A method and system for assessing finger strength rehabilitation

Abstract

This invention relates to the field of hand function rehabilitation assessment technology, specifically a method and system for assessing finger strength rehabilitation. The method includes: obtaining multiple sets of grasping training data from a patient, where each set of grasping training data includes grip strength data at multiple moments during a single grasping training session; constructing a grip strength-time matrix; calculating the Mahalanobis distance between each row element of the grip strength-time matrix and the matrix itself; determining whether each set of target training data is valid; calculating an assessment coefficient; and adding a rehabilitation label to the patient when the assessment coefficient exceeds a preset assessment threshold. This invention improves the accuracy of assessment results by reducing data errors caused by improper movements or accidental factors.

Description

Technical Field

[0001] This invention generally relates to the field of hand function rehabilitation assessment technology. More specifically, this invention relates to a method and system for assessing finger strength rehabilitation. Background Technology

[0002] Fingers are an important part of the human hand, serving multiple functions such as grasping, manipulation, and sensation. However, due to various reasons, such as accidents, illnesses, and treatments, fingers may be damaged or lose their function. For example, in people with stroke, hand dysfunction often has a serious impact on their lives.

[0003] Finger rehabilitation assessment is the process of evaluating and diagnosing finger injuries or functional impairments. Its aim is to determine the functional status of the fingers, the extent of the injury, and rehabilitation needs, providing a scientific basis for rehabilitation treatment. Through rehabilitation assessment, the condition of the fingers' movement, sensation, strength, and coordination can be understood.

[0004] Existing methods for assessing finger rehabilitation mainly include three types: observational assessment, scale-based assessment, and instrument-based assessment. Observational assessment judges finger function by observing its appearance, posture, and movement trajectory. While simple and easy to perform, it is highly subjective and requires comprehensive analysis in conjunction with other assessment methods. Scale-based assessment uses standardized scales to evaluate finger function. Common scales include finger function assessment scales and hand motor function assessment scales. Scale-based assessments offer advantages such as objectivity and repeatability, but require professional operation, and results may be influenced by the subject's subjectivity. Instrument-based assessment uses specialized instruments to evaluate finger function. Common instruments include finger strength testing devices and finger dexterity testing devices. Instrument-based assessments offer advantages such as objectivity and accuracy, but require professional operation, and the equipment is expensive.

[0005] When assessing finger strength using the three methods described above, the standard for judging finger strength is usually whether the patient's grip strength reaches a preset standard. However, due to various reasons (such as compensatory force) during grip strength training, patients may occasionally exhibit non-standard grip movements, causing grip strength data to exceed the preset standard. This can affect the accuracy of the patient's finger strength rehabilitation assessment results. Summary of the Invention

[0006] To address the technical problem that improper grip movements by patients affect the accuracy of finger strength rehabilitation assessment results, this invention provides solutions in the following aspects.

[0007] In the first aspect, a method for assessing finger strength rehabilitation includes: obtaining multiple sets of grasping training data from a patient, wherein each set of grasping training data includes grip strength data from multiple moments during a single grasping exercise; constructing a grip strength-time matrix, wherein the grip strength-time matrix is... i Line number j Column elements x ij This indicates that the patient is undergoing the first... i The first grasp j Grip strength data at any given moment. i , j All are positive integers; calculate the Mahalanobis distance between each row element of the grip strength-time matrix and the grip strength-time matrix; determine whether each group of target training data is valid data based on the Mahalanobis distance between each row element of the grip strength-time matrix and the grip strength-time matrix; calculate the evaluation coefficient, and add a rehabilitation label to the patient when the evaluation coefficient is greater than the preset evaluation threshold, wherein the evaluation coefficient is proportional to the number of valid training data in the grip training data.

[0008] Preferably, calculating the Mahalanobis distance between each row element of the grip strength-time matrix and the grip strength-time matrix includes: calculating the column mean matrix. U The column mean matrix comprises one row of elements, and the first row of the column mean matrix is... j Column elements μ j satisfy: , m Let be the number of columns in the grip strength-time matrix and the column mean matrix; construct the covariance matrix Σ; obtain the Mahalanobis distance between each row element of the grip strength-time matrix and the grip strength-time matrix, wherein the _i_th column of the grip strength-time matrix is ​​calculated. i The formula for the Mahalanobis distance of a row is: ,in X i =( x i1 , x i2 ,......, x im ) T , x i1 The first in the grip strength-time matrix i The element in the first column of the row, x i2 The first in the grip strength-time matrix i The element in the second column of the row, x im The first in the grip strength-time matrix i Line number m Column elements, U =(x i1 , x i2 ,......, x im ).

[0009] Preferably, the covariance matrix Σ satisfies the expression: , Let be the element in the first row and first column of the covariance matrix Σ. The first covariance matrix Σ is the covariance matrix Σ. m The element in the first column of the row, The first row of the covariance matrix Σ m Column elements, The first covariance matrix Σ is the covariance matrix Σ. m Line number m The elements of the column.

[0010] Preferably, the covariance matrix Σ of the first... j Line number k Column elements Satisfying the formula:

[0011] in, The first column of the mean matrix k Column elements, For the grip force-time matrix, the first... i Line number k Column elements, n Let be the row number of the grip strength-time matrix.

[0012] Preferably, the formula for calculating the evaluation coefficient is: ,in λ The evaluation coefficient is... k 1 represents the number of valid training data points in the captured training data. K The total number of all grasp training data.

[0013] Preferably, it further includes: determining whether there are multiple consecutive moments in each group of grasping training data where the grip strength data exceeds a preset grip strength threshold; determining whether the difference between any two adjacent moments in each group of grasping training data is less than a preset change threshold; wherein, determining the first i Whether the training data for the target group is valid includes: in response to the first i In the group of grip training data, the grip strength data at multiple consecutive moments exceeds the preset grip strength threshold, and the grip strength-time matrix is... i The Mahalanobis distance between the row element and the grip strength-time matrix is ​​less than a preset distance threshold, and the 1st row element... iIf the difference between any two adjacent grip strength data points in the group of grip training data is less than a preset change threshold, then the first group is determined to be... i The group grasping training data are valid data.

[0014] Preferably, the change threshold satisfies the formula: , The time interval between two adjacent moments. α The change threshold, This is a preset threshold coefficient for size variation.

[0015] Preferably, the grip strength threshold is 30 Newtons.

[0016] Preferably, the grip force-time matrix satisfies the expression: ,in A For the grip force-time matrix, This data represents the patient's grip strength at the very first moment during their initial grasp. For the patient during the first grasp m Grip strength data at any given moment. For the patient during the first n Grip strength data at the first moment of the first grasp. For the patient during the first n The first grasp m Grip strength data at any given moment. n This represents the row number of the grip strength-time matrix.

[0017] In a second aspect, a finger strength rehabilitation assessment system includes a processor and a memory, the memory storing a computer program, the processor executing the computer program to implement a finger strength rehabilitation assessment method as described in any one of the above-described inventions.

[0018] The beneficial effects of this invention are as follows:

[0019] This invention obtains standard grip strength training data (grip strength data at multiple consecutive moments in the grasping training data exceeds a preset grip strength threshold, and the difference between grip strength data at any two adjacent moments is less than a preset change threshold), and filters the standard grip strength training data (using the Mahalanobis distance corresponding to the grip strength training data). Specifically, this invention identifies and eliminates abnormal data caused by random factors by constructing a grip strength-time matrix and combining it with Mahalanobis distance calculation. This invention can filter valid data from multiple sets of grasping training data, thereby obtaining the number of times the user accurately completes the required grip strength movements. Therefore, this invention improves the accuracy of the evaluation results by reducing data errors caused by non-standard movements or random factors. Attached Figure Description

[0020] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent upon reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of the invention are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein:

[0021] Figure 1 This is a schematic flowchart illustrating the steps of a finger strength rehabilitation assessment method according to an embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram illustrating the structure of a finger strength rehabilitation assessment system according to an embodiment of the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0025] Figure 1 This is a schematic flowchart illustrating the steps of a finger strength rehabilitation assessment method according to an embodiment of the present invention.

[0026] like Figure 1 As shown, a method for assessing finger strength rehabilitation includes steps S1 to S5.

[0027] Step S1: Obtain multiple sets of grasping training data from the patient.

[0028] One set of grasp training data includes the patient's grip strength data at multiple moments during a single grasp training session.

[0029] It should be noted that patients perform grasping training using a grip force sensor device (e.g., a grip ball with flexible pressure sensors evenly distributed along its surface). The grip force sensor device collects grip force data at various moments and transmits it to a finger strength rehabilitation assessment system. All grip force data collected by the grip force sensor device during a single grasping motion constitutes the grip force training data. In one embodiment, a set of grasping training data includes grip force data from 15 consecutive moments during a single grasping exercise.

[0030] In one embodiment, the time interval between two adjacent moments is 0.1 s. During a patient's grasping motion, grip force data is collected starting when the grip force sensor detects a grip force of 5 N. This ensures that the collected grasping training data sets are similar, thus making the Mahalanobis distance calculated subsequently meaningful in reflecting the degree of outlier (the degree to which the grasping training data deviates from the standard pattern) of each set.

[0031] Step S2: Construct the grip strength-time matrix.

[0032] Among them, the grip strength-time matrix is ​​the first i Line number j Column elements x ij This indicates that the patient is undergoing the first... i The first grasp j Grip strength data at any given moment. i , j All are positive integers.

[0033] In one embodiment, the patient performed n grasping movements, and each group of grasping training data included grip force data at m time points. The grip force-time matrix satisfies the expression: ,in A For the grip force-time matrix, This data represents the patient's grip strength at the very first moment during their initial grasp. For the patient during the first grasp m Grip strength data at any given moment. For the patient during the first n Grip strength data at the first moment of the first grasp. For the patient during the first n The first grasp m Grip strength data at any given moment.

[0034] It should be noted that the purpose of constructing the grip strength-time matrix is ​​to structure multiple sets of time-series data, thereby facilitating calculations in subsequent steps.

[0035] Step S3: Calculate the Mahalanobis distance between each row element in the grip force-time matrix and the grip force-time matrix.

[0036] It's important to note that Mahalanobis distance is a statistical measure of distance between samples. It considers the covariance structure of the dataset and better reflects the correlation between different features. Mahalanobis distance is used to determine the outlier degree of each row element (i.e., each group of training data) in the grip strength-time matrix. If the grip training data collected by the sensor in a patient's grip strength training session differs significantly from the grip training data collected in other grip training sessions, the Mahalanobis distance will be larger.

[0037] In one embodiment, calculating the Mahalanobis distance between each row element of the grip strength-time matrix and the grip strength-time matrix includes: calculating the column mean matrix. U The column mean matrix comprises one row of elements, and the first row of the column mean matrix is... j Column elements μ j satisfy: , m Let be the number of columns in the grip strength-time matrix and the column mean matrix; construct the covariance matrix Σ; obtain the Mahalanobis distance between each row element of the grip strength-time matrix and the grip strength-time matrix, wherein the _i_th column of the grip strength-time matrix is ​​calculated. i The formula for the Mahalanobis distance of a row is:

[0038] .

[0039] in, X i =( x i1 , x i2 ,......, x im ) T , x i1 The first in the grip strength-time matrix i The element in the first column of the row, x i2 The first in the grip strength-time matrix i The element in the second column of the row, x im The first in the grip strength-time matrix i Line number m Column elements, U =( x i1 , x i2 ,......, x im ).

[0040] In one embodiment, the covariance matrix Σ satisfies the expression: , Let be the element in the first row and first column of the covariance matrix Σ. The first covariance matrix Σ is the covariance matrix Σ. m The element in the first column of the row, The first row of the covariance matrix Σ m Column elements, The first covariance matrix Σ is the covariance matrix Σ. m Line number m The elements of the column.

[0041] In one embodiment, the covariance matrix Σ of the first j Line number k Column elements Satisfying the formula:

[0042] in, The first column of the mean matrix k Column elements, For the grip force-time matrix, the first... i Line number k Column elements, n Let be the row number of the grip strength-time matrix.

[0043] It should be noted that the covariance matrix Σ is an m×m square matrix that describes the typical pattern of grip strength change over time when a patient is performing grasping actions (i.e., under normal training behavior).

[0044] Step S4: Determine whether the target training data for each group is valid data.

[0045] In one embodiment, in response to the first of the grip force-time matrix i If the Mahalanobis distance between the row element and the grip strength-time matrix is ​​less than a preset distance threshold, the i-th group of grip training data is determined to be valid data.

[0046] In another embodiment, it is determined whether there are multiple consecutive moments in the grasping training data that have a grip strength greater than a preset grip strength threshold; it is also determined whether the difference between any two adjacent moments in the grasping training data is less than a preset change threshold; wherein, it is determined that the first... i Whether the training data for the target group is valid includes: in response to the first i In the group of grip training data, the grip strength data at multiple consecutive moments exceeds the preset grip strength threshold, and the grip strength-time matrix is... i The Mahalanobis distance between the row element and the grip strength-time matrix is ​​less than a preset distance threshold, and the 1st row element... i If the difference between any two adjacent grip strength data points in the group of grip training data is less than a preset change threshold, then the first group is determined to be... iThe group grasping training data are valid data.

[0047] It should be noted that, in response to the first i If there are no consecutive moments in the grip training data where the grip strength exceeds the preset grip strength threshold, then it indicates that the first set of grip training data... i The grasp training data represents the data corresponding to patients' failure to perform grasp training. The reason is that if there are no consecutive moments with grip strength data greater than the preset threshold, it means that the patient failed to maintain sufficient grip strength during training. In other words, the patient is unable to continuously activate the target muscle group during training due to the corresponding condition (such as central nervous system drive disorder, muscle energy metabolism disorder, etc.).

[0048] Response to the grip force-time matrix i The Mahalanobis distance between the row element and the grip strength-time matrix is ​​greater than the preset distance threshold, which also indicates that the [missing information]... i The grasping training data represents data corresponding to patients' failure to perform grasping training, the reason being: the patient did not perform normal grasping training. Normally, the grasping training data corresponding to standard grasping performed by the patient under the guidance of a physician follows a bell-shaped curve (normal exertion - peak value - relaxation). If the grasping data in a particular grasping attempt exhibits a bimodal curve (such as secondary exertion due to cerebral palsy spasticity), the corresponding Maslavian distance for that grasping training attempt will be significantly increased; or if the patient compensates with their shoulder, resulting in a flattening of grip force (a relatively high value is maintained for a shorter period, with no peak release), the corresponding Maslavian distance for that grasping training attempt will be significantly increased.

[0049] In response to the i In the first set of grip training data, the difference between grip strength data at any two adjacent time points was greater than the preset change threshold, indicating that the first set of grip training data... i The grasping training data represents the data corresponding to patients' failure to perform grasping training. The reason is that high-frequency abrupt changes in force output indicate instability of the neuromuscular control system, and patients are unable to achieve smooth force regulation.

[0050] In one embodiment, the change threshold satisfies the formula: , The time interval between two adjacent moments. α The change threshold, This is a preset threshold coefficient for size variation.

[0051] In one embodiment, the grip strength threshold is 30 Newtons. It should be noted that when a patient's grip strength reaches 30 Newtons or more, it indicates that the patient can basically rebuild daily living abilities (the patient can perform actions such as opening doors).

[0052] Step S5: Calculate the assessment coefficient and add a rehabilitation label to the patient when the assessment coefficient is greater than the preset assessment threshold.

[0053] The evaluation coefficient is proportional to the number of valid training data in the grasp training data.

[0054] In one embodiment, the formula for calculating the evaluation coefficient is: ,in λ The evaluation coefficient is... k 1 represents the number of valid training data points in the captured training data. K The total number of all grasp training data.

[0055] It should be noted that this invention quantifies rehabilitation progress and determines whether a patient is marked as rehabilitated based on the proportion of effective data to grasping training data. Evaluation coefficient. λ It can directly reflect the quality of a patient's rehabilitation; a higher percentage indicates that the patient is more able to stably perform grasping movements. Rehabilitation tags are used for clinical records and for physicians to adjust the patient's subsequent rehabilitation plan.

[0056] Figure 2 This is a schematic diagram illustrating the structure of a finger strength rehabilitation assessment system according to this embodiment.

[0057] This invention also provides a finger strength rehabilitation assessment system. For example... Figure 2 As shown, the system includes a processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement a finger strength rehabilitation assessment method according to the first aspect of the present invention.

[0058] The system also includes other components well known to those skilled in the art, such as communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

[0059] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented using computer-readable / executable instructions that can be stored or otherwise maintained by such a computer-readable medium.

[0060] In the description of this specification, "multiple" or "several" means at least two, such as two, three or more, unless otherwise explicitly specified.

[0061] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.

Claims

1. A method for assessing finger strength rehabilitation, characterized in that, include: Multiple sets of grasp training data were obtained from the patient, one set of grasp training data including the patient's grip strength data at multiple moments during a single grasp training session; Construct a grip strength-time matrix, where the grip strength-time matrix is ​​at position n. i Line number j Column elements x ij This indicates that the patient is undergoing the first... i The first grasp j Grip strength data at any given moment. i , j All are positive integers; Calculate the Mahalanobis distance between each row element of the grip force-time matrix and the grip force-time matrix itself; The validity of each group of target training data is determined based on the Mahalanobis distance between each row element of the grip strength-time matrix and the matrix itself. This includes: determining whether there are multiple consecutive moments in each group of grip training data where the grip strength data exceeds a preset grip strength threshold; determining whether the difference between any two adjacent moments in each group of grip training data is less than a preset change threshold; and responding to the... i In the group of grip training data, the grip strength data at multiple consecutive moments exceeds the preset grip strength threshold, and the grip strength-time matrix is... i The Mahalanobis distance between the row element and the grip strength-time matrix is ​​less than a preset distance threshold, and the 1st row element... i If the difference between any two adjacent grip strength data points in the group of grip training data is less than a preset change threshold, then the first group is determined to be... i The group grasping training data is valid data; Calculate the evaluation coefficient and add a rehabilitation label to the patient when the evaluation coefficient is greater than a preset evaluation threshold, wherein the evaluation coefficient is proportional to the number of valid training data in the grasp training data.

2. The finger strength rehabilitation assessment method according to claim 1, characterized in that, Calculating the Mahalanobis distance between each row element of the grip strength-time matrix and the grip strength-time matrix includes: Calculate the column mean matrix U The column mean matrix comprises one row of elements, and the first row of the column mean matrix is... j Column elements μ j satisfy: , m This represents the number of columns in the grip strength-time matrix and the column mean matrix; Construct the covariance matrix Σ; Obtain the Mahalanobis distance between each row element of the grip strength-time matrix and the matrix itself, wherein the first row element of the grip strength-time matrix is ​​calculated. i The formula for the Mahalanobis distance of a row is: ,in X i =( x i1 , x i2 ,......, x im ) T , x i1 The first in the grip strength-time matrix i The element in the first column of the row, x i2 The first in the grip strength-time matrix i The element in the second column of the row, x im The first in the grip strength-time matrix i Line number m Column elements, U =( x i1 , x i2 ,......, x im ).

3. The finger strength rehabilitation assessment method according to claim 2, characterized in that, The covariance matrix Σ satisfies the expression: , Let be the element in the first row and first column of the covariance matrix Σ. The first covariance matrix Σ is the covariance matrix Σ. m The element in the first column of the row, The first row of the covariance matrix Σ m Column elements, The first covariance matrix Σ is the covariance matrix Σ. m Line number m The elements of the column.

4. The finger strength rehabilitation assessment method according to claim 3, characterized in that, The first covariance matrix Σ j Line number k Column elements Satisfying the formula: in, The first column of the mean matrix k Column elements, For the grip force-time matrix, the first... i Line number k Column elements, n Let be the row number of the grip strength-time matrix.

5. The finger strength rehabilitation assessment method according to claim 1, characterized in that, The formula for calculating the evaluation coefficient is: ,in λ The evaluation coefficient is... k 1 represents the number of valid training data points in the captured training data. K The total number of all grasp training data.

6. The finger strength rehabilitation assessment method according to claim 5, characterized in that, The change threshold satisfies the formula: , The time interval between two adjacent moments. α The change threshold, This is a preset threshold coefficient for size variation.

7. A method for assessing finger strength rehabilitation according to claim 5, characterized in that, The grip strength threshold is 30 Newtons.

8. A method for assessing finger strength rehabilitation according to claim 1, characterized in that, The grip force-time matrix satisfies the expression: ,in A For the grip force-time matrix, This data represents the patient's grip strength at the very first moment during their initial grasp. For the patient during the first grasp m Grip strength data at any given moment. For the patient during the first n Grip strength data at the first moment of the first grasp. For the patient during the first n The first grasp m Grip strength data at any given moment. n This represents the row number of the grip strength-time matrix.

9. A finger strength rehabilitation assessment system, comprising a processor and a memory, wherein the memory stores a computer program, characterized in that, The processor executes the computer program to implement a finger strength rehabilitation assessment method as described in any one of claims 1-8.

Images