Multi-modal regulation and control system of intelligent joint rehabilitation monitoring protector
By integrating static and dynamic data through intelligent joint rehabilitation monitoring and protection gear, and using the LSTM neural network model to predict future functional recovery trends, the problem of insufficient data integration in traditional rehabilitation methods is solved, and personalized and timely adjustments to rehabilitation plans are achieved.
Patent Information
- Application Number
- CN202510817522.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-18
- Publication Date
- 2025-09-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional rehabilitation methods rely on manual data recording, which is inefficient, lacks multi-dimensional data integration and analysis, and cannot dynamically adapt to individual differences, resulting in a lack of personalization and timely adjustment of rehabilitation programs.
Intelligent joint rehabilitation monitoring and protection gear is used to integrate static properties and dynamic monitoring data, analyze time series data through the LSTM neural network model, predict future functional recovery trends, and automatically generate control instructions or adjust rehabilitation plans.
It achieves a comprehensive portrayal of the patient's rehabilitation status, accurately predicts future functional recovery trends, assists medical staff in making scientific decisions quickly, and improves the personalization and timeliness of rehabilitation plans.
Smart Images
Figure CN120708808A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of rehabilitation decision-making technology, and in particular to a multimodal control system for an intelligent joint rehabilitation monitoring brace. Background Art
[0002] With the aging of the population and the increase in the number of patients with sports injuries, the demand for joint rehabilitation treatment is growing. Traditional rehabilitation methods rely on medical staff to manually record patient data and evaluate rehabilitation progress through regular follow-up visits, which has problems such as low efficiency and delayed feedback. Although existing intelligent rehabilitation equipment can collect some physiological data (such as joint range of motion and heart rate), it is mostly limited to the monitoring of single-modality data and lacks the integrated analysis of multi-dimensional data (such as patient attributes, dynamic rehabilitation indicators, historical treatment records, etc.). In addition, traditional systems rely on simple statistical models for risk assessment and trend prediction, and are unable to dynamically adapt to individual differences, resulting in a lack of personalization and timely adjustment of rehabilitation programs. Summary of the Invention
[0003] In response to the shortcomings of the existing technology, the present invention proposes a multimodal control system for intelligent joint rehabilitation monitoring and protection gear. The present invention integrates static attributes (age, surgical history) and dynamic monitoring data (electromyographic signals, pain scores) to comprehensively characterize the patient's recovery status; analyzes time series data through the LSTM neural network model to accurately predict future functional recovery trends; automatically generates control instructions or adjusts rehabilitation plans based on risk thresholds and functional recovery index (FRI); optimizes model parameters through training sets and test sets to ensure the reliability of prediction results, assisting medical staff in making scientific decisions quickly.
[0004] To achieve the above object, the technical solution of the present invention is as follows:
[0005] A multimodal control system for an intelligent joint rehabilitation monitoring and protective gear, characterized in that the system includes a cloud database, an information collection port, an information analysis port and an information feedback port, wherein the cloud database is used to store patients' joint function assessment data, injury index, rehabilitation compliance score, treatment record and rehabilitation stage information; the information collection port is used to collect patients' static attribute data and dynamic rehabilitation monitoring data; the information analysis port is used to calculate joint rehabilitation risk score and functional recovery change index; and the information feedback port is used to send control instructions or personalized rehabilitation suggestions to medical staff or patients.
[0006] Preferably, the information collection port includes a patient attribute information collection module and a real-time rehabilitation data collection module. The patient attribute information collection module is used to collect the patient's electronic medical record information, including age, gender, joint injury type, course of disease, surgical history, current rehabilitation plan, and nutritional status; the real-time rehabilitation data collection module is used to collect joint range of motion, surface electromyography signals, pain scores, rehabilitation training completion rates, and exercise feedback in the patient's daily activity log.
[0007] Preferably, the information analysis port includes a data retrieval module, a risk analysis module and a trend prediction module. The data retrieval module is used to retrieve the joint function scores, pain fluctuation ranges, and rehabilitation compliance scores of similar patients matching the current patient in the cloud database; the risk analysis module is used to run the joint rehabilitation risk score calculation strategy; and the trend prediction module is used to run the LSTM neural network model to predict future functional recovery trends.
[0008] Preferably, the risk analysis module runs a joint rehabilitation risk score calculation strategy, which includes the following specific steps:
[0009] S11. Extract the time-varying curves of the patient's joint range of motion and pain score at the current rehabilitation stage, and obtain the benchmark range of rehabilitation scores for similar patients;
[0010] S12. Calculate the joint rehabilitation risk score. The calculation formula for the joint rehabilitation risk score is:
[0011]
[0012] Among them, JRS i represents the joint rehabilitation risk score of the patient at the i-th assessment, k represents the k-th indicator, which are the joint range of motion deviation, the number of days with excessive pain, and the training completion rate, ΔD k Indicates the number of days that the kth indicator exceeds the benchmark range, ΔD max Indicates the total number of days in the evaluation period, ΔV k Represents the standard deviation of the k-th indicator within the period, V norm It represents the average standard deviation of indicators of similar patients, α and β are weight factors, α+β=1.
[0013] S13, preset risk threshold JRS0, compare the joint rehabilitation risk score JRS of the patient at the i-th assessment i The relationship between the risk threshold JRS0 and the risk threshold JRS0 is as follows: i When the risk threshold is greater than or equal to JRS0, a high-risk warning signal is sent to the information feedback port. iWhen the risk threshold JRS0 is less than the threshold, no warning is activated, and the joint rehabilitation risk score JRS i Transmitted to the trend prediction module.
[0014] Preferably, the trend prediction module predicts the future functional recovery trend, and the predicting of the future functional recovery trend includes the following specific steps:
[0015] S21. Obtain the joint rehabilitation risk score of the patient in the previous i assessments, divide this data into a 70% training set and a 30% test set, and construct the input JRS i-2 、JRS i-1 、JRS i , the output is JRS i+1 The time series prediction model is trained using 70% of the training set to obtain the initial time series prediction model.
[0016] S22. Test the initial time series prediction model using a 30% coefficient test set, optimize the model parameters using mean square error, select the model with the smallest prediction error on the test set as the final time series prediction model, and predict the joint rehabilitation risk score for the i+1th assessment;
[0017] S23. Output the predicted joint rehabilitation risk score for the i+1th assessment.
[0018] Preferably, the predicting of future functional recovery trends further includes:
[0019] S24. Extract the joint rehabilitation risk score (JRS) of the i+1th assessment i+1 ;
[0020] S25. Calculate the patient's functional recovery change index, where the calculation formula for the functional recovery change index is:
[0021]
[0022] S26: Determine whether it is necessary to send a decision adjustment signal to the information feedback port.
[0023] Preferably, the time series prediction model in S22 is an LSTM neural network model.
[0024] Preferably, the specific content of S26 is: presetting the FRI threshold, when the functional recovery change index FRI is greater than the FRI threshold, continuing to execute the current nursing strategy, and when the functional recovery change index FRI is less than or equal to the FRI threshold, sending a rehabilitation decision adjustment signal to the information feedback port.
[0025] The technical effects of the present invention are as follows:
[0026] A multimodal control system for intelligent joint rehabilitation monitoring and brace is proposed. This system integrates static attributes (age, surgical history) with dynamic monitoring data (electromyographic signals, pain scores) to comprehensively characterize the patient's recovery status. It uses an LSTM neural network model to analyze time series data and accurately predict future functional recovery trends. It automatically generates control instructions or adjusts rehabilitation plans based on risk thresholds and the functional recovery index (FRI). It optimizes model parameters through training and test sets to ensure the reliability of prediction results and assist medical staff in making scientific decisions quickly. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:
[0028] Figure 1 This is a structural schematic diagram of a multimodal control system for an intelligent joint rehabilitation monitoring brace of the present invention. DETAILED DESCRIPTION
[0029] Example 1
[0030] This embodiment proposes a multimodal control system for intelligent joint rehabilitation monitoring and protection equipment. The present invention integrates static attributes (age, surgical history) and dynamic monitoring data (electromyographic signals, pain scores) to comprehensively characterize the patient's recovery status; analyzes time series data through an LSTM neural network model to accurately predict future functional recovery trends; automatically generates control instructions or adjusts rehabilitation plans based on risk thresholds and functional recovery indexes (FRI); optimizes model parameters through training sets and test sets to ensure the reliability of prediction results, assisting medical staff in making scientific decisions quickly.
[0031] like Figure 1 As shown, a multimodal control system for an intelligent joint rehabilitation monitoring brace is characterized in that the system includes a cloud database, an information collection port, an information analysis port and an information feedback port. The cloud database is used to store patients' joint function assessment data, injury index, rehabilitation compliance score, treatment records and rehabilitation stage information; the information collection port is used to collect patients' static attribute data and dynamic rehabilitation monitoring data; the information analysis port is used to calculate joint rehabilitation risk scores and functional recovery change indexes; the information feedback port is used to send control instructions or personalized rehabilitation suggestions to medical staff or patients.
[0032] In this embodiment, the information collection port includes a patient attribute information collection module and a real-time rehabilitation data collection module. The patient attribute information collection module is used to collect the patient's electronic medical record information, including age, gender, joint injury type, course of disease, surgical history, current rehabilitation plan, and nutritional status; the real-time rehabilitation data collection module is used to collect joint range of motion, surface electromyography signals, pain scores, rehabilitation training completion rates, and exercise feedback in the patient's daily activity log.
[0033] Example 2
[0034] In this embodiment, the information analysis port includes a data retrieval module, a risk analysis module and a trend prediction module. The data retrieval module is used to retrieve the joint function scores, pain fluctuation ranges, and rehabilitation compliance scores of similar patients matching the current patient in the cloud database; the risk analysis module is used to run the joint rehabilitation risk score calculation strategy; the trend prediction module is used to run the LSTM neural network model to predict future functional recovery trends.
[0035] In this embodiment, the risk analysis module runs a joint rehabilitation risk score calculation strategy, which includes the following specific steps:
[0036] S11. Extract the time-varying curves of the patient's joint range of motion and pain score at the current rehabilitation stage, and obtain the baseline range of rehabilitation scores for similar patients;
[0037] S12. Calculate the joint rehabilitation risk score. The calculation formula for the joint rehabilitation risk score is:
[0038]
[0039] Among them, JRS i represents the joint rehabilitation risk score of the patient at the i-th assessment, k represents the k-th indicator, which are the joint range of motion deviation, the number of days with excessive pain, and the training completion rate, ΔD k Indicates the number of days that the kth indicator exceeds the benchmark range, ΔD max Indicates the total number of days in the evaluation period, ΔV k Represents the standard deviation of the k-th indicator within the period, V norm It represents the average standard deviation of indicators of similar patients, α and β are weight factors, α+β=1.
[0040] S13, preset risk threshold JRS0, compare the joint rehabilitation risk score JRS of the patient at the i-th assessment i The relationship between the risk threshold JRS0 and the risk threshold JRS0 is as follows: i When the risk threshold is greater than or equal to JRS0, a high-risk warning signal is sent to the information feedback port.i When the risk threshold JRS0 is less than the threshold, no warning is activated, and the joint rehabilitation risk score JRS i Transmitted to the trend prediction module.
[0041] Example 3
[0042] In this embodiment, the trend prediction module predicts the future functional recovery trend, and the predicting of the future functional recovery trend includes the following specific steps:
[0043] S21. Obtain the joint rehabilitation risk score of the patient in the previous i assessments, divide this data into a 70% training set and a 30% test set, and construct the input JRS i-2 、JRS i-1 、JRS i , the output is JRS i+1 The time series prediction model is trained using 70% of the training set to obtain the initial time series prediction model.
[0044] S22. Test the initial time series prediction model using a 30% coefficient test set, optimize the model parameters using mean square error, select the model with the smallest prediction error on the test set as the final time series prediction model, and predict the joint rehabilitation risk score for the i+1th assessment;
[0045] S23. Output the predicted joint rehabilitation risk score for the i+1th assessment.
[0046] In this embodiment, predicting future functional recovery trends further includes:
[0047] S24. Extract the joint rehabilitation risk score (JRS) of the i+1th assessment i+1 ;
[0048] S25. Calculate the patient's functional recovery change index, where the calculation formula for the functional recovery change index is:
[0049]
[0050] S26: Determine whether it is necessary to send a decision adjustment signal to the information feedback port.
[0051] In this embodiment, the time series prediction model in S22 is an LSTM neural network model.
[0052] Example 4
[0053] In this embodiment, the specific content of S26 is: presetting the FRI threshold, when the functional recovery change index FRI is greater than the FRI threshold, continuing to execute the current nursing strategy; when the functional recovery change index FRI is less than or equal to the FRI threshold, sending a rehabilitation decision adjustment signal to the information feedback port.
[0054] It should be noted here that the present invention integrates static attributes (age, surgical history) and dynamic monitoring data (electromyographic signals, pain scores) to comprehensively characterize the patient's recovery status; analyzes time series data through the LSTM neural network model to accurately predict future functional recovery trends; automatically generates control instructions or adjusts rehabilitation plans based on risk thresholds and functional recovery index (FRI); optimizes model parameters through training sets and test sets to ensure the reliability of prediction results and assist medical staff in making scientific decisions quickly.
[0055] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0056] It should be understood that determining B based on A does not mean determining B based solely on A. B can also be determined based on A and / or other information.
[0057] The above embodiments can be implemented in whole or in part through software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.
[0058] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.
[0059] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0060] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0061] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.
[0062] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0063] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
[0064] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.
Claims
1. A multimodal control system for intelligent joint rehabilitation monitoring and protection equipment, characterized in that: The system includes a cloud database, an information collection port, an information analysis port, and an information feedback port. The cloud database is used to store the patient's joint function assessment data, injury index, rehabilitation compliance score, treatment record, and rehabilitation stage information; The information collection port is used to collect static attribute data and dynamic rehabilitation monitoring data of patients; The information analysis port is used to calculate the joint rehabilitation risk score and the functional recovery change index; The information feedback port is used to send control instructions or personalized rehabilitation suggestions to medical staff or patients.
2. The multimodal control system of the intelligent joint rehabilitation monitoring and protection device according to claim 1 is characterized in that: The information collection port includes a patient attribute information collection module and a real-time rehabilitation data collection module. The patient attribute information collection module is used to collect the patient's electronic medical record information, including age, gender, joint injury type, course of disease, surgical history, current rehabilitation plan, and nutritional status; The real-time rehabilitation data acquisition module is used to collect joint range of motion, surface electromyography signals, pain scores, rehabilitation training completion rates, and movement feedback from patients' daily activity logs.
3. The multimodal control system of the intelligent joint rehabilitation monitoring and protection device according to claim 2 is characterized in that: The information analysis port includes a data retrieval module, a risk analysis module, and a trend prediction module. The data retrieval module is used to retrieve the joint function scores, pain fluctuation range, and rehabilitation compliance scores of similar patients matching the current patient in the cloud database; The risk analysis module is used to run the joint rehabilitation risk score calculation strategy; The trend prediction module is used to run the LSTM neural network model to predict future functional recovery trends.
4. The multimodal control system of the intelligent joint rehabilitation monitoring and protection device according to claim 3 is characterized in that: The risk analysis module executes a joint rehabilitation risk score calculation strategy, which includes the following specific steps: S11. Extract the time-varying curves of the patient's joint range of motion and pain score at the current rehabilitation stage, and obtain the baseline range of rehabilitation scores for similar patients; S12. Calculate the joint rehabilitation risk score. The calculation formula for the joint rehabilitation risk score is: Among them, JRS i represents the joint rehabilitation risk score of the patient at the i-th assessment, k represents the k-th indicator, which are the joint range of motion deviation, the number of days with excessive pain, and the training completion rate, ΔD k Indicates the number of days that the kth indicator exceeds the benchmark range, ΔD max Indicates the total number of days in the evaluation period, ΔV k Represents the standard deviation of the k-th indicator within the period, V norm It represents the average standard deviation of indicators of similar patients, α and β are weight factors, α+β=1. S13, preset risk threshold JRS0, compare the joint rehabilitation risk score JRS of the patient at the i-th assessment i The relationship between the risk threshold JRS0 and the risk threshold JRS0 is as follows: i When the risk threshold is greater than or equal to JRS0, a high-risk warning signal is sent to the information feedback port. i When the risk threshold JRS0 is less than the threshold, no warning is activated, and the joint rehabilitation risk score JRS i Transmitted to the trend prediction module.
5. The multimodal control system of the intelligent joint rehabilitation monitoring and protection device according to claim 4 is characterized in that: The trend prediction module predicts the future functional recovery trend, and the predicting of the future functional recovery trend includes the following specific steps: S21. Obtain the joint rehabilitation risk score of the patient in the previous i assessments, divide this data into a 70% training set and a 30% test set, and construct the input JRS i-2 、JRS i-1 、JRS i , the output is JRS i+1 The time series prediction model is trained using 70% of the training set to obtain the initial time series prediction model. S22. Test the initial time series prediction model using a 30% coefficient test set, optimize the model parameters using mean square error, select the model with the smallest prediction error on the test set as the final time series prediction model, and predict the joint rehabilitation risk score for the i+1th assessment; S23. Output the predicted joint rehabilitation risk score for the i+1th assessment.
6. The multimodal control system of the intelligent joint rehabilitation monitoring and protection device according to claim 5 is characterized in that: The prediction of future functional recovery trends also includes: S24. Extract the joint rehabilitation risk score (JRS) of the i+1th assessment i+1 ; S25. Calculate the patient's functional recovery change index, where the calculation formula for the functional recovery change index is: S26: Determine whether it is necessary to send a decision adjustment signal to the information feedback port.
7. The multimodal control system of the intelligent joint rehabilitation monitoring and support device according to claim 6, characterized in that: The time series prediction model in S22 is an LSTM neural network model.
8. The multimodal control system of the intelligent joint rehabilitation monitoring and protection device according to claim 7 is characterized in that: The specific content of S26 is: presetting the FRI threshold, when the functional recovery change index FRI is greater than the FRI threshold, continuing to execute the current nursing strategy; when the functional recovery change index FRI is less than or equal to the FRI threshold, sending a rehabilitation decision adjustment signal to the information feedback port.