Cerebral stroke rehabilitation training method and computer program product

By combining motor and cognitive tasks in stroke rehabilitation training, and utilizing VR/AR technology and dynamic adjustment algorithms, the problems of task fragmentation and scenario disconnection were solved, thereby improving the personalized rehabilitation training effect.

CN121054178APending Publication Date: 2025-12-02SHANGHAI LIANYING ZHIYUAN MEDICAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202511129473.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-08-12
Publication Date
2025-12-02

AI Technical Summary

Technical Problem

Existing stroke rehabilitation training methods suffer from task fragmentation, scenario disconnect, and insufficient adaptability, failing to effectively simulate real-life needs and affecting rehabilitation outcomes and the patient's overall functional recovery.

Method used

This paper presents a method for stroke rehabilitation training. By constructing dual-task and single-task training scenarios, combining motor and cognitive tasks, and using VR/AR technology to conduct training in daily life scenarios, the training difficulty is adjusted in real time through multimodal sensor data and dynamic adjustment algorithms to achieve synchronous activation and personalized adaptation of motor and cognitive functions.

Benefits of technology

It improved the fun, functionality, and adherence of rehabilitation training, enhanced the transfer of patients' abilities in real life, and achieved comprehensive functional recovery and improved training results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121054178A_ABST
    Figure CN121054178A_ABST
Patent Text Reader

Abstract

The invention discloses a stroke rehabilitation training method and a computer program product, a double-task training scene and a single-task training scene are provided, the double-task training scene comprises a motion task and a cognitive task which are executed at the same time, and the single-task training scene comprises a motion task and a cognitive task which are executed respectively; acquiring a first performance quantized value for executing the motion task and a second performance quantized value for executing the cognitive task in the single-task training scene by the user; acquiring a third performance quantized value for executing a motion task and a fourth performance quantized value for executing a cognitive task in the double-task training scene by the user; determining an athletic performance decrease quantized value based on the first and third performance quantized values; determining a cognitive performance decrease quantized value based on the second and fourth performance quantized values; a dual-task comprehensive performance decline quantized value is calculated based on the athletic performance decline quantized value and the cognitive performance decline quantized value to determine a rehabilitation performance of the user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of rehabilitation medicine, specifically to a method for stroke rehabilitation training and a computer program product. Background Technology

[0002] Stroke is a common neurological disorder that can lead to various problems, including motor and cognitive impairments. Stroke rehabilitation training is an important means of helping patients regain function, with the recovery of motor and cognitive functions being particularly crucial.

[0003] However, existing stroke rehabilitation training methods still have the following shortcomings. First, existing rehabilitation training methods generally suffer from task fragmentation. Traditional rehabilitation training often separates motor training from cognitive training, designing training content and assessment standards for each independently. This separated training approach cannot simulate the dual-task requirement of "thinking while acting" in real life, making it difficult for patients to cope with multi-task situations in real life.

[0004] Secondly, existing training methods suffer from a disconnect between training content and real-life scenarios. Although some programs incorporate technologies such as virtual reality, the connection between the training content and daily life activities remains weak. This makes it difficult for patients to effectively transfer the skills they acquire during training to real-life situations, thus affecting the practicality of the rehabilitation outcomes.

[0005] Third, existing training programs lack adaptability. Most rehabilitation training systems employ relatively static training programs, lacking a mechanism for dynamic adjustment based on the patient's real-time performance. This lack of personalization and adaptability prevents timely adjustments to the difficulty and content of training in response to the patient's rehabilitation progress, thus affecting the efficiency and effectiveness of rehabilitation training.

[0006] Furthermore, existing technologies lack a quantitative method that can comprehensively assess a patient's motor and cognitive performance under dual-task conditions, making it difficult to objectively evaluate the patient's overall rehabilitation performance and to adjust the training program accordingly.

[0007] Therefore, there is an urgent need for a stroke rehabilitation training method that can simultaneously train motor and cognitive functions, is close to daily life scenarios, and has dynamic adaptability, in order to improve patients' overall functional recovery level and quality of life. Summary of the Invention

[0008] To address the technical problems of task fragmentation, scenario disconnect, and insufficient adaptability in existing chronic stroke rehabilitation training, and to achieve functional integration, precise adaptation, and improved interest, functionality, and adherence in rehabilitation training, this invention provides a stroke rehabilitation training method.

[0009] The technical solution adopted in this invention is as follows: a stroke rehabilitation training method is provided, comprising the following steps: providing a dual-task training scenario and a single-task training scenario, wherein the dual-task training scenario includes a motor task and a cognitive task, wherein the motor task and the cognitive task are executed simultaneously in the dual-task training scenario, and the motor task and the cognitive task are executed separately in the single-task training scenario; obtaining a first performance quantification value of the user performing the motor task in the single-task training scenario; obtaining a second performance quantification value of the user performing the cognitive task in the single-task training scenario; obtaining a third performance quantification value of the user performing the motor task in the dual-task training scenario; obtaining a fourth performance quantification value of the user performing the cognitive task in the dual-task training scenario; determining a motor performance decline quantification value based on the first performance quantification value and the third performance quantification value; determining a cognitive performance decline quantification value based on the second performance quantification value and the fourth performance quantification value; and calculating a comprehensive dual-task performance decline quantification value based on the motor performance decline quantification value and the cognitive performance decline quantification value to determine the user's rehabilitation performance.

[0010] A further technical solution of the present invention is: based on the quantitative value of the decline in motor performance and the quantitative value of the decline in cognitive performance, a quantitative value of the overall decline in dual-task performance is calculated to determine the user's rehabilitation performance.

[0011] A further technical solution of the present invention is that the first, second, third, or fourth quantitative values ​​are positive indicators.

[0012] A further technical solution of the present invention is: when the first, second, third, or fourth quantitative value is a negative indicator, the negative indicator is converted into a positive indicator.

[0013] A further technical solution of the present invention is: the conversion includes calculating the reciprocal of the first, second, third or fourth expressed quantization value or theoretical extreme value difference compensation.

[0014] A further technical solution of the present invention is: determining the quantitative value of the decline in athletic performance includes calculating the percentage of the third performance quantitative value to the first performance quantitative value.

[0015] A further technical solution of the present invention is: determining the quantitative value of cognitive performance decline includes calculating the percentage of the fourth performance quantitative value to the second performance quantitative value.

[0016] A further technical solution of the present invention is: the calculation of the quantitative value of the decline in the overall performance of the dual tasks includes multiplying the quantitative value of the decline in motor performance and the quantitative value of the decline in cognitive performance by preset weights and summing them.

[0017] A further technical solution of the present invention is: adjusting the user's rehabilitation training goals according to the user's rehabilitation performance, including: obtaining a sports task consumption value based on the quantitative value of the decline in sports performance, and modifying the sports task when the sports task consumption value is greater than a first preset threshold; or obtaining a cognitive task consumption value based on the quantitative value of the decline in cognitive performance, and modifying the cognitive task when the cognitive task consumption value is greater than a second preset threshold; or obtaining a comprehensive consumption value based on the quantitative value of the decline in the combined performance of the two tasks, and modifying the sports task and the cognitive task when the comprehensive consumption value is greater than a third preset threshold.

[0018] The beneficial effects of this invention are as follows: By constructing a scenario-based task matrix, motor training tasks and cognitive training tasks are combined in daily life scenarios, achieving synchronous activation of neural circuits for motor coordination and visual-spatial processing, overcoming the problem of task fragmentation in traditional rehabilitation training; by embedding motor tasks such as upper limb grasping and lower limb stepping with cognitive tasks such as continuous subtraction of 7 and word fluency into various daily scenarios such as balcony gardening and dining, the problem of scenario disconnect between traditional rehabilitation training and daily life activities with weak correlation is solved, achieving effective improvement in daily life activities; by establishing a dynamic coupling model of cognitive-motor tasks, and dynamically adjusting the task difficulty based on multimodal sensor data and dual-task consumption algorithm, the problem of insufficient adaptability of traditional static training programs is solved, improving training compliance and effectiveness; at the same time, this invention avoids the problem of patient resource competition and prevents erroneous compensation through dynamic resource balance theory, while inducing neural plasticity adaptation, thereby comprehensively improving the rehabilitation training effect of patients in the chronic phase of stroke. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this specification and form part of this specification, illustrate exemplary embodiments and are used to explain this specification, but do not constitute an undue limitation thereof. In the drawings:

[0020] Figure 1 This is a schematic diagram of a stroke rehabilitation training method described in this manual.

[0021] Figure 2 This is a schematic diagram of the hardware and / or software components of an exemplary computing device according to some embodiments of this application. Detailed Implementation

[0022] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings and embodiments. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0023] like Figure 1 As shown, this embodiment provides a stroke rehabilitation training method 100, which includes the following steps:

[0024] First, step 101 provides a dual-task training scenario and a single-task training scenario. The dual-task training scenario includes a motor task and a cognitive task, which are executed simultaneously. In the single-task training scenario, the motor task and the cognitive task are executed separately.

[0025] Next, we obtain the first performance quantification value 102 of the user performing a motion task in a single-task training scenario. This step involves recording the user's performance parameters when performing only a motion task, such as completion time, accuracy, or range of motion, and converting these parameters into quantified values.

[0026] Next, the second performance quantification value 103 of the user performing a cognitive task in a single-task training scenario is obtained. This step involves recording the user's performance parameters when performing only cognitive tasks, such as reaction time, accuracy, or memory, and converting these parameters into quantified values.

[0027] Next, the third performance quantification value 104 of the user performing the motor task in the dual-task training scenario is obtained. This step involves recording the performance parameters of the motor task portion when the user performs both motor and cognitive tasks simultaneously, and converting these parameters into quantified values.

[0028] Subsequently, the fourth performance quantification value, 105, of the user's cognitive task performance in the dual-task training scenario is obtained. This step involves recording the performance parameters of the cognitive task portion when the user performs both motor and cognitive tasks simultaneously, and converting these parameters into quantified values.

[0029] Based on the first and third performance quantification values, a performance decline quantification value of 106 is determined. Specifically, the performance decline quantification value is determined by calculating the percentage of the third performance quantification value to the first performance quantification value. For example, if the first performance quantification value is 100 points and the third performance quantification value is 80 points, then the performance decline quantification value is 80%.

[0030] In another example, Those skilled in the art will be able to conceive of different calculation methods to achieve the measurement decrease, and no limitation is made here.

[0031] Based on the second and fourth performance quantification values, a cognitive performance decline quantification value of 107 was determined. Specifically, the cognitive performance decline quantification value was determined by calculating the percentage of the fourth performance quantification value to the second performance quantification value. For example, if the second performance quantification value is 100 points and the fourth performance quantification value is 70 points, then the cognitive performance decline quantification value is 70%. In another example,

[0032] The user's rehabilitation performance is determined based on the quantitative values ​​of decline in motor performance and cognitive performance. Specifically, the calculation of the quantitative value of decline in combined dual-task performance involves multiplying the quantitative values ​​of decline in motor performance and cognitive performance by preset weights and then summing them. For example, if the quantitative value of decline in motor performance is 80%, the quantitative value of decline in cognitive performance is 70%, the weight of the motor task is 0.6, and the weight of the cognitive task is 0.4, then the quantitative value of decline in combined dual-task performance is 80% × 0.6 + 70% × 0.4 = 76%.

[0033] In a specific example, a VR / AR virtual environment can be used to combine motor training tasks with cognitive training tasks in everyday life scenarios, achieving simultaneous activation of neural circuits for motor coordination and visuospatial processing. The dual tasks can include the following: Motor task library: containing upper limb, lower limb, and trunk categories. Upper limb task selection: Task-oriented training, such as grasping, picking up, and manipulating objects; Lower limb task selection: Weight-Bearing Stepping; Trunk task selection: Seated dynamic center of gravity transfer. Cognitive task library: containing computation, language, and spatial categories. Computation task selection: Serial-7 Subtraction; Language task selection: Category Fluency; Spatial task selection: Mental Rotation.

[0034] Integrating exercise and cognitive training into the same daily life scenario can significantly improve the enjoyment, functionality, and adherence to rehabilitation. Example of a task matrix:

[0035]

[0036] The evaluation metrics for the two tasks are shown in the table below. Choose one metric from the two options based on the task details.

[0037]

[0038] While determining the task evaluation indicators, we need to clarify the measurement methods for the relevant indicators: motor tasks can be monitored in real time through multimodal sensing, while cognitive tasks can rely on task status / outcome monitoring.

[0039] The path to task evaluation needs to return to the device platform: to realize task content based on daily scenarios, a virtual environment needs to be provided to enhance the immersion of rehabilitation training, thereby improving patient compliance. The design utilizes AR glasses + camera + smart sensing hardware to build the training environment, which can be conditionally deployed in hospitals, communities, or homes.

[0040] In this method, performance metrics are positive indicators, meaning higher values ​​indicate better performance. Examples include accuracy (% correct), number of tasks completed, and balance maintenance time (seconds, longer is better). When performance metrics are negative, they need to be converted to positive indicators. Smaller negative values ​​represent better performance. Examples include task reaction time (seconds, shorter is better) and task completion time (seconds, shorter is better). The conversion involves calculating the reciprocal of the performance metric or compensating for the difference between theoretical and actual extreme values. For example, if the original metric is the time required to complete a task (a negative indicator, shorter is better), it can be converted to a positive metric by calculating its reciprocal or by subtracting the actual time from a preset maximum time.

[0041] Examples of some positive and negative indicators can be found in the table below.

[0042]

[0043] Based on the user's rehabilitation performance, the performance is compared with preset thresholds, and the user's rehabilitation training goals are adjusted according to the comparison results. Adjustments include modifying motor tasks and / or cognitive tasks. Specifically, adjusting the user's rehabilitation training goals includes:

[0044] In one example, the exercise task consumption value is obtained based on the quantitative value of the decline in athletic performance. The exercise task consumption value is calculated as (1 - the quantitative value of the decline in athletic performance in both tasks) * 100%. When the exercise task consumption value exceeds a first preset threshold, the exercise task is modified. For example, if the exercise task consumption value is 30% and the first preset threshold is 25%, then the difficulty of the exercise task needs to be reduced or the type of exercise task needs to be changed.

[0045] In another example, when the exercise quantification value is a negative indicator, the exercise task consumption value (exercise performance decline quantification value) = (dual task exercise quantification value (third performance quantification value) - single task exercise quantification value (first performance quantification value)) / |single task exercise quantification value (first performance quantification value)| * 100%.

[0046] When the exercise quantification value is a positive indicator, the exercise task consumption value (exercise performance decline quantification value) = (single-task exercise quantification value (first performance quantification value) - dual-task exercise quantification value (third performance quantification value)) / single-task exercise quantification value (first performance quantification value) * 100%. In this example, those skilled in the art will understand that the exercise task consumption value and the exercise performance decline quantification value can be the same.

[0047] In one example, the cognitive task consumption value is obtained based on the quantification of cognitive performance decline. The cognitive task consumption value is calculated as (1 - quantification of cognitive performance decline) * 100%. When the cognitive task consumption value exceeds a second preset threshold, the cognitive task is modified. For example, if the cognitive task consumption value is 35% and the second preset threshold is 30%, then the difficulty of the cognitive task needs to be reduced or the type of cognitive task needs to be changed.

[0048] In another example, when the cognitive quantification value is a negative indicator, the cognitive task consumption value (cognitive performance decline quantification value) = (dual-task cognitive quantification value (fourth performance quantification value) - single-task cognitive quantification value (second performance quantification value)) / |single-task cognitive quantification value (second performance quantification value) | * 100%.

[0049] When the cognitive quantification value is a positive indicator, the cognitive task consumption value (cognitive performance decline quantification value) = (single-task cognitive quantification value (second performance quantification value) - dual-task cognitive quantification value (fourth performance quantification value)) / single-task cognitive quantification value (second performance quantification value) * 100%. In this example, those skilled in the art will understand that the cognitive task consumption value and the cognitive performance decline quantification value can be the same. The comprehensive task consumption value, i.e., the dual-task comprehensive performance decline quantification value, can be obtained by multiplying the cognitive task consumption value by a weighting coefficient and adding the motor task consumption value by a weighting coefficient. The difficulty setting can then be adjusted by comparing the comprehensive task consumption value with a threshold.

[0050] In one example, the overall consumption value can be obtained based on the quantitative value of the overall performance decline in both tasks. The overall task consumption value = (1 - quantitative value of overall performance decline in both tasks) * 100%. When the overall consumption value is greater than a third preset threshold, the motor task and the cognitive task are modified. For example, if the overall consumption value is 32% and the third preset threshold is 28%, then the difficulty or type of both the motor task and the cognitive task needs to be adjusted simultaneously.

[0051] The difficulty adjustment strategy is as follows.

[0052] 1. Cognitive task adjustment a. Difficulty increase strategy

[0053]

[0054] b. Difficulty Reduction Strategy

[0055]

[0056] 2. Adjustment of Exercise Tasks a. Strategy for Increasing Difficulty

[0057]

[0058] b. Difficulty Increase Strategy

[0059]

[0060] The above methods can be used to scientifically assess the performance of stroke patients in rehabilitation training, and to dynamically adjust the training plan based on the assessment results, thereby improving the pertinence and effectiveness of rehabilitation training.

[0061] This embodiment provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the stroke rehabilitation training method as described in Embodiment 1.

[0062] Figure 2 This is a schematic diagram of the hardware and / or software components of an exemplary computing device 200 according to some embodiments of this application. The computing device 200 may include a processor 210, a memory 220, an input / output (I / O) port 230, and a communication port 240.

[0063] The computer program product can be stored on a computer-readable storage medium, such as a hard drive, solid-state drive, optical disc, USB flash drive, memory card, or cloud storage. The computer program product contains program code, and when the program code is loaded and executed by a computer, the computer will perform all the steps of the stroke rehabilitation training method described in Embodiment 1.

[0064] Specifically, the computer program product includes program modules for performing the following functions: a module for providing dual-task training scenarios and single-task training scenarios, a module for obtaining performance quantification values, a module for calculating performance decline quantification values, and a module for assessing rehabilitation performance.

[0065] The dual-task and single-task training scenario modules generate training scenario interfaces on the computer, allowing users to perform rehabilitation training. The performance quantification value acquisition module records and calculates user performance data in different training scenarios. The performance decline quantification value calculation module calculates various decline indicators based on the acquired performance quantification values. The rehabilitation performance evaluation module comprehensively analyzes the user's training performance and provides evaluation results.

[0066] In a preferred embodiment, the computer program product further includes a training goal adjustment module, which is used to automatically adjust the training difficulty and content according to the user's rehabilitation performance to achieve a personalized rehabilitation training program.

[0067] This computer program product can be applied to various computing devices, including but not limited to personal computers, tablets, smartphones, and professional medical equipment, providing stroke patients with convenient and efficient rehabilitation training tools.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for stroke rehabilitation training, characterized in that, Includes the following steps: The system provides dual-task training scenarios and single-task training scenarios. The dual-task training scenario includes a motor task and a cognitive task. In the dual-task training scenario, the motor task and the cognitive task are executed simultaneously. In the single-task training scenario, the motor task and the cognitive task are executed separately. Obtain the first performance quantification value of the user performing a motion task in the single-task training scenario; Obtain the second performance quantification value of the user performing a cognitive task in the single-task training scenario; Obtain the third performance quantification value of the user performing a motion task in the dual-task training scenario; Obtain the fourth performance quantification value of the user performing the cognitive task in the dual-task training scenario; Based on the first performance quantification value and the third performance quantification value, a decrease in motor performance quantification value is determined; based on the second performance quantification value and the fourth performance quantification value, a decrease in cognitive performance quantification value is determined; based on the decrease in motor performance quantification value and the decrease in cognitive performance quantification value, the user's rehabilitation performance is determined.

2. The method according to claim 1, characterized in that, Determining a user's rehabilitation performance based on the quantitative values ​​of the decline in motor performance and the decline in cognitive performance includes calculating a quantitative value of the overall decline in dual-task performance based on the quantitative values ​​of the decline in motor performance and the decline in cognitive performance, in order to determine the user's rehabilitation performance.

3. The method according to claim 1, characterized in that, The first, second, third, or fourth performance values ​​are positive indicators.

4. The method according to claim 3, characterized in that, When the first, second, third, or fourth performance quantification value is a negative indicator, the negative indicator is converted into a positive indicator.

5. The method according to claim 4, characterized in that: The conversion includes calculating the reciprocal of the first, second, third, or fourth performance quantization value or the theoretical extreme value difference compensation.

6. The method according to claim 1, characterized in that: The determination of the quantitative value of the decline in athletic performance includes calculating the percentage of the third performance quantitative value relative to the first performance quantitative value.

7. The method according to claim 1, characterized in that: The determination of the cognitive performance decline quantification value includes calculating the percentage of the fourth performance quantification value to the second performance quantification value.

8. The method according to claim 2, characterized in that: The calculation of the quantitative value of the overall performance decline in the dual tasks includes multiplying the quantitative value of the decline in athletic performance and the quantitative value of the decline in cognitive performance by preset weights and then summing them.

9. The method according to claim 1, characterized in that: This includes adjusting the user's rehabilitation training goals based on the user's rehabilitation performance, which includes: The exercise task consumption value is obtained based on the quantitative value of the decline in athletic performance. When the exercise task consumption value is greater than a first preset threshold, the exercise task is modified; or Based on the quantified value of cognitive performance decline, a cognitive task consumption value is obtained. When the cognitive task consumption value exceeds a second preset threshold, the cognitive task is modified; or Based on the quantitative value of the decline in the overall performance of the dual tasks, a comprehensive consumption value is obtained. When the comprehensive consumption value is greater than a third preset threshold, the motion task and the cognitive task are modified.

10. A computer program product comprising instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1-9.