing unit can be equipped with an impact detection module, a fall determination module, or a palm-based rapid ground-striking event recognition module, depending on the system complexity, to identify falls, palm-based impacts, and sudden over-limit movements. This invention combines external fall event recognition with wrist posture / impact signals for a higher level of safety protection. The entire distributed wrist-forearm monitoring system should ideally use a unified main control board for synchronous sampling and preprocessing. The onboard low-power MCU can first complete noise reduction, drift compensation, motion segmentation, feature compression, and initial anomaly screening, and then transmit the key feature vectors to the mobile phone or cloud model via BLE or Wi-Fi.

[0037] 3. Individualized Assessment and Decision-Making Module like Figure 3 The individualized assessment and decision-making module integrates and analyzes data collected from the brace, including posture, force, electromyography, physiology, and local tolerance. It combines this data with information such as patient age, body type, disease type, surgical procedure, postoperative time, pain score, and rehabilitation stage to construct a patient-specific assessment model. The system can perform collaborative computing between the edge and cloud terminals to continuously assess wrist joint fixation and rehabilitation status, enabling functions such as rehabilitation stage identification, abnormal movement detection, stress risk warning, recovery trend prediction, and training compliance assessment.

[0038] The system first performs time synchronization, filtering, normalization, and motion segmentation on data from different sensor sources. Then, it extracts clinically interpretable feature vectors based on the patient's different states, such as resting, walking, office work, holding objects, grasping training, palmar flexion / dorsiflexion training, or wrist protective activities. In resting and wearing assessment scenarios, the system focuses on the contact pressure distribution, fixation tightness, palm support position, and brace symmetry in the forearm, wrist, and palm. In daily activity scenarios, the system focuses on palmar flexion / dorsiflexion, ulnar / radial deviation amplitude and frequency, abnormal impact events, and sustained high-risk movements. In training scenarios, it focuses on analyzing movement completion, rhythm stability, fatigue trends, and brace involvement. Through multimodal feature fusion, the system can avoid biases caused by misjudgments based on single angle or pressure values, and more accurately determine whether the current fixation is appropriate and whether high-risk movements actually occur.

[0039] Building upon this foundation, the system further establishes a patient-specific "digital twin wrist joint support model" to dynamically estimate the current safe range of palmar flexion / dorsiflexion, permissible ulnar / radial deviation, recommended fixation tension, local pressure tolerance threshold, and recovery progress. This model integrates patient basic information, disease type, clinical stage, physician-set parameters, and historical monitoring data to progressively depict the dynamic progression from "individual baseline to current state to degree of risk deviation." The system can also automatically or semi-automatically identify the patient's stage of acute fixation protection, early mild activity recovery, functional training assistance, intensive training, and long-term maintenance and recurrence prevention. The risk significance of the same movement differs at different stages. For example, early excessive dorsiflexion after distal radius fracture reduction is clearly a high-risk behavior, while controlled mild activities in the mid-to-late stages may be part of the rehabilitation task.

[0040] Based on the above assessment, the system can identify and classify warnings for problems such as excessive palmar flexion / dorsiflexion, excessive ulnar / radial deviation, persistently high local pressure, palm impact risk, wearing too loose or too tight, long-term incomplete training or excessive grip training load, and further output individualized rehabilitation suggestions such as daily recommended wearing time, recommended fixed angle, recommended strap tension, training tasks and repetitions, grip training rhythm, and whether it is appropriate to gradually reduce brace dependence.

[0041] 4. Closed-loop regulation and doctor-patient interaction module The closed-loop adjustment and doctor-patient interaction module is the execution and feedback center of this system. Its function is to further transform the above analysis results into real-time responses for patients, braces, and doctors. When the system detects excessive palmar flexion or dorsiflexion, excessive ulnar / radial deviation, abnormal local pressure, improper band tightness, risk of palm impact, or insufficient training compliance, it can first issue an immediate reminder to the patient through vibration, buzzer, light, or mobile APP, guiding them to reduce the range of motion, adjust the wearing position, re-secure the brace, or suspend the current activity.

[0042] Under authorized conditions, the system can also drive the actuators within the brace to automatically adjust the local support and restraint states, achieving closed-loop control from "risk identification" to "parameter intervention." Preferably, the actuators may include a miniature winding motor, a local tightening mechanism, a controllable locking element, a short-stroke angle adjustment actuator, and a palm cushion trigger unit. When the system detects a dangerous palm flexion or extension movement, it can prioritize adjusting the locking or limiting state of the wrist transition zone to enhance the blocking in the corresponding direction; when the system detects excessive ulnar / radial deviation, it can apply stronger restraint to the palm support and transition zone through the local adjustment mechanism; when the system detects a risk of falling and landing or a palm impact event, it can trigger the palm cushion unit or dynamic blocking mechanism to improve the protection level; when the dangerous movement is eliminated or a low-risk resting state is entered, it gradually returns to a more comfortable conventional support state.

[0043] The patient-side app is primarily used to receive training tasks, view wearing time, monitor palmar flexion / dorsiflexion and deviation statistics, record risk events, input pain and fatigue feedback, and view phased wrist function trends. The doctor-side platform is used to view remote patient monitoring data, identify high-risk individuals, adjust training prescriptions, update fixed angle and threshold strategies, and evaluate posture management effectiveness at different stages. Through continuous accumulation and analysis in the cloud data center, the system can achieve an integrated closed loop of home rehabilitation, remote follow-up, and doctor-patient collaborative management, while providing a data foundation for subsequent algorithm optimization, threshold correction, and parameter adaptation for different disease groups.

[0044] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A personalized intelligent wrist joint brace system with multimodal sensing and closed-loop feedback, characterized in that, include: The brace body is for wearing on the patient's forearm, wrist and palm, and includes a forearm fixation mechanism, a wrist transition mechanism, a palm fixation mechanism, and an angle adjustment mechanism and a dynamic blocking and cushioning component disposed on the brace body. A distributed wrist-forearm monitoring system, integrated into the brace body, includes at least a kinematic / posture sensing unit, a dynamics / contact sensing unit, and a muscle function sensing unit, for collecting wrist joint posture, local pressure, and muscle activity data while in use; The individualized assessment and decision-making module is communicatively connected to the distributed wrist and forearm monitoring system, receives and integrates the monitoring data, constructs an individualized assessment model based on the patient's individual information, and outputs decision information, including rehabilitation stage identification results, risk warning information, and parameter adjustment suggestions. The closed-loop adjustment and doctor-patient interaction module includes an actuator mounted on the brace body and a user interaction unit communicatively connected to the individualized assessment and decision-making module. The actuator drives the angle adjustment mechanism and / or the dynamic blocking and buffering components to perform actions based on the decision information in order to adjust the support state of the brace body.

2. The system according to claim 1, characterized in that, The brace body is formed by 3D printing based on the shape data of the patient's distal forearm, wrist, palm and thumb regions. The forearm fixation mechanism, wrist transition mechanism and palm fixation mechanism are integrated or modular splicing structures.

3. The system according to claim 1, characterized in that, The kinematics / posture sensing unit includes multiple nine-axis IMU sensors, which are respectively fixed to the dorsal side of the palm fixation mechanism, the wrist transition area, and the proximal end of the forearm fixation mechanism. The IMU sensors output palmar flexion angle, dorsiflexion angle, ulnar deviation angle, radial deviation angle, and forearm rotation trend data of the wrist joint. The dynamics / contact sensing unit includes a multi-region distributed pressure sensing pad and a tension band sensor. The pressure sensing pad is set in the forearm area, palm area, and palm buffer zone to detect the contact pressure distribution between the brace and the limb. The tension band sensor is used to detect the tension of the fixation strap. The muscle function sensing unit is a surface electromyography (SEMG) module, which is arranged in at least one location in the forearm extensor and flexor muscle groups to collect electromyographic signals and extract muscle activation features.

4. The system according to claim 1, characterized in that, When integrating the monitoring data, the individualized assessment and decision-making module extracts multimodal motion feature vectors and integrates information such as patient age, body type, disease type, surgical procedure, postoperative time, and rehabilitation stage to construct a patient-specific digital twin wrist joint support model. This model dynamically estimates the safe range of motion, recommends fixation tension and local pressure tolerance thresholds, and outputs the decision information accordingly.

5. The system according to claim 1, characterized in that, The actuator includes at least one of a miniature winding motor, a partial tightening mechanism, a controllable locking element, a short-stroke angle adjustment actuator, and a palm cushioning trigger unit; the actuator responds to the decision information and actively adjusts the palmar flexion / dorsiflexion angle limitation, ulnar / radial deviation angle limitation, band tension, or palm cushioning state of the wrist joint.

6. The system according to claim 1, characterized in that, The user interaction unit includes a patient-side application and a doctor-side platform. The patient-side application receives and displays training tasks, posture and stress statistics, and risk alerts. The doctor-side platform remotely acquires the patient's monitoring data and assessment results, and receives instructions from the doctor to adjust rehabilitation prescriptions and update brace parameter thresholds.

7. The system according to claim 1, characterized in that, The distributed wrist-forearm monitoring system also includes a physiological and local microenvironment sensing unit, which includes a temperature sensor and a humidity sensor, arranged in a high-contact area inside the brace body to collect temperature and humidity data of the wearing environment; the individualized assessment and decision module also assesses wearing comfort and skin tolerance based on the temperature and humidity data.

8. The system according to claim 1, characterized in that, The distributed wrist-forearm monitoring system also includes an auxiliary abnormal event sensing unit, which includes an impact detection module and / or a fall determination module, used to identify fall or palm-on impact events; when the event is detected, the closed-loop adjustment and doctor-patient interaction module triggers the dynamic blocking and buffering components to switch to a high protection state.

9. The system according to claim 1, characterized in that, The brace body also includes a functional training auxiliary component, which includes at least one of a torsion spring, a telescopic strip, an elastic band, a finger sleeve assembly, and a thumb sleeve assembly. The functional training auxiliary component is detachably connected between the palm fixation mechanism and the forearm fixation mechanism to provide passive or active training resistance in the mid-to-late stages of rehabilitation.

10. The system according to claim 1, characterized in that, The dynamic blocking and buffering assembly includes at least one of a limiting block, an elastic buffer, and a palm buffer unit disposed at the wrist transition mechanism; the limiting block is used to restrict the excessive movement of the wrist joint in palmar flexion, dorsiflexion, ulnar deviation, or radial deviation; the elastic buffer is used to provide damping buffer when the wrist joint approaches a preset activity boundary; and the palm buffer unit is used to provide local buffering support when the palm is on the ground or when an impact event occurs.

Images