CN-121647682-B - System for evaluating patient lower limb strength and walking gait influence

CN121647682BCN 121647682 BCN121647682 BCN 121647682BCN-121647682-B

Abstract

The invention provides a system for evaluating the lower limb strength and walking gait influence of a patient, and relates to the technical field of gait evaluation. The data acquisition module comprises a constant-speed muscle strength test unit, a surface electromyographic signal acquisition unit and an optical motion capture unit, the synchronous control module is in communication connection with the data acquisition module, the data processing and analyzing module is configured to receive and time align lower limb muscle strength data, lower limb muscle electrophysiological data and lower limb kinematics data, extract lower limb strength indexes, electromyographic activity indexes and gait parameters from the aligned data, establish a correlation model between the lower limb strength indexes, electromyographic activity indexes and gait parameters based on the extracted indexes and parameters, and output an evaluation result. The invention can produce remarkable effects from data island to association fusion, subjective experience to objective quantification and description to revealing etiology.

Inventors

HUANG CUIPING
Cai Lingqin
LI XIAOKAI
XU TINGYUAN
Yang Xiongmei
GAO HUIMIN

Assignees

中国人民解放军西部战区总医院

Dates

Publication Date: 20260512
Application Date: 20260206

Claims (6)

1. A system for assessing the effects of patient lower limb strength and gait, comprising: the data acquisition module comprises a constant-speed muscle strength test unit, a surface electromyographic signal acquisition unit and an optical motion capture unit, and is used for acquiring lower limb muscle strength data, lower limb muscle electrophysiological data and lower limb kinematics data of a subject respectively; The synchronous control module is in communication connection with the data acquisition module and is used for sending synchronous signals to the data acquisition module so as to enable the muscle strength data, the muscle electrophysiology data and the kinematic data to have a unified time reference; the data processing and analyzing module is in communication connection with the data acquisition module and the synchronous control module and is configured to: receiving and time-aligning the lower limb muscle strength data, the lower limb muscle electrophysiology data, and the lower limb kinematics data; Extracting lower limb strength indexes, myoelectric activity indexes and gait parameters from the aligned data; Based on the extracted indexes and parameters, establishing a correlation model among the lower limb strength indexes, the myoelectric activity indexes and the gait parameters, and outputting an evaluation result; the data processing and analyzing module is configured to perform association analysis by calculating a correlation coefficient between the lower limb strength index and the gait parameter; the data processing and analysis module is further configured to calculate a comprehensive myo-step association index to quantify the contribution of a particular muscle to overall gait performance, the myo-step association index calculated by: In the formula (I), in the formula (II), Represent the first Muscle-step association index of a block muscle, Indicating the preset first The weight factors of the individual gait parameters, Represent the first Core strength index of block muscle The correlation coefficient between the individual gait parameters, Represent the first Normalized values of individual gait parameters; the normalized value The actual gait parameter value of the subject is obtained by dividing the actual gait parameter value of the subject by the normal model value of the healthy population; The data processing and analysis module is configured to construct and train a machine learning model to implement the associative modeling, the machine learning model including a forward predictive model and a reverse inference model; The forward prediction model takes the extracted lower limb strength index and myoelectric activity index as input and takes gait parameters as output for predicting gait expression, and the reverse inference model takes the extracted gait parameters and myoelectric activity index as input and takes the probability diagnosis of lower limb strength index or muscle weakness group as output for assisting etiology diagnosis.
2. The system for assessing the effects of patient lower limb strength and gait of claim 1, wherein the data processing and analysis module is configured to extract lower limb strength indicators from the lower limb muscle strength data including peak moment, total work, moment acceleration energy and peak moment ratio of active and antagonistic muscles for one or more periarticular muscle groups.
3. The system for assessing the effects of patient lower limb strength and gait of claim 1, wherein the data processing and analysis module is configured to extract myoelectric activity indicators and gait parameters from the lower limb muscle electrophysiology data and the lower limb kinematics data including activation strength, activation timing, and step size, pace, stride frequency and joint angle of each target muscle in the gait cycle.
4. The system for assessing the effects of patient lower limb strength and gait of claim 3, wherein the data processing and analysis module is further configured to conduct gait anomaly attribution analysis by comparing the myoelectric activity index with the temporal relationship of the lower limb kinematics data, the attribution analysis comprising determining that the anomaly is due to muscle weakness, activation timing errors or synergetic over-contraction.
5. The system for assessing the effects of patient lower limb strength and gait of claim 1, wherein the machine learning model employs an algorithm comprising one or more of a random forest, gradient lift tree or neural network.
6. A computer readable storage medium, having stored thereon a computer program, which when executed by a processor, performs the function of the data processing and analysis module of the system for assessing the effects of patient lower limb strength and gait as claimed in any one of claims 1 to 5.

Description

System for evaluating patient lower limb strength and walking gait influence Technical Field The invention relates to the technical field of gait evaluation, in particular to a system for evaluating the influence of lower limb strength and walking gait of a patient. Background At present, traditional methods such as manual muscle strength test (MMT) and visual gait observation are generally adopted for evaluating the functions of lower limbs in clinic, and the methods have the defects of strong subjectivity and insufficient precision. Although there are objective quantification techniques such as isokinetic muscle strength test, surface myoelectricity (sEMG) analysis, and optical motion capture, the existing solutions are often used in isolation, and only can provide isolated muscle strength or gait parameter data, so that synchronous measurement and correlation analysis cannot be realized. This results in an inability to accurately reveal causal links between gait abnormalities and specific muscle group hypo-strength or nerve control dysfunction, thus lacking in accuracy in clinical diagnosis, and often blindness in the formulation of rehabilitation training protocols. Disclosure of Invention In order to solve the problems in the related art, the present invention provides a system for evaluating the effects of patient lower limb strength and gait. In order to achieve the above purpose, the technical scheme adopted by the invention comprises the following steps: according to a first aspect of the present invention there is provided a system for assessing the effects of patient lower limb strength and gait, comprising: the data acquisition module comprises a constant-speed muscle strength test unit, a surface electromyographic signal acquisition unit and an optical motion capture unit, and is used for acquiring lower limb muscle strength data, lower limb muscle electrophysiological data and lower limb kinematics data of a subject respectively; The synchronous control module is in communication connection with the data acquisition module and is used for sending synchronous signals to the data acquisition module so as to enable the muscle strength data, the muscle electrophysiology data and the kinematic data to have a unified time reference; the data processing and analyzing module is in communication connection with the data acquisition module and the synchronous control module and is configured to: receiving and time-aligning the lower limb muscle strength data, the lower limb muscle electrophysiology data, and the lower limb kinematics data; Extracting lower limb strength indexes, myoelectric activity indexes and gait parameters from the aligned data; Based on the extracted indexes and parameters, establishing a correlation model among the lower limb strength indexes, the myoelectric activity indexes and the gait parameters, and outputting an evaluation result. Optionally, the data processing and analysis module is configured to extract lower limb strength metrics from the lower limb muscle strength data including peak moment, total work, moment acceleration energy, and peak moment ratio of active to antagonistic muscles for one or more periarticular muscle groups. Optionally, the data processing and analyzing module is configured to extract myoelectric activity indexes and gait parameters from the lower limb muscle electrophysiology data and the lower limb kinematics data, wherein the myoelectric activity indexes and gait parameters comprise the activation intensity, activation time sequence, step length, pace speed, step frequency and joint angle of each target muscle in a gait cycle. Optionally, the data processing and analysis module is further configured to perform gait abnormality attribution analysis by comparing the myoelectric activity index with the time series relationship of the lower limb kinematics data, the attribution analysis comprising determining that the abnormality is due to muscle weakness, activation timing errors or synergetic over-contraction. Optionally, the data processing and analysis module is configured to perform a correlation analysis by calculating a correlation coefficient between the lower limb strength index and the gait parameter. Optionally, the data processing and analysis module is further configured to calculate a comprehensive myo-step association index to quantify the contribution of a particular muscle to overall gait performance, the myo-step association index calculated by: In the formula, Represent the firstMuscle-step association index of a block muscle,Indicating the preset firstThe weight factors of the individual gait parameters,Represent the firstCore strength index of block muscleThe correlation coefficient between the individual gait parameters,Represent the firstNormalized values of individual gait parameters. Optionally, the normalized valueBy dividing the actual gait parameter value of the subject by the normal model value of the healthy population.