System for assessing lower extremity strength and gait effects in patients
By simultaneously collecting and fusing lower limb muscle strength, electrophysiological, and kinematic data, a correlation model between gait abnormalities and muscle function is established, solving the problem of difficulty in determining causal relationships in existing technologies and enabling precise lower limb function assessment and personalized rehabilitation guidance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHENGDU MILITARY GENERAL HOSPITAL OF PLA
- Filing Date
- 2026-02-06
- Publication Date
- 2026-05-12
AI Technical Summary
Existing technologies cannot accurately reveal the causal relationship between gait abnormalities and insufficient strength of specific muscle groups or dysfunction of neural control, resulting in a lack of precision in clinical diagnosis and blindness in rehabilitation training programs.
Isokinetic muscle strength testing, surface electromyography signal acquisition, and optical motion capture technology were used to simultaneously collect lower limb muscle strength, electrophysiological, and kinematic data. A synchronization control module ensured that the data time reference was consistent. Combined with the data processing and analysis module, multimodal data fusion and correlation modeling were performed to establish a correlation model between muscle function and gait parameters.
It achieves the synchronization and integration of multimodal data, ensures the accurate recording of causal relationships, outputs objective and repeatable assessment results, provides direct directional guidance for clinical intervention, and improves the accuracy of rehabilitation training.
Smart Images
Figure CN121647682B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of gait assessment technology, and more specifically to a system for assessing the impact of a patient's lower limb strength on walking gait. Background Technology
[0002] Currently, in clinical practice, lower limb function is typically assessed using traditional methods such as manual muscle testing (MMT) and visual gait observation. These methods suffer from high subjectivity and insufficient precision. While objective quantitative techniques such as isokinetic muscle strength testing, surface electromyography (sEMG) analysis, and optical motion capture exist, current protocols often use them in isolation, providing only isolated muscle strength or gait parameter data without enabling simultaneous measurement and correlation analysis. This makes it impossible to accurately reveal the causal link between gait abnormalities and specific muscle group weakness or neurological control dysfunction, resulting in a lack of precision in clinical diagnosis and often leading to the development of rehabilitation training programs with a degree of uncertainty. Summary of the Invention
[0003] To address the problems in related technologies, this invention provides a system for assessing the impact of lower limb strength and gait on a patient's walking gait.
[0004] To achieve the above objectives, the technical solution adopted by the present invention includes:
[0005] According to a first aspect of the present invention, a system for assessing the impact of lower limb strength and gait on a patient is provided, comprising:
[0006] The data acquisition module includes an isokinetic muscle strength testing unit, a surface electromyography signal acquisition unit, and an optical motion capture unit, which are used to acquire the subject's lower limb muscle strength data, lower limb muscle electrophysiological data, and lower limb kinematic data, respectively.
[0007] A synchronization control module is communicatively connected to the data acquisition module and is used to send a synchronization signal to the data acquisition module so that the muscle strength data, muscle electrophysiological data and kinematic data have a unified time reference.
[0008] The data processing and analysis module, which is communicatively connected to the data acquisition module and the synchronization control module, is configured as follows:
[0009] Receive and time-align the lower limb muscle strength data, the lower limb muscle electrophysiological data, and the lower limb kinematic data;
[0010] Lower limb strength indices, electromyographic activity indices, and gait parameters were extracted from the aligned data.
[0011] Based on the extracted indicators and parameters, a correlation model is established between the lower limb strength indicators, the electromyographic activity indicators and the gait parameters, and the evaluation results are output.
[0012] Optionally, the data processing and analysis module is configured to extract lower limb strength indicators from the lower limb muscle strength data, including: peak torque, total work done, torque acceleration energy, and peak torque ratio of one or more periarticular muscle groups.
[0013] Optionally, the data processing and analysis module is configured to extract electromyographic activity indicators and gait parameters from the lower limb muscle electrophysiological data and the lower limb kinematic data, including: activation intensity, activation sequence, stride length, stride speed, stride frequency and joint angle of each target muscle in the gait cycle.
[0014] Optionally, the data processing and analysis module is further configured to perform gait abnormality attribution analysis by comparing the temporal relationship between the electromyographic activity index and the lower limb kinematic data. The attribution analysis includes determining whether the abnormality is caused by muscle weakness, incorrect activation timing, or excessive synergistic contraction.
[0015] Optionally, the data processing and analysis module is configured to perform correlation analysis by calculating the correlation coefficient between the lower limb strength index and the gait parameters.
[0016] Optionally, the data processing and analysis module is further configured to calculate a comprehensive muscle-gait correlation index to quantify the contribution of a specific muscle to overall gait performance. The formula for calculating the muscle-gait correlation index is as follows:
[0017]
[0018] In the formula, Indicates the first Myostep correlation index of a muscle group Indicates the pre-set number Weighting factors for each gait parameter, Indicates the first Core strength indicators of bulky muscles and the first The correlation coefficients between the gait parameters Indicates the first Normalized values of each gait parameter.
[0019] Optionally, the normalized value It is obtained by dividing the actual gait parameter values of the subjects by the norm values of healthy individuals.
[0020] Optionally, the data processing and analysis module is configured to build and train a machine learning model to achieve the association modeling, the machine learning model including a forward prediction model and a backward inference model;
[0021] The positive prediction model takes the extracted lower limb strength indicators and electromyographic activity indicators as inputs and gait parameters as outputs to predict gait performance; the reverse inference model takes the extracted gait parameters and electromyographic activity indicators as inputs and outputs the probability diagnosis of lower limb strength indicators or weak muscle groups to assist in etiological diagnosis.
[0022] Optionally, the machine learning model employs one or more algorithms, including random forest, gradient boosting tree, or neural network.
[0023] According to a second aspect of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, performs the functions of a data processing and analysis module of a system for assessing the influence of a patient's lower limb strength and gait as described in any of the technical solutions of the first aspect of the present invention.
[0024] Beneficial effects:
[0025] 1. Through the above technical solution, firstly, it is possible to achieve the synchronization and integration of multimodal data. Specifically, the system of the present invention for assessing the impact of patients' lower limb strength and gait can acquire three types of heterogeneous data—muscle strength, electrophysiology, and kinematics—from the subject simultaneously and synchronously, thereby solving the problems of data fragmentation and inconsistent states caused by multiple, time-sharing tests in traditional methods.
[0026] Second, by using a unified time reference, this invention ensures that the cause (e.g., the exertion of a muscle at a certain moment) and the effect (e.g., the change in joint angle at the same moment) are accurately corresponded and recorded on the time axis, providing more reliable data quality for subsequent revelation of the intrinsic relationship between the two, thus laying the data foundation for causal association analysis.
[0027] Third, the system output of the present invention for assessing the impact of lower limb strength and gait on patients is based on extracted preset indicators and established correlation models, which can effectively avoid subjective qualitative judgments, thereby making the lower limb function assessment results repeatable and comparable in objectivity.
[0028] Fourth, the final output of the system for assessing the impact of lower limb strength and gait on patients in this invention is no longer an isolated numerical report, but a conclusion based on a correlation model that can explain the relationship between gait abnormalities and muscle function. In this way, it can provide direct directional guidance for clinical intervention.
[0029] 2. Other beneficial effects or advantages of the present invention will be described in detail in conjunction with specific structures in specific embodiments. Attached Figure Description
[0030] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In addition, it should be understood that the proportional relationship of each component in the drawings of this specification does not represent the proportional relationship in the actual material selection and design, but is only a schematic diagram of the structure or position, wherein:
[0031] Figure 1 This is a schematic diagram of the layout framework of a system for assessing the impact of a patient's lower limb strength and gait, provided by an exemplary embodiment of the present invention. Detailed Implementation
[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.
[0033] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.
[0034] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. It should also be noted that in embodiments of this invention, the words "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in embodiments of this invention should not be construed as preferred or advantageous over other embodiments or designs. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.
[0035] To facilitate a clearer and more accurate understanding of the technical solutions of this invention by those skilled in the art, the existing related technologies and their technical problems will be described in more detail below.
[0036] In clinical practice in rehabilitation medicine, neurology, and orthopedics, accurate assessment of lower limb dysfunction is central to developing effective rehabilitation strategies. Currently, routine clinical assessments primarily rely on two types of techniques: First, manual muscle testing (MMT), where physicians subjectively assess muscle strength (e.g., 0-5) by manually resisting specific directional movements of the patient's lower limbs (e.g., instructing the patient to extend their knee while applying resistance). Second, visual gait observation, where physicians visually observe the patient's walking posture to qualitatively determine the presence of abnormal patterns such as limping, dragging, or circling.
[0037] The limitations of existing technology can be highlighted by a typical clinical case: a stroke patient with hemiplegia complained of gait instability and difficulty walking. MMT assessment revealed that the quadriceps muscle strength on the affected side was grade 3 (able to complete a full range of motion against gravity, but only able to resist partial resistance), and the hamstring and gluteus maximus muscles were also grade 3. Visual gait observation revealed instability during the stance phase and difficulty in foot clearance during the swing phase of the gait cycle. However, based on this isolated information, it is difficult for physicians to determine whether the patient's gait abnormality is primarily caused by quadriceps weakness, or by hamstring or gluteus maximus weakness, or by a timing error in muscle activation due to neurological damage (e.g., failure to contract when required, or excessive tension when required).
[0038] While more advanced objective measurement techniques, such as isokinetic muscle strength testing systems, surface electromyography (sEMG), and optical motion capture systems, are widely used in research, they are often used in isolation in clinical practice. A physician might schedule a patient for an isokinetic muscle strength test to obtain quantitative data such as peak torque and work done by the flexor and extensor muscles of the knee, hip, and ankle joints; a gait analysis would then be performed on a separate day to obtain parameters such as gait speed, stride length, and joint range of motion.
[0039] This "data silo" model has fundamental flaws: First, the patient's physical condition, effort level, and functional performance may differ between the two tests, leading to asynchronous and incomparable data; second, and more importantly, even with two independent reports, doctors still find it difficult to answer the direct link between cause and effect—that is, they cannot determine to what extent the "decrease in gait speed of 0.3 m / s" can be attributed to "a decrease of 30 Nm in peak quadriceps torque" or "a delay of 50 ms in gluteus medius activation."
[0040] This lack of causal relationship directly leads to the blindness of rehabilitation treatment. In the above case, the therapist may only be able to adopt a crude strategy of "comprehensively strengthening lower limb muscle strength" or rely on experience to guess for training, and be unable to tailor the most accurate and efficient plan for the patient (for example, whether to focus on the explosive power training of the quadriceps or the coordination activation training of the hamstrings), thus prolonging the rehabilitation period and affecting the treatment effect.
[0041] Based on this, the present invention proposes an innovative system solution. The core idea of the present invention is to simultaneously collect muscle strength, electromyography, and kinematic data in a single test through a synchronous control protocol, ensuring that all data are strictly aligned on the time axis; then, through multimodal data fusion and correlation modeling algorithms, quantitative mathematical models between muscle function (cause) and gait performance (effect) are established, ultimately achieving a leap from problem discovery to root cause localization, providing irrefutable data evidence for precise rehabilitation.
[0042] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings.
[0043] like Figure 1 As shown, according to a first aspect of the present invention, a system for assessing the influence of lower limb strength and gait on a patient is provided, comprising a data acquisition module, a synchronization control module, and a data processing and analysis module. The data acquisition module includes an isokinetic muscle strength testing unit, a surface electromyography signal acquisition unit, and an optical motion capture unit, respectively used to acquire lower limb muscle strength data, lower limb muscle electrophysiological data, and lower limb kinematic data of the subject; the synchronization control module is communicatively connected to the data acquisition module and is used to send synchronization signals to the data acquisition module to ensure that the muscle strength data, muscle electrophysiological data, and kinematic data have a unified time reference; the data processing and analysis module is communicatively connected to the data acquisition module and the synchronization control module, and is configured to:
[0044] Receive and time-align lower limb muscle strength data, lower limb muscle electrophysiological data, and lower limb kinematic data;
[0045] Lower limb strength indices, electromyographic activity indices, and gait parameters were extracted from the aligned data.
[0046] Based on the extracted indicators and parameters, a correlation model is established between lower limb strength indicators, electromyographic activity indicators and gait parameters, and the evaluation results are output.
[0047] Through the above technical solution, firstly, it is possible to achieve the synchronization and integration of multimodal data. Specifically, the system of the present invention for assessing the impact of patients' lower limb strength and gait can acquire three types of heterogeneous data—muscle strength, electrophysiology, and kinematics—from subjects simultaneously and concurrently, thereby solving the problems of data fragmentation and inconsistent states caused by multiple, time-segmented tests in traditional methods.
[0048] Second, by using a unified time reference, this invention ensures that the cause (e.g., the exertion of a muscle at a certain moment) and the effect (e.g., the change in joint angle at the same moment) are accurately corresponded and recorded on the time axis, providing more reliable data quality for subsequent revelation of the intrinsic relationship between the two, thus laying the data foundation for causal association analysis.
[0049] Third, the system output of the present invention for assessing the impact of lower limb strength and gait on patients is based on extracted preset indicators and established correlation models, which can effectively avoid subjective qualitative judgments, thereby making the lower limb function assessment results repeatable and comparable in objectivity.
[0050] Fourth, the final output of the system for assessing the impact of lower limb strength and gait on patients in this invention is no longer an isolated numerical report, but a conclusion based on a correlation model that can explain the relationship between gait abnormalities and muscle function. In this way, it can provide direct directional guidance for clinical intervention.
[0051] In this embodiment, it should be noted that, firstly, for the data acquisition module, its isokinetic muscle strength testing unit, surface electromyography (SEMG) signal acquisition unit, and optical motion capture unit operate based on three different physical principles: biomechanics, electrophysiology, and optical measurement. This allows for the capture of information from different dimensions of human movement through various technical pathways. Specifically, the isokinetic muscle strength unit provides the maximum torque generated by muscle contraction and the work capacity (force output potential). The SEMG unit provides the electrical signals that drive the muscles through nerves (force control commands and timing). The optical motion capture unit provides the final limb movement trajectory and posture (the final effect of force). Combining these three components forms a complete information chain from neural control to force generation and then to motor performance, laying the data foundation for comprehensive evaluation.
[0052] Secondly, for the synchronization control module, a high-precision common time source (synchronization signal) is introduced as the timestamp reference for all heterogeneous data streams. This solves the time registration problem in multi-sensor data fusion, ensuring that during analysis, a single millisecond of electromyographic burst signal can be accurately correlated with changes in joint torque and kinematic posture within the same millisecond.
[0053] Third, for the data processing and analysis module, time alignment is based on synchronization signals, fusing the three data streams along the time axis. The extracted indicators and parameters are derived from the aligned raw data through calculations (e.g., integration, averaging, finding extrema) to extract information-level features (e.g., peak torque, average electromyography, joint angles) that represent muscle function and gait characteristics. This transforms raw, high-dimensional, and difficult-to-understand data into interpretable, low-dimensional features with clear physiological significance. The established correlation model uses mathematical or statistical methods (e.g., correlation analysis, regression models) to find and quantify the mapping relationship from one set of feature indicators (muscle function) to another set of feature indicators (gait parameters). This effectively uncovers the inherent patterns between these features, enabling the generation of corresponding evaluation results.
[0054] Overall, the system of this invention, through its unique system architecture (data acquisition module, synchronization control module, and data processing and analysis module) and methodology (synchronization-alignment-extraction-modeling), cleverly utilizes multimodal complementarity, unified time reference, and data fusion and modeling to produce significant effects, from "data silos" to "correlated fusion," from "subjective experience" to "objective quantification," and from "describing phenomena" to "revealing the causes."
[0055] In one embodiment of the present invention, the data processing and analysis module of the present invention is configured to extract lower limb strength indicators from lower limb muscle strength data, including: peak torque, total work done, torque acceleration energy, and peak torque ratio of one or more periarticular muscle groups.
[0056] The technical solution of the present invention will be described in detail below with reference to a specific embodiment.
[0057] I. Basic Information Description
[0058] Real-time scenario: A hospital's rehabilitation department conducts a precise assessment of lower limb function for Mr. Zhang, a patient with right hemiplegia following a stroke.
[0059] Real-time objective: To accurately diagnose the root cause of Zhang's gait abnormalities (dragging and unsteady walking) and to develop a precise rehabilitation training plan for him.
[0060] II. System Construction and Data Synchronization Acquisition
[0061] Staff had Mr. Zhang sit on the isokinetic muscle strength testing system, fixing his torso and thigh, and tested his right (affected) knee joint for knee extension and flexion at angular velocities of 60° / s and 180° / s, respectively. The isokinetic muscle strength testing system automatically recorded and calculated the peak torque of the quadriceps femoris muscle. Total work Torque acceleration energy and the peak torque ratio of the hamstrings to the quadriceps. Similarly, the strength indices of the major muscle groups in the hip and ankle joints are tested and obtained, which together constitute the lower limb strength index vector F.
[0062] Simultaneously, sEMG electrodes were attached to the surface of target muscles in Zhang's right leg, including the rectus femoris (quadriceps), biceps femoris (hamstrings), tibialis anterior, and gastrocnemius muscles. Optical reflective markers were also attached to major bony landmarks in his lower limbs.
[0063] Subsequently, Zhang conducted a walking test on the treadmill. The optical motion capture system recorded the three-dimensional coordinates of the marker points during his walk, thereby calculating gait parameter vectors G such as stride length, stride speed, cadence, and maximum knee flexion angle. The sEMG system simultaneously recorded the electrical signals of various muscles during the walking process.
[0064] Before the start of the entire test, the synchronization control module sends out a spike pulse signal, which is simultaneously recorded by the isokinetic muscle strength system, sEMG system and motion capture system, giving all subsequent data streams a unified timestamp and achieving time synchronization of all data.
[0065] III. Data Processing and Anomaly Attribution
[0066] The data processing and analysis module first aligns all data in time based on a synchronization signal.
[0067] This module analyzes sEMG signals and calculates the activation intensity (root mean square amplitude RMS, normalized to %MVC) and activation timing (onset / offset time points) of each muscle during the gait cycle.
[0068] Anomaly attribution analysis was performed by comparing sEMG timing with joint kinematic timing.
[0069] Analysis revealed that during the mid-stance phase of gait (when the quadriceps are needed to stabilize the knee joint), Zhang's rectus femoris sEMG activation intensity was significantly lower than that of the healthy side (<%MVC), and the activation onset time was significantly delayed. However, at the end of the swing phase, the hamstring sEMG activity persisted excessively, exhibiting excessive synergistic contraction with the tibialis anterior. This preliminarily suggests that his gait problems are related to quadriceps weakness and delayed activation, as well as impaired coordination between the hamstrings and the tibialis anterior.
[0070] Simultaneously, the Pearson correlation coefficient between lower limb strength indicators and gait parameters was calculated. Preliminary findings revealed that Zhang's quadriceps peak torque... With pace It shows a moderate positive correlation (r=0.65).
[0071] IV. Core Relationship Modeling and Precise Diagnosis
[0072] To further quantify, the system invokes the muscle-step association index (GMLI) model. Taking the quadriceps femoris as an example, its... :
[0073]
[0074] in, The weights are set to 1.2 for step speed and 1 for other parameters in this example. The correlation coefficients between quadriceps PT and various gait parameters. These are the values of Zhang's gait parameters after normalization to the health norm.
[0075] The calculation results showed that the GMLI value of his quadriceps was significantly higher than that of other muscle groups. This indicates that quadriceps function is currently the most critical factor limiting Zhang's gait performance and should be the primary target for rehabilitation training.
[0076] Run the pre-trained machine learning model.
[0077] The forward prediction model (using the random forest algorithm as an example) inputs Zhang's current strength index F and predicts that if his quadriceps strength increases by 20%, his walking speed has an 85% probability of increasing by 0.15 m / s. The backward inference model (using the gradient boosting tree algorithm as an example) inputs his abnormal gait parameter G and outputs a diagnosis result with a 78% probability of "quadriceps weakness" and a 65% probability of "poor hamstring coordination," which corroborates the results of other analyses.
[0078] V. Output Results and Clinical Decisions
[0079] A comprehensive report was generated, concluding that the main cause of the patient's gait abnormality was insufficient strength and delayed activation of the right quadriceps femoris muscle, while the secondary cause was excessive synergistic contraction of the antagonist muscle.
[0080] Based on this, the original conventional plan of "comprehensively strengthening the lower limbs" was abandoned, and a targeted rehabilitation plan was formulated for Zhang: focusing on isokinetic concentric training and explosive power training of the right quadriceps (to address TAE deficiency); combining biofeedback to conduct active triggering training of the quadriceps in the mid-gait support phase (to correct activation sequence); and conducting relaxation and coordination training of the hamstrings and tibialis anterior muscles.
[0081] Overall, through this implementation, the system of the present invention integrates multimodal data synchronous acquisition, refined anomaly attribution, statistical correlation analysis, innovative GMLI index calculation, and intelligent machine learning prediction / diagnosis into a complete "measurement-analysis-diagnosis-decision" closed loop, ultimately achieving accurate tracing of the causes of complex lower limb dysfunction and personalized rehabilitation guidance.
[0082] In this invention, it should be noted that,
[0083] First, an explanation of the "interrelationship calculation between the three data points".
[0084] The "association calculation" in this invention is a systematic analysis process, the specific methods of which are clearly described in the specification and claims, and mainly include the following two aspects:
[0085] Statistical correlation analysis (preliminary association): As described above, the association calculation (or analysis) refers to "calculating the correlation coefficient between lower limb strength indicators and gait parameters." This is a basic association calculation method that reveals the linear relationship between variables. For example, calculating the Pearson correlation coefficient between the "peak torque" of the quadriceps and "gait speed" quantifies the degree of influence of muscle strength on gait speed.
[0086] Nonlinear mapping based on machine learning models (deep association modeling): As mentioned earlier, "the data processing and analysis module is configured to build and train machine learning models to achieve the association modeling." This represents a more advanced level of association computation. Specifically, it includes a forward prediction model and a backward inference model. The forward prediction model learns the functional relationship from "causes" (lower limb strength indicators, electromyographic activity indicators) to "results" (gait parameters) to predict gait performance. The backward inference model learns the functional relationship from "results" (gait parameters) and some "causes" (electromyographic activity indicators) to infer another part of the "causes" (lower limb strength indicators), used to assist in etiological diagnosis.
[0087] Therefore, in this invention, "association computation" does not refer to a single algorithm, but rather encompasses a series of technical means aimed at establishing quantitative relationships between multimodal data, ranging from simple correlation coefficient calculations to complex machine learning model construction. The "core association modeling" mentioned above is a summary of this deep computation process.
[0088] Second, an explanation of the "logical relationship between the muscle-step association index (GMLI) model and the data".
[0089] The logical relationships of the GMLI model are precisely defined by its calculation formula, which has been described above: Each term in the formula clearly defines its logical input relationship with the three types of data:
[0090] The correlation coefficient is essentially the result of the "correlation calculation" described in the first point. It comes directly from the correlation analysis between the "lower limb strength index" (of the i-th muscle) and the "gait parameter" (of the j-th muscle), and is the core input of the model.
[0091] (Normalized value), as mentioned above, is obtained by dividing the subject's actual gait parameter values by the norm values of healthy individuals. This introduces the clinical context of the subject's degree of gait abnormality.
[0092] (Weighting Factor): Represents the clinical importance weight of different time-phase parameters.
[0093] Therefore, the logical relationship of the GMLI model is: it acts as a comprehensive evaluator, receiving results from "associative computation" ( ) and clinically standardized gait data ( This method uses a weighted summation approach to output a single, quantifiable index to evaluate the "overall contribution" or "influence weight" of a particular muscle to overall gait performance. Its design aims to address the difficulty of directly comparing and drawing conclusions from multiple datasets, condensing complex multivariate relationships into an intuitive clinical decision indicator.
[0094] Third, an explanation of "how the technical solution was ultimately evaluated".
[0095] The final evaluation conclusion of the technical solution of this invention is derived by logically integrating all the aforementioned analyses and calculations. The specific implementation examples provided above clearly demonstrate the complete logical chain from data to conclusions:
[0096] Abnormal Attribution (Locating the Nature of the Problem): As mentioned earlier, the system first performs "gait abnormality attribution analysis" by comparing the temporal relationship between "electromyography (EMG) indicators" and "lower limb kinematic data" to determine whether the abnormality stems from "muscle weakness," "incorrect activation timing," or "excessive synergistic contraction." Specifically, in a concrete case, during the mid-stance of gait (when the quadriceps are needed to stabilize the knee joint), Mr. Zhang's rectus femoris sEMG activation intensity was significantly lower than that of the healthy side (<%MVC), and the activation onset time was significantly delayed. At the end of the swing phase, his hamstring sEMG activity persisted excessively, exhibiting excessive synergistic contraction with the tibialis anterior. This initially indicates that his gait problem is related to quadriceps weakness and delayed activation, as well as impaired coordination between the hamstrings and the tibialis anterior. This completes the qualitative assessment of the problem's nature.
[0097] Key Target Localization (Locating the Source of the Problem): Next, the system invokes the GMLI model and the machine learning model. By calculating and comparing the GMLI values of different muscles (see "The GMLI value of its quadriceps is significantly higher than that of other muscle groups" in the previous text), or by using the reverse inference model to output the probability of weakness in different muscle groups (see "The probability of the diagnosis result being 'quadriceps weakness' is 78%" in the previous text), the primary and secondary responsible muscle groups causing gait abnormalities are quantitatively located.
[0098] Generate assessment conclusions (output conclusions): Finally, the system integrates all the above analyses to generate a structured assessment report. The conclusion format of this report is clearly exemplified above: "The main cause of the patient's gait abnormality is insufficient strength and delayed activation timing of the right quadriceps femoris muscle, and the secondary cause is excessive synergistic contraction of the antagonist muscle."
[0099] This conclusion is not merely an isolated list of numbers, but rather the final logical integration of the aforementioned multimodal data correlation calculation, GMLI index analysis, and attribution judgment. It directly answers the core question of "how to assess" and provides a clear target for clinical intervention.
[0100] According to a second aspect of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the data processing and analysis module of a system for assessing the influence of a patient's lower limb strength and gait as described in any of the technical solutions of the first aspect of the present invention.
[0101] In this embodiment, the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), a register, a hard disk, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof, or any other form of computer-readable storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in an application-specific integrated circuit (ASIC). In embodiments of the present invention, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.
[0102] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A system for assessing the impact of lower limb strength and gait on a patient, characterized in that, include: The data acquisition module includes an isokinetic muscle strength testing unit, a surface electromyography signal acquisition unit, and an optical motion capture unit, which are used to acquire the subject's lower limb muscle strength data, lower limb muscle electrophysiological data, and lower limb kinematic data, respectively. A synchronization control module is communicatively connected to the data acquisition module and is used to send a synchronization signal to the data acquisition module so that the muscle strength data, muscle electrophysiological data and kinematic data have a unified time reference. The data processing and analysis module, which is communicatively connected to the data acquisition module and the synchronization control module, is configured as follows: Receive and time-align the lower limb muscle strength data, the lower limb muscle electrophysiological data, and the lower limb kinematic data; Lower limb strength indices, electromyographic activity indices, and gait parameters were extracted from the aligned data. Based on the extracted indicators and parameters, a correlation model is established between the lower limb strength indicators, the electromyographic activity indicators and the gait parameters, and the evaluation results are output. The data processing and analysis module is configured to perform correlation analysis by calculating the correlation coefficient between the lower limb strength index and the gait parameters; The data processing and analysis module is further configured to calculate a comprehensive muscle-gait correlation index to quantify the contribution of a specific muscle to overall gait performance. The formula for calculating the muscle-gait correlation index is as follows: In the formula, Indicates the first Myostep correlation index of a muscle group Indicates the pre-set number Weighting factors for each gait parameter, Indicates the first Core strength indicators of bulky muscles and the first The correlation coefficients between the gait parameters Indicates the first Normalized values of each gait parameter; The normalized value It was obtained by dividing the actual gait parameter values of the subjects by the norm values of healthy individuals; The data processing and analysis module is configured to build and train a machine learning model to achieve the association modeling, the machine learning model including a forward prediction model and a backward inference model; The positive prediction model takes the extracted lower limb strength indicators and electromyographic activity indicators as inputs and gait parameters as outputs to predict gait performance; the reverse inference model takes the extracted gait parameters and electromyographic activity indicators as inputs and outputs the probability diagnosis of lower limb strength indicators or weak muscle groups to assist in etiological diagnosis.
2. The system for assessing the impact of lower limb strength and gait on a patient according to claim 1, characterized in that, The data processing and analysis module is configured to extract lower limb strength indicators from the lower limb muscle strength data, including: peak torque, total work done, torque acceleration energy, and peak torque ratio of one or more periarticular muscle groups.
3. The system for assessing the impact of lower limb strength and gait on a patient according to claim 1, characterized in that, The data processing and analysis module is configured to extract electromyographic activity indicators and gait parameters from the lower limb muscle electrophysiological data and the lower limb kinematic data, including: activation intensity, activation sequence, stride length, stride speed, stride frequency and joint angle of each target muscle in the gait cycle.
4. The system for assessing the impact of lower limb strength and gait on a patient according to claim 3, characterized in that, The data processing and analysis module is further configured to perform gait abnormality attribution analysis by comparing the temporal relationship between the electromyographic activity index and the lower limb kinematic data. The attribution analysis includes determining whether the abnormality is caused by muscle weakness, incorrect activation timing, or excessive synergistic contraction.
5. The system for assessing the impact of lower limb strength and gait on a patient according to claim 1, characterized in that, The machine learning model employs one or more algorithms, including random forest, gradient boosting tree, or neural network.
6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it performs the functions of the data processing and analysis module of the system for assessing the impact of a patient's lower limb strength and gait as described in any one of claims 1-5.