A rehabilitation assessment method and device based on abnormal gait recognition

Abstract

The application provides a rehabilitation evaluation method and device based on abnormal gait recognition, and belongs to the technical field of auxiliary diagnosis, and specifically comprises the following steps: determining an age interval in which a target patient is located and effective electroencephalogram features matched by the target patient based on basic information of the target patient; when a change in a disease state of the target patient occurs, extracting gait features and plantar pressure features of the target patient by means of a change in the effective electroencephalogram features of the target patient and an identification effective value of different effective electroencephalogram features; and outputting a disease type of the target patient and a disease rehabilitation evaluation result of the target patient in combination with the effective electroencephalogram features of the target patient and the identification effective value of the effective electroencephalogram features, so that the reliability of the rehabilitation evaluation result is further improved.

Description

Technical Field

[0001] This invention belongs to the field of auxiliary diagnostic technology, and in particular relates to a rehabilitation assessment method and device based on abnormal gait recognition. Background Technology

[0002] Most neuropsychiatric disorders, such as depression, Alzheimer's disease, and Parkinson's disease, have insidious onset, atypical early symptoms, and remission-progression after onset, requiring long-term home-based health management. The brain's gait motor control system interacts with other cortical and subcortical structures; any disease that impairs this interaction or the gait control execution system will result in altered gait characteristics. Therefore, gait characteristics are an objective clinical marker of activity levels in individuals with neuropsychiatric disorders, making the identification of neuropsychiatric diseases based on gait characteristics a pressing technical problem to be solved.

[0003] To address the aforementioned technical problems, existing technical solutions combine the knee joint range of motion, gait function, and muscle strength information to assess the rehabilitation status of the test subject. Specifically, similar technical means are presented in invention patents CN202011475921.5 "A Rehabilitation Assessment Method and System Based on Wearable Sensors" and CN201511017130.7 "A Step Counting and Movement Status Assessment Device." However, analysis reveals the following technical problems: The direct correlation between neurological diseases and users' brain signals is the EEG signal. If the user's brain signals are ignored, it is impossible to accurately assess the user's recovery status. At the same time, due to the differences in users' mental states, the fluctuation of brain signals is quite serious. Therefore, if the effective characteristic signals of brain signals cannot be screened, it is also impossible to accurately assess the user's recovery status.

[0004] To address the aforementioned technical problems, this invention provides a rehabilitation assessment method and device based on abnormal gait recognition. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted: According to one aspect of the present invention, a product module partitioning method based on a clustering algorithm is provided.

[0006] A rehabilitation assessment method based on abnormal gait recognition, characterized in that it specifically includes: S1 divides the patients into different age ranges based on their age, and determines the disease association coefficients between different EEG characteristics and different disease types within different age ranges, as well as the disease differentiation factors between different disease types, based on the patients' EEG characteristics, disease types, and disease severity. S2 determines the effective identification value of the EEG feature in different age ranges through the disease association coefficient and disease differentiation factor, and identifies the effective EEG feature in different age ranges based on the effective identification value; S3 determines the age range of the target patient and the effective EEG characteristics matched by the target patient based on the basic information of the target patient. When the disease status of the target patient changes by the changes in the effective EEG characteristics of the target patient and the effective identification value of different effective EEG characteristics, proceed to the next step. S4 extracts the gait characteristics and plantar pressure characteristics of the target patient, and combines them with the effective EEG characteristics and the effective values ​​of the effective EEG characteristics to output the disease type and disease rehabilitation assessment results of the target patient.

[0007] A further technical solution is that the age range is divided into equal intervals according to a preset age interval, wherein the preset age interval is determined according to the number of patients, and the more patients there are, the smaller the preset age interval is.

[0008] A further technical solution is that the disease types include, but are not limited to, depression, Alzheimer's disease, and Parkinson's disease.

[0009] A further technical solution is that the severity of the disease is determined based on the indicator data of different disease-related indicators of the patient's disease type, and the specific severity of the disease is divided based on percentages.

[0010] A further technical solution is that the gait characteristics are obtained using a gait balance monitor with a sampling frequency of 16 frames / s, an image resolution of 800*600, and a minimum gait judgment period of 10.

[0011] A further technical solution is that the output of the target patient's disease type and disease rehabilitation assessment results is based on a gait balance analyzer, with 4 channels for information input and 10 built-in processing subsystems. The target patient's disease type and disease rehabilitation assessment results are output by printing a comprehensive analysis report.

[0012] On the other hand, the present invention provides a rehabilitation assessment device based on abnormal gait recognition, employing the aforementioned rehabilitation assessment method based on abnormal gait recognition, characterized in that it specifically includes: EEG feature assessment module, EEG feature screening module, variation assessment module, and result output module; The EEG feature assessment module is responsible for classifying patients into different age ranges based on their age, and determining the disease correlation coefficients between different EEG features and different disease types within different age ranges, as well as the disease differentiation factors between different disease types, based on the patients' EEG features, disease types, and disease severity. The EEG feature screening module is responsible for determining the effective recognition values ​​of the EEG features in different age ranges through the disease correlation coefficient and disease differentiation factor, and for recognizing effective EEG features in different age ranges based on the effective recognition values. The change assessment module is responsible for determining the age range of the target patient and the effective EEG characteristics matched by the target patient based on the basic information of the target patient. It determines whether the disease status of the target patient has changed by the changes in the effective EEG characteristics of the target patient and the identification effective values ​​of different effective EEG characteristics. The result output module is responsible for extracting the gait characteristics and plantar pressure characteristics of the target patient, and combining the effective EEG characteristics and the effective values ​​of the effective EEG characteristics of the target patient to output the disease type and disease rehabilitation assessment results of the target patient.

[0013] The beneficial effects of this invention are as follows: 1. Based on the identification of valid values, effective EEG features are identified in different age ranges. The differences in the fluctuation state of EEG features due to the differences in age ranges are fully considered. At the same time, by further considering the differentiation of disease types and the correlation of different EEG features, effective brain point features are screened, which also lays the foundation for further evaluation of the changes in rehabilitation status and disease status.

[0014] 2. By analyzing the changes in the effective EEG characteristics of the target patient and the effective identification values ​​of different effective EEG characteristics, it is possible to determine whether the patient's disease status has changed. This approach not only considers the changes in the effective EEG characteristics of different target patients, but also takes into account the degree of influence of the changes in different effective EEG characteristics by combining them with the effective identification values. This enables an accurate assessment of whether the disease status has changed and lays the foundation for further implementing differentiated rehabilitation assessment measures for different target patients.

[0015] 3. By using gait characteristics, plantar pressure characteristics, and effective EEG characteristics of the target patient, the disease type and rehabilitation assessment results of the target patient are output. This achieves the determination of the disease rehabilitation assessment results of the target patient from the perspective of multiple feature fusion, avoiding the technical problem of low accuracy caused by using a single feature, and ensuring the accuracy of the disease rehabilitation assessment results.

[0016] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0019] Figure 1 This is a flowchart of a rehabilitation assessment method based on abnormal gait recognition; Figure 2 This is a flowchart illustrating the method for determining the disease association coefficient; Figure 3 This is a framework diagram of a rehabilitation assessment system based on abnormal gait recognition. Detailed Implementation

[0020] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0021] The terms “a,” “one,” “the,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended meaning of inclusion and that other elements / components / etc. may exist in addition to the listed elements / components / etc. Example

[0022] To solve the above problems, according to one aspect of the present invention, such as Figure 1 As shown, according to one aspect of the present invention, a rehabilitation assessment method based on abnormal gait recognition is provided, characterized in that it specifically includes: S1 divides the patients into different age ranges based on their age, and determines the disease association coefficients between different EEG characteristics and different disease types within different age ranges, as well as the disease differentiation factors between different disease types, based on the patients' EEG characteristics, disease types, and disease severity. Furthermore, the age range is divided into equal intervals according to a preset age interval, wherein the preset age interval is determined according to the number of patients, and the more patients there are, the smaller the preset age interval is.

[0023] It is understood that the types of diseases mentioned include, but are not limited to, depression, Alzheimer's disease, and Parkinson's disease.

[0024] It should be noted that the severity of the disease is determined based on the indicator data of different disease-related indicators of the patient's disease type, and the specific severity of the disease is divided based on percentages.

[0025] Specific examples, such as Figure 2 As shown, the method for determining the disease association coefficient in step S2 above is as follows: Patients with the disease type within the age range are selected as assessment patients. The magnitude of the change in the EEG characteristics of different assessment patients within a specified time period is determined based on the changes in the EEG characteristics of different assessment patients. The consistency of the EEG characteristics is determined based on the magnitude of the change in the EEG characteristics of different assessment patients within a specified time period. Based on the electroencephalogram (EEG) characteristics and the severity of the disease in different patients, the correlation coefficient between the EEG characteristics and the disease type was determined using Pearson correlation coefficient analysis. The disease association coefficient between the EEG features and the disease type is determined based on the consistency and the correlation coefficient between the EEG features and the disease type.

[0026] Furthermore, the disease correlation coefficient ranges from 0 to 1, and the larger the disease correlation coefficient, the higher the correlation between the EEG feature and the disease type.

[0027] In another embodiment, the method for determining the disease association coefficient in step S1 above is as follows: Patients with the disease type within the age range are selected as assessment patients. The variation range of the EEG characteristics of different assessment patients within a specified time period is determined based on the variation of the EEG characteristics of different assessment patients. When the number of assessment patients whose variation range does not meet the requirements is greater than the preset number of patients, the disease correlation coefficient between the EEG characteristics and the disease type is determined based on the preset correlation coefficient. When the number of patients whose variation range does not meet the requirements is not greater than the preset number of patients, the consistency of the EEG characteristics is determined based on the variation range of the EEG characteristics of different patients within a specified time and the number of patients being assessed. It is then determined whether the consistency of the EEG characteristics meets the requirements. If yes, proceed to the next step; otherwise, determine the disease correlation coefficient between the EEG characteristics and the disease type based on the preset correlation coefficient. Based on the EEG characteristics and the severity of the disease in different patients, the Pearson correlation coefficient analysis method is used to determine the correlation coefficient between the EEG characteristics and the disease type. Based on the correlation coefficient, it is determined whether there is an association between the EEG characteristics and the disease type. If yes, proceed to the next step; if no, determine the disease association coefficient between the EEG characteristics and the disease type based on a preset correlation coefficient. The disease association coefficient between the EEG features and the disease type is determined based on the consistency and the correlation coefficient between the EEG features and the disease type.

[0028] For example, the method for determining the disease differentiating factors is as follows: The disease type to be analyzed is taken as the preset disease type. Based on the EEG characteristics of patients of the preset disease type, the number of similarities between the EEG characteristics of patients of the preset disease type and the EEG characteristics of patients of a specific disease type is determined. The disease distinguishing factor of the EEG characteristics between the preset disease type and the specific disease type is determined by combining the number of patients of the preset disease type and the number of patients of the specific disease type.

[0029] Furthermore, the value of the disease differentiation factor ranges from 0 to 1, and the larger the disease differentiation factor, the better the EEG feature can differentiate between a preset disease type and a specific disease type.

[0030] S2 determines the effective identification value of the EEG feature in different age ranges through the disease association coefficient and disease differentiation factor, and identifies the effective EEG feature in different age ranges based on the effective identification value; For example, the method for determining the effective value of the EEG feature is as follows: The number of strongly correlated disease types and the number of weakly correlated disease types are determined based on the disease correlation coefficients between the EEG features and different disease types, and the comprehensive disease correlation coefficient of the EEG features is determined by combining the disease correlation coefficients between the EEG features and different disease types. Based on the disease differentiation factors of the EEG features among different disease types, the number of strongly differentiating disease types and the number of weakly differentiating disease types are determined, and the comprehensive disease differentiation factor of the EEG features is determined by combining the disease differentiation factors of the EEG features with those of different disease types. The effective identification values ​​of the EEG features in different age ranges are determined by the comprehensive disease correlation coefficient and the comprehensive disease differentiation factor.

[0031] Furthermore, when the disease differentiation factor between the disease types is less than a preset regional value, the disease type is determined to be a weakly differentiated disease type.

[0032] It should be noted that when the correlation coefficient between the EEG features and the disease type does not meet the requirements, the disease type is determined to be a weakly correlated disease type.

[0033] In another embodiment, the method for determining the valid value of the EEG feature in step S2 above is as follows: The number of weakly associated disease types is determined based on the disease correlation coefficient between the EEG features and different disease types. If the number of weakly associated disease types does not meet the requirements, the EEG features are determined not to be valid EEG features. When the number of weakly associated disease types meets the requirements, the number of weakly distinguishable disease types is determined based on the disease distinguishing factor of the EEG feature between different disease types. When the number of weakly distinguishable disease types does not meet the requirements, the EEG feature is determined not to be a valid EEG feature. The comprehensive disease correlation coefficient of the EEG feature is determined based on the number of strongly correlated disease types and the number of weakly correlated disease types, as well as the disease correlation coefficient between the EEG feature and different disease types. If the comprehensive disease correlation coefficient of the EEG feature does not meet the requirements, the EEG feature is determined not to be a valid EEG feature. When the disease comprehensive correlation coefficient of the EEG feature meets the requirements, the disease comprehensive differentiation factor of the EEG feature is determined based on the number of strongly distinguishable disease types and the number of weakly distinguishable disease types, as well as the disease differentiation factor between the EEG feature and different disease types. When the disease comprehensive differentiation factor of the EEG feature does not meet the requirements, the EEG feature is determined not to be a valid EEG feature. When the disease comprehensive distinguishing factor of the EEG feature meets the requirements, the effective identification value of the EEG feature in different age ranges is determined by the disease comprehensive correlation coefficient and the disease comprehensive distinguishing factor.

[0034] In another embodiment, the method for determining the valid value of the EEG feature in step S2 above is as follows: The number of weakly associated disease types is determined based on the disease correlation coefficients between the EEG features and different disease types. The association problem assessment quantity of the EEG features is determined by combining the disease correlation coefficients of different weakly associated disease types. It is then determined whether the association problem assessment quantity of the EEG features meets the requirements. If yes, proceed to the next step; otherwise, it is determined that the EEG features are not valid EEG features. The number of weakly distinguishable disease types is determined based on the disease differentiation factors of the EEG features among different disease types. The differentiation problem assessment quantity is determined by combining the EEG features with the disease differentiation factors of different weakly distinguishable disease types. It is then determined whether the differentiation problem assessment quantity meets the requirements. If yes, proceed to the next step. If no, it is determined that the EEG features are not valid EEG features. The comprehensive disease correlation coefficient of the EEG feature is determined based on the number of strongly correlated disease types and the number of weakly correlated disease types, as well as the disease correlation coefficient between the EEG feature and different disease types. The comprehensive disease differentiation factor of the EEG feature is determined based on the number of strongly distinguishable disease types and the number of weakly distinguishable disease types, as well as the disease differentiation factor between the EEG feature and different disease types. The effective identification values ​​of the EEG features in different age ranges are determined by the comprehensive disease correlation coefficient and the comprehensive disease differentiation factor.

[0035] Specifically, based on the identified valid values, the identification of valid EEG features within different age ranges includes: When the valid recognition value of the EEG feature within the age range is greater than a preset threshold, the EEG feature is determined to be a valid EEG feature within the age range.

[0036] S3 determines the age range of the target patient and the effective EEG characteristics matched by the target patient based on the basic information of the target patient. When the disease status of the target patient changes by the changes in the effective EEG characteristics of the target patient and the effective identification value of different effective EEG characteristics, proceed to the next step. Furthermore, the variation of the effective EEG characteristics includes both the magnitude and the amount of variation.

[0037] For specific examples, determining whether the target patient's disease status has changed includes: Based on the changes in the effective EEG characteristics of the target patient, the amplitude and amount of change of different effective EEG characteristics are determined, and the comprehensive amount of change of different effective EEG characteristics is determined by combining the effective identification values ​​of different effective EEG characteristics. The characteristic variation of the target patient is determined based on the comprehensive variation of different effective EEG characteristics, and the disease status of the target patient is determined based on the characteristic variation of the target patient.

[0038] In another embodiment, determining whether the disease status of the target patient has changed in step S3 above specifically includes: S41 takes the effective EEG characteristics of the target patient that have changed as the changed EEG characteristics, and determines whether the number of changed EEG characteristics of the target patient meets the requirements. If yes, proceed to the next step; otherwise, determine that the disease status of the target patient has changed. S42 determines whether the target patient has EEG characteristics whose amplitude or amount of change does not meet the requirements. If so, the EEG characteristics whose amplitude or amount of change does not meet the requirements are regarded as drastic changes and proceed to the next step. If not, proceed to step S44. S43 determines whether the number of the drastic change features meets the requirements. If yes, proceed to the next step; otherwise, determine that the disease status of the target patient has changed. S44 determines the amplitude and amount of change of different effective EEG features based on the changes in the effective EEG features of the target patient, and determines the comprehensive amount of change of different effective EEG features in combination with the effective identification value of different effective EEG features. It then determines whether there are any effective EEG features whose comprehensive amount of change does not meet the requirements. If so, proceed to the next step; otherwise, determine that the disease status of the target patient has not changed. S45 determines the characteristic variation of the target patient based on the comprehensive variation of different effective EEG characteristics, and determines whether the disease status of the target patient has changed based on the characteristic variation of the target patient.

[0039] In another embodiment, determining whether the disease status of the target patient has changed in step S3 above specifically includes: The effective EEG characteristics that change in the target patient are considered as variable EEG characteristics, and the variable EEG characteristics whose amplitude or amount of change does not meet the requirements are considered as drastic variable characteristics. When the patient does not have drastic variable characteristics: When the number of changing EEG features of the target patient is within a preset range, it is determined that the disease status of the target patient has not changed. When the number of changing EEG features of the target patient is not within a preset range, it is determined that the disease status of the target patient has changed; When the patient exhibits drastic changes in characteristics or the number of changing EEG characteristics in the target patient is outside the preset range: If the number of drastic changes in the target patient's characteristics does not meet the requirements or the number of changes in the target patient's EEG characteristics is not within the preset range, then it is determined that the target patient's disease status has changed. When the number of drastic changes in the target patient's features meets the requirements and the number of changes in the target patient's EEG features is within a preset range, the amplitude and amount of change of different effective EEG features are determined based on the changes in the effective EEG features of the target patient, and the comprehensive amount of change of different effective EEG features is determined by combining the effective identification values ​​of different effective EEG features. The characteristic variation of the target patient is determined based on the comprehensive variation of different effective EEG characteristics, and the disease status of the target patient is determined based on the characteristic variation of the target patient.

[0040] S4 extracts the gait characteristics and plantar pressure characteristics of the target patient, and combines them with the effective EEG characteristics and the effective values ​​of the effective EEG characteristics to output the disease type and disease rehabilitation assessment results of the target patient.

[0041] Furthermore, the gait features are obtained using a gait balance monitor with a sampling frequency of 16 frames / s, an image of 800*600, and a minimum gait judgment period of 10. (2) Gait balance analyzer (0-X): 4 channels for information input, 10 built-in processing subsystems, and a comprehensive analysis report for result output.

[0042] It should be noted that the output of the target patient's disease type and disease rehabilitation assessment results is based on a gait balance analyzer with 4 input channels and 10 built-in processing subsystems. The target patient's disease type and disease rehabilitation assessment results are output by printing a comprehensive analysis report. Example

[0043] On the other hand, such as Figure 3 As shown, this invention provides a rehabilitation assessment device based on abnormal gait recognition, employing the aforementioned rehabilitation assessment method based on abnormal gait recognition, characterized in that it specifically includes: EEG feature assessment module, EEG feature screening module, variation assessment module, and result output module; The EEG feature assessment module is responsible for classifying patients into different age ranges based on their age, and determining the disease correlation coefficients between different EEG features and different disease types within different age ranges, as well as the disease differentiation factors between different disease types, based on the patients' EEG features, disease types, and disease severity. The EEG feature screening module is responsible for determining the effective recognition values ​​of the EEG features in different age ranges through the disease correlation coefficient and disease differentiation factor, and for recognizing effective EEG features in different age ranges based on the effective recognition values. The change assessment module is responsible for determining the age range of the target patient and the effective EEG characteristics matched by the target patient based on the basic information of the target patient. It determines whether the disease status of the target patient has changed by the changes in the effective EEG characteristics of the target patient and the identification effective values ​​of different effective EEG characteristics. The result output module is responsible for extracting the gait characteristics and plantar pressure characteristics of the target patient, and combining the effective EEG characteristics and the effective values ​​of the effective EEG characteristics of the target patient to output the disease type and disease rehabilitation assessment results of the target patient.

[0044] Through the above embodiments, this application achieves the following technical effects: 1. Based on the identification of valid values, effective EEG features are identified in different age ranges. The differences in the fluctuation state of EEG features due to the differences in age ranges are fully considered. At the same time, by further considering the differentiation of disease types and the correlation of different EEG features, effective brain point features are screened, which also lays the foundation for further evaluation of the changes in rehabilitation status and disease status.

[0045] 2. By analyzing the changes in the effective EEG characteristics of the target patient and the effective identification values ​​of different effective EEG characteristics, it is possible to determine whether the patient's disease status has changed. This approach not only considers the changes in the effective EEG characteristics of different target patients, but also takes into account the degree of influence of the changes in different effective EEG characteristics by combining them with the effective identification values. This enables an accurate assessment of whether the disease status has changed and lays the foundation for further implementing differentiated rehabilitation assessment measures for different target patients.

[0046] 3. By using gait characteristics, plantar pressure characteristics, and effective EEG characteristics of the target patient, the disease type and rehabilitation assessment results of the target patient are output. This achieves the determination of the disease rehabilitation assessment results of the target patient from the perspective of multiple feature fusion, avoiding the technical problem of low accuracy caused by using a single feature, and ensuring the accuracy of the disease rehabilitation assessment results.

[0047] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0048] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0049] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A rehabilitation assessment device based on abnormal gait recognition, characterized in that, Specifically, it includes: EEG feature assessment module, EEG feature screening module, variation assessment module, and result output module; The EEG feature assessment module is responsible for classifying patients into different age ranges based on their age, and determining the disease correlation coefficients between different EEG features and different disease types within different age ranges, as well as the disease differentiation factors between different disease types, based on the patients' EEG features, disease types, and disease severity. The EEG feature screening module is responsible for determining the effective recognition values ​​of the EEG features in different age ranges through the disease correlation coefficient and disease differentiation factor, and for recognizing effective EEG features in different age ranges based on the effective recognition values. The change assessment module is responsible for determining the age range of the target patient and the effective EEG characteristics matched by the target patient based on the basic information of the target patient. It determines whether the disease status of the target patient has changed by the changes in the effective EEG characteristics of the target patient and the identification effective values ​​of different effective EEG characteristics. The result output module is responsible for extracting the gait characteristics and plantar pressure characteristics of the target patient, and combining the effective EEG characteristics and the effective values ​​of the effective EEG characteristics of the target patient to output the disease type and disease rehabilitation assessment results of the target patient. The method for determining the disease-distinguishing factors is as follows: The disease type to be analyzed is taken as the preset disease type. Based on the EEG characteristics of patients of the preset disease type, the number of similarities between the EEG characteristics of patients of the preset disease type and the EEG characteristics of patients of a specific disease type is determined. The disease distinguishing factor of the EEG characteristics between the preset disease type and the specific disease type is determined by combining the number of patients of the preset disease type and the number of patients of the specific disease type. The method for determining the effective value of the EEG features is as follows: The number of strongly correlated disease types and the number of weakly correlated disease types are determined based on the disease correlation coefficients between the EEG features and different disease types, and the comprehensive disease correlation coefficient of the EEG features is determined by combining the disease correlation coefficients between the EEG features and different disease types. Based on the disease differentiation factors of the EEG features among different disease types, the number of strongly differentiating disease types and the number of weakly differentiating disease types are determined, and the comprehensive disease differentiation factor of the EEG features is determined by combining the disease differentiation factors of the EEG features with those of different disease types. The effective identification values ​​of the EEG features in different age ranges are determined by the comprehensive disease correlation coefficient and the comprehensive disease differentiation factor.

2. The rehabilitation assessment device based on abnormal gait recognition as described in claim 1, characterized in that, The age range is divided into equal intervals according to a preset age interval, wherein the preset age interval is determined according to the number of patients, and the more patients there are, the smaller the preset age interval is.

3. The rehabilitation assessment device based on abnormal gait recognition as described in claim 1, characterized in that, The types of diseases mentioned include, but are not limited to, depression, Alzheimer's disease, and Parkinson's disease.

4. The rehabilitation assessment device based on abnormal gait recognition as described in claim 1, characterized in that, The severity of the disease is determined based on the data of disease-related indicators for different disease types of the patient, and the specific severity of the disease is divided based on percentages.

5. The rehabilitation assessment device based on abnormal gait recognition as described in claim 1, characterized in that, The method for determining the disease association coefficient is as follows: Patients with the disease type within the age range are selected as assessment patients. The magnitude of the change in the EEG characteristics of different assessment patients within a specified time period is determined based on the changes in the EEG characteristics of different assessment patients. The consistency of the EEG characteristics is determined based on the magnitude of the change in the EEG characteristics of different assessment patients within a specified time period. Based on the electroencephalogram (EEG) characteristics and the severity of the disease in different patients, the correlation coefficient between the EEG characteristics and the disease type was determined using Pearson correlation coefficient analysis. The disease association coefficient between the EEG features and the disease type is determined based on the consistency and the correlation coefficient between the EEG features and the disease type.

6. The rehabilitation assessment device based on abnormal gait recognition as described in claim 5, characterized in that, The disease association coefficient ranges from 0 to 1, and the larger the disease association coefficient, the higher the correlation between the EEG feature and the disease type.

7. The rehabilitation assessment device based on abnormal gait recognition as described in claim 1, characterized in that, Determining whether the disease status of the target patient has changed specifically includes: Based on the changes in the effective EEG characteristics of the target patient, the amplitude and amount of change of different effective EEG characteristics are determined, and the comprehensive amount of change of different effective EEG characteristics is determined by combining the effective identification values ​​of different effective EEG characteristics. The characteristic variation of the target patient is determined based on the comprehensive variation of different effective EEG characteristics, and the disease status of the target patient is determined based on the characteristic variation of the target patient.

8. The rehabilitation assessment device based on abnormal gait recognition as described in claim 1, characterized in that, The gait characteristics were obtained using a gait balance monitor with a sampling frequency of 16 frames / s and an image resolution of 800*600.

9. The rehabilitation assessment device based on abnormal gait recognition as described in claim 1, characterized in that, The output of the target patient's disease type and disease rehabilitation assessment results is based on a gait balance analyzer with 4 input channels and 10 built-in processing subsystems. The target patient's disease type and disease rehabilitation assessment results are output by printing a comprehensive analysis report.

Images