Patient gait analysis method and system based on motion detection data

Abstract

The invention provides a patient gait analysis method and system based on motion detection data, and relates to the technical field of gait analysis. The method comprises the following steps: acquiring to-be-analyzed motion detection data and electromyographic signal data of a patient, extracting motion state period data corresponding to a plurality of target gait periods, and performing gait coordination sliding window detection on the plurality of groups of motion state period data, generating coordination scores respectively corresponding to the plurality of reference motion state sequences, and determining a plurality of gait coordination abnormal periods; extracting abnormal motion state data and reference motion state data of each gait coordination abnormal period, and generating motion disassembly data corresponding to a plurality of local motion stages; and constructing a local motion state sequence of each local motion stage, and carrying out gait local coordination detection on the plurality of gait coordination abnormity periods to obtain a target gait abnormity detection result of the patient. According to the invention, high-precision detection of tiny anomalies existing in the gait of the patient is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of gait analysis, and in particular to a patient gait analysis method and system based on motion detection data. Background Art

[0002] During the rehabilitation process of stroke patients, gait analysis is one of the important means to evaluate and guide rehabilitation treatment. In the later stage of the rehabilitation stage, the gait of the hemiplegic side and the healthy side of the patient gradually tend to be consistent, and the overall gait balance may appear relatively normal. However, although the gait appears to have recovered on the surface, there may still be slight differences or abnormalities between the hemiplegic side and the healthy side. These slight abnormalities are generally difficult to observe from the analysis of the overall gait balance, but these slight differences may have an important impact on the patient's gait stability and long-term rehabilitation effect. Identifying subtle details that may hide rehabilitation obstacles or future gait function problems, early detection of these slight gait abnormalities and intervention can provide patients with more personalized rehabilitation feedback and training programs, thereby improving the patient's gait rehabilitation effect. Summary of the invention

[0003] In view of this, the present invention proposes a patient gait analysis method and system based on motion detection data. By collecting and analyzing relevant detection data on the patient's motion state and electromyographic state, the slight abnormalities that may exist in the patient's gait are mined with high precision, thereby assisting rehabilitation physicians to adjust treatment strategies in time according to slight gait abnormalities, thereby improving the patient's gait rehabilitation effect.

[0004] A first aspect of the present invention provides a method for analyzing a patient's gait based on motion detection data, comprising: Acquire the patient's motion detection data and electromyographic signal data to be analyzed, and extract motion state cycle data corresponding to a plurality of target gait cycles from the motion detection data and electromyographic signal data to be analyzed, wherein each set of motion state cycle data includes the patient's healthy side state data and the affected side state data; Extracting a reference motion state sequence and a target motion state sequence from each set of motion state periodic data, and constructing a reference state matrix containing a plurality of reference motion state sequences and a target state matrix containing a plurality of target motion state sequences; Performing gait coordination sliding window detection on multiple groups of motion state cycle data, including generating a global motion feature sequence in each sliding window based on a target state matrix, performing gait coordination detection on multiple reference motion state sequences in the sliding window according to the global motion feature sequence, generating coordination scores corresponding to the multiple reference motion state sequences, and determining multiple gait coordination abnormality cycles according to the coordination scores; Extracting abnormal motion state data and reference motion state data of each gait coordination abnormal cycle from multiple sets of motion state cycle data, performing motion phase segmentation on the multiple sets of abnormal motion state data and reference motion state data, and obtaining motion disassembly data corresponding to the abnormal motion state data and the reference motion state data in multiple local motion phases; Multiple motion state parameters of each group of motion decomposition data are extracted, and a local motion state sequence of each local motion stage is constructed. Based on the multiple local motion state sequences, local gait coordination detection is performed on multiple gait coordination abnormality cycles to obtain the patient's target gait abnormality detection result.

[0005] Preferably, performing gait coordination sliding window detection on multiple sets of motion state cycle data includes: Through the sliding window, the reference state matrix and the target state matrix are traversed in time step association to generate coordination scores corresponding to multiple reference motion state sequences; Wherein, for a plurality of reference motion state sequences and a target motion state sequence in any sliding window, a global motion feature sequence in the sliding window is generated according to the plurality of reference motion state sequences, and similarity distances between the plurality of reference motion state sequences and the global motion feature sequence are calculated respectively; The standard deviation of multiple similarity distances is calculated to obtain the local gait correlation parameter, and the multiple target motion state sequences are subjected to stationary analysis to obtain the fluctuation parameter. The local gait correlation parameter is processed according to the fluctuation parameter to generate an adaptive correction parameter. The similarity distance between the reference motion state sequence at the center of the sliding window and the global motion feature sequence is corrected according to the adaptive correction parameter to obtain the coordination score of the reference motion state sequence at the center of the sliding window. A plurality of reference motion state sequences are screened out by using a coordination score threshold, and the target gait cycles corresponding to the screened plurality of reference motion state sequences are recorded as gait coordination abnormality cycles.

[0006] Preferably, performing gait local coordination detection on multiple gait coordination abnormality cycles based on multiple local motion state sequences includes: For the reference motion state data of the gait coordination abnormality cycle, including the healthy side state data corresponding to multiple target gait cycles, a local state matrix corresponding to each group of healthy side state data is constructed according to multiple local motion state sequences; A plurality of local state matrices are fused to generate a phase change state matrix of a gait coordination abnormality cycle, and a correction state matrix of each group of healthy side state data is determined based on the phase change state matrix; For the abnormal motion state data of the gait coordination abnormality cycle, including the affected side state data corresponding to multiple target gait cycles, a stage coordination state matrix corresponding to each group of the affected side state data is constructed according to multiple local motion state sequences; According to the correlation between each group of abnormal motion state data and the reference motion state data, the collaborative state matrices of multiple stages are respectively corrected based on multiple correction state matrices to obtain collaborative state correction matrices of multiple stages; The local gait coordination detection is performed on the gait coordination abnormality cycle according to the multi-stage coordination state correction matrix, including local stage coordination analysis on the multi-stage coordination state correction matrix to generate coordination feature parameters of each local motion stage, and based on the coordination feature parameters and the stage change state matrix of the gait coordination abnormality cycle, the local gait coordination detection is performed on the multi-stage coordination state correction matrix of the gait coordination abnormality cycle to obtain the local gait abnormality result of each gait coordination abnormality cycle.

[0007] Preferably, the method of performing gait local coordination detection on the gait coordination abnormality period according to the multiple stage collaborative state correction matrices further includes: Performing local phase coordination analysis on multiple phase coordination state correction matrices, extracting multiple local phase state sequences of each local motion phase from the multiple phase coordination state correction matrices, performing autocorrelation analysis on the multiple local phase state sequences of each local motion phase, and calculating coordination feature parameters of the multiple local phase state sequences of each local motion phase; According to the phase change state matrix, a similarity analysis based on the local motion phase is performed on the multiple phase collaborative state correction matrices of the gait coordination abnormality cycle, including calculating the similarity parameters of each local motion phase in the phase collaborative state correction matrix, fusing the similarity parameters of the multiple local motion phases according to the multiple collaborative feature parameters, obtaining the local phase similarity parameters of the phase collaborative state correction matrix, and generating the similarity analysis results of the multiple phase collaborative state correction matrices of the gait coordination abnormality cycle; According to the similarity analysis results of the collaborative state correction matrices of multiple stages, a gait local coordination feature detection vector of the gait coordination abnormality period is generated; according to the multiple local state matrices of the gait coordination abnormality period, a gait local coordination feature fluctuation vector of the gait coordination abnormality period is generated; based on the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector, a local gait abnormality result of the gait coordination abnormality period is generated.

[0008] Preferably, generating a local gait abnormality result of a gait coordination abnormality period based on the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector includes: Calculate the distance parameter between the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector. If the distance parameter between the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector is less than a preset distance threshold, then it is recorded that there is no local gait abnormality in the gait coordination abnormality period. Otherwise, it is recorded that there is local gait abnormality in the gait coordination abnormality period, and the abnormal local motion stage is determined according to the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector, including determining the local stage coordination threshold of the gait coordination abnormality period according to the gait local coordination feature fluctuation vector, determining the coordination difference value of each local motion stage of the gait coordination abnormality period according to the local stage similarity parameter of the stage coordination state correction matrix, judging whether the coordination difference value of the local motion stage is greater than the local stage coordination threshold of the gait coordination abnormality period, recording the local motion stage whose coordination difference value is greater than the local stage coordination threshold of the gait coordination abnormality period as the abnormal local motion stage, generating the local gait abnormality result of the gait coordination abnormality period, and generating the target gait abnormality detection result of the patient according to the local gait abnormality results of multiple gait coordination abnormality periods.

[0009] Preferably, for the gait local coordination characteristic fluctuation vector, it also includes: By calculating the similarity parameters between multiple local state matrices of the gait coordination abnormality cycle and the phase change state matrices of the gait coordination abnormality cycle, a gait local coordination characteristic fluctuation vector is constructed according to the multiple similarity parameters.

[0010] A second aspect of the present invention provides a patient gait analysis system based on motion detection data, which is used to implement the above-mentioned patient gait analysis method based on motion detection data, comprising: A data acquisition module is used to obtain the patient's motion detection data and electromyographic signal data to be analyzed, and extract motion state cycle data corresponding to a plurality of target gait cycles from the motion detection data and electromyographic signal data to be analyzed, wherein each set of motion state cycle data includes the patient's healthy side state data and the affected side state data; A feature extraction module is used to extract a reference motion state sequence and a target motion state sequence of each set of motion state periodic data, and construct a reference state matrix containing multiple reference motion state sequences and a target state matrix containing multiple target motion state sequences; A coordinated sliding window detection module is used to perform gait coordination sliding window detection on multiple sets of motion state cycle data, including generating a global motion feature sequence in each sliding window based on a target state matrix, performing gait coordination detection on multiple reference motion state sequences in the sliding window according to the global motion feature sequence, generating coordination scores corresponding to the multiple reference motion state sequences, and determining multiple gait coordination abnormality cycles according to the coordination scores; A gait coordination anomaly analysis module is used to extract abnormal motion state data and reference motion state data of each gait coordination anomaly cycle from multiple sets of motion state cycle data, perform motion phase segmentation on multiple sets of abnormal motion state data and reference motion state data, and obtain motion disassembly data corresponding to the abnormal motion state data and reference motion state data in multiple local motion phases; The gait local coordination detection module is used to extract multiple motion state parameters from each set of motion decomposition data, construct a local motion state sequence for each local motion stage, perform gait local coordination detection on multiple gait coordination abnormality cycles based on multiple local motion state sequences, and obtain the patient's target gait abnormality detection result.

[0011] The present invention has the following beneficial effects: The present invention performs preliminary abnormality analysis based on the gait cycle on the patient's motion detection data and electromyographic signal data, and analyzes the data in multiple gait cycles based on the gait coordination sliding window detection technology, so as to determine multiple cycles with gait coordination abnormalities in the data to be analyzed from the perspective of cycle coordination, and further decomposes the gait cycle into stages. For the multiple abnormal cycles determined from the perspective of the overall motion state of the gait cycle, analysis is performed from multiple motion decomposition stages, and the synergistic correlation between different local motion stages is combined. The local coordination characteristics of the gait of the abnormal cycle in the adjacent cycle are considered, and an in-depth analysis is performed on whether there is abnormality in the local coordination of the patient's gait. The possible minor abnormalities in the patient's gait are detected with high precision, which is convenient for medical staff to provide patients with personalized rehabilitation training programs and improve the rehabilitation effect of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 The present invention is a flowchart of a method for analyzing patient gait based on motion detection data provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0013] In order to make those skilled in the art better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0014] like Figure 1 As shown, one embodiment of the present invention provides a patient gait analysis method based on motion detection data, which accurately analyzes the gait-related detection data of stroke patients in the late stage of rehabilitation, identifies gait deviations from different angles to mine subtle gait abnormalities, and helps clinical personnel accurately evaluate the patient's gait recovery, so as to provide patients with personalized rehabilitation training programs. Specifically, the method includes the following steps: Step S1, obtaining the motion detection data and electromyographic signal data to be analyzed of the patient, and extracting motion state cycle data corresponding to a plurality of target gait cycles from the motion detection data and electromyographic signal data to be analyzed.

[0015] Among them, the patient's motion detection data can be collected through wearable motion detection devices such as inertial measurement units, pressure sensors, etc. to reflect the patient's motion state at different times during walking, and the electromyographic signal data of the patient during walking can be collected through an electromyographic signal acquisition instrument to reflect the patient's electromyographic activity level. After the collected raw data is cleaned, the data can be segmented according to the target gait cycle. The target gait cycle is used to indicate the patient's periodically repeated motion pattern. The process starting from one foot landing, through the support period, the swing period, and then ending with the other foot landing is regarded as a cycle. The motion detection data and electromyographic signal data to be analyzed are segmented according to the target gait cycle, so as to obtain the motion state cycle data corresponding to each target gait cycle, which includes the patient's healthy side state data and the affected side state data, that is, the motion detection corresponding to the healthy side and the affected side and the electromyographic activity detection corresponding to the data, so as to analyze the patient's gait characteristics from the perspective of kinematics and electromyography.

[0016] Step S2: extract the reference motion state sequence and the target motion state sequence of each set of motion state periodic data, and construct a reference state matrix containing multiple reference motion state sequences and a target state matrix containing multiple target motion state sequences.

[0017] Among them, the reference motion state sequence and the target motion state sequence represent the patient's gait level on the healthy side and the affected side in one gait cycle, respectively, which include parameters related to the key changes in motion state and parameters related to the key changes in electromyographic state in a gait cycle, such as motion state parameters such as step duration, stride, support time, swing time, and electromyographic state parameters such as electromyographic activation time and electromyographic amplitude. The reference motion state sequences and target motion state sequences corresponding to multiple target gait cycles are spliced ​​to generate a reference state matrix representing the overall gait level of the healthy side of the patient during the entire movement process, and a target state matrix of the overall gait level of the affected side.

[0018] Step S3: Perform gait coordination sliding window detection on multiple groups of motion state cycle data, generate coordination scores corresponding to multiple reference motion state sequences, and determine multiple gait coordination abnormality cycles according to the coordination scores.

[0019] Among them, for the reference state matrix and the target state matrix, a sliding window detection method is used to realize gait coordination sliding window detection of multiple sets of motion state cycle data. In this process, based on the time step alignment method, for multiple reference motion state sequences and target motion state sequences under the same sliding window, a global motion feature sequence in the sliding window is generated based on the target state matrix to reflect the motion pattern in the entire gait cycle. Then, gait coordination detection is performed on the multiple reference motion state sequences in the sliding window according to the global motion feature sequence, and the coordination between the target motion state sequence and the reference motion state sequence is evaluated. Finally, the coordination scores corresponding to the multiple reference motion state sequences are calculated to quantify the gait coordination degree of each reference motion state sequence and the target motion state sequence, so as to preliminarily determine multiple gait coordination abnormal cycles, that is, in some target gait cycles, the overall gait level performance of the patient is inconsistent or uncoordinated with the healthy side, and a more detailed analysis is needed to determine the specific abnormal situation.

[0020] Step S4, extracting abnormal motion state data and reference motion state data of each gait coordination abnormal period from multiple sets of motion state cycle data, performing motion stage segmentation on the multiple sets of abnormal motion state data and reference motion state data, and obtaining motion decomposition data corresponding to the abnormal motion state data and the reference motion state data in multiple local motion stages.

[0021] Among them, after identifying the abnormal gait coordination cycle, the abnormal motion state data and reference motion state data of each abnormal gait coordination cycle are extracted from the multiple groups of motion state cycle data obtained by previous segmentation. The data extraction process is centered on the abnormal gait coordination cycle, and the data corresponding to the affected side and the healthy side in multiple adjacent cycles are extracted, such as data within three or five gait cycles, to generate abnormal motion state data and reference motion state data of the abnormal gait coordination cycle, and then the motion stage segmentation is performed for these data used for further analysis, for example, one gait cycle is further decomposed into multiple local motion stages. A gait cycle can be roughly divided into the support phase and the swing phase. The support phase refers to the process from one foot touching the ground to the other foot starting to swing. The swing phase is the process from one foot leaving the ground and going through a series of swinging movements until it touches the ground again. The two major phases can be further divided into the initial stage, the middle stage, and the final stage. Through this motion decomposition method, for each local motion stage, the motion decomposition data corresponding to the stage is extracted, that is, the data related to the patient's motion state and electromyographic state in the stage, and the abnormal motion state data and reference motion state data of the gait coordination abnormality cycle are decomposed and segmented. It is convenient to analyze the motion characteristics of each local motion stage, and then identify the abnormal performance in the specific stage according to the correlation characteristics between different local motion stages.

[0022] Step S5, extract multiple motion state parameters from each group of motion decomposition data, construct a local motion state sequence for each local motion stage, perform gait local coordination detection on multiple gait coordination abnormality cycles based on the multiple local motion state sequences, and obtain the patient's target gait abnormality detection result.

[0023] Among them, for multiple groups of motion disassembly data about different local motion stages, more detailed motion state parameters are further extracted, such as the angle parameters of different joints in the motion detection data, the duration of the local motion stage, and the electromyographic state parameters corresponding to the specific key muscle parts used to evaluate the motion state in the electromyographic signal data, etc., to characterize the patient's detailed motion state in each local motion stage in detail. Therefore, the local motion state sequence of the local motion stage is constructed according to the multiple motion state parameters of each local motion stage, and finally the affected side is analyzed by combining the association between different local motion states with the data of the healthy side, and the multiple gait coordination abnormality cycles determined in the above steps are subjected to gait local coordination detection based on the changes in the coordination association between different stages, so as to identify the subtle differences between the affected side and the healthy side in each local motion stage. These subtle abnormal changes in the later stage of rehabilitation are crucial to the long-term rehabilitation of patients. The target gait abnormality detection results finally generated will provide important data references in the process of providing patients with personalized rehabilitation training programs.

[0024] As one implementation process, in the above step S3, gait coordination sliding window detection is performed on multiple sets of motion state cycle data, specifically including: The reference state matrix and the target state matrix are traversed in time step association through a sliding window to generate coordination scores corresponding to multiple reference motion state sequences.

[0025] In the traversal process, the reference motion state sequence of each sliding window center is analyzed to calculate the corresponding coordination score. The size of the sliding window can be 3 or 5 gait cycles. For the convenience of calculation, the first multiple target gait cycles are discarded according to the size of the sliding window, so as to calculate the coordination score of the gait cycle of each sliding window center with respect to the reference motion state sequence. This process is specifically generated by analyzing the multiple reference motion state sequences and target motion state sequences corresponding to the time step association in the sliding window.

[0026] Taking multiple reference motion state sequences and target motion state sequences in any sliding window as examples, a global motion feature sequence in the sliding window is generated based on multiple reference motion state sequences to capture the overall dynamic changes of multiple reference motion state sequences and reflect the trend of the entire gait cycle. In this embodiment, the mean of multiple reference motion state sequences in the sliding window can be taken as the global motion feature sequence in the sliding window. Then, through a distance measurement algorithm such as Euclidean distance, the similarity distances between multiple reference motion state sequences and the global motion feature sequence are calculated respectively. Then, the standard deviation of multiple similarity distances is calculated to obtain the gait local correlation parameter, which is used to reflect the data fluctuation characteristics of multiple reference motion state sequences as reference data.

[0027] A stationary analysis of multiple target motion state sequences is performed to obtain fluctuation parameters. The local associated parameters of gait are processed according to the fluctuation parameters to generate adaptive correction parameters. The similarity distance between the reference motion state sequence at the center of the sliding window and the global motion feature sequence is corrected according to the adaptive correction parameters to obtain the coordination score of the reference motion state sequence at the center of the sliding window.

[0028] Among them, a stationary analysis is performed on multiple target motion state sequences, including constructing a covariance matrix by performing covariance calculation on multiple target motion state sequences, and taking the trace of the covariance matrix as the fluctuation parameter of multiple target motion state sequences. Then, the gait local correlation parameter is processed according to the fluctuation parameter to generate an adaptive correction parameter. Specifically, the adaptive correction parameter is the ratio of the fluctuation parameter to the gait local correlation parameter. The larger the fluctuation parameter, the more discrete the multiple target motion state sequences are, and the greater the possibility of abnormality. The smaller the gait local correlation parameter, the more reference the data on the healthy side is, and the abnormality originally existing on the affected side will not be covered up due to too large fluctuations. For the similarity distance between the reference motion state sequence at the center of the sliding window and the global motion feature sequence. Compared with directly measuring the coordination level of the affected side and the healthy side based on the similarity distance, the similarity distance is corrected according to the adaptive correction parameter, and the product of the two is recorded as the coordination score of the reference motion state sequence at the center of the sliding window, which can better reflect the coordination and normality of the gait. The similarity distance can be Euclidean distance. The smaller the value, the higher the coordination. The smaller the adaptive correction parameter, the smaller the data fluctuation in the adjacent period of the reference motion state sequence, indicating that the patient's gait tends to be stable and will not fluctuate greatly due to potential abnormalities. The higher the final coordination score, the greater the degree of prediction. The coordination score threshold is used to screen out multiple reference motion state sequences with coordination scores greater than the threshold. The target gait cycles corresponding to the multiple reference motion state sequences are recorded as gait coordination abnormality cycles to reveal the difference in overall coordination between the affected side and the healthy side, considering the data fluctuations on the healthy side itself, so as to preliminarily determine the presence of abnormal gait cycles.

[0029] As one implementation process, in the above step S5, gait local coordination detection is performed on multiple gait coordination abnormality cycles based on multiple local motion state sequences, specifically including: For the reference motion state data of the gait coordination abnormality cycle, which includes healthy side state data corresponding to multiple target gait cycles, the local motion state sequences corresponding to the multiple groups of healthy side state data are spliced ​​to construct a local state matrix corresponding to each group of healthy side state data, and then the multiple local state matrices are fused to generate a phase change state matrix of the gait coordination abnormality cycle, which is used to characterize the overall motion state of different local motion stages in multiple adjacent gait cycles. The phase change state matrix can be generated by taking the average of multiple local state matrices, and then each local state matrix is ​​analyzed for differences through the phase change state matrix to extract the corrected state matrix of each group of healthy side state data.

[0030] Among them, the significance of the modified state matrix is ​​to characterize the difference between each group of healthy side state data and the stage change state matrix used for reference. It is worth noting that in actual data collection, it is difficult for the patient's own behavior to achieve a unified standard. Even the limbs of the healthy side will fluctuate during the actual walking process, which will cause the affected side to follow the changes. For example, the healthy side may have a slightly higher step frequency than the normal level at a certain stage, and the affected side will also increase accordingly. However, if the affected side originally has a step frequency lower than the normal level, then this situation in which the affected side follows the healthy side to respond for the sake of body coordination is likely to cover up the abnormal situation that the step frequency is slightly lower than the normal level. Therefore, by extracting the modified state matrix, the natural fluctuation phenomenon on the healthy side can be further analyzed, so as to consider its impact on the affected side based on the coordinated nature of the steps.

[0031] For abnormal motion state data of gait coordination abnormality cycle, including multiple affected side state data corresponding to target gait cycles, the local motion state sequences corresponding to multiple groups of affected side state data are spliced ​​to construct the stage coordination state matrix corresponding to each group of affected side state data. Then, according to the association between each group of abnormal motion state data and reference motion state data, multiple stage coordination state matrices are respectively corrected based on multiple correction state matrices, that is, through the teammate relationship between multiple groups of affected side state data and healthy side state data in each group of abnormal motion state data and reference motion state data, the stage coordination state matrix corresponding to the associated affected side state data is corrected through the correction state matrix of each group of healthy side state data. For example, if a motion state parameter in the correction state matrix is ​​higher than the value in the standard stage change state matrix, the motion state parameter in the stage coordination state matrix corresponding to the affected side state data needs to subtract this difference, so as to remove the data fluctuations in the affected side state data that naturally occur during the patient's walking process as much as possible, and obtain a motion state that can better reflect the original state of the affected side. Finally, the stage coordination state correction matrix corresponding to each group of affected side state data is obtained through correction to generate multiple stage coordination state correction matrices.

[0032] Finally, the local gait coordination detection is performed on the gait coordination abnormality cycle according to the collaborative state correction matrix of multiple stages, and the local gait abnormality result of each gait coordination abnormality cycle is obtained.

[0033] This process includes performing local stage coordination analysis on multiple stage coordination state correction matrices to generate coordination feature parameters for each local motion stage, and performing gait local coordination detection on multiple stage coordination state correction matrices of the gait coordination abnormality cycle based on the coordination feature parameters and the stage change state matrix of the gait coordination abnormality cycle to obtain the local gait abnormality results for each gait coordination abnormality cycle.

[0034] Specifically, a local stage collaborative analysis process is performed on multiple stage collaborative state correction matrices, including analyzing each local motion stage, extracting the local stage state sequence corresponding to each local motion stage in each stage collaborative state correction matrix, thereby obtaining multiple local stage state sequences for each local motion stage, and then performing autocorrelation analysis on the multiple local stage state sequences for each local motion stage, and calculating the collaborative feature parameters of the multiple local stage state sequences for each local motion stage.

[0035] Among them, autocorrelation analysis can be used to analyze the coordination of the patient's performance level in multiple adjacent gait cycles in the same local movement stage, and the autocorrelation value calculated by the autocorrelation analysis is used as the coordination feature parameter of the local stage state sequence. For example, if the state sequence of a local stage shows high consistency in multiple cycles, the coordination feature parameter will be high, indicating that the stage has good stability in the gait cycle; if the autocorrelation value is low, it means that there is a large fluctuation or abnormality in the stage.

[0036] According to the phase change state matrix, a similarity analysis based on the local motion phase is performed on the multiple phase collaborative state correction matrices of the gait coordination abnormality cycle, and a similarity analysis result of the multiple phase collaborative state correction matrices of the gait coordination abnormality cycle is generated.

[0037] Among them, the process of similarity analysis based on the local motion stage is specifically to first calculate the similarity parameters of each local motion stage in the stage collaborative state correction matrix, that is, for the stage change state matrix and multiple stage collaborative state correction matrices of the gait coordination abnormality cycle, first analyze each local motion stage, calculate the similarity between the state sequences corresponding to each local motion stage in each stage collaborative state correction matrix and the stage change state matrix, such as Euclidean distance, cosine similarity, etc., to obtain the similarity parameters corresponding to each local motion stage. For the multiple local motion stages corresponding to the stage collaborative state correction matrix, the similarity parameters corresponding to the multiple local motion stages are fused. The fusion process determines the fusion weight according to the collaborative feature parameter to achieve weighted fusion. The collaborative feature parameter characterizes the collaborative characteristics of a local motion stage. The lower the collaborative feature parameter, the more unstable the local motion stage is in multiple adjacent gait cycles, indicating that the possibility of abnormality is higher, and the weight value can be high, that is, the difference in this part needs more attention. On the contrary, the higher the collaborative feature parameter, the more stable it is, and the possibility of abnormal smile fluctuation is lower. The weight value can be low to avoid excessive attention to the difference in this stage. In this way, the similarity parameters of multiple local motion stages are fused according to multiple collaborative feature parameters to obtain the local stage similarity parameters of the collaborative state correction matrix of each stage of the gait coordination abnormality cycle, and finally generate the similarity analysis results of the collaborative state correction matrices of multiple stages of the gait coordination abnormality cycle.

[0038] Finally, based on the similarity analysis results of the collaborative state correction matrices of multiple stages, the gait local coordination feature detection vector of the gait coordination abnormality period is generated, which characterizes the coordination change relationship between the local stages of multiple gait cycles from the perspective of local motion stages within multiple adjacent gait cycles.

[0039] And according to the multiple local state matrices of the gait coordination abnormality cycle, the gait local coordination characteristic fluctuation vector of the gait coordination abnormality cycle is generated. Among them, for the construction of the gait local coordination characteristic fluctuation vector, by calculating the similarity parameters between the multiple local state matrices of the gait coordination abnormality cycle and the stage change state matrix of the gait coordination abnormality cycle, the same method as above is adopted, such as the Euclidean distance to calculate the similarity parameters between the multiple local state matrices and the stage change state matrix, the difference is that the changes in the specific stage are not considered, but the overall motion state is measured, because the local state matrix and the stage change state matrix used as reference do not need to consider the actual possible local abnormalities, that is, they are assumed to be normal and used for comparison reference, and are only used as the reference range of fluctuations at the normal level. For the data on the affected side, it is necessary to further explore the potential abnormalities, so the abnormal characteristics are highlighted according to the relative importance of the fluctuations.

[0040] Then, based on the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector, a local gait abnormality result of the gait coordination abnormality period is generated.

[0041] The distance parameter between the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector is calculated. If the distance parameter between the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector is less than the preset distance threshold, then it is recorded that there is no local gait abnormality in the gait coordination abnormality period, that is, it is considered to be a normal fluctuation phenomenon, and similar motion state fluctuations will also occur during the actual walking process of the healthy side.

[0042] Otherwise, it is recorded that there is a local gait abnormality in the gait coordination abnormality cycle, and the abnormal local motion stage is determined according to the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector. Specifically, the local stage coordination threshold of the gait coordination abnormality cycle is determined according to the gait local coordination feature fluctuation vector, for example, the maximum value of multiple element values ​​in the gait local coordination feature fluctuation vector is taken as a reference, that is, the maximum fluctuation reference upper limit value, and then the local fluctuation upper limit value of each local motion stage is determined. For example, a gait cycle is divided into six local motion stages, and the local fluctuation upper limit value of each local motion stage is the local stage coordination threshold value, which can be specifically one-sixth of the maximum value of multiple element values ​​in the gait local coordination feature fluctuation vector. Then, the coordination difference value of the gait coordination abnormality cycle with respect to each local motion stage is determined according to the local stage similarity parameter of the stage coordination state correction matrix, which is specifically the numerical value corresponding to the similarity parameter of each local motion stage after the similarity parameters of multiple local motion stages are fused through the coordination feature parameter in the process of calculating the local stage similarity parameter, that is, the numerical component used to constitute the local stage similarity parameter of each local motion stage.

[0043] It is judged whether the coordination difference value of the local motion stage is greater than the local stage coordination threshold of the gait coordination abnormality cycle. If not, it indicates that the local motion stage is in a normal fluctuation state. Otherwise, the local motion stage whose coordination difference value is greater than the local stage coordination threshold of the gait coordination abnormality cycle is recorded as an abnormal local motion stage, and a local gait abnormality result of the gait coordination abnormality cycle is generated to further indicate which specific local motion stage or stages are abnormal. In this way, the local gait abnormality results of multiple gait coordination abnormality cycles are obtained, which provides an important basis for medical staff to judge the patient's gait condition and provides direction for personalized rehabilitation training. Finally, the patient's target gait abnormality detection result is generated according to the local gait abnormality results of multiple gait coordination abnormality cycles, so as to realize accurate gait analysis and abnormality detection of patients.

[0044] One embodiment of the present invention further provides a patient gait analysis system based on motion detection data, which is specifically used to implement the above-mentioned patient gait analysis method based on motion detection data, including: A data acquisition module is used to obtain the patient's motion detection data and electromyographic signal data to be analyzed, and extract motion state cycle data corresponding to a plurality of target gait cycles from the motion detection data and electromyographic signal data to be analyzed, wherein each set of motion state cycle data includes the patient's healthy side state data and the affected side state data; A feature extraction module is used to extract a reference motion state sequence and a target motion state sequence of each set of motion state periodic data, and construct a reference state matrix containing multiple reference motion state sequences and a target state matrix containing multiple target motion state sequences; A coordinated sliding window detection module is used to perform gait coordination sliding window detection on multiple sets of motion state cycle data, including generating a global motion feature sequence in each sliding window based on a target state matrix, performing gait coordination detection on multiple reference motion state sequences in the sliding window according to the global motion feature sequence, generating coordination scores corresponding to the multiple reference motion state sequences, and determining multiple gait coordination abnormality cycles according to the coordination scores; Specifically, gait coordination sliding window detection is performed on multiple sets of motion state cycle data, including: Through the sliding window, the reference state matrix and the target state matrix are traversed in time step association to generate coordination scores corresponding to multiple reference motion state sequences; Wherein, for a plurality of reference motion state sequences and a target motion state sequence in any sliding window, a global motion feature sequence in the sliding window is generated according to the plurality of reference motion state sequences, and similarity distances between the plurality of reference motion state sequences and the global motion feature sequence are calculated respectively; The standard deviation of multiple similarity distances is calculated to obtain the local gait correlation parameter, and the multiple target motion state sequences are subjected to stationary analysis to obtain the fluctuation parameter. The local gait correlation parameter is processed according to the fluctuation parameter to generate an adaptive correction parameter. The similarity distance between the reference motion state sequence at the center of the sliding window and the global motion feature sequence is corrected according to the adaptive correction parameter to obtain the coordination score of the reference motion state sequence at the center of the sliding window. A plurality of reference motion state sequences are screened out by using a coordination score threshold, and the target gait cycles corresponding to the screened plurality of reference motion state sequences are recorded as gait coordination abnormality cycles.

[0045] A gait coordination anomaly analysis module is used to extract abnormal motion state data and reference motion state data of each gait coordination anomaly cycle from multiple sets of motion state cycle data, perform motion phase segmentation on multiple sets of abnormal motion state data and reference motion state data, and obtain motion disassembly data corresponding to the abnormal motion state data and reference motion state data in multiple local motion phases; The gait local coordination detection module is used to extract multiple motion state parameters from each set of motion decomposition data, construct a local motion state sequence for each local motion stage, perform gait local coordination detection on multiple gait coordination abnormality cycles based on multiple local motion state sequences, and obtain the patient's target gait abnormality detection result.

[0046] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. Parts not described in detail in this specification belong to the prior art known to those skilled in the art.

Claims

1. A patient gait analysis method based on motion detection data, characterized in that: include: Acquire the patient's motion detection data and electromyographic signal data to be analyzed, and extract motion state cycle data corresponding to a plurality of target gait cycles from the motion detection data and electromyographic signal data to be analyzed, wherein each set of motion state cycle data includes the patient's healthy side state data and the affected side state data; Extracting a reference motion state sequence and a target motion state sequence from each set of motion state periodic data, and constructing a reference state matrix containing a plurality of reference motion state sequences and a target state matrix containing a plurality of target motion state sequences; Performing gait coordination sliding window detection on multiple groups of motion state cycle data, including generating a global motion feature sequence in each sliding window based on a target state matrix, performing gait coordination detection on multiple reference motion state sequences in the sliding window according to the global motion feature sequence, generating coordination scores corresponding to the multiple reference motion state sequences, and determining multiple gait coordination abnormality cycles according to the coordination scores; Extracting abnormal motion state data and reference motion state data of each gait coordination abnormal cycle from multiple sets of motion state cycle data, performing motion phase segmentation on the multiple sets of abnormal motion state data and reference motion state data, and obtaining motion disassembly data corresponding to the abnormal motion state data and the reference motion state data in multiple local motion phases; Multiple motion state parameters of each group of motion decomposition data are extracted, and a local motion state sequence of each local motion stage is constructed. Based on the multiple local motion state sequences, local gait coordination detection is performed on multiple gait coordination abnormality cycles to obtain the patient's target gait abnormality detection result.

2. A patient gait analysis method based on motion detection data according to claim 1, characterized in that: Perform gait coordination sliding window detection on multiple sets of motion state cycle data, including: Through the sliding window, the reference state matrix and the target state matrix are traversed in time step association to generate coordination scores corresponding to multiple reference motion state sequences; Wherein, for a plurality of reference motion state sequences and a target motion state sequence in any sliding window, a global motion feature sequence in the sliding window is generated according to the plurality of reference motion state sequences, and similarity distances between the plurality of reference motion state sequences and the global motion feature sequence are calculated respectively; The standard deviation of multiple similarity distances is calculated to obtain the local gait correlation parameter, and the multiple target motion state sequences are subjected to stationary analysis to obtain the fluctuation parameter. The local gait correlation parameter is processed according to the fluctuation parameter to generate an adaptive correction parameter. The similarity distance between the reference motion state sequence at the center of the sliding window and the global motion feature sequence is corrected according to the adaptive correction parameter to obtain the coordination score of the reference motion state sequence at the center of the sliding window. A plurality of reference motion state sequences are screened out by using a coordination score threshold, and the target gait cycles corresponding to the screened plurality of reference motion state sequences are recorded as gait coordination abnormality cycles.

3. The method for analyzing patient gait based on motion detection data according to claim 1, characterized in that: The gait local coordination detection is performed on multiple gait coordination abnormality cycles based on multiple local motion state sequences, including: For the reference motion state data of the gait coordination abnormality cycle, including the healthy side state data corresponding to multiple target gait cycles, a local state matrix corresponding to each group of healthy side state data is constructed according to multiple local motion state sequences; A plurality of local state matrices are fused to generate a phase change state matrix of a gait coordination abnormality cycle, and a correction state matrix of each group of healthy side state data is determined based on the phase change state matrix; For the abnormal motion state data of the gait coordination abnormality cycle, including the affected side state data corresponding to multiple target gait cycles, a stage coordination state matrix corresponding to each group of the affected side state data is constructed according to multiple local motion state sequences; According to the correlation between each group of abnormal motion state data and the reference motion state data, the collaborative state matrices of multiple stages are respectively corrected based on multiple correction state matrices to obtain collaborative state correction matrices of multiple stages; The local gait coordination detection is performed on the gait coordination abnormality cycle according to the multi-stage coordination state correction matrix, including local stage coordination analysis on the multi-stage coordination state correction matrix to generate coordination feature parameters of each local motion stage, and based on the coordination feature parameters and the stage change state matrix of the gait coordination abnormality cycle, the local gait coordination detection is performed on the multi-stage coordination state correction matrix of the gait coordination abnormality cycle to obtain the local gait abnormality result of each gait coordination abnormality cycle.

4. The method for analyzing patient gait based on motion detection data according to claim 3, characterized in that: The gait local coordination detection is performed on the gait coordination abnormality cycle according to the multi-stage collaborative state correction matrix, and also includes: Performing local phase coordination analysis on multiple phase coordination state correction matrices, extracting multiple local phase state sequences of each local motion phase from the multiple phase coordination state correction matrices, performing autocorrelation analysis on the multiple local phase state sequences of each local motion phase, and calculating coordination feature parameters of the multiple local phase state sequences of each local motion phase; According to the phase change state matrix, a similarity analysis based on the local motion phase is performed on the multiple phase collaborative state correction matrices of the gait coordination abnormality cycle, including calculating the similarity parameters of each local motion phase in the phase collaborative state correction matrix, fusing the similarity parameters of the multiple local motion phases according to the multiple collaborative feature parameters, obtaining the local phase similarity parameters of the phase collaborative state correction matrix, and generating the similarity analysis results of the multiple phase collaborative state correction matrices of the gait coordination abnormality cycle; According to the similarity analysis results of the collaborative state correction matrices of multiple stages, a gait local coordination feature detection vector of the gait coordination abnormality period is generated; according to the multiple local state matrices of the gait coordination abnormality period, a gait local coordination feature fluctuation vector of the gait coordination abnormality period is generated; based on the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector, a local gait abnormality result of the gait coordination abnormality period is generated.

5. The method for analyzing patient gait based on motion detection data according to claim 4, characterized in that: A local gait abnormality result of a gait coordination abnormality period is generated based on a gait local coordination feature detection vector and a gait local coordination feature fluctuation vector, including: Calculate the distance parameter between the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector. If the distance parameter between the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector is less than a preset distance threshold, then it is recorded that there is no local gait abnormality in the gait coordination abnormality period. Otherwise, it is recorded that there is local gait abnormality in the gait coordination abnormality period, and the abnormal local motion stage is determined according to the gait local coordination feature detection vector and the gait local coordination feature fluctuation vector, including determining the local stage coordination threshold of the gait coordination abnormality period according to the gait local coordination feature fluctuation vector, determining the coordination difference value of each local motion stage of the gait coordination abnormality period according to the local stage similarity parameter of the stage coordination state correction matrix, judging whether the coordination difference value of the local motion stage is greater than the local stage coordination threshold of the gait coordination abnormality period, recording the local motion stage whose coordination difference value is greater than the local stage coordination threshold of the gait coordination abnormality period as the abnormal local motion stage, generating the local gait abnormality result of the gait coordination abnormality period, and generating the target gait abnormality detection result of the patient according to the local gait abnormality results of multiple gait coordination abnormality periods.

6. The method for analyzing patient gait based on motion detection data according to claim 4, characterized in that: For the gait local coordination feature fluctuation vector, it also includes: By calculating the similarity parameters between multiple local state matrices of the gait coordination abnormality cycle and the phase change state matrices of the gait coordination abnormality cycle, a gait local coordination characteristic fluctuation vector is constructed according to the multiple similarity parameters.

7. A patient gait analysis system based on motion detection data, characterized in that: The system is used to implement a patient gait analysis method based on motion detection data as described in any one of claims 1 to 6, comprising: A data acquisition module is used to obtain the patient's motion detection data and electromyographic signal data to be analyzed, and extract motion state cycle data corresponding to a plurality of target gait cycles from the motion detection data and electromyographic signal data to be analyzed, wherein each set of motion state cycle data includes the patient's healthy side state data and the affected side state data; A feature extraction module is used to extract a reference motion state sequence and a target motion state sequence of each set of motion state periodic data, and construct a reference state matrix containing multiple reference motion state sequences and a target state matrix containing multiple target motion state sequences; A coordinated sliding window detection module is used to perform gait coordination sliding window detection on multiple sets of motion state cycle data, including generating a global motion feature sequence in each sliding window based on a target state matrix, performing gait coordination detection on multiple reference motion state sequences in the sliding window according to the global motion feature sequence, generating coordination scores corresponding to the multiple reference motion state sequences, and determining multiple gait coordination abnormality cycles according to the coordination scores; A gait coordination anomaly analysis module is used to extract abnormal motion state data and reference motion state data of each gait coordination anomaly cycle from multiple sets of motion state cycle data, perform motion phase segmentation on multiple sets of abnormal motion state data and reference motion state data, and obtain motion disassembly data corresponding to the abnormal motion state data and reference motion state data in multiple local motion phases; The gait local coordination detection module is used to extract multiple motion state parameters from each set of motion decomposition data, construct a local motion state sequence for each local motion stage, perform gait local coordination detection on multiple gait coordination abnormality cycles based on multiple local motion state sequences, and obtain the patient's target gait abnormality detection result.

Images