A non-walking gait simulation evaluation system based on virtual reality interaction

Abstract

The application relates to the technical field of medical data processing, and discloses a non-walking type gait simulation evaluation system based on virtual reality interaction, which uses a virtual reality interaction module to make a to-be-tested person complete a gait task of simulated walking in any one or any combination of a cognitive load task, an emotional load task and a space obstacle task in a virtual reality test scene, so that real-time gait changes of the to-be-tested person in different scenes are simulated, efficient and accurate gait evaluation is realized in combination with a data acquisition module and a processor, the safety of the to-be-tested person in the gait evaluation process can be ensured, and the objectivity of the evaluation process can be ensured, especially in the case that the to-be-tested person often has a frozen gait, the time and frequency of footstep stagnation or change can be accurately recorded, doctors can accurately understand the occurrence mode of the frozen gait of Parkinson's patients, and effective data guidance is provided for personalized treatment of the patients.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical data processing, and particularly relates to a non-walking gait simulation evaluation system based on virtual reality interaction. BACKGROUND

[0002] Parkinson's disease is a high-incidence and high-disability neurodegenerative disease. This not only seriously affects the quality of life of patients, but also brings great challenges to the medical and social security system. Therefore, early diagnosis, accurate assessment and targeted treatment have become the core needs of the clinical management of Parkinson's disease.

[0003] Freezing of gait (FOG) is one of the typical symptoms of Parkinson's disease, which is characterized by sudden difficulty in starting or maintaining walking, accompanied by gait arrest and loss of balance. This symptom significantly increases the risk of falling and is an important cause of disability and even death in patients. However, the pathological mechanism of FOG has not been fully elucidated, and its triggering factors and mechanisms still need further research. The International Movement Disorder Society (MDS) has included FOG in the Parkinson's disease assessment scale, but the existing clinical assessment methods still have significant limitations:

[0004] Subjectivity is strong and lacks objective standards: current methods mainly rely on manual observation and questionnaire surveys, which are easily affected by the experience of the evaluator, the subjective description of the patient and environmental interference, resulting in poor consistency of the results and difficulty in accurate quantification.

[0005] Safety hazards are prominent: actual walking tests may induce patients to fall, especially for patients with moderate to severe FOG, the testing process has a high risk, which limits its clinical application.

[0006] Limited assessment coverage: subtle gait abnormalities in patients with mild FOG are difficult to detect through traditional methods, which may delay intervention; while patients with severe symptoms are limited in their ability to move, and can only be assessed through descriptive records, which cannot analyze specific gait characteristics.

[0007] Cannot quantify the influence of cognition and emotion: FOG is often closely related to cognitive load (such as performing dual tasks) and emotional state (such as anxiety), but existing methods cannot introduce specific tasks into the evaluation to quantify the role of these factors, which restricts the development of personalized treatment.

[0008] Therefore, a new non-walking gait simulation evaluation system based on virtual reality interaction is needed to assist doctors in objectively, comprehensively and accurately evaluating the freezing gait of Parkinson's disease, while improving the safety of patients during the evaluation process. SUMMARY

[0009] The application provides a non-walking gait simulation evaluation system based on virtual reality interaction, to solve the defects of the existing Parkinson's disease frozen gait evaluation method, which is not objective, low accuracy, and cannot guarantee the safety of the patient during the evaluation process.

[0010] The application provides a non-walking gait simulation evaluation system based on virtual reality interaction, comprising:

[0011] A virtual reality interaction module is arranged to present a dynamically adjustable virtual reality test scene to the subject, and the virtual reality test scene contains gait tasks of different difficulty levels simulating walking;

[0012] A static body position support unit includes a rigid bearing structure and a pedal, configured to support the patient in a non-walking static posture;

[0013] A data acquisition module includes one or more motion sensors fixedly arranged on the pedal, configured to acquire non-walking simulation gait data of the subject in real time when the subject responds to the gait tasks simulating walking and send the data to the data processing unit;

[0014] A data processing unit is in communication connection with the data acquisition module and the virtual reality interaction module, including a processor and a memory, the processor is configured to execute the computer program stored in the memory, and the processor executes the computer program to realize the following steps: receiving the non-walking simulation gait data of the subject sent by the data acquisition module, and obtaining the gait evaluation result of the subject according to the non-walking simulation gait data of the subject.

[0015] According to the non-walking gait simulation evaluation system based on virtual reality interaction provided by the application, the subject is a Parkinson's disease patient, the gait evaluation result is a Parkinson's disease frozen gait evaluation result, and the gait tasks of different difficulty levels include gait tasks coordinated with any one or any combination of the following: cognitive load tasks, emotional load tasks, and spatial obstacle tasks.

[0016] In an embodiment, the gait task can be for the subject to walk in the prompt in the virtual reality test scene to simulate a real walking scene.

[0017] In an embodiment, the gait task coordinated with the cognitive load task can be for the subject to perform cognitive response and decision-making while completing the gait task in the virtual reality test scene, to simulate the influence of complex cognitive load on the gait of the subject.

[0018] In an embodiment, the cognitive load task adopts a multi-level cognitive task paradigm, and a progressive difficulty gradient task is designed from a baseline walking task to a complex cognitive-motor integration task.

[0019] In an embodiment, the gait task cooperated with the emotional load task can be to first increase the spatial height in the virtual reality test scene to simulate the cliff effect, etc., and then let the person to be tested complete the gait task, or to add a situation that can bring emotional pressure to the person to be tested in the process of completing the gait task by the person to be tested, to simulate the gait performance of the person to be tested under emotional pressure.

[0020] In an embodiment, the emotional load task is realized by constructing a multi-modal emotion induction system, using virtual reality scene design, physiological signal monitoring and task parameter control to realize the accurate application and quantification of emotional pressure.

[0021] In an embodiment, the gait task cooperated with the spatial obstacle task can be to add narrow doors, obstacles and other spatial obstacles in the virtual reality test scene, and then let the person to be tested complete the gait task, to simulate the gait ability of the person to be tested in a complex environment, especially in the case of obstacle avoidance and obstacle crossing, which is helpful to more accurately evaluate the occurrence and changes of the person to be tested.

[0022] In an embodiment, the spatial obstacle task adopts a parameterized environment modeling method, and a three-dimensional space structure with precise size control is dynamically generated by a virtual reality engine, focusing on investigating two types of parameters, i.e., channel restriction and obstacle layout.

[0023] When the gait task occurs alone, the gait task at this time is a gait task with a difficulty level of 0, when the gait task occurs cooperatively with any one of the cognitive load task, the emotional load task and the spatial obstacle task, the gait task at this time is a gait task with a difficulty level of I, when the gait task occurs cooperatively with any two of the cognitive load task, the emotional load task and the spatial obstacle task, the gait task at this time is a gait task with a difficulty level of II, and when the gait task occurs cooperatively with the cognitive load task, the emotional load task and the spatial obstacle task, the gait task at this time is a gait task with a difficulty level of III.

[0024] According to the non-walking gait simulation evaluation system based on virtual reality interaction provided by the application, the non-walking simulation gait data includes any one or any combination of the following: step time, step frequency, step length, step speed, gait rhythm and reaction time to prompt words.

[0025] In an embodiment, the step time refers to the time interval of continuous two times of landing of a single side foot, the step frequency refers to the number of steps completed per unit time (reciprocal of the step time), the step speed refers to the distance traveled per unit time (step frequency x step length), the gait rhythm refers to the time regularity of the step sequence (such as the symmetry of left and right step time), and the reaction time to prompt words refers to the time length from the issuance of the prompt words to start walking to the start of walking by the person to be tested.

[0026] According to the application, a non-walking gait simulation evaluation system based on virtual reality interaction is provided, which obtains a gait evaluation result of a to-be-tested person according to non-walking simulation gait data of the to-be-tested person, and comprises the following steps of:

[0027] The non-walking simulation gait data of the to-be-tested person is analyzed in real time by using a dynamic sliding window method, and key index data of the non-walking simulation gait data in each analysis window is obtained.

[0028] According to the key index data of the non-walking simulation gait data in each analysis window, a first gait evaluation result of the to-be-tested person is obtained in combination with a preset evaluation standard.

[0029] According to the application, a non-walking gait simulation evaluation system based on virtual reality interaction is provided, and the key index data comprises data of any one of the following indexes or any combination thereof: a step time mode and a distribution characteristic thereof, a step frequency mean value and a standard deviation, a gait rhythm variation coefficient (gait rhythm variation coefficient CV=gait rhythm standard deviation / step rhythm mean value*100%), and an average reaction time to a prompt and a dispersion degree thereof.

[0030] According to the application, a non-walking gait simulation evaluation system based on virtual reality interaction is provided, and the preset evaluation standard comprises the following:

[0031] A. For each analysis window, when the following two or more conditions are met at the same time, a frozen event occurrence window is determined:

[0032] The current step time is more than 2 times the step time mode in the analysis window;

[0033] The gait rhythm variation coefficient is greater than 0.4;

[0034] The current reaction time to the prompt is more than 2 standard deviations of the reaction time mean value of the analysis window;

[0035] The current step frequency is lower than 60% of the step frequency mean value of the analysis window;

[0036] B. When two or more frozen event occurrence windows occur continuously, or the frozen event occurrence window occurs multiple times within a preset time period, a continuous frozen gait event is determined to occur, and the specific time of the frozen gait event is recorded.

[0037] According to the application, a non-walking gait simulation evaluation system based on virtual reality interaction is provided, which obtains a gait evaluation result of a to-be-tested person according to non-walking simulation gait data of the to-be-tested person, and comprises the following steps of:

[0038] According to the non-walking simulation gait data of the to-be-tested person, the difficulty of the cognitive load task and the dose-response relationship of the change of the non-walking simulation gait data are analyzed respectively, the dose-response relationship of the emotional intensity of the emotional load task and the freezing duration is analyzed, and the dose-response relationship of the constraint intensity of the spatial obstacle task and the freezing occurrence is analyzed.

[0039] The difficulty of the cognitive load task and the dose-response relationship of the change of the non-walking simulation gait data, the dose-response relationship of the emotional intensity of the emotional load task and the freezing duration, and the dose-response relationship of the constraint intensity of the spatial obstacle task and the freezing occurrence are comprehensively analyzed, the synergistic effect mode of the multi-dimensional factors is analyzed by using a random forest algorithm, and the second gait evaluation result of the to-be-tested person is obtained.

[0040] According to the non-walking simulation gait evaluation system based on virtual reality interaction provided by the application, the second gait evaluation result includes any one or any combination of the following: the severity quantitative index data of the freezing event, the probability distribution characteristics of the freezing occurrence under different inducing factors, the freezing gait subtype classification based on multi-dimensional data analysis, and the freezing gait subtype includes cognitive load dominant type, emotional stress induced type and spatial constraint sensitive type.

[0041] In an embodiment, a user interaction terminal is further included, which is in communication connection with the data processing unit and is used to provide the gait evaluation result to the user.

[0042] In an embodiment, the pedal can be hinged on the seat body for the to-be-tested person to step on. One or more gait sensing components can be installed on, in or at the bottom of the pedal, such as a plurality of sensors, for example, pressure sensors or sensor arrays, for sensing the foot bottom pressure distribution, the size and timing of the vertical ground reaction force, the pressure center trajectory, the starting time and duration of each stage of the gait cycle; an inertial measurement unit for measuring three-dimensional acceleration and angular velocity of the pedal / foot, foot posture, gait speed, step length and step frequency and other parameters (in combination with pressure parameters); a position / displacement sensor, for example, an optical or ultrasonic sensor, for accurately measuring the relative position of the foot on the pedal (for example, from heel to toe), and the like. In a specific embodiment, a pressure sensor array can be installed at the bottom of the pedal for synchronous acquisition of the timing of the foot bottom pressure distribution and feedback of the stepping depth of the pedal. In an embodiment, an embedded microcontroller or microprocessor can also be installed in or near the pedal for real-time acquisition of all sensor data, signal preprocessing (for example, filtering, denoising, baseline correction), and conversion of analog signals sensed by the sensors into digital signals, generation of non-walking simulation gait data and sending to the processor of the data processing unit.

[0043] In one embodiment, the system of the present application can further comprise a seat or a customized railing, preferably a seat. In this way, the subject can sit on the seat to complete the gait assessment process, or hold the railing to complete the gait assessment process.

[0044] In one embodiment, for patients dominated by cognitive load, a daily life activity guidance program can be provided according to the dose-response relationship between the difficulty of cognitive load tasks and the change in non-walking gait data. For example, mild patients can perform low-complexity dual-task walking, such as simple counting or naming exercises while walking, but should avoid complex environment walking that requires quick decision-making; moderate patients should choose structured walking training, such as rhythmic walking on a fixed route, but should avoid sudden disturbances or route changes; severe patients are only recommended to walk a short distance on a straight path without interference, and are prohibited from any distracting movement tasks.

[0045] In one embodiment, for patients sensitive to spatial constraints, a progressive spatial adaptation training program can be provided based on the analysis results of parameters such as the ratio of passage width to shoulder width and obstacle density. For example, when the ratio of passage width to shoulder width is <1.2, open environment walking training is recommended; when the ratio is between 1.2 and 1.5, standard width passage walking can be tried; when the ratio is >1.5, narrow space adaptability training can be performed. At the same time, according to the obstacle density threshold, the corresponding obstacle avoidance training plan is designed.

[0046] In one embodiment, for patients induced by emotional stress, targeted psychological intervention suggestions can be provided according to the results of emotional induction tests. For those highly sensitive to threatening environments, systematic desensitization therapy is recommended; for those sensitive to social evaluation, social scene exposure training is suggested; for those sensitive to time pressure, relaxation training and time management strategies are provided.

[0047] The data processing unit can be in communication connection with the virtual reality interaction module and the user interaction terminal through wireless or wired means. When connected wirelessly, the data processing unit can include a wireless communication module for establishing a low-power data transmission channel with the data acquisition module, such as using Bluetooth or ZigBee protocol.

[0048] As a user interaction terminal, it can be a mobile terminal or an embedded tablet device, or an electronic medical record system in a hospital, for providing the user (doctor or other medical staff participating in the assessment) with the Parkinson's disease freezing assessment results and assessment report of the subject. In the present application, the provision includes but is not limited to visual display, electronic file export, physical printing, and network transmission delivery methods.

[0049] In an embodiment, the data processing unit can further comprise a visualization module configured to visualize the evaluation result of the freezing of gait of the subject with Parkinson's disease, to obtain a visualization report of the evaluation of the freezing of gait of the subject with Parkinson's disease. Further, the evaluation report can comprise personalized guidance information made according to the evaluation result of the freezing of gait of the subject with Parkinson's disease, wherein the personalized guidance information can comprise any one or any combination of the following: gait improvement suggestions, freezing gait occurrence warning information, and task completion status.

[0050] It is to be noted that the visualization module can also be configured in the user interaction terminal, but based on the sensitivity of medical data, from the perspective of data security, it is preferred to be configured in the data processing center (for example, a central server, a data center of a private cloud architecture, etc.).

[0051] In an embodiment, the content displayed in the evaluation report of the freezing of gait of the subject with Parkinson's disease can comprise any one or any combination of the following: gait performance of the subject under different difficulty levels of gait tasks, occurrence of freezing gait, and potential for gait improvement, etc., and the report content can provide a reference basis for subsequent treatment plan formulation.

[0052] In an embodiment, the visualization module comprises multiple dimensions of data presentation methods. In terms of severity visualization, a gradual color scale from light green to dark red is used to represent the change trend from light to severe symptoms, while the specific clinical score value and the corresponding symptom description are labeled, so that medical personnel can quickly grasp the overall condition of the patient. For the visualization of subtypes, a three-dimensional coordinate system chart can be generated, with cognitive load, spatial constraint and emotional stress as coordinate axes, and the dominant subtype characteristics of the patient data points are intuitively reflected by the position distribution, and supplemented by the text description of typical symptoms.

[0053] In an embodiment, the visualization module comprises a graphical interactive interface. For motion guidance suggestions, the graphical interactive interface can display a dynamic simulation of human motion schematic diagram, label the amplitude, frequency and duration of recommended actions, and identify the contraindicated actions with warning icons. The environmental adaptation suggestions are displayed through virtual scene reconstruction technology, and the channel width, obstacle density and other parameters can be adjusted to intuitively demonstrate the patient's walking performance under different environmental configurations. The training progress tracking part adopts a time axis form to compare and display the historical evaluation data with the preset target value, and automatically calculates the recommended value of the training intensity in the next stage.

[0054] All visualized contents support multi-level information display, and users can obtain more detailed data analysis through clicking or zooming operation. The visualization module can further include a report generation module, which can generate a standardized evaluation document containing key charts and data summaries, facilitating clinical archiving and cross-department collaboration. The output results of the visualization module can be directly associated with the electronic medical record system of the hospital, providing intuitive basis for the multi-disciplinary treatment team to develop personalized intervention programs.

[0055] The application also provides a gait evaluation method realized by the gait evaluation system based on virtual reality interaction, comprising the following steps:

[0056] S1. The virtual reality test scene with dynamic adjustment is loaded to the subject to be tested through the virtual reality interaction module, and the virtual reality test scene contains gait tasks with different difficulties;

[0057] S2. The non-walking simulation gait data of the subject to be tested when performing the simulation walking gait task are collected in real time by the data acquisition module and transmitted to the data processing unit;

[0058] S3. The non-walking simulation gait data of the subject to be tested sent by the data acquisition module are received by the data processing unit, and the gait evaluation result of the subject to be tested is obtained according to the non-walking simulation gait data of the subject to be tested.

[0059] In a preferred embodiment, the visualization module of the data processing center generates a visual gait evaluation report based on the gait evaluation result, and the user interaction terminal receives and displays the evaluation report to the user.

[0060] The gait evaluation system based on virtual reality interaction provided by the application uses the virtual reality interaction module to make the subject to be tested complete the simulation walking gait task in the virtual reality test scene in cooperation with any one or any combination of cognitive load task, emotional load task and spatial obstacle task, to simulate the real-time gait changes of the subject to be tested in different scenes, and realizes efficient and accurate gait evaluation in combination with the data acquisition module and the processor, which can guarantee the safety of the subject to be tested in the gait evaluation process and the objectivity of the evaluation process, especially in the case of frozen gait of the subject to be tested, the time and frequency of footstep stagnation or change can be accurately recorded, which helps doctors accurately understand the occurrence mode of frozen gait and provides effective data guidance for personalized treatment of patients. BRIEF DESCRIPTION OF DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0062] Figure 1 A structure schematic diagram of a non-walking gait simulation and evaluation system based on virtual reality interaction provided by the present application.

[0063] Figure 2 A structure schematic diagram of a non-walking gait simulation and evaluation system based on virtual reality interaction provided by the present application applied to the evaluation of frozen gait of Parkinson's disease. The reference signs are as follows: 1, VR glasses; 2, static body position support unit; 3, data acquisition module; 4, non-walking gait simulation and evaluation system based on virtual reality interaction.

[0064] Figure 3 A flowchart of a non-walking gait simulation and evaluation system based on virtual reality interaction provided by the present application applied to the evaluation of frozen gait of Parkinson's disease. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solutions and advantages of the present application more clear, the technical solutions in the present application will be described clearly and completely in the following with reference to the accompanying drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. They should not be understood as a limitation to the present application. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without any creative effort belong to the protection scope of the present application. In the description of the present application, it should be understood that the used terms are only for the purpose of description, and should not be understood as indicating or implying relative importance.

[0066] Figure 1 A structure schematic diagram of a non-walking gait simulation and evaluation system based on virtual reality interaction provided by the present application. Figure 2 And 3 A structure schematic diagram and a flowchart of a non-walking gait simulation and evaluation system based on virtual reality interaction provided by the present application applied to the evaluation of frozen gait of Parkinson's disease.

[0067] Referring to Figures 1 to 3 The non-walking gait simulation and evaluation system based on virtual reality interaction provided by the present application can include:

[0068] A, a virtual reality interaction module, configured to present a dynamically adjustable virtual reality test scene to a subject, the virtual reality test scene comprising gait tasks of different difficulty levels simulating walking, wherein the subject is a Parkinson's disease patient.

[0069] In the present application, the virtual reality interaction module can include one or more of the following components: a virtual reality head-mounted device, such as a head-mounted display device HMD; a reality scene acquisition and reconstruction system (including a laser radar scanner, a multi-view panoramic camera array, etc.); a reality fusion enhancement module (including a high-definition RGB camera); a motion capture device (such as an optical motion capture system, an inertial motion capture device, etc.); an environmental sensor (such as a light sensor, a sound sensor, etc.); a voice interaction device (including a high-fidelity earphone, a microphone). Virtual reality interaction modules can be constructed using existing virtual interaction hardware and related software in the art as needed. Figure 2 In an embodiment, the virtual reality interaction module is implemented using VR glasses.

[0070] In an embodiment, the gait tasks of different difficulty levels include gait tasks in coordination with any one or any combination of the following: cognitive load tasks, emotional load tasks, spatial obstacle tasks.

[0071] In an embodiment, the gait tasks can be for the subject to walk in the prompt of the virtual reality test scene to simulate a real walking scene.

[0072] The gait task in coordination with the cognitive load task can be for the subject to perform cognitive responses and decisions while completing the gait task in the virtual reality test scene to simulate the impact of complex cognitive load on the subject's gait. The cognitive load task in this embodiment uses a multi-level cognitive task paradigm to design progressive difficulty gradient tasks, from baseline walking tasks to complex cognitive-motor integration tasks.

[0073] The gait task in coordination with the emotional load task can be for the subject to complete the gait task after first increasing the spatial height in the virtual reality test scene to simulate a cliff effect, etc., or can be for the subject to complete the gait task while additional situations that can cause emotional stress to the subject are added to simulate the subject's gait performance under emotional stress. The emotional load task in this embodiment uses a multi-modal emotion induction system to achieve precise application and quantification of emotional stress through virtual reality scene design, physiological signal monitoring, and task parameter control.

[0074] The gait task cooperated with the spatial obstacle task can be that a narrow door, an obstacle or the like is added in the virtual reality test scene, and the to-be-tested person is required to complete the gait task, so as to simulate the gait ability of the to-be-tested person in a complex environment, especially in the case of obstacle avoidance and obstacle crossing, which is helpful to more accurately evaluate the occurrence and change of the freezing gait of the to-be-tested person. The spatial obstacle task in the embodiment adopts a parameterized environment modeling method, and a three-dimensional space structure with accurate size control is dynamically generated through a virtual reality engine, and two types of parameters, i.e., channel restriction and obstacle layout, are focused on.

[0075] In an embodiment, when the gait task occurs alone, the gait task at this time is a gait task with a difficulty level of 0, when the gait task occurs cooperatively with any one of the cognitive load task, the emotional load task and the spatial obstacle task, the gait task at this time is a gait task with a difficulty level of I, when the gait task occurs cooperatively with any two of the cognitive load task, the emotional load task and the spatial obstacle task, the gait task at this time is a gait task with a difficulty level of II, and when the gait task occurs cooperatively with the cognitive load task, the emotional load task and the spatial obstacle task, the gait task at this time is a gait task with a difficulty level of III.

[0076] B, a data acquisition module, configured to acquire the non-walking simulation gait data of the to-be-tested person in real time when the to-be-tested person performs the gait task, and send the non-walking simulation gait data of the to-be-tested person to the processor.

[0077] In an embodiment, the non-walking simulation gait data includes any one or any combination of the following: step time, step frequency, step length, step speed, gait rhythm, reaction time to prompt. The step time refers to the time interval between the landing of a single foot twice in succession, the step frequency refers to the number of steps completed per unit time (reciprocal of the step time), the step speed refers to the distance traveled per unit time (step frequency x step length), the gait rhythm refers to the time regularity of the step sequence (such as the symmetry of left and right step time), and the reaction time to the prompt refers to the length of time from the issuance of the prompt for the to-be-tested person to start walking to the start of walking by the to-be-tested person.

[0078] C, a data processing unit, in communication connection with the data acquisition module and the virtual reality interaction module, including a processor and a memory, the processor being configured to execute a computer program stored in the memory, and the processor, when executing the computer program, implements the following steps: receiving the non-walking simulation gait data of the to-be-tested person sent by the data acquisition module, and obtaining the gait evaluation result of the to-be-tested person according to the non-walking simulation gait data of the to-be-tested person, which is the freezing gait evaluation result of Parkinson's disease in the embodiment.

[0079] In an embodiment, the obtaining of the gait evaluation result of the subject according to the non-walking simulation gait data of the subject can comprise:

[0080] The non-walking simulation gait data of the subject is analyzed in real time by using a dynamic sliding window method to obtain key indicator data of the non-walking simulation gait data in each analysis window (in this embodiment, the window length is set to 30 seconds, and the sliding step length is set to 5 seconds, which can effectively capture the dynamic characteristics of the gait cycle changes and meet the real-time analysis requirements), wherein the key indicator data includes any one of the following indicators or data of any combination thereof: mode of step time and distribution characteristics, mean and standard deviation of step frequency, gait rhythm variation coefficient (gait rhythm variation coefficient CV = gait rhythm standard deviation / gait rhythm mean x 100%), average reaction time to prompt and its dispersion degree;

[0081] According to the key indicator data of the non-walking simulation gait data in each analysis window, the first gait evaluation result of the subject is obtained in combination with a preset evaluation standard, wherein the preset evaluation standard is that when two or more of the following conditions are met simultaneously, it is determined that a freezing event occurs:

[0082] The preset evaluation standard includes:

[0083] I. For each analysis window, when two or more of the following conditions are met simultaneously, it is determined that a freezing event occurs:

[0084] The current step time is more than 2 times the mode of step time in the analysis window;

[0085] The gait rhythm variation coefficient is greater than 0.4;

[0086] The current reaction time to the prompt is more than 2 standard deviations of the mean reaction time in the analysis window;

[0087] The current step frequency is lower than 60% of the mean step frequency in the analysis window;

[0088] II. When two or more freezing event occurrence windows occur continuously, or the freezing event occurrence window occurs multiple times within a preset time period (for example, 1 minute), it is determined that a continuous freezing gait event occurs, and the specific time of the freezing gait event is recorded.

[0089] In each analysis window, the so-called "current step time", "current reaction time to prompt", "current step frequency" and other current index values actually refer to the latest data collected in real time in the analysis window. The latest data is compared with the historical data in the same window: for example, the "current step time" is compared with the step time mode of the window, and the "current reaction time" is compared with the mean and standard deviation of the reaction time of the window. This means that each time the sliding window is analyzed, the data points newly entering the window are always compared with the historical statistical values inside the window.

[0090] For example, assume that in analysis window 1 (0-30 seconds), the step frequency mean = 100 steps / minute, the step mode = 0.6 seconds / step, the gait rhythm CV = 0.3, the average reaction time to prompt = 1 second, and the standard deviation = 0.2 seconds; if the latest step frequency at the end of the analysis window is 55 steps / minute (60% lower than the mean), and the latest step time is 1.3 seconds (more than 2 times the mode); at this time, analysis window 1 meets 2 freezing conditions, so it is marked as a "freezing event occurrence window". When the analysis window slides to the next stage (5-35 seconds), the same analysis is performed again; if several consecutive analysis windows appear with the "freezing event occurrence window" mark, it is determined that a continuous freezing event has occurred.

[0091] For the determination of whether a freezing phenomenon occurs, the embodiment establishes a multi-index joint decision mechanism, and the multi-index cross-validation method can significantly improve the accuracy of the evaluation of Parkinson's disease freezing gait compared with the traditional single threshold method.

[0092] In one embodiment, a two-stage analysis method can be used to establish a multi-dimensional task evaluation system: first, the independent effects of each single dimension are quantified by a generalized linear mixed model; then, by constructing a three-order interaction term of cognition × space × emotion, the synergistic effect pattern of multi-dimensional factors is analyzed by using a random forest algorithm. This method can achieve three technical innovations: standardized grading ensures that the experimental conditions are repeatable; continuous variable modeling avoids information loss; and explicit analysis of multi-dimensional interactions. The final quantitative correlation model not only reveals the independent influence of each parameter, but also discovers the synergistic effect of key parameter combinations.

[0093] Specifically, the gait evaluation result of the to-be-tested person can be obtained according to the non-walking simulation gait data of the to-be-tested person, which can include:

[0094] According to the non-walking simulation gait data of the to-be-tested person, the difficulty of the cognitive load task and the dose-response relationship of the change in the non-walking simulation gait data (which can be analyzed by using a machine learning method), the dose-response relationship of the emotional intensity of the emotional load task and the freezing duration (which can be analyzed by using a time series alignment technique and a survival analysis method), and the dose-response relationship of the constraint intensity of the spatial obstacle task and the freezing occurrence (which can be analyzed by using a mixed effect model) are analyzed respectively.

[0095] The difficulty of the comprehensive cognitive load task and the dose-response relationship of the non-walking simulation gait data change, the emotional intensity of the emotional load task and the dose-response relationship of the freezing duration, and the constraint intensity of the spatial obstacle task and the dose-response relationship of the freezing occurrence are analyzed by using the random forest algorithm to analyze the synergistic effect mode of multiple factors, and the second gait evaluation result of the to-be-tested person is obtained.

[0096] In an embodiment, the freezing gait evaluation result of Parkinson's disease can include any one or any combination of the following: quantitative indicator data of the severity of freezing events (including freezing event duration (such as continuous window cumulative duration), freezing event frequency (number of events per unit time), freezing event proportion (percentage of freezing duration to total test duration)), probability distribution characteristics of freezing occurrence under different inducing factors, freezing gait subtype classification based on multi-dimensional data analysis, and wherein the freezing gait subtype includes cognitive load dominant type, emotional stress induced type, and spatial constraint sensitive type. These evaluation results can provide objective, quantitative and scientific basis for clinical diagnosis and treatment plan formulation, and help to realize individualized precision medicine. In particular, by identifying specific freezing gait subtypes such as cognitive load dominant type, spatial constraint sensitive type and emotional stress induced type, the clinician can be provided with targeted treatment recommendations, significantly improving the intervention effect.

[0097] Specifically, the probability distribution characteristics of freezing occurrence under different inducing factors and the freezing gait subtype classification based on multi-dimensional data analysis can be obtained in the following way.

[0098] Probability distribution characteristics of freezing occurrence under different inducing factors:

[0099] (I) Obtaining method:

[0100] The following three-dimensional task tests are performed respectively, and the corresponding non-walking simulation gait data is collected in real time:

[0101] Cognitive load dimension: multi-level cognitive task paradigm, difficulty increasing step by step;

[0102] Emotional load dimension: virtual reality scene and physiological signal monitoring to apply emotional stress in real time;

[0103] Spatial obstacle dimension: dynamically increasing obstacles and spatial constraints in virtual reality environment.

[0104] The collected non-walking simulation gait data is analyzed respectively to determine the relationship between freezing events and the intensity of each inducing factor.

[0105] (II) Specific determination conditions and analysis methods:

[0106] Analysis by statistical models or machine learning algorithms, including:

[0107] Dose-response analysis: e.g. using generalized linear mixed models, mixed effects models or survival analysis methods to calculate the relationship between the strength of the provoking factor and the incidence of freezing events.

[0108] Analysis of each task dimension separately: how the probability of freezing events (e.g. freezing frequency, duration) changes with increasing task difficulty / strength.

[0109] Final probability distribution curve of freezing events as a function of different provoking factor strengths.

[0110] Classification of freezing gait subtypes based on multi-dimensional data analysis:

[0111] (i) Obtaining method:

[0112] On the basis of single-dimensional dose-response analysis, multi-dimensional comprehensive analysis is carried out:

[0113] First stage: use generalized linear mixed models (GLMM) to determine the independent effect of each provoking factor dimension (cognition, emotion, spatial obstacle);

[0114] Second stage: construct a three-way interaction term of cognition × space × emotion, and use the random forest algorithm (RandomForest) to analyze the synergistic action pattern of multi-dimensional factors, and further identify the freezing gait subtypes of patients under the joint action of different dimensions.

[0115] (ii) Specific determination conditions and analysis methods:

[0116] Random forest classification model: input multi-dimensional task data to train the classification model.

[0117] The input features of the model may include: cognitive task performance and its correlation with non-walking gait simulation data; emotional stress intensity and corresponding freezing duration; spatial obstacle constraint intensity and freezing frequency.

[0118] Analysis by random forest algorithm:

[0119] Variable importance analysis (such as Mean Decrease Gini) to determine which factors have the greatest impact on freezing gait;

[0120] Sample clustering or classification to identify freezing gait subtypes, for example: cognition load dominant type: cognitive load increase significantly induces freezing; emotional stress provoking type: freezing events significantly increase when emotional stress is high; spatial constraint sensitive type: spatial obstacles or narrow environment significantly induce freezing.

[0121] D, a user interaction terminal, in communication connection with the data processing unit, configured to provide the user with the evaluation result of the freezing of gait of Parkinson's disease.

[0122] In an embodiment, the non-walking gait simulation evaluation system based on virtual reality interaction further comprises a feedback module configured to provide personalized guidance content according to the evaluation result of the freezing of gait of Parkinson's disease of the subject, wherein the personalized guidance content can include any one or any combination of the following: gait improvement suggestions, early warning information of freezing of gait, task completion status.

[0123] For patients dominated by cognitive load, daily life activity guidance programs can be provided according to the dose-response relationship between the difficulty of the cognitive load task and the change in the non-walking gait simulation data (for example, the correlation between the performance of the cognitive load task and the gait parameters). For example: mild patients can perform low-complexity dual-task walking, such as simple counting or naming exercises while walking, but should avoid complex environment walking that requires quick decision-making; moderate patients should choose structured walking training, such as rhythmic walking on a fixed route, but should avoid sudden disturbances or route changes; severe patients are only recommended to walk a short distance on a straight path without interference, and any distracting movement tasks are prohibited.

[0124] For patients sensitive to spatial constraints, progressive spatial adaptation training programs can be provided based on the analysis results of parameters such as the ratio of passage width to shoulder width and obstacle density. For example: when the ratio of passage width to shoulder width is <1.2, open environment walking training is recommended; when the ratio is between 1.2 and 1.5, standard width passage walking can be tried; when the ratio is >1.5, narrow space adaptability training can be performed. At the same time, according to the obstacle density threshold, the corresponding obstacle avoidance training plan is designed.

[0125] For patients induced by emotional stress, targeted psychological intervention suggestions can be provided according to the results of emotional induction tests. For those highly sensitive to threatening environments, systematic desensitization therapy is recommended; for those sensitive to social evaluation, social scene exposure training is suggested; for those sensitive to time pressure, relaxation training and time management strategies are provided.

[0126] In an embodiment, the non-walking gait simulation evaluation system based on virtual reality interaction can further comprise a visualization module configured to visualize the evaluation result of the freezing of gait of Parkinson's disease of the subject, to obtain a freezing of gait of Parkinson's disease evaluation report, wherein the content displayed in the freezing of gait of Parkinson's disease evaluation report can include any one or any combination of the following: gait performance of the subject under different difficulty gait tasks, occurrence of freezing of gait, potential for gait improvement, etc., and the report content can provide a reference basis for the subsequent development of treatment programs.

[0127] In one embodiment, the visualization module includes multiple dimensions of data presentation. In terms of severity visualization, a gradual color scale is used to represent the trend of symptom severity from light green to dark red, while specific clinical score values and corresponding symptom descriptions are labeled to enable medical personnel to quickly grasp the overall condition of the patient. For subtype classification visualization, a three-dimensional coordinate system chart can be generated, with cognitive load, spatial constraint, and emotional stress as coordinate axes. The dominant subtype characteristics of the patient are reflected by the position distribution of the data points, and the typical symptoms are supplemented by textual descriptions.

[0128] In terms of specific recommended visualization presentation, an interactive interface design can be used. For exercise guidance recommendations, dynamic simulation of human motion diagrams is displayed, with recommended motion amplitude, frequency, and duration labeled, and contraindicated actions identified with warning icons. Environmental adaptation recommendations are displayed through virtual scene reconstruction technology, with adjustable parameters such as passage width and obstacle density to visually demonstrate the patient's walking performance in different environmental configurations. The training progress tracking section uses a timeline format to compare historical evaluation data with preset target values and automatically calculates the recommended training intensity value for the next stage.

[0129] All visualization content supports multi-level information display, and users can obtain more detailed data analysis through clicking or zooming operations. The system can also provide report export function to generate standardized evaluation documents containing key charts and data summaries for clinical archiving and cross-department collaboration. The output of the visualization module can be directly linked to the hospital's electronic medical record system, providing intuitive evidence for the multidisciplinary treatment team to develop personalized intervention programs.

[0130] Based on the above-mentioned virtual reality interaction-based non-walking gait simulation evaluation system, the present application also provides a method for evaluating the freezing gait of Parkinson's disease, comprising the following steps:

[0131] S1. Load a dynamically adjustable virtual reality test scene to the subject to be tested through the virtual reality interaction module, the virtual reality test scene including different difficulty levels of simulated walking gait tasks, wherein the subject to be tested is a Parkinson's disease patient;

[0132] S2. The data acquisition module acquires non-walking simulation gait data of the subject to be tested in real time when performing the gait task and transmits it to the data processing unit;

[0133] S3. The data processing unit receives the non-walking simulation gait data of the subject to be tested sent by the data acquisition module, and obtains the evaluation result of the freezing gait of Parkinson's disease of the subject to be tested according to the non-walking simulation gait data of the subject to be tested.

[0134] Figure 3Embodiments of the method for evaluating freezing gait of Parkinson's disease are provided. In the evaluation, the subject can first wear VR glasses in the virtual reality interactive module and adjust the sitting position and foot pedal position, then the doctor enters the non-walking gait simulation evaluation system based on virtual reality interaction by using the computer and selects the gait task, so that the subject performs the task to start the virtual reality motion evaluation, the non-walking simulation gait data of the subject when performing the gait task are collected in real time by the data acquisition module of the non-walking gait simulation evaluation system based on virtual reality interaction, the data processing unit obtains the evaluation result of the freezing gait of Parkinson's disease of the subject according to the non-walking simulation gait data of the subject, and then the user interaction terminal receives and provides the evaluation result of the freezing gait of Parkinson's disease to the doctor to assist the doctor in accurately diagnosing and treating the subject.

[0135] The non-walking gait simulation evaluation system and method based on virtual reality interaction provided by the application use the virtual reality interactive module to make the subject complete the gait task in the virtual reality test scene, which is coordinated with any one or any combination of cognitive load tasks, emotional load tasks and spatial obstacle tasks, to simulate the real-time gait changes of the subject in different scenes, and the data acquisition module and the processor are combined to realize efficient and accurate evaluation of the freezing gait of Parkinson's disease, which can not only ensure the safety of the subject in the gait evaluation process, but also ensure the objectivity of the evaluation process, especially in the case of frequent freezing gait of the subject, the time and frequency of footstep stagnation or change can be accurately recorded, which helps doctors accurately understand the occurrence mode of freezing gait and provides effective data guidance for personalized treatment of patients.

[0136] The non-walking gait simulation evaluation system based on virtual reality interaction provided by the application breaks through the limitations of traditional gait evaluation. The previous evaluation methods mostly rely on simplified gait tests and subjective evaluation, and cannot fully simulate complex multiple environmental factors that may affect freezing gait. Through virtual reality technology, the application can create highly restored virtual scenes, which can include various complex situations that patients may encounter in real life, such as busy streets, sudden obstacles, narrow passage environments, etc.

[0137] The application of virtual reality makes the evaluation process not limited to static gait tests, but can dynamically simulate the influence of various environments on the gait of patients. Through the simulation of these complex factors, doctors can observe the occurrence and aggravation of freezing gait of patients in specific situations, so as to more comprehensively understand the inducing conditions and mechanism of freezing gait.

[0138] In addition, the safety of the patient is also considered in the present application. The patient does not need to walk back and forth during the evaluation, but can sit down and take the test. In this way, the patient can save physical strength, take a more careful evaluation for a longer time, avoid the risk of falling caused by walking, and ensure the safety of the evaluation process.

[0139] Various factors that can induce freezing gait can be analyzed through the present application. For example, external stimuli appearing in the environment (such as pedestrians, traffic, noise, etc.), the narrowness of the space, the dynamic changes of the environment, etc. can all affect the gait performance of the patient. Changes in these factors are often difficult to reproduce in traditional evaluation methods, but in a virtual reality environment, the patient can be tested in a controlled and adjustable scenario, making the evaluation process more consistent with real-life situations.

[0140] In addition, virtual reality can also combine sensors and motion capture devices to collect real-time non-walking simulation gait data of the patient and perform dynamic analysis. These data can not only help evaluate the frequency and duration of freezing gait, but also provide valuable experimental data for studying the physiological mechanisms of freezing gait. Through deep learning algorithms, the virtual reality evaluation system can identify different inducing factors and further explore their specific effects on the patient's gait.

[0141] The present application helps to explore the pathophysiological mechanisms of freezing gait in Parkinson's disease, and can help researchers further explore the pathophysiological mechanisms of freezing gait in Parkinson's disease. Through precise gait analysis, the system can help reveal the underlying physiological causes of freezing gait, such as degeneration of the nervous system, damage to motor neurons, muscle coordination problems, etc. This process provides technical support for in-depth understanding of the pathogenesis of Parkinson's disease, and also lays the foundation for the development of new treatment methods and intervention strategies.

[0142] The device embodiments described above are only illustrative, wherein the units illustrated as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e. they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0143] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0144] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A non-walking gait simulation and evaluation system based on virtual reality interaction, characterized in that, include: A virtual reality interaction module is configured to present a dynamically adjustable virtual reality test scene to the test subject, the virtual reality test scene including gait tasks of different difficulty simulating walking. A static postural support unit, comprising a rigid load-bearing structure and a footplate, is configured to support the patient in a non-walking static posture. The data acquisition module includes one or more motion sensors fixedly mounted on the pedal, configured to acquire non-walking simulated gait data of the subject in real time when the subject responds to the simulated walking gait task and send it to the data processing unit. The data processing unit, which is communicatively connected to the data acquisition module and the virtual reality interaction module, includes a processor and a memory. The processor is configured to execute a computer program stored in the memory. When the processor executes the computer program, it performs the following steps: receiving non-walking simulated gait data of the subject sent by the data acquisition module, and obtaining the gait evaluation result of the subject based on the non-walking simulated gait data of the subject. The subject of the test is a Parkinson's disease patient, the gait assessment result is the Parkinson's disease frozen gait assessment result, and the gait tasks of different difficulty include gait tasks that occur in conjunction with any one or any combination of the following: cognitive load task, emotional load task, and spatial obstacle task. Specifically, when the gait task occurs alone, it is a gait task with a difficulty level of 0. When the gait task occurs in conjunction with any one of the cognitive load task, emotional load task, or spatial obstacle task, it is a gait task with a difficulty level of I. When the gait task occurs in conjunction with any two of the cognitive load task, emotional load task, or spatial obstacle task, it is a gait task with a difficulty level of II. When the gait task occurs in conjunction with the cognitive load task, emotional load task, or spatial obstacle task, it is a gait task with a difficulty level of III. The step of obtaining the gait assessment result of the test subject based on the non-walking simulated gait data of the test subject includes: The dynamic sliding window method was used to analyze the non-walking simulated gait data of the subjects in real time, and the key indicator data of the non-walking simulated gait data in each analysis window were obtained. Based on the key indicator data of each analysis window of the non-walking simulated gait data, combined with the preset evaluation criteria, the first step gait evaluation result of the test subject is obtained. The pre-set evaluation criteria include: A. For each analysis window, a window is determined to be a frozen event window if two or more of the following conditions are met simultaneously: The current step time is more than twice the mode of the step time within the analysis window; The coefficient of variation of gait rhythm is greater than 0.4; The current reaction time to the prompt exceeds two standard deviations of the mean reaction time in the analysis window; The current step frequency is less than 60% of the average step frequency in the analysis window; B. When two or more freeze event windows occur consecutively, or when freeze event windows occur multiple times within a preset time period, a continuous freeze gait event is determined to have occurred, and the specific time of the freeze gait event is recorded. The step of obtaining the gait assessment result of the test subject based on the non-walking simulated gait data of the test subject includes: Based on the non-walking simulated gait data of the test subjects, the dose-response relationship between the difficulty of the cognitive load task and the change in non-walking simulated gait data, the dose-response relationship between the emotional intensity of the emotional load task and the duration of freezing, and the dose-response relationship between the constraint intensity of the spatial obstacle task and the occurrence of freezing were analyzed. By analyzing the dose-response relationship between the difficulty of the cognitive load task and changes in non-walking simulated gait data, the dose-response relationship between the emotional intensity of the emotional load task and the duration of freeze, and the dose-response relationship between the constraint intensity of the spatial obstacle task and the occurrence of freeze, the synergistic effect pattern of multidimensional factors was analyzed using the random forest algorithm to obtain the second gait assessment results of the test subjects.

2. The non-walking gait simulation and evaluation system based on virtual reality interaction according to claim 1, characterized in that, Non-walking simulated gait data includes any one or any combination of the following: stride time, cadence, stride length, gait speed, gait rhythm, and reaction time to cues.

3. The non-walking gait simulation and evaluation system based on virtual reality interaction according to claim 1, characterized in that, Key performance indicator data include data for any one of the following indicators or any combination thereof: mode of gait time and its distribution characteristics, mean and standard deviation of gait frequency, coefficient of variation of gait rhythm, average reaction time to cues and its dispersion.

4. The non-walking gait simulation and evaluation system based on virtual reality interaction according to claim 1, characterized in that, The second gait assessment results include any one of the following or any combination thereof: quantitative indicators of the severity of freezing events, probability distribution characteristics of freezing under different triggering factors, classification of freezing gait subtypes based on multidimensional data analysis, and among which, freezing gait subtypes include cognitive load-dominated type, emotional stress-induced type, and spatial constraint-sensitive type.

5. The non-walking gait simulation and evaluation system based on virtual reality interaction according to any one of claims 1-4, characterized in that, It also includes a user interaction terminal, which is communicatively connected to the data processing unit and is used to provide gait assessment results to the user.

6. A gait assessment method based on the virtual reality interaction-based non-walking gait simulation assessment system according to any one of claims 1-5, comprising: S1. Load a dynamically adjustable virtual reality test scenario onto the test subject through a virtual reality interaction module. The virtual reality test scenario includes gait tasks of varying difficulty. S2. The data acquisition module collects non-walking simulated gait data of the subject in real time when performing simulated walking gait tasks and transmits it to the data processing unit; S3. The data processing unit receives the non-walking simulated gait data of the test subject sent by the data acquisition module, and obtains the gait evaluation result of the test subject based on the non-walking simulated gait data.

Images