Method and system for tracking the rehabilitation progress of orthopedic patients
Patent Information
- Application Number
- CN202411435034.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-15
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-10-15
Smart Images

Figure CN118940155B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of orthopedic rehabilitation, and in particular to a method and system for tracking the rehabilitation progress of orthopedic patients. Background Art
[0002] The orthopedic patient rehabilitation progress tracking system belongs to the category of intelligent rehabilitation systems in the field of medical rehabilitation. Intelligent rehabilitation systems use sensor technology, data processing algorithms, and computer-aided equipment to help patients effectively monitor and evaluate the rehabilitation process. In this specific field, orthopedic rehabilitation is particularly important, especially for patients with lower limb injuries. The system aims to provide medical staff with accurate rehabilitation progress monitoring and evaluation by collecting real-time data such as patients' gait, joints, muscle strength, and pain, thereby optimizing rehabilitation treatment plans.
[0003] At this stage, traditional rehabilitation treatment methods mainly rely on the experience and subjective judgment of physical therapists, and lack accurate quantitative analysis of the patient's rehabilitation progress. This approach is not only prone to misjudgment, but also fails to provide accurate data support to evaluate rehabilitation effects and progress. In addition, existing rehabilitation monitoring equipment usually only provides single-dimensional data, such as gait analysis or muscle strength measurement, which cannot fully reflect the patient's overall rehabilitation status. These shortcomings make it difficult to predict the effect of rehabilitation treatment, and it is difficult to quantify and optimize the patient's rehabilitation progress. At the same time, the traditional rehabilitation process tracking system at this stage is not easy to perform hierarchical analysis of data, resulting in abnormal system data processing load. Summary of the invention
[0004] In view of the deficiencies in the prior art, the present invention provides a method and system for tracking the rehabilitation progress of orthopedic patients, which solves the problems mentioned in the background technology.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:
[0006] An orthopedic patient rehabilitation progress tracking system includes a patient rehabilitation tracking module, a central processing module, a health analysis module, a comprehensive rehabilitation progress analysis module and a rehabilitation adjustment analysis module;
[0007] The patient rehabilitation tracking module collects rehabilitation data of orthopedic patients with leg injuries in real time by integrating rehabilitation detection equipment, and encapsulates the rehabilitation data and sends it to the central processing module;
[0008] The central processing module is used to receive the rehabilitation data in real time, pre-process the rehabilitation data, obtain a rehabilitation data set, and then perform feature extraction based on the obtained rehabilitation data set to obtain a rehabilitation feature set;
[0009] The health analysis module is used to construct a rehabilitation algorithm formula set, perform loading calculations based on the acquired rehabilitation feature set, and obtain a gait stability index GS, a muscle fatigue index MF, and a movement coordination index MC;
[0010] The comprehensive rehabilitation process analysis module is used to integrate the gait stability index GS, muscle fatigue index MF and movement coordination index MC output by the health analysis module, calculate and obtain the first rehabilitation index KFZ, and preset the rehabilitation threshold K for preliminary comparative evaluation, preliminarily analyze the rehabilitation status of orthopedic patients in the current rehabilitation plan, and generate preliminary rehabilitation plan adjustment prompt information based on the preliminary evaluation results;
[0011] The rehabilitation adjustment analysis module is used to calculate the joint friction coefficient JF and the pain induction time PE based on the rehabilitation feature set, and then perform a comprehensive calculation with the obtained first rehabilitation index KFZ to obtain the second rehabilitation index KFZ2, and then perform a secondary comparative evaluation with the rehabilitation threshold K, in-depth analysis of the rehabilitation status of orthopedic patients in the current rehabilitation plan, and secondary generation of rehabilitation plan adjustment prompt information based on the secondary evaluation results.
[0012] Preferably, the patient rehabilitation tracking module includes a data acquisition unit and a data transmission unit;
[0013] The data acquisition unit collects rehabilitation data of orthopedic patients with leg injuries in real time by using orthopedic medical detection equipment, wherein the rehabilitation data includes gait data, joint data, muscle strength data and pain data;
[0014] The data transmission unit is used to encapsulate the collected rehabilitation data into a rehabilitation data packet in JSON format, set a WIFi wireless transmission protocol to wirelessly connect to the central processing module, and transmit the rehabilitation data packet to the central processing module.
[0015] Preferably, the central processing module includes a data preprocessing unit and a feature extraction unit;
[0016] The data preprocessing unit is used to receive the rehabilitation data packet in real time, use the Python programming language to convert the rehabilitation data packet string in JSON format into a data structure, and perform preprocessing, wherein the preprocessing method includes using a statistical method to identify outliers for deletion and using one-hot encoding to convert data classification variables into numerical variables, and then converting the preprocessed data into a unified unit format, and summarizing to generate a rehabilitation data set;
[0017] The feature extraction unit extracts features based on the preprocessed rehabilitation data set to obtain a rehabilitation feature set, wherein the rehabilitation feature set includes a gait feature set, a joint feature set, a muscle strength feature, a pain feature, and a movement coordination feature set;
[0018] The gait feature set includes horizontal gait displacement X i and vertical gait displacement Y i ;
[0019] The joint feature set includes joint motion friction force Ff and joint force Fn;
[0020] The muscle strength characteristics include electromyographic signal intensity EMG;
[0021] The pain characteristics include action-induced pain time Tt;
[0022] The motion coordination feature set includes the horizontal gait displacement deviation ΔX i and vertical gait displacement deviation △Y i ;
[0023] The gait feature set tracks the foot position of each step through a 3D gait analysis device, records the displacement data in three-dimensional space, calculates the horizontal gait position and vertical gait position of each step, and then extracts the horizontal gait displacement X by differentiating the continuous footstep position data. i and vertical gait displacement Y i , and perform mean processing to extract the average value of horizontal gait displacement and the average vertical gait displacement ;
[0024] The joint feature set is recorded by a force sensor, and the force detected at the joint is decomposed into a component force perpendicular to the contact force sensor and a component force parallel to the contact force sensor, and the horizontal force is extracted as the joint motion friction force Ff, and the vertical force is the joint force Fn;
[0025] The muscle force feature collects electromyographic signals through an electromyographic sensor, extracts the electromyographic signal strength EMG, and performs time series analysis on the electromyographic signal strength EMG to extract the electromyographic signal strength EMG (t) at the action time t;
[0026] The pain characteristics are obtained by recording the time when orthopedic patients with leg injuries feel pain when performing specific actions, recording the specific time when each action induces pain, and extracting the induced pain time Tt by using time series analysis;
[0027] The motion coordination feature set is obtained by i and vertical gait displacement Y i , and at the same time, the preset horizontal gait standard displacement X is performed based on the rehabilitation plan ideal and vertical gait standard displacement Y ideal , the horizontal gait displacement X i and vertical gait displacement Y i Standard displacement X with horizontal gaitideal and vertical gait standard displacement Y ideal , perform difference processing and extract the horizontal gait displacement deviation △X i and vertical gait displacement deviation △Y i .
[0028] Preferably, the health analysis module includes a gait stability analysis unit, a muscle fatigue analysis unit and a movement coordination analysis unit;
[0029] The gait stability analysis unit is used to construct a gait stability algorithm formula, transmit the extracted gait feature set to the gait stability analysis algorithm formula, and perform calculation to obtain a gait stability index GSI;
[0030] The gait stability index GSI is calculated by the following gait stability analysis algorithm formula:
[0031] ;
[0032] Where N represents the total number of gaits, X i represents the horizontal gait displacement of the i-th gait, Y i represents the vertical gait displacement of the i-th gait.
[0033] Preferably, the muscle fatigue analysis unit is used to construct a muscle fatigue algorithm formula, load the extracted muscle strength characteristics into the muscle fatigue algorithm formula, and calculate to obtain a muscle fatigue index MF;
[0034] The muscle fatigue index MF is calculated by the following muscle fatigue algorithm formula:
[0035] ;
[0036] Where, EMG max represents the peak value of the electromyographic signal, dt represents the time variable, T represents the measurement time, and t represents the time point.
[0037] Preferably, the movement coordination analysis unit is used to construct a movement coordination algorithm formula, load the extracted movement coordination feature set into the movement coordination algorithm formula, and perform calculation to obtain the movement coordination index MC;
[0038] The movement coordination index MC is calculated by the following movement coordination algorithm formula:
[0039] ;
[0040] Wherein, L represents the ideal motion path length, and the specific value is set by the user.
[0041] Preferably, the comprehensive rehabilitation progress analysis module includes a comprehensive rehabilitation progress calculation unit and a rehabilitation progress evaluation unit;
[0042] The comprehensive rehabilitation process calculation unit is used to be integrated with the health analysis module, and to perform correlation calculation to obtain the first rehabilitation index KFZ according to the gait stability index GS, the muscle fatigue index MF and the movement coordination index MC output by the health analysis module;
[0043] The first rehabilitation index KFZ is obtained by the following algorithm formula:
[0044] ;
[0045] In the formula, , and represent the preset weight values of gait stability index GS, muscle fatigue index MF and movement coordination index MC, respectively, and + + =1, the specific value is set by the user, exp represents exponential function, and sin represents sine function;
[0046] The rehabilitation process evaluation unit presets a rehabilitation threshold value K through the planned rehabilitation index, and then performs a preliminary comparative evaluation with the obtained first rehabilitation index KFZ to evaluate the rehabilitation status of the currently formulated rehabilitation plan for the orthopedic patient with leg injury;
[0047] The specific evaluation plan is as follows:
[0048] When the first rehabilitation index KFZ ≥ the rehabilitation threshold K, it means that the currently formulated rehabilitation plan is normal for orthopedic patients with leg injuries. At this time, the secondary evaluation mechanism is implemented to deeply analyze the rehabilitation situation;
[0049] When the first rehabilitation index KFZ is less than the rehabilitation threshold K, it indicates that the currently formulated rehabilitation plan is abnormal for orthopedic patients with leg injuries. At this time, the first prompt information is generated to make preliminary adjustments to the rehabilitation plan.
[0050] Preferably, the rehabilitation adjustment analysis module is triggered when it is evaluated that the preliminary rehabilitation plan is effective for the recovery of the orthopedic patient with leg injury, and the rehabilitation adjustment analysis module includes a depth analysis calculation unit, a secondary comprehensive rehabilitation process calculation unit and a secondary evaluation unit;
[0051] The depth analysis calculation unit includes a joint friction calculation unit and a pain induction calculation unit;
[0052] The joint friction calculation unit is used to calculate and obtain the joint friction coefficient JF according to the extracted joint feature set;
[0053] The joint friction coefficient JF is calculated by the following algorithm:
[0054] ;
[0055] In the formula, Ff represents the friction force of joint movement, and Fn represents the force on the joint;
[0056] The pain induction calculation unit is used to calculate and obtain the pain induction time PE according to the extracted pain characteristics;
[0057] The pain induction time PE is calculated by the following algorithm formula:
[0058] ;
[0059] Where, Tt j represents the time of pain induced by the jth action, and M is the number of pain-induced measurements.
[0060] Preferably, the secondary comprehensive rehabilitation process calculation unit is used to associate the obtained joint friction coefficient JF and pain induction time PE with the obtained first rehabilitation index KFZ to obtain the second rehabilitation index KFZ2;
[0061] The second rehabilitation index KFZ2 is calculated by the following algorithm formula:
[0062] ;
[0063] Where a1, a2, and a3 represent the preset weight values of the first rehabilitation index KFZ, the joint friction coefficient JF, and the pain induction time PE, respectively, and the specific parameters are set by the user, and log represents the logarithmic function;
[0064] The secondary evaluation unit is used to perform a secondary comparative evaluation on the obtained second rehabilitation index KFZ2 and the rehabilitation threshold K, and deeply evaluate the rehabilitation status of the currently formulated rehabilitation plan for orthopedic patients with leg injuries;
[0065] The specific evaluation plan is as follows:
[0066] When the second rehabilitation index KFZ2 ≥ the rehabilitation threshold K, it means that the current patient's rehabilitation status is normal, and the current rehabilitation plan continues to be implemented;
[0067] When the second rehabilitation indicator KFZ2 is less than the rehabilitation threshold K, it indicates that the current patient's rehabilitation state is abnormal, and at this time, a second prompt message is generated to adjust the secondary rehabilitation plan.
[0068] A method for tracking the rehabilitation progress of an orthopedic patient, comprising:
[0069] Through the integration of rehabilitation detection equipment, the rehabilitation data of orthopedic patients with leg injuries are collected in real time, and the rehabilitation data is packaged and sent to the central processing module;
[0070] After receiving the rehabilitation data in real time, preprocessing the rehabilitation data to obtain a rehabilitation data set, and then extracting features based on the obtained rehabilitation data set to obtain a rehabilitation feature set;
[0071] Construct a rehabilitation algorithm formula set, perform loading calculations based on the acquired rehabilitation feature set, and obtain the gait stability index GS, muscle fatigue index MF, and movement coordination index MC;
[0072] The gait stability index GS, muscle fatigue index MF and movement coordination index MC output by the integrated health analysis module are calculated to obtain the first rehabilitation index KFZ, and the rehabilitation threshold K is preset for preliminary comparative evaluation, and the rehabilitation status of orthopedic patients in the current rehabilitation plan is preliminarily analyzed, and preliminary rehabilitation plan adjustment prompt information is generated based on the preliminary evaluation results;
[0073] The joint friction coefficient JF and the pain induction time PE are calculated based on the rehabilitation feature set, and then the second rehabilitation index KFZ2 is obtained by comprehensive calculation with the first rehabilitation index KFZ. A secondary comparative evaluation is performed with the rehabilitation threshold K to deeply analyze the rehabilitation status of orthopedic patients in the current rehabilitation plan, and the rehabilitation plan adjustment prompt information is generated based on the secondary evaluation results.
[0074] The present invention provides a method and system for tracking the rehabilitation progress of orthopedic patients, which has the following beneficial effects:
[0075] The system can collect rehabilitation data of orthopedic patients with leg injuries in real time, including gait data, joint data, muscle strength data and pain data, through the patient rehabilitation tracking module and integrated rehabilitation detection equipment. The accuracy and comprehensiveness of the data are ensured by using advanced equipment such as 3D gait analysis equipment, force sensors and electromyography sensors. The data acquisition unit encapsulates these data into a rehabilitation data packet in JSON format and sends it to the central processing module via the WIFI wireless transmission protocol. Such a real-time data acquisition and transmission mechanism can continuously track the patient's rehabilitation status and provide timely basic data support for subsequent analysis.
[0076] The system preprocesses and extracts features from the received rehabilitation data through the central processing module to obtain rehabilitation feature sets including gait feature sets, joint feature sets, muscle strength feature sets, pain feature sets and movement coordination feature sets. The health analysis module uses these feature sets to construct corresponding algorithm formulas to calculate the gait stability index GS, muscle fatigue index MF and movement coordination index MC. Subsequently, the comprehensive rehabilitation process analysis module integrates these indexes, obtains the first rehabilitation index KFZ by calculation, and compares and evaluates it with the preset rehabilitation threshold K. It preliminarily analyzes the current rehabilitation plan for the patient's rehabilitation process, and adjusts the preliminary rehabilitation plan based on the evaluation results. This multi-dimensional analysis method makes the assessment of the patient's rehabilitation status more accurate and comprehensive, and helps to formulate a more targeted rehabilitation plan.
[0077] After the initial assessment, the system further calculates the joint friction coefficient JF and the pain induction time PE through the rehabilitation adjustment analysis module, and calculates the second rehabilitation index KFZ2 in combination with the first rehabilitation index KFZ. Based on the comparison results of the second rehabilitation index KFZ2 and the rehabilitation threshold K, the system conducts a secondary assessment and in-depth adjustment of the rehabilitation plan. If the rehabilitation status is abnormal, the system will prompt to adjust the range of joint motion or increase lubrication exercises to reduce friction and pain, and recommend increasing low-intensity or no-load exercises. In this way, the system can conduct in-depth combined analysis during the patient's rehabilitation process, further reduce the system data processing load, and provide continuous, personalized adjustments and optimizations under in-depth evaluation to ensure the effectiveness and safety of the rehabilitation process. BRIEF DESCRIPTION OF THE DRAWINGS
[0078] Figure 1 A schematic diagram of a process flow of a system for tracking the rehabilitation progress of orthopedic patients according to the present invention;
[0079] Figure 2 The present invention is a schematic diagram of the steps of a method for tracking the rehabilitation progress of an orthopedic patient. DETAILED DESCRIPTION
[0080] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0081] Example 1: Please refer to Figure 1 The present invention provides a system for tracking the rehabilitation progress of orthopedic patients. To achieve the above purpose, the present invention is implemented through the following technical solutions: including a patient rehabilitation tracking module, a central processing module, a health analysis module, a comprehensive rehabilitation progress analysis module and a rehabilitation adjustment analysis module;
[0082] The patient rehabilitation tracking module collects the rehabilitation data of orthopedic patients with leg injuries in real time by integrating rehabilitation detection equipment, and encapsulates the rehabilitation data and sends it to the central processing module;
[0083] The central processing module is used to receive the rehabilitation data in real time, pre-process the rehabilitation data, obtain a rehabilitation data set, and then perform feature extraction based on the obtained rehabilitation data set to obtain a rehabilitation feature set;
[0084] The health analysis module is used to construct a rehabilitation algorithm formula set, load calculations based on the acquired rehabilitation feature set, and obtain the gait stability index GS, muscle fatigue index MF, and movement coordination index MC;
[0085] The comprehensive rehabilitation process analysis module is used to integrate the gait stability index GS, muscle fatigue index MF and movement coordination index MC output by the health analysis module, calculate and obtain the first rehabilitation index KFZ, and preset the rehabilitation threshold K for preliminary comparative evaluation, preliminarily analyze the rehabilitation status of orthopedic patients in the current rehabilitation plan, and generate preliminary rehabilitation plan adjustment prompt information based on the preliminary evaluation results;
[0086] The rehabilitation adjustment analysis module is used to calculate the joint friction coefficient JF and the pain induction time PE based on the rehabilitation feature set, and then perform a comprehensive calculation with the first rehabilitation index KFZ to obtain the second rehabilitation index KFZ2, and then perform a secondary comparative evaluation with the rehabilitation threshold K, in order to deeply analyze the rehabilitation status of orthopedic patients in the current rehabilitation plan, and generate rehabilitation plan adjustment prompt information based on the secondary evaluation results.
[0087] In this embodiment, the system forms a complete set of rehabilitation data collection, processing, analysis and feedback mechanisms by integrating the patient rehabilitation tracking module, the central processing module, the health analysis module, the comprehensive rehabilitation process analysis module and the rehabilitation adjustment analysis module. The patient rehabilitation tracking module collects data in real time through the rehabilitation detection equipment, and the central processing module pre-processes and extracts features of these data to generate a rehabilitation feature set, providing a basis for subsequent analysis. This systematic data flow ensures the integrity and coherence of information in the rehabilitation process, realizes real-time monitoring and accurate analysis, and effectively records the patient's rehabilitation process. The health analysis module constructs the calculation formulas of the gait stability index GS, the muscle fatigue index MF and the movement coordination index MC based on the extracted rehabilitation feature set to comprehensively evaluate the patient's rehabilitation status. The comprehensive rehabilitation process analysis module calculates the first rehabilitation index KFZ and compares it with the preset rehabilitation threshold K to preliminarily evaluate the effect of the current rehabilitation plan. Compared with the traditional rehabilitation monitoring method, this multi-dimensional evaluation method is more refined and comprehensive, which makes it possible to make a more accurate judgment on the patient's rehabilitation status, so that a more personalized rehabilitation plan can be formulated for each patient. The rehabilitation adjustment analysis module further calculates the joint friction coefficient JF and the pain induction time PE, combined with the first rehabilitation index KFZ, to calculate the second rehabilitation index KFZ2. Based on the secondary evaluation results, the system can dynamically adjust the rehabilitation plan and put forward specific improvement suggestions for different patients' rehabilitation conditions.
[0088] Example 2: This example is an explanation of Example 1. Figure 1 ,Specifically: the patient rehabilitation tracking module includes a data acquisition unit and a data transmission unit;
[0089] The data collection unit collects the rehabilitation data of orthopedic patients with leg injuries in real time by using orthopedic medical testing equipment. The rehabilitation data includes gait data, joint data, muscle strength data and pain data.
[0090] Joint data is collected through 3D gait analysis equipment;
[0091] Joint data is collected through force sensors;
[0092] Muscle force data is collected through electromyography sensors;
[0093] The data transmission unit is used to encapsulate the collected rehabilitation data into a rehabilitation data packet in JSON format, set a WIFi wireless transmission protocol to wirelessly connect to the central processing module, and transmit the rehabilitation data packet to the central processing module.
[0094] In this embodiment, the patient rehabilitation tracking module realizes the comprehensive real-time collection of rehabilitation data of orthopedic patients with leg injuries through the integration of the data acquisition unit and the data transmission unit. Using 3D gait analysis equipment, force sensors and electromyography sensors, the system can accurately obtain gait data, joint data, muscle strength data and pain data to fully reflect the patient's rehabilitation status. By encapsulating these data into rehabilitation data packets in JSON format and using WiFi wireless transmission protocol, the data is efficiently transmitted to the central processing module to ensure the stability and timeliness of data transmission.
[0095] Example 3: This example is an explanation of Example 2. Figure 1 ,Specifically: the central processing module includes a data preprocessing unit and a feature extraction unit;
[0096] The data preprocessing unit is used to receive rehabilitation data packets in real time, and use Python programming language to convert rehabilitation data packet strings in JSON format into data structures and perform preprocessing. The preprocessing methods include using statistical methods to identify outliers for deletion and using one-hot encoding to convert data classification variables into numerical variables, and then converting the preprocessed data into a unified unit format, and summarizing and generating a rehabilitation data set;
[0097] The feature extraction unit extracts features based on the pre-processed rehabilitation data set to obtain a rehabilitation feature set, where the rehabilitation feature set includes a gait feature set, a joint feature set, a muscle strength feature, a pain feature, and a movement coordination feature set;
[0098] The gait feature set includes the horizontal gait displacement X i and vertical gait displacement Y i ;
[0099] The joint feature set includes the joint motion friction force Ff and the joint force Fn;
[0100] Muscle strength characteristics include electromyographic signal strength (EMG);
[0101] Pain characteristics include movement-evoked pain time Tt;
[0102] The motion coordination feature set includes the horizontal gait displacement deviation △X i and vertical gait displacement deviation △Y i ;
[0103] The gait feature set tracks the foot position of each step through the 3D gait analysis device, records the displacement data in three-dimensional space, calculates the horizontal gait position and vertical gait position of each step, and then extracts the horizontal gait displacement X by differentiating the continuous footstep position data. i and vertical gait displacement Y i, and perform mean processing to extract the average value of horizontal gait displacement and the average vertical gait displacement , horizontal gait displacement X i =X step -X prev , vertical gait displacement Y i =Y step -Y Prev , where X step and Y step Represents the current horizontal gait position X and vertical gait position Y, X prev and Y Prev Represents the position of one step forward in horizontal gait and one step forward in vertical gait, and the average value of horizontal gait displacement and the average vertical gait displacement , N represents the total number of gaits;
[0104] The joint feature set is recorded by the force sensor, and the force detected at the joint is decomposed into a component perpendicular to the contact force sensor and a component parallel to the contact force sensor. The horizontal force is extracted as the joint motion friction force Ff, and the vertical force is the joint force Fn;
[0105] The muscle force characteristics collect the electromyographic signal through the electromyographic sensor, extract the electromyographic signal strength EMG, and perform time series analysis on the electromyographic signal strength EMG to extract the electromyographic signal strength EMG (t) at the action time t;
[0106] The pain characteristics were obtained by orthopedic patients with leg injuries recording the time when they felt pain when performing specific movements. The real-time recording system recorded the specific time when each movement induced pain, and the induced pain time Tt was extracted by using time series analysis;
[0107] The motion coordination feature set is obtained by i and vertical gait displacement Y i , and at the same time, the preset horizontal gait standard displacement X is performed based on the rehabilitation plan ideal and vertical gait standard displacement Y ideal , the horizontal gait displacement X i and vertical gait displacement Y i Standard displacement X with horizontal gait ideal and vertical gait standard displacement Y ideal , perform difference processing and extract the horizontal gait displacement deviation △X i and vertical gait displacement deviation △Y i , horizontal gait displacement deviation △X i =X i -X ideal , vertical gait displacement deviation △Yi =Y i -Y ideal .
[0108] In this embodiment, the central processing module plays a core role in the patient rehabilitation progress tracking system. Through the data preprocessing unit, the module can receive and process the rehabilitation data packets from the patient rehabilitation tracking module in real time, use the Python programming language to convert the data in JSON format into a usable data structure, further identify and process outliers, and convert categorical variables into numerical variables through unique hot encoding. This preprocessing step ensures the accuracy and consistency of the data and provides a reliable data basis for subsequent analysis. Subsequently, the feature extraction unit extracts gait features, joint features, muscle strength features, pain features, and motion coordination features from the preprocessed data set. These features reflect the patient's rehabilitation status in detail.
[0109] Example 4: This example is an explanation of Example 3. Figure 1 ,Specifically: the health analysis module includes a gait stability analysis unit, a muscle fatigue analysis unit, and a movement coordination analysis unit;
[0110] The gait stability analysis unit is used to construct a gait stability algorithm formula, transfer the extracted gait feature set to the gait stability analysis algorithm formula, and calculate and obtain the gait stability index GSI;
[0111] The gait stability index GSI is calculated using the following gait stability analysis algorithm formula:
[0112] ;
[0113] Where N represents the total number of gaits, X i represents the horizontal gait displacement of the i-th gait, Y i represents the vertical gait displacement of the i-th gait.
[0114] The muscle fatigue analysis unit is used to construct a muscle fatigue algorithm formula, load the extracted muscle strength characteristics into the muscle fatigue algorithm formula, and calculate to obtain the muscle fatigue index MF;
[0115] The muscle fatigue index MF is calculated using the following muscle fatigue algorithm formula:
[0116] ;
[0117] Where, EMG max represents the peak value of the electromyographic signal, dt represents the time variable, T represents the measurement time, and t represents the time point.
[0118] The motion coordination analysis unit is used to construct a motion coordination algorithm formula, load the extracted motion coordination feature set into the motion coordination algorithm formula, and perform calculation to obtain the motion coordination index MC;
[0119] The movement coordination index MC is calculated by the following movement coordination algorithm formula:
[0120] ;
[0121] Wherein, L represents the ideal motion path length, and the specific value is set by the user.
[0122] In this embodiment, the health analysis module realizes a multi-dimensional quantitative evaluation of the patient's rehabilitation process through a gait stability analysis unit, a muscle fatigue analysis unit, and a motion coordination analysis unit. The gait stability analysis unit uses the extracted gait feature set to calculate the gait stability index GSI, which effectively evaluates the stability of the patient when walking. The muscle fatigue analysis unit evaluates the degree of muscle fatigue of the patient during exercise by calculating the muscle fatigue index MF based on muscle strength characteristics. The motion coordination analysis unit uses the motion coordination feature set to calculate the motion coordination index MC to measure the patient's motion coordination and the accuracy of the motion path. The system realizes data-driven quantitative evaluation by constructing a detailed algorithm formula. This precise quantitative analysis not only improves the scientificity and objectivity of rehabilitation evaluation, but also provides a solid foundation for the formulation of personalized rehabilitation plans.
[0123] Example 5: This example is an explanation of Example 4. Figure 1 ,Specifically: the comprehensive rehabilitation process analysis module includes a comprehensive rehabilitation ,process calculation unit and a rehabilitation process evaluation unit;
[0124] The comprehensive rehabilitation process calculation unit is used to integrate with the health analysis module, and perform correlation calculation to obtain the first rehabilitation index KFZ according to the gait stability index GS, muscle fatigue index MF and movement coordination index MC output by the health analysis module;
[0125] The first rehabilitation index KFZ is obtained by the following algorithm formula:
[0126] ;
[0127] In the formula, , and represent the preset weight values of gait stability index GS, muscle fatigue index MF and movement coordination index MC, respectively, and + + =1, the specific value is set by the user, exp represents exponential function, and sin represents sine function;
[0128] The rehabilitation process evaluation unit presets the rehabilitation threshold K through the planned rehabilitation index, and then makes a preliminary comparative evaluation with the obtained first rehabilitation index KFZ to evaluate the rehabilitation status of the currently formulated rehabilitation plan for orthopedic patients with leg injuries;
[0129] The specific evaluation plan is as follows:
[0130] When the first rehabilitation index KFZ ≥ the rehabilitation threshold K, it means that the currently formulated rehabilitation plan is normal for orthopedic patients with leg injuries. At this time, the secondary evaluation mechanism is implemented to deeply analyze the rehabilitation situation;
[0131] When the first rehabilitation index KFZ is less than the rehabilitation threshold K, it indicates that the currently formulated rehabilitation plan is abnormal for the orthopedic patient with leg injury, and at this time, the first prompt information is generated to adjust the preliminary rehabilitation plan;
[0132] Initial rehabilitation program modifications included increasing the intensity of balance training and gait correction exercises by 10% to improve gait stability while decreasing the intensity of training by 10%.
[0133] In this embodiment, the comprehensive rehabilitation process analysis module realizes the comprehensive evaluation and timely adjustment of the rehabilitation effect through the comprehensive rehabilitation process calculation unit and the rehabilitation process evaluation unit. The comprehensive rehabilitation process calculation unit combines the gait stability index GS, the muscle fatigue index MF and the movement coordination index MC to calculate the first rehabilitation index KFZ, which provides an overall evaluation basis for the rehabilitation process. The rehabilitation process evaluation unit performs a preliminary comparative evaluation of the first rehabilitation index KFZ according to the preset rehabilitation threshold K, judges the effectiveness of the rehabilitation plan, and gives adjustment suggestions. When the first rehabilitation index KFZ reaches or exceeds the rehabilitation threshold K, the system starts the secondary evaluation mechanism for a more in-depth analysis; if the first rehabilitation index KFZ does not reach the rehabilitation threshold K, the system recommends increasing the intensity of balance training and gait correction exercises, while moderately reducing the intensity of other training. This precise and flexible evaluation mechanism significantly improves the personalization and dynamic adjustment capabilities of the rehabilitation program, and has obvious advantages over the traditional static evaluation method. Through real-time monitoring and adjustment, it ensures that the patient's rehabilitation process is more scientific and efficient, ultimately accelerating the patient's rehabilitation speed and improving the overall rehabilitation quality. At the same time, the hierarchical evaluation method helps to reduce the system data processing volume and improve the system's processing performance.
[0134] Example 6: This example is an explanation of Example 5. Please refer to Figure 1,Specifically: the rehabilitation adjustment analysis module is triggered when it is evaluated that ,the initial rehabilitation plan is effective for the orthopedic patient with leg injury to recover normally, and the rehabilitation adjustment analysis ,module includes a deep analysis calculation unit, a secondary comprehensive rehabilitation ,process calculation unit and a secondary evaluation unit;
[0135] The depth analysis calculation unit includes a joint friction calculation unit and a pain induction calculation unit;
[0136] The joint friction calculation unit is used to calculate and obtain the joint friction coefficient JF according to the extracted joint feature set;
[0137] The joint friction coefficient JF is calculated using the following algorithm:
[0138] ;
[0139] In the formula, Ff represents the friction force of joint movement, and Fn represents the force on the joint;
[0140] The pain induced calculation unit is used to calculate and obtain the pain induced time PE according to the extracted pain features;
[0141] The pain induced time PE is calculated by the following algorithm formula:
[0142] ;
[0143] Where, Tt j represents the time of pain induced by the jth action, and M is the number of pain-induced measurements.
[0144] The secondary comprehensive rehabilitation process calculation unit is used to correlate the obtained joint friction coefficient JF and pain induction time PE with the obtained first rehabilitation index KFZ to obtain the second rehabilitation index KFZ2.
[0145] The second rehabilitation index KFZ2 is calculated by the following algorithm formula:
[0146] ;
[0147] Where a1, a2, and a3 represent the preset weight values of the first rehabilitation index KFZ, the joint friction coefficient JF, and the pain induction time PE, respectively, and the specific parameters are set by the user, and log represents the logarithmic function;
[0148] The secondary evaluation unit is used to conduct a secondary comparative evaluation of the obtained second rehabilitation index KFZ2 and the rehabilitation threshold K, and deeply evaluate the rehabilitation status of the currently formulated rehabilitation plan for orthopedic patients with leg injuries;
[0149] The specific evaluation plan is as follows:
[0150] When the second rehabilitation index KFZ2 ≥ the rehabilitation threshold K, it means that the current patient's rehabilitation status is normal, and the current rehabilitation plan continues to be implemented;
[0151] When the second rehabilitation indicator KFZ2 is less than the rehabilitation threshold K, it indicates that the current patient's rehabilitation status is abnormal. At this time, a second prompt message is generated to adjust the secondary rehabilitation plan. The secondary rehabilitation plan adjustment includes adjusting the range of motion of the joints or adding lubrication exercises to reduce friction and reduce pain-inducing movements, and increasing low-intensity or no-load exercises to ensure that the patient does not experience unnecessary pain during training.
[0152] In this embodiment, the rehabilitation adjustment analysis module further optimizes the patient's rehabilitation plan through in-depth analysis and secondary evaluation of the preliminary rehabilitation results. The in-depth analysis calculation unit in the module provides more detailed rehabilitation feature data by calculating the joint friction coefficient JF and the pain induction time PE. The secondary comprehensive rehabilitation process calculation unit combines the joint friction coefficient JF and the pain induction time PE with the first rehabilitation index KFZ to calculate the second rehabilitation index KFZ2, providing a more comprehensive evaluation basis for the rehabilitation status. The secondary evaluation unit determines whether the patient's rehabilitation progress is normal by comparing the second rehabilitation index KFZ2 with the rehabilitation threshold K, and puts forward targeted adjustment suggestions, such as adjusting the range of joint motion, increasing lubrication exercises, and reducing pain-inducing movements. This refined and in-depth analysis method considers the patient's rehabilitation process more comprehensively and ensures the scientificity and personalization of the rehabilitation plan.
[0153] Example 7: Please refer to Figure 1 and Figure 2 In an embodiment of the present invention, a method for tracking the rehabilitation progress of an orthopedic patient comprises the following steps:
[0154] S1: Through the integrated rehabilitation detection equipment, the rehabilitation data of orthopedic patients with leg injuries are collected in real time, and the rehabilitation data is packaged and sent to the central processing module;
[0155] S2: After receiving the rehabilitation data in real time, preprocessing the rehabilitation data to obtain a rehabilitation data set, and then extracting features based on the obtained rehabilitation data set to obtain a rehabilitation feature set;
[0156] S3: Construct a rehabilitation algorithm formula set, perform loading calculations based on the acquired rehabilitation feature set, and obtain the gait stability index GS, the muscle fatigue index MF, and the movement coordination index MC;
[0157] S4: Integrate the gait stability index GS, muscle fatigue index MF and movement coordination index MC output by the health analysis module, calculate and obtain the first rehabilitation index KFZ, and preset the rehabilitation threshold K for preliminary comparative evaluation, preliminarily analyze the rehabilitation status of orthopedic patients in the current rehabilitation plan, and generate preliminary rehabilitation plan adjustment prompt information based on the preliminary evaluation results;
[0158] S5: Calculate the joint friction coefficient JF and the pain induction time PE based on the rehabilitation feature set, and then perform a comprehensive calculation with the first rehabilitation index KFZ to obtain the second rehabilitation index KFZ2, and then perform a secondary comparative evaluation with the rehabilitation threshold K to deeply analyze the rehabilitation status of orthopedic patients in the current rehabilitation plan, and generate a secondary rehabilitation plan adjustment prompt information based on the secondary evaluation results.
[0159] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.
Claims
1. A rehabilitation progress tracking system for orthopedic patients, characterized in that: It includes patient rehabilitation tracking module, central processing module, health analysis module, comprehensive rehabilitation process analysis module and rehabilitation adjustment analysis module; The patient rehabilitation tracking module collects rehabilitation data of orthopedic patients with leg injuries in real time by integrating rehabilitation detection equipment, and encapsulates the rehabilitation data and sends it to the central processing module; The central processing module is used to receive the rehabilitation data in real time, pre-process the rehabilitation data, obtain a rehabilitation data set, and then perform feature extraction based on the obtained rehabilitation data set to obtain a rehabilitation feature set; The health analysis module is used to construct a rehabilitation algorithm formula set, perform loading calculations based on the acquired rehabilitation feature set, and obtain a gait stability index GS, a muscle fatigue index MF, and a movement coordination index MC; The comprehensive rehabilitation process analysis module is used to integrate the gait stability index GS, muscle fatigue index MF and movement coordination index MC output by the health analysis module, calculate and obtain the first rehabilitation index KFZ, and preset the rehabilitation threshold K for preliminary comparative evaluation, preliminarily analyze the rehabilitation status of orthopedic patients in the current rehabilitation plan, and generate preliminary rehabilitation plan adjustment prompt information based on the preliminary evaluation results; The rehabilitation adjustment analysis module is used to calculate the joint friction coefficient JF and the pain induction time PE according to the rehabilitation feature set, and then perform a comprehensive calculation with the obtained first rehabilitation index KFZ to obtain the second rehabilitation index KFZ2, and then perform a secondary comparative evaluation with the rehabilitation threshold K, deeply analyze the rehabilitation status of orthopedic patients in the current rehabilitation plan, and generate a secondary rehabilitation plan adjustment prompt information based on the secondary evaluation results; The patient rehabilitation tracking module includes a data acquisition unit and a data transmission unit; The data acquisition unit collects rehabilitation data of orthopedic patients with leg injuries in real time by using orthopedic medical detection equipment, wherein the rehabilitation data includes gait data, joint data, muscle strength data and pain data; The data transmission unit is used to encapsulate the collected rehabilitation data into a rehabilitation data packet in JSON format, set a WIFi wireless transmission protocol to wirelessly connect to the central processing module, and transmit the rehabilitation data packet to the central processing module; The central processing module includes a data preprocessing unit and a feature extraction unit; The data preprocessing unit is used to receive the rehabilitation data packet in real time, use the Python programming language to convert the rehabilitation data packet string in JSON format into a data structure, and perform preprocessing, wherein the preprocessing method includes using a statistical method to identify outliers for deletion and using one-hot encoding to convert data classification variables into numerical variables, and then converting the preprocessed data into a unified unit format, and summarizing to generate a rehabilitation data set; The feature extraction unit extracts features based on the preprocessed rehabilitation data set to obtain a rehabilitation feature set, wherein the rehabilitation feature set includes a gait feature set, a joint feature set, a muscle strength feature, a pain feature, and a movement coordination feature set; The gait feature set includes horizontal gait displacement X i and vertical gait displacement Y i ; The joint feature set includes joint motion friction force Ff and joint force Fn; The muscle strength characteristics include electromyographic signal intensity EMG; The pain characteristics include action-induced pain time Tt; The gait feature set includes horizontal gait displacement X i and vertical gait displacement Y i ; The joint feature set includes joint motion friction force Ff and joint force Fn; The muscle strength characteristics include electromyographic signal intensity EMG; The pain characteristics include action-induced pain time Tt; The motion coordination feature set includes the horizontal gait displacement deviation ΔX i and vertical gait displacement deviation △Y i ; The gait feature set tracks the foot position of each step through a 3D gait analysis device, records the displacement data in three-dimensional space, calculates the horizontal gait position and vertical gait position of each step, and then extracts the horizontal gait displacement X by differentiating the continuous footstep position data. i and vertical gait displacement Y i , and perform mean processing to extract the average value of horizontal gait displacement and the average vertical gait displacement ; The joint feature set is recorded by a force sensor, and the force detected at the joint is decomposed into a component force perpendicular to the contact force sensor and a component force parallel to the contact force sensor, and the horizontal force is extracted as the joint motion friction force Ff, and the vertical force is the joint force Fn; The muscle force feature collects electromyographic signals through an electromyographic sensor, extracts the electromyographic signal strength EMG, and performs time series analysis on the electromyographic signal strength EMG to extract the electromyographic signal strength EMG (t) at the action time t; The pain characteristics are obtained by recording the time when orthopedic patients with leg injuries feel pain when performing specific actions, recording the specific time when each action induces pain, and extracting the induced pain time Tt by using time series analysis; The motion coordination feature set is obtained by i and vertical gait displacement Y i , and at the same time, the preset horizontal gait standard displacement X is performed based on the rehabilitation plan ideal and vertical gait standard displacement Y ideal , the horizontal gait displacement X i and vertical gait displacement Y i Standard displacement X with horizontal gait ideal and vertical gait standard displacement Y ideal , perform difference processing and extract the horizontal gait displacement deviation △X i and vertical gait displacement deviation △Y i .
2. The orthopedic patient rehabilitation progress tracking system according to claim 1, characterized in that: The health analysis module includes a gait stability analysis unit, a muscle fatigue analysis unit and a movement coordination analysis unit; The gait stability analysis unit is used to construct a gait stability algorithm formula, transmit the extracted gait feature set to the gait stability analysis algorithm formula, and perform calculation to obtain a gait stability index GSI; The gait stability index GSI is calculated by the following gait stability analysis algorithm formula: ; Where N represents the total number of gaits, X i represents the horizontal gait displacement of the i-th gait, Y i represents the vertical gait displacement of the i-th gait.
3. The orthopedic patient rehabilitation progress tracking system according to claim 2, characterized in that: The muscle fatigue analysis unit is used to construct a muscle fatigue algorithm formula, load the extracted muscle strength characteristics into the muscle fatigue algorithm formula, and calculate to obtain a muscle fatigue index MF; The muscle fatigue index MF is calculated by the following muscle fatigue algorithm formula: ; Where, EMG max represents the peak value of the electromyographic signal, dt represents the time variable, T represents the measurement time, and t represents the time point.
4. The orthopedic patient rehabilitation progress tracking system according to claim 3, characterized in that: The motion coordination analysis unit is used to construct a motion coordination algorithm formula, load the extracted motion coordination feature set into the motion coordination algorithm formula, and perform calculation to obtain the motion coordination index MC; The movement coordination index MC is calculated by the following movement coordination algorithm formula: ; Wherein, L represents the ideal motion path length, and the specific value is set by the user.
5. The orthopedic patient rehabilitation progress tracking system according to claim 4, characterized in that: The comprehensive rehabilitation process analysis module includes a comprehensive rehabilitation process calculation unit and a rehabilitation process evaluation unit; The comprehensive rehabilitation process calculation unit is used to be integrated with the health analysis module, and to perform correlation calculation to obtain the first rehabilitation index KFZ according to the gait stability index GS, the muscle fatigue index MF and the movement coordination index MC output by the health analysis module; The first rehabilitation index KFZ is obtained by the following algorithm formula: ; In the formula, , and represent the preset weight values of gait stability index GS, muscle fatigue index MF and movement coordination index MC, respectively, and + + =1, the specific value is set by the user, exp represents exponential function, and sin represents sine function; The rehabilitation process evaluation unit presets a rehabilitation threshold value K through the planned rehabilitation index, and then performs a preliminary comparative evaluation with the obtained first rehabilitation index KFZ to evaluate the rehabilitation status of the currently formulated rehabilitation plan for the orthopedic patient with leg injury; The specific evaluation plan is as follows: When the first rehabilitation index KFZ ≥ the rehabilitation threshold K, it means that the currently formulated rehabilitation plan is normal for orthopedic patients with leg injuries. At this time, the secondary evaluation mechanism is implemented to deeply analyze the rehabilitation situation; When the first rehabilitation index KFZ is less than the rehabilitation threshold K, it indicates that the currently formulated rehabilitation plan is abnormal for orthopedic patients with leg injuries. At this time, the first prompt information is generated to make preliminary adjustments to the rehabilitation plan.
6. The orthopedic patient rehabilitation progress tracking system according to claim 5, characterized in that: The rehabilitation adjustment analysis module is triggered when it is evaluated that the preliminary rehabilitation plan is effective for the recovery of the orthopedic patient with leg injury, and the rehabilitation adjustment analysis module includes a depth analysis calculation unit, a secondary comprehensive rehabilitation process calculation unit and a secondary evaluation unit; The depth analysis calculation unit includes a joint friction calculation unit and a pain induction calculation unit; The joint friction calculation unit is used to calculate and obtain the joint friction coefficient JF according to the extracted joint feature set; The joint friction coefficient JF is calculated by the following algorithm: ; In the formula, Ff represents the friction force of joint movement, and Fn represents the force on the joint; The pain induction calculation unit is used to calculate and obtain the pain induction time PE according to the extracted pain characteristics; The pain induction time PE is calculated by the following algorithm formula: ; Where, Tt j represents the time of pain induced by the jth action, and M is the number of pain-induced measurements.
7. The orthopedic patient rehabilitation progress tracking system according to claim 6, characterized in that: The secondary comprehensive rehabilitation process calculation unit is used to calculate the obtained joint friction coefficient JF and pain induction time PE in association with the obtained first rehabilitation index KFZ to obtain the second rehabilitation index KFZ2; The second rehabilitation index KFZ2 is calculated by the following algorithm formula: ; Where a1, a2, and a3 represent the preset weight values of the first rehabilitation index KFZ, the joint friction coefficient JF, and the pain induction time PE, respectively, and the specific parameters are set by the user, and log represents the logarithmic function; The secondary evaluation unit is used to perform a secondary comparative evaluation on the obtained second rehabilitation index KFZ2 and the rehabilitation threshold K, and deeply evaluate the rehabilitation status of the currently formulated rehabilitation plan for orthopedic patients with leg injuries; The specific evaluation plan is as follows: When the second rehabilitation index KFZ2 ≥ the rehabilitation threshold K, it means that the current patient's rehabilitation status is normal, and the current rehabilitation plan continues to be implemented; When the second rehabilitation indicator KFZ2 is less than the rehabilitation threshold K, it indicates that the current patient's rehabilitation state is abnormal, and at this time, a second prompt message is generated to adjust the secondary rehabilitation plan.
8. A method for tracking the rehabilitation progress of orthopedic patients, applied to the orthopedic patient rehabilitation progress tracking system according to any one of claims 1 to 7, characterized in that: include: Through the integration of rehabilitation detection equipment, the rehabilitation data of orthopedic patients with leg injuries are collected in real time, and the rehabilitation data is packaged and sent to the central processing module; After receiving the rehabilitation data in real time, preprocessing the rehabilitation data to obtain a rehabilitation data set, and then extracting features based on the obtained rehabilitation data set to obtain a rehabilitation feature set; Construct a rehabilitation algorithm formula set, perform loading calculations based on the acquired rehabilitation feature set, and obtain the gait stability index GS, muscle fatigue index MF, and movement coordination index MC; The gait stability index GS, muscle fatigue index MF and movement coordination index MC output by the integrated health analysis module are calculated to obtain the first rehabilitation index KFZ, and the rehabilitation threshold K is preset for preliminary comparative evaluation, and the rehabilitation status of orthopedic patients in the current rehabilitation plan is preliminarily analyzed, and preliminary rehabilitation plan adjustment prompt information is generated based on the preliminary evaluation results; The joint friction coefficient JF and the pain induction time PE are calculated based on the rehabilitation feature set, and then the second rehabilitation index KFZ2 is obtained by comprehensive calculation with the first rehabilitation index KFZ. A secondary comparative evaluation is performed with the rehabilitation threshold K to deeply analyze the rehabilitation status of orthopedic patients in the current rehabilitation plan, and the rehabilitation plan adjustment prompt information is generated based on the secondary evaluation results.
