A neural disease diagnosis device based on fusion information

Abstract

The application provides a neural disease diagnosis device based on fusion information and belongs to the technical field of auxiliary diagnosis, and specifically comprises: a gait acquisition module, a plantar pressure acquisition module, an electroencephalogram signal acquisition module and a result output module. The result output module is responsible for determining the disease probability of a patient according to the time length of an evaluation period, the gait comprehensive similarity in the evaluation period, the pressure comprehensive similarity and the electroencephalogram characteristic quantity, and when the disease probability is greater than a preset probability, the presumed diagnosis result of the neural disease of the patient and the credibility of different presumed diagnosis results are obtained through the gait characteristics, the plantar pressure characteristic quantity and the electroencephalogram characteristic quantity of the patient in the evaluation period, so that the efficiency and accuracy of disease diagnosis are improved.

Description

Technical Field

[0001] This invention belongs to the field of auxiliary diagnostic technology, and in particular relates to a diagnostic device for neurological diseases based on fused information. Background Technology

[0002] Most neuropsychiatric disorders, such as depression, Alzheimer's disease, and Parkinson's disease, often have an insidious onset, with atypical early symptoms and subsequent remission and progression. Currently, the clinical diagnosis and treatment assessment of these diseases require highly trained senior specialists to conduct a comprehensive analysis, including medical history taking, physical examination, scale assessment, and imaging examinations, to reach a conclusion. However, primary care hospitals and community physicians have insufficient expertise in diagnosing and treating these diseases. Therefore, achieving rapid screening and diagnosis of neurological disorders has become an urgent technical challenge.

[0003] To address the aforementioned technical issues, the existing technical solution CN202111653438.6, "A Detection Method, Device, and Readable Storage Medium for Motor Neurological Diseases," obtains a pathological feature vector by feature stitching together reference posture data and reference plantar pressure data. Based on this pathological feature vector, it outputs the diagnostic results for motor neurological diseases, achieving rapid and accurate determination of the diagnostic results. However, at the same time, the following technical problems exist:

[0004] Existing technical solutions neglect to use EEG signals to diagnose neurological diseases and to screen posture and plantar pressure data. Specifically, joint degenerative diseases can also cause a certain degree of deterioration in patients' posture and plantar pressure data. Therefore, if EEG signals are not considered for screening posture and plantar pressure data, the accuracy of the diagnosis of neurological diseases cannot be guaranteed.

[0005] To address the aforementioned technical problems, this invention provides a diagnostic device for neurological diseases based on fused information. Summary of the Invention

[0006] To achieve the objectives of this invention, the following technical solution is adopted:

[0007] According to one aspect of the present invention, a product module partitioning method based on a clustering algorithm is provided.

[0008] A diagnostic device for neurological diseases based on fused information, characterized in that it specifically includes:

[0009] Gait acquisition module, plantar pressure acquisition module, EEG signal acquisition module, and result output module;

[0010] The gait acquisition module is responsible for determining the abnormal gait periods and gait characteristics based on the patient's gait images at different time periods. The abnormal gait periods are then filtered by the comprehensive gait similarity of the patient at different abnormal gait periods.

[0011] The plantar pressure acquisition module is responsible for determining the plantar pressure characteristics of the patient during the screening period, and further dividing the screening period into reliable time periods based on the comprehensive similarity of pressure during different screening periods.

[0012] The EEG signal acquisition module is responsible for determining the EEG characteristics of the patient during a reliable time period, and dividing the reliable time period into evaluation time periods based on the EEG characteristics of the patient during the reliable time period.

[0013] The result output module is responsible for determining the patient's disease probability based on the duration of the assessment period, the comprehensive similarity of gait, the comprehensive similarity of pressure, and the EEG characteristics during the assessment period. When the disease probability is greater than a preset probability, the module obtains the patient's inferred diagnosis of neurological diseases and the credibility of different inferred diagnosis results through the patient's gait characteristics, plantar pressure characteristics, and EEG characteristics during the assessment period.

[0014] The beneficial effects of this invention are as follows:

[0015] 1. By screening abnormal gait periods through the comprehensive similarity of patients' gait at different abnormal gait periods, the interfering periods can be screened based on the similarity of gait characteristics. This not only improves the accuracy of diagnosis but also reduces the collection of unnecessary stress monitoring data, thereby improving the efficiency of diagnosis and treatment.

[0016] 2. By dividing the credible time period based on the patient's EEG characteristics during the credible time period, the assessment time period is obtained. This enables the screening of time periods with abnormal gait characteristics or prolonged stress characteristics caused by other diseases from the perspective of EEG characteristics, which further improves the accuracy of diagnosis and treatment, while also reducing the pressure of data processing and analysis.

[0017] 3. By analyzing the patient's gait characteristics, plantar pressure characteristics, and electroencephalogram (EEG) characteristics during the assessment period, we can obtain the inferred diagnostic results for the patient's neurological diseases and assess the reliability of different inferred diagnostic results. This approach not only considers the disease diagnosis results at a single time period but also improves the accuracy of the diagnosis results through comprehensive evaluation of the disease diagnosis results at multiple time periods. It also reduces the technical problem of low accuracy caused by data interference at certain time periods.

[0018] A further technical solution is that the abnormal gait period is determined based on the matching results of the patient's gait features at different time periods. Specifically, the patient's gait features are extracted based on the gait images of the patient at different time periods, and the abnormal gait features are identified based on the matching results of the gait features and preset abnormal gait features. The time period containing the abnormal gait features is taken as the abnormal gait period.

[0019] A further technical solution is that the gait characteristics include the patient's trunk walking posture, joint swing posture, step frequency, and step distance.

[0020] A further technical solution is that the method for determining the screening period is as follows:

[0021] Similar gait periods are determined based on the comprehensive gait similarity between different abnormal gait periods and a preset similarity threshold, and these similar gait periods are used as filtering periods.

[0022] A further technical solution involves dividing the credible time period into assessment time periods based on the patient's EEG characteristics during the credible time period, specifically including:

[0023] Based on the aforementioned EEG characteristics, a reliable time period in which abnormal EEG characteristics exist is determined, and this reliable time period in which abnormal EEG characteristics exist is used as the evaluation period.

[0024] 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.

[0025] 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

[0026] 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.

[0027] Figure 1 This is a framework diagram of a neurological disease diagnostic device based on fused information.

[0028] Figure 2 This is a flowchart illustrating the method for determining the overall similarity of pressure during different screening periods. Detailed Implementation

[0029] 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.

[0030] 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.

[0031] 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 diagnostic device for neurological diseases based on fused information is provided, characterized in that it specifically includes:

[0032] Gait acquisition module, plantar pressure acquisition module, EEG signal acquisition module, and result output module;

[0033] The gait acquisition module is responsible for determining the abnormal gait periods and gait characteristics based on the patient's gait images at different time periods. The abnormal gait periods are then filtered by the comprehensive gait similarity of the patient at different abnormal gait periods.

[0034] It should be noted that the abnormal gait time period is determined based on the matching results of the patient's gait features at different time periods. Specifically, the patient's gait features are extracted based on the gait images of the patient at different time periods, and the abnormal gait features are identified based on the matching results of the gait features and preset abnormal gait features. The time period containing the abnormal gait features is taken as the abnormal gait time period.

[0035] Specifically, the gait characteristics include the patient's trunk walking posture, joint swing posture, step frequency, and step distance.

[0036] For example, the method for determining the gait comprehensive similarity is as follows:

[0037] The gait characteristics of the patient during different abnormal gait periods are obtained, and the number of abnormal gait characteristics of the patient during the abnormal gait periods and the corresponding times of different abnormal gait characteristics are determined based on the gait characteristics at different times during different abnormal gait periods.

[0038] Based on the number of abnormal gait features of the patient in different abnormal gait periods, the basic similarity of different abnormal gait periods is determined, and it is determined whether the basic similarity meets the requirements. If yes, proceed to the next step; otherwise, the basic similarity is used as the comprehensive gait similarity between different abnormal gait periods.

[0039] The number of similar abnormal gait features in different abnormal gait periods is determined by the similarity of abnormal gait features. The gait feature similarity between different abnormal gait periods is determined based on the number of similar abnormal gait features, the similarity, the deviation value of the number of abnormal gait features, and the number of deviations in abnormal gait features. It is then determined whether the gait feature similarity meets the requirements. If yes, proceed to the next step; otherwise, the gait feature similarity is used as the comprehensive gait similarity between different abnormal gait periods.

[0040] The distribution time of abnormal gait features in different abnormal gait periods is determined by analyzing the distribution of abnormal gait features in different abnormal gait periods. The temporal similarity between different abnormal gait periods is determined by combining the similarity of abnormal gait features at different distribution times and the number of times when the similarity does not meet the requirements.

[0041] The number and distribution time of normal gait features in different abnormal gait periods are obtained. Based on the number, distribution time and similarity of normal gait features in different abnormal gait periods, the similarity of normal gait features between different abnormal gait periods is determined. The comprehensive gait similarity between different abnormal gait periods is determined by combining the temporal similarity, gait feature similarity and basic similarity.

[0042] It is understood that the method for determining the screening period is as follows:

[0043] Similar gait periods are determined based on the comprehensive gait similarity between different abnormal gait periods and a preset similarity threshold, and these similar gait periods are used as filtering periods.

[0044] In another possible embodiment, the method for determining the gait comprehensive similarity of the abnormal gait period is as follows:

[0045] The gait characteristics of the patient during different abnormal gait periods are obtained, and the number of abnormal gait characteristics of the patient during the abnormal gait periods and the corresponding times of different abnormal gait characteristics are determined based on the gait characteristics at different times during different abnormal gait periods.

[0046] The number of similar abnormal gait features in different abnormal gait time periods is determined by the similarity of abnormal gait features. The similarity of gait features between different abnormal gait time periods is determined based on the number of similar abnormal gait features, the similarity, the deviation value of the number of abnormal gait features, and the number of deviations in abnormal gait features.

[0047] The distribution time of abnormal gait features in different abnormal gait periods is determined by analyzing the distribution of abnormal gait features in different abnormal gait periods. The temporal similarity between different abnormal gait periods is determined by combining the similarity of abnormal gait features at different distribution times and the number of times when the similarity does not meet the requirements.

[0048] When the temporal similarity and gait feature similarity between the abnormal gait periods cannot meet the requirements:

[0049] The comprehensive gait similarity between different abnormal gait periods is determined by the minimum value of the temporal similarity and gait feature similarity between the abnormal gait periods.

[0050] When the temporal similarity and gait feature similarity between the abnormal gait periods both meet the requirements:

[0051] Based on the number of abnormal gait features of the patient in different abnormal gait periods, the basic similarity of different abnormal gait periods is determined. The number and distribution time of normal gait features in different abnormal gait periods are obtained. Based on the number, distribution time and similarity of normal gait features in different abnormal gait periods, the similarity of normal gait features between different abnormal gait periods is determined. Finally, the comprehensive gait similarity between different abnormal gait periods is determined by combining the temporal similarity, gait feature similarity and basic similarity.

[0052] The plantar pressure acquisition module is responsible for determining the plantar pressure characteristics of the patient during the screening period, and further dividing the screening period into reliable time periods based on the comprehensive similarity of pressure during different screening periods.

[0053] It should be noted that, as Figure 2 As shown, the method for determining the overall similarity of pressure during different screening periods is as follows:

[0054] The plantar pressure characteristics of the patient at different screening time periods are obtained, and the number of abnormal pressure characteristics of the patient at different times during different screening time periods and the corresponding times of different abnormal pressure characteristics are determined based on the plantar pressure characteristics at different times during different screening time periods.

[0055] The number of similar abnormal pressure features in different abnormal pressure periods is determined by the similarity of abnormal pressure features. The similarity of pressure features between different screening periods is determined based on the number and similarity of similar abnormal pressure features, the deviation value of the number of abnormal pressure features, and the number of deviations in abnormal pressure features.

[0056] The distribution time of abnormal pressure features in different screening periods is determined by analyzing the distribution of abnormal pressure features in different screening periods. The temporal similarity between different screening periods is determined by combining the similarity of abnormal pressure features at different distribution times and the number of times when the similarity does not meet the requirements.

[0057] The number and distribution time of normal pressure features in different screening periods are obtained, and the similarity of normal pressure features between different screening periods is determined based on the number, distribution time and similarity of normal pressure features in different screening periods. The comprehensive pressure similarity between different screening periods is determined by combining the temporal similarity and gait feature similarity.

[0058] It is understandable that the screening periods are further divided into reliable periods based on the comprehensive similarity of pressure during different screening periods, specifically including:

[0059] Based on the overall pressure similarity of different screening periods and a preset pressure similarity threshold, similar pressure periods in the screening periods are determined, and these similar pressure periods are taken as reliable periods.

[0060] The EEG signal acquisition module is responsible for determining the EEG characteristics of the patient during a reliable time period, and dividing the reliable time period into evaluation time periods based on the EEG characteristics of the patient during the reliable time period.

[0061] Specifically, the assessment period is obtained by dividing the patient's EEG characteristics into reliable time periods, which include:

[0062] Based on the aforementioned EEG characteristics, a reliable time period in which abnormal EEG characteristics exist is determined, and this reliable time period in which abnormal EEG characteristics exist is used as the evaluation period.

[0063] The result output module is responsible for determining the patient's disease probability based on the duration of the assessment period, the comprehensive similarity of gait, the comprehensive similarity of pressure, and the EEG characteristics during the assessment period. When the disease probability is greater than a preset probability, the module obtains the patient's inferred diagnosis of neurological diseases and the credibility of different inferred diagnosis results through the patient's gait characteristics, plantar pressure characteristics, and EEG characteristics during the assessment period.

[0064] For example, the method for determining the patient's probability of developing the disease is as follows:

[0065] The number of assessment periods and the duration of different assessment periods are obtained to determine the total duration of the assessment periods. It is then determined whether the total duration of the assessment periods is greater than the preset minimum duration. If so, proceed to the next step. If not, it is determined that the patient's probability of having the disease is not greater than the preset probability and there is no risk of having the disease.

[0066] The degree of EEG abnormality in different assessment periods is determined by measuring EEG characteristics at different assessment periods. Based on the degree of EEG abnormality, gait similarity, and stress similarity in different assessment periods, a comprehensive assessment value is determined for each assessment period. Based on the comprehensive assessment value, suspected problem periods are identified within the assessment periods. It is then determined whether the total duration of the suspected problem periods is greater than a preset minimum duration. If so, the process proceeds to the next step. If not, it is determined that the patient's probability of having the disease is not greater than a preset probability, and there is no risk of having the disease.

[0067] The distribution of suspected problem periods in different time intervals and their duration are determined based on the distribution time of different suspected problem periods. The reliability of the patient's monitoring data is determined by combining the number of suspected problem periods and the comprehensive assessment of different suspected problem periods.

[0068] The reliability of the patient's monitoring data is determined by the number of assessment periods, the duration of different assessment periods, and the comprehensive assessment amount. The patient's disease probability is determined by combining the reliability of the monitoring data.

[0069] It should be further explained that the method for assessing the reliability of the inferred diagnostic results is as follows:

[0070] S11 determines the disease diagnosis results for different assessment periods by measuring the patient's gait characteristics, plantar pressure characteristics, and electroencephalogram characteristics at different assessment periods, and determines the inferred diagnosis results of the patient's neurological diseases based on the disease diagnosis results for different assessment periods.

[0071] S12 takes the assessment period when the disease diagnosis result is a presumed diagnosis result as the matching assessment period and determines whether the number of the matching assessment periods is greater than the preset number of periods. If yes, proceed to step S14; otherwise, proceed to the next step.

[0072] S13 determines the degree of EEG abnormality for different matching assessment periods based on the EEG characteristic values ​​of the matching assessment periods, and determines the weight values ​​for different assessment periods based on the degree of EEG abnormality, gait similarity, and stress similarity. Based on the number of weight values ​​of the matching assessment periods, it determines whether the inferred diagnosis result is accurate. If so, proceed to the next step; otherwise, assess the reliability of the inferred diagnosis result based on the number of weight values ​​of the matching assessment periods.

[0073] S14 determines the number and duration of the matching evaluation periods in different time intervals based on the distribution time of different matching evaluation periods, and determines the credibility of different inferred diagnostic results by combining the weight values ​​of different matching evaluation periods.

[0074] In another possible embodiment, the method for assessing the reliability of the speculative diagnostic result is as follows:

[0075] The disease diagnosis results for different assessment periods are determined by measuring the patient's gait characteristics, plantar pressure characteristics, and electroencephalogram (EEG) characteristics at different assessment periods, and the inferred diagnosis results of the patient's neurological diseases are determined based on the disease diagnosis results for different assessment periods.

[0076] The assessment period when the disease diagnosis result is a presumptive diagnosis result is used as the matching assessment period. When the number of the matching assessment periods is not greater than the number of preset periods, the credibility of the presumptive diagnosis result is assessed by the proportion of the number of the matching assessment periods.

[0077] When the number of matching evaluation periods is greater than the preset number of periods, the degree of EEG abnormality in different matching evaluation periods is determined by the EEG characteristic values ​​of the matching evaluation periods, and the weight values ​​of different matching evaluation periods are determined based on the degree of EEG abnormality in different matching evaluation periods, as well as gait comprehensive similarity and stress comprehensive similarity, and the reliable periods in the matching evaluation periods are determined by the weight values.

[0078] When the number of reliable time periods does not meet the requirements, the reliability of the inferred diagnostic results is determined by the number of reliable time periods and the weight value.

[0079] When the number of reliable time periods meets the requirements, the distribution quantity and duration of the matching evaluation time periods in different time intervals are determined by the distribution time of different matching evaluation time periods. The basic credibility of the inferred diagnosis result is determined by combining the weight values ​​of different matching evaluation time periods. The credibility of the inferred diagnosis result is obtained by correcting the basic credibility of the inferred diagnosis result by the number of reliable time periods and the weight values.

[0080] Through the above embodiments, the applicant has achieved the following technical effects:

[0081] 1. By screening abnormal gait periods through the comprehensive similarity of patients' gait at different abnormal gait periods, the interfering periods can be screened based on the similarity of gait characteristics. This not only improves the accuracy of diagnosis but also reduces the collection of unnecessary stress monitoring data, thereby improving the efficiency of diagnosis and treatment.

[0082] 2. By dividing the credible time period based on the patient's EEG characteristics during the credible time period, the assessment time period is obtained. This enables the screening of time periods with abnormal gait characteristics or prolonged stress characteristics caused by other diseases from the perspective of EEG characteristics, which further improves the accuracy of diagnosis and treatment, while also reducing the pressure of data processing and analysis.

[0083] 3. By analyzing the patient's gait characteristics, plantar pressure characteristics, and electroencephalogram (EEG) characteristics during the assessment period, we can obtain the inferred diagnostic results for the patient's neurological diseases and assess the reliability of different inferred diagnostic results. This approach not only considers the disease diagnosis results at a single time period but also improves the accuracy of the diagnosis results through comprehensive evaluation of the disease diagnosis results at multiple time periods. It also reduces the technical problem of low accuracy caused by data interference at certain time periods.

[0084] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for 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.

[0085] 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.

[0086] 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 diagnostic device for neurological diseases based on fused information, characterized in that, Specifically, it includes: Gait acquisition module, plantar pressure acquisition module, electroencephalogram (EEG) signal acquisition module, and result output module; The gait acquisition module is responsible for determining the abnormal gait periods and gait characteristics based on the patient's gait images at different time periods. The abnormal gait periods are then filtered by the comprehensive gait similarity of the patient at different abnormal gait periods. The gait characteristics include the patient's trunk walking posture, joint swing posture, step frequency, and step distance; The method for determining the screening period is as follows: Similar gait periods are determined based on the comprehensive gait similarity between different abnormal gait periods and a preset similarity threshold, and these similar gait periods are used as filtering periods. The plantar pressure acquisition module is responsible for determining the plantar pressure characteristics of the patient during the screening period, and further dividing the screening period into reliable time periods based on the comprehensive similarity of pressure during different screening periods. Specifically, it includes: Based on the overall pressure similarity of different screening periods and a preset pressure similarity threshold, similar pressure periods in the screening periods are determined, and these similar pressure periods are taken as reliable periods. The EEG signal acquisition module is responsible for determining the EEG characteristics of the patient during a reliable time period, and dividing the reliable time period into evaluation time periods based on the EEG characteristics of the patient during the reliable time period. Specifically, it includes: Based on the aforementioned EEG characteristics, a reliable time period in which abnormal EEG characteristics exist is determined, and the reliable time period in which abnormal EEG characteristics exist is used as the evaluation period. The result output module is responsible for determining the patient's disease probability based on the duration of the assessment period, the comprehensive similarity of gait, the comprehensive similarity of pressure, and the EEG characteristics during the assessment period. When the disease probability is greater than a preset probability, the module obtains the patient's inferred diagnosis of neurological diseases and the credibility of different inferred diagnosis results through the patient's gait characteristics, plantar pressure characteristics, and EEG characteristics during the assessment period. The method for determining the patient's probability of having the disease is as follows: The number of assessment periods and the duration of different assessment periods are obtained to determine the total duration of the assessment periods. It is then determined whether the total duration of the assessment periods is greater than the preset minimum duration. If so, proceed to the next step. If not, it is determined that the patient's probability of having the disease is not greater than the preset probability and there is no risk of having the disease. The degree of EEG abnormality in different assessment periods is determined by measuring EEG characteristics at different assessment periods. Based on the degree of EEG abnormality, gait similarity, and stress similarity in different assessment periods, a comprehensive assessment value is determined for each assessment period. Based on the comprehensive assessment value, suspected problem periods are identified within the assessment periods. It is then determined whether the total duration of the suspected problem periods is greater than a preset minimum duration. If so, the process proceeds to the next step. If not, it is determined that the patient's probability of having the disease is not greater than a preset probability, and there is no risk of having the disease. The distribution of suspected problem periods in different time intervals and their duration are determined based on the distribution time of different suspected problem periods. The reliability of the patient's monitoring data is determined by combining the number of suspected problem periods and the comprehensive assessment of different suspected problem periods. The reliability of the patient's monitoring data is determined by the number of assessment periods, the duration of different assessment periods, and the comprehensive assessment amount. The patient's disease probability is determined by combining the reliability of the monitoring data.

2. The diagnostic device for neurological diseases as described in claim 1, characterized in that, The abnormal gait time period is determined based on the matching results of the patient's gait features at different time periods. Specifically, the patient's gait features are extracted based on the gait images of the patient at different time periods, and the abnormal gait features are identified based on the matching results of the gait features and preset abnormal gait features. The time period containing the abnormal gait features is taken as the abnormal gait time period.

3. The diagnostic device for neurological diseases as described in claim 1, characterized in that, The method for determining the gait comprehensive similarity is as follows: The gait characteristics of the patient during different abnormal gait periods are obtained, and the number of abnormal gait characteristics of the patient during the abnormal gait periods and the corresponding times of different abnormal gait characteristics are determined based on the gait characteristics at different times during different abnormal gait periods. Based on the number of abnormal gait features of the patient in different abnormal gait periods, the basic similarity of different abnormal gait periods is determined, and it is determined whether the basic similarity meets the requirements. If yes, proceed to the next step; otherwise, the basic similarity is used as the comprehensive gait similarity between different abnormal gait periods. The number of similar abnormal gait features in different abnormal gait periods is determined by the similarity of abnormal gait features. The gait feature similarity between different abnormal gait periods is determined based on the number of similar abnormal gait features, the similarity, the deviation value of the number of abnormal gait features, and the number of deviations in abnormal gait features. It is then determined whether the gait feature similarity meets the requirements. If yes, proceed to the next step; otherwise, the gait feature similarity is used as the comprehensive gait similarity between different abnormal gait periods. The distribution time of abnormal gait features in different abnormal gait periods is determined by analyzing the distribution of abnormal gait features in different abnormal gait periods. The temporal similarity between different abnormal gait periods is determined by combining the similarity of abnormal gait features at different distribution times and the number of times when the similarity does not meet the requirements. The number and distribution time of normal gait features in different abnormal gait periods are obtained. Based on the number, distribution time and similarity of normal gait features in different abnormal gait periods, the similarity of normal gait features between different abnormal gait periods is determined. The comprehensive gait similarity between different abnormal gait periods is determined by combining the temporal similarity, gait feature similarity and basic similarity.

4. The diagnostic device for neurological diseases as described in claim 1, characterized in that, The method for determining the overall similarity of pressure during different screening periods is as follows: The plantar pressure characteristics of the patient at different screening time periods are obtained, and the number of abnormal pressure characteristics of the patient at different times during different screening time periods and the corresponding times of different abnormal pressure characteristics are determined based on the plantar pressure characteristics at different times during different screening time periods. The number of similar abnormal pressure features in different abnormal pressure periods is determined by the similarity of abnormal pressure features. The similarity of pressure features between different screening periods is determined based on the number and similarity of similar abnormal pressure features, the deviation value of the number of abnormal pressure features, and the number of deviations in abnormal pressure features. The distribution time of abnormal pressure features in different screening periods is determined by analyzing the distribution of abnormal pressure features in different screening periods. The temporal similarity between different screening periods is determined by combining the similarity of abnormal pressure features at different distribution times and the number of times when the similarity does not meet the requirements. The number and distribution time of normal pressure features in different screening periods are obtained, and the similarity of normal pressure features between different screening periods is determined based on the number, distribution time and similarity of normal pressure features in different screening periods. The comprehensive pressure similarity between different screening periods is determined by combining the temporal similarity and gait feature similarity.

Images