Balance function evaluation method and device, electronic equipment and readable storage medium

Abstract

The application provides a balance function evaluation method and device, electronic equipment and a readable storage medium, wherein the method comprises: collecting first gait test data corresponding to a balance function related index of a patient to be evaluated when performing a first gait test, second gait test data corresponding to the balance function related index when performing a second gait test, and third gait test data corresponding to the balance function related index when performing a double task gait test; for the same balance function related index, calculating a first improvement rate of the second gait test data relative to the first gait test data; inputting the first gait test data, the second gait test data, the third gait test data and the first improvement rate into a balance function evaluation model, and outputting an evaluation result for representing the balance function of the patient to be evaluated through the balance function evaluation model. Through the method, the objectivity, accuracy and comprehensiveness of the evaluation of the balance function of the patient are improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a balance function assessment method, device, electronic device, and readable storage medium. Background Art

[0002] Balance assessment in the elderly is crucial for maintaining health and improving quality of life. As a primary indicator of health status, balance function, including balance ability and gait characteristics, can reflect potential muscle and bone disorders and neurological damage, helping healthcare professionals identify potential health issues early and implement interventions and management.

[0003] Currently, clinical assessment of balance function is mainly based on scales. Professional medical staff use test items such as standing, sitting, and turning to score the patient's balance and walking ability. The final score can be used to judge the patient's balance function.

[0004] Because professional medical staff's assessments of patients' balance and walking abilities are often influenced by their subjective observations and judgments, as well as their personal experience and professional background, these assessments are highly subjective and inefficient. Furthermore, existing solutions often focus on a single dimension of assessment parameters, failing to fully capture the patient's movement characteristics, potentially resulting in incomplete assessment results. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a balance function assessment method, device, electronic device and readable storage medium to improve the objectivity, accuracy and comprehensiveness of the patient's balance function assessment.

[0006] In a first aspect, an embodiment of the present application provides a method for evaluating balance function, comprising:

[0007] Collecting first gait test data corresponding to the balance function-related indicators of the patient to be evaluated when performing the first gait test, second gait test data corresponding to the balance function-related indicators when performing the second gait test, and third gait test data corresponding to the balance function-related indicators when performing the dual-task gait test;

[0008] For the same balance function related index, calculating a first improvement rate of the second gait test data relative to the first gait test data;

[0009] The first gait test data, the second gait test data, the third gait test data and the first lifting rate are input into a balance function evaluation model, and the balance function evaluation model outputs an evaluation result for characterizing the balance function of the patient to be evaluated.

[0010] In combination with the first aspect, an embodiment of the present application provides a first possible implementation method of the first aspect, wherein the balance function-related indicators include any one or more of the following: walking speed, stride, step height, step width, stance phase, swing phase, double support phase, stride speed, swing speed, completion time and turn time.

[0011] In combination with the first aspect, an embodiment of the present application provides a second possible implementation of the first aspect, wherein, for the same balance function-related indicator, calculating a first improvement rate of the second gait test data relative to the first gait test data includes:

[0012] For the same balance function related index, calculating the difference between the second gait test data and the first gait test data corresponding to the balance function related index;

[0013] The ratio between the difference and the first posture test data corresponding to the balance function related index is calculated to obtain the first improvement rate.

[0014] In combination with the first aspect, the embodiment of the present application provides a third possible implementation of the first aspect, wherein the balance function assessment model includes a gait test model and a balance test model; the first gait test data, the second gait test data, the third gait test data, and the first lift rate are input into the balance function assessment model, and the balance function assessment model outputs an assessment result for characterizing the balance function of the patient to be assessed, including:

[0015] inputting a first step test feature for characterizing the first step test data into the gait test model, and outputting a target gait test score through the gait test model;

[0016] inputting a second gait test feature for characterizing the second gait test data, a third gait test feature for characterizing the third gait test data, and a first lift rate feature for characterizing the first lift rate into the balance test model, and outputting a target balance test score through the balance test model;

[0017] The sum of the target gait test score and the target balance test score is calculated to obtain the evaluation result.

[0018] In combination with the first aspect, the embodiment of the present application provides a fourth possible implementation of the first aspect, wherein, after obtaining the evaluation result, the method further includes:

[0019] When the patient to be evaluated is being evaluated for the first time, determining the balance function training content required for the patient to be evaluated based on the evaluation result;

[0020] When the patient to be evaluated is not being evaluated for the first time, the balance function training content determined for the patient to be evaluated at a historical moment is adjusted according to the evaluation result and historical evaluation results to obtain new balance function training content.

[0021] In combination with the first aspect, the embodiment of the present application provides a fifth possible implementation of the first aspect, wherein the gait test model and the balance test model are trained in the following manner:

[0022] Obtaining first sample gait test data corresponding to the balance function-related index of the training sample patient when performing the first gait test, second sample gait test data corresponding to the balance function-related index when performing the second gait test, third sample gait test data corresponding to the balance function-related index when performing the dual-task gait test, and the actual balance test score and actual gait test score of the training sample patient;

[0023] For the same balance function-related indicator, calculating a second improvement rate of the second sample gait test data relative to the first sample gait test data;

[0024] Inputting a first sample gait test feature for characterizing the first sample gait test data into a first regression model to be trained, and outputting a predicted gait test score through the first regression model;

[0025] inputting a second sample gait test feature for characterizing the second sample gait test data, a third sample gait test feature for characterizing the third sample gait test data, and a second lift rate feature for characterizing the second lift rate into a second regression model to be trained, and outputting a predicted balance test score through the second regression model;

[0026] Training the first regression model according to the actual gait test score and the predicted gait test score, and stopping the training when a training cutoff condition is reached, thereby obtaining the gait test model after training;

[0027] The second regression model is trained according to the true balance test score and the predicted balance test score. When a training cutoff condition is reached, the training is stopped to obtain the balance test model after training.

[0028] In combination with the first aspect, the embodiment of the present application provides a sixth possible implementation of the first aspect, wherein, after obtaining the trained balance function assessment model, the method further includes:

[0029] Obtaining fourth gait test data corresponding to the balance function-related index of the test patient when performing the first gait test, fifth gait test data corresponding to the balance function-related index when performing the second gait test, sixth gait test data corresponding to the balance function-related index when performing the dual-task gait test, and a true assessment score of the test patient;

[0030] For the same balance function-related indicator, calculating a third improvement rate of the fifth gait test data relative to the fourth gait test data;

[0031] inputting the fourth gait test data, the fifth gait test data, the sixth gait test data, and the third improvement rate into the balance function assessment model, and outputting a test assessment score for characterizing the balance function of the test patient through the balance function assessment model;

[0032] Based on the real evaluation score and the test evaluation score, the model evaluation parameters used to characterize the accuracy of the user model evaluation are calculated; the model evaluation parameters include any one or more of the following: mean absolute error, mean absolute percentage error, mean square error, root mean square error, and determination coefficient.

[0033] In a second aspect, an embodiment of the present application further provides a balance function assessment device, comprising:

[0034] An acquisition module is used to acquire first gait test data corresponding to the balance function-related indicators of the patient to be evaluated when performing the first gait test, second gait test data corresponding to the balance function-related indicators when performing the second gait test, and third gait test data corresponding to the balance function-related indicators when performing the dual-task gait test;

[0035] a calculation module, configured to calculate, for the same balance function-related index, a first improvement rate of the second gait test data relative to the first gait test data;

[0036] An input module is used to input the first gait test data, the second gait test data, the third gait test data and the first lifting rate into a balance function evaluation model, and output an evaluation result for characterizing the balance function of the patient to be evaluated through the balance function evaluation model.

[0037] In combination with the second aspect, an embodiment of the present application provides a first possible implementation scheme of the second aspect, wherein the balance function-related indicators include any one or more of the following: walking speed, stride, step height, step width, stance phase, swing phase, double support phase, stride speed, swing speed, completion time and turn time.

[0038] In conjunction with the second aspect, an embodiment of the present application provides a second possible implementation of the second aspect, wherein the calculation module, when used to calculate a first improvement rate of the second gait test data relative to the first gait test data for the same balance function-related indicator, is specifically configured to:

[0039] For the same balance function related index, calculating the difference between the second gait test data and the first gait test data corresponding to the balance function related index;

[0040] The ratio between the difference and the first posture test data corresponding to the balance function related index is calculated to obtain the first improvement rate.

[0041] In combination with the second aspect, the embodiment of the present application provides a third possible implementation of the second aspect, wherein the balance function assessment model includes a gait test model and a balance test model;

[0042] The input module is used to input the first gait test data, the second gait test data, the third gait test data, and the first lift rate into a balance function evaluation model, and output an evaluation result for characterizing the balance function of the patient to be evaluated through the balance function evaluation model, specifically for:

[0043] inputting a first step test feature for characterizing the first step test data into the gait test model, and outputting a target gait test score through the gait test model;

[0044] inputting a second gait test feature for characterizing the second gait test data, a third gait test feature for characterizing the third gait test data, and a first lift rate feature for characterizing the first lift rate into the balance test model, and outputting a target balance test score through the balance test model;

[0045] The sum of the target gait test score and the target balance test score is calculated to obtain the evaluation result.

[0046] In combination with the second aspect, the embodiment of the present application provides a fourth possible implementation of the second aspect, wherein the apparatus further includes:

[0047] A determination module is used to determine the balance function training content required for the patient to be evaluated based on the evaluation result when the patient to be evaluated is being evaluated for the first time;

[0048] The adjustment module is used to adjust the balance function training content determined at a historical moment for the patient to be evaluated according to the evaluation result and the historical evaluation result when the patient to be evaluated is not being evaluated for the first time, so as to obtain new balance function training content.

[0049] In combination with the second aspect, the embodiment of the present application provides a fifth possible implementation of the second aspect, wherein the apparatus further includes a training module, and the training model is used to:

[0050] Obtaining first sample gait test data corresponding to the balance function-related index of the training sample patient when performing the first gait test, second sample gait test data corresponding to the balance function-related index when performing the second gait test, third sample gait test data corresponding to the balance function-related index when performing the dual-task gait test, and the actual balance test score and actual gait test score of the training sample patient;

[0051] For the same balance function-related indicator, calculating a second improvement rate of the second sample gait test data relative to the first sample gait test data;

[0052] Inputting a first sample gait test feature for characterizing the first sample gait test data into a first regression model to be trained, and outputting a predicted gait test score through the first regression model;

[0053] inputting a second sample gait test feature for characterizing the second sample gait test data, a third sample gait test feature for characterizing the third sample gait test data, and a second lift rate feature for characterizing the second lift rate into a second regression model to be trained, and outputting a predicted balance test score through the second regression model;

[0054] Training the first regression model according to the actual gait test score and the predicted gait test score, and stopping the training when a training cutoff condition is reached, thereby obtaining the gait test model after training;

[0055] The second regression model is trained according to the true balance test score and the predicted balance test score. When a training cutoff condition is reached, the training is stopped to obtain the balance test model after training.

[0056] In combination with the second aspect, the embodiment of the present application provides a sixth possible implementation of the second aspect, wherein the apparatus further includes a model evaluation module, and the model evaluation module is used to:

[0057] Obtaining fourth gait test data corresponding to the balance function-related index of the test patient when performing the first gait test, fifth gait test data corresponding to the balance function-related index when performing the second gait test, sixth gait test data corresponding to the balance function-related index when performing the dual-task gait test, and a true assessment score of the test patient;

[0058] For the same balance function-related indicator, calculating a third improvement rate of the fifth gait test data relative to the fourth gait test data;

[0059] inputting the fourth gait test data, the fifth gait test data, the sixth gait test data, and the third improvement rate into the balance function assessment model, and outputting a test assessment score for characterizing the balance function of the test patient through the balance function assessment model;

[0060] Based on the real evaluation score and the test evaluation score, the model evaluation parameters used to characterize the accuracy of the user model evaluation are calculated; the model evaluation parameters include any one or more of the following: mean absolute error, mean absolute percentage error, mean square error, root mean square error, and determination coefficient.

[0061] In a third aspect, an embodiment of the present application further provides an electronic device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of any possible implementation method of the first aspect above are performed.

[0062] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any possible implementation method of the first aspect are executed.

[0063] The embodiments of the present application provide a balance function assessment method, device, electronic device and readable storage medium, wherein, by having the patient to be assessed perform a first gait test, a second gait test and a dual-task gait test respectively, the first gait test data, the second gait test data and the third gait test data corresponding to the balance function related indicators of the patient to be assessed when performing the first gait test, the second gait test and the dual-task gait test are respectively collected. Compared with the method of only having the patient to be assessed perform one gait test, the method of the present application evaluates from multiple test dimensions, comprehensively captures the gait test data of the patient to be assessed, and is conducive to improving the comprehensiveness of the balance function assessment of the patient to be assessed. At the same time, the present application automatically evaluates the balance function of the patient to be assessed through a balance function assessment model. Compared with the method of scoring by medical staff, the method of the present application is conducive to improving the objectivity and accuracy of the balance function assessment of the patient to be assessed.

[0064] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0066] Figure 1 A flow chart of a balance function evaluation method provided in an embodiment of the present application is shown;

[0067] Figure 2 A schematic diagram of walking provided by an embodiment of the present application is shown;

[0068] Figure 3 A schematic structural diagram of a balance function assessment device provided in an embodiment of the present application is shown;

[0069] Figure 4 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of this application.

[0071] In the medical field, the assessment of balance function in the elderly is crucial to maintaining health levels and improving quality of life. Balance functions such as balance ability and gait characteristics are the main indicators of health status. They can reflect potential muscle and bone diseases and nervous system damage, helping medical practitioners to detect potential health problems early and intervene and manage them. In addition, falls related to balance dysfunction may lead to consequences such as fractures and head injuries, seriously affecting the patient's independence in daily life and even endangering their lives. The assessment of balance function in the elderly can effectively help medical professionals judge their fall risk and take corresponding preventive measures. Through rehabilitation training and other means, it can reduce health problems caused by falls and medical expenses in subsequent rehabilitation care. Therefore, the development of an effective balance function assessment method can identify potential risks, prevent falls, improve care levels, and optimize the allocation of medical resources. It is of great significance to individual patients and the medical system as a whole.

[0072] Currently, clinical assessment of balance function is mainly based on scales, such as the Berg Balance Scale, the Tinetti Balance and Gait Rating Scale, the Morse Fall Risk Scale, and the Timed Up and Go (TUG) test. These scales use test items such as standing, sitting, and turning, and professional medical staff score the patient's balance and walking ability. The final score can be used to judge the patient's balance function. Among them, the Tinetti Balance and Gait Rating Scale (hereinafter referred to as the Tinetti scale) was developed by Mary E. Tinetti in 1986 and is a tool widely used to assess the gait and balance ability of the elderly in daily life. The Tinetti scale has a total score of 28 points and mainly consists of two parts: balance test (maximum score 16 points) and gait test (maximum score 12 points). The balance test requires the patient to sit in a hard chair without armrests and score nine test items, including sitting balance, standing up, attempting to stand up, balance function when standing up immediately, and balance when sitting down. The gait test focuses on characteristics such as stride length, gait symmetry, stride continuity, and trunk stability while the patient walks three meters at a comfortable pace. After the test, the doctor uses the score to determine the patient's balance dysfunction and fall risk. A score of less than 24 indicates a balance dysfunction, while a score of less than 18 indicates a fall risk.

[0073] Balance function assessment scales, represented by the Tinetti scale, are scored by doctors or trained medical professionals based on specific scoring criteria through observation of patients' behaviors and movements. The scales involve doctors' subjective observations and judgments in implementation, scoring, and result interpretation, and are potentially biased.

[0074] Based on this, the embodiments of the present application provide a balance function assessment method, device, electronic device and readable storage medium to improve the objectivity, accuracy and comprehensiveness of the patient's balance function assessment, which is described below through embodiments.

[0075] Example 1:

[0076] To facilitate understanding of this embodiment, a balance function evaluation method disclosed in an embodiment of the present application is first introduced in detail. Figure 1 A flow chart of a balance function evaluation method provided in an embodiment of the present application is shown. Figure 1 As shown, the following steps are included:

[0077] S101: Collecting the first gait test data corresponding to the balance function related indicators of the patient to be evaluated when performing the first gait test, the second gait test data corresponding to the balance function related indicators when performing the second gait test, and the third gait test data corresponding to the balance function related indicators when performing the dual-task gait test.

[0078] In this embodiment, the patient to be evaluated may be a patient who needs to undergo a balance function evaluation, such as an elderly person. Before performing the balance function evaluation, the patient to be evaluated is first asked to undergo a first gait test, a second gait test, and a dual-task gait test. Among them, the first gait test requires the patient to be evaluated to walk at a normal speed; the second gait test requires the patient to be evaluated to walk as fast as possible, therefore, the walking speed required in the second gait test is greater than the walking speed required in the first gait test. The dual-task gait test requires that a cognitive test (such as calculation, memory, cognition, etc.) be performed while the first gait test is being performed. During the process of the patient to be evaluated undergoing the three gait tests, sensor technology, such as a depth vision sensor, a wireless electromyography sensor, etc., is used to collect gait test data corresponding to each balance function-related indicator.

[0079] In a possible embodiment, the balance function-related indicators include any one or more of the following: step speed, stride length, step height, step width, stance phase, swing phase, double support phase, stride speed, swing speed, completion time and turn time.

[0080] In this embodiment, when the balance function-related indicators include walking speed, stride length, step height, step width, stance phase, swing phase, double support phase, stride speed, swing speed, completion time, and turn time, the first gait test data includes: first speed data, first stride length data, first height data, first width data, first stance phase data, first swing phase data, first double support phase data, first stride speed data, first swing speed data, first completion time data, and first turn time data. Similarly, the second gait test data includes: second speed data, second stride length data, second step height data, second step width data, second stance phase data, second swing phase data, second double support phase data, second stride speed data, second swing speed data, second completion time data, and second turn time data. The third gait test data includes: third speed data, third stride length data, third step height data, third step width data, third stance phase data, third swing phase data, third double support phase data, third stride speed data, third swing speed data, third completion time data, and third turn time data.

[0081] Figure 2 A schematic diagram of walking provided by an embodiment of the present application is shown, such as Figure 2 As shown in the figure, stride speed is the distance / duration between the start and end points (meters / second). Stride length is the distance (meters) between two single-foot landings. For example, during walking, the distance between the first and second landings of the right foot. The stride length during the entire gait test can be averaged. Stride height is the highest distance from the ground during the swing of a single foot (meters). Stride width is the width between the left and right feet (meters).

[0082] Stance phase: The percentage of time (in %) the left (or right) foot spends in stance during each left (or right) stride cycle. The left (or right) stride cycle is the time from the heel of the left (or right) foot touching the ground to the heel landing again. The left (or right) stance time is the time from the heel of the left (or right) foot touching the ground to the heel leaving the ground again during a left (or right) stride cycle.

[0083] Swing phase: The percentage of time (%) that the left (or right) foot spends swinging during each left (or right) stride cycle. The swing phase refers to the time it takes for the left (or right) foot's heel to leave the ground and land again during a left (or right) stride cycle.

[0084] Double support phase: The percentage of time spent standing on both feet during each stride cycle (%). Stride speed: Left (right) stride distance (the distance from the heel of the left (right) foot touching the ground to the heel touching the ground again) / stride time (the duration of one stride cycle) (m / s). Swing speed: Single-leg swing distance / Single-leg swing time (m / s), where single-leg swing distance refers to the distance from the toe leaving the ground to the heel touching the ground again, and single-leg swing time refers to the time from the toe leaving the ground to the heel touching the ground again.

[0085] Completion time: The total time taken to complete the entire gait test. Turn time: The time taken from the last foot lift with a turning tendency (turn start) to the first foot lift to start walking straight (turn end).

[0086] S102: For the same balance function related indicator, calculate a first improvement rate of the second gait test data relative to the first gait test data.

[0087] In this embodiment, for each balance function related indicator, a first improvement rate between the data corresponding to the balance function related indicator in the second gait test data and the data corresponding to the balance function related indicator in the first gait test data is calculated.

[0088] For example, when the balance function related indicator is gait speed, the data corresponding to the balance function related indicator in the first gait test data is 1 meter / second, and the data corresponding to the balance function related indicator in the second gait test data may be 2 meters / second.

[0089] In a possible implementation, when executing step S102, the following steps may be specifically performed:

[0090] S1021: For the same balance function related index, calculating the difference between the second gait test data and the first gait test data corresponding to the balance function related index;

[0091] S1022: Calculate the ratio between the difference and the first posture test data corresponding to the balance function related indicator to obtain a first improvement rate.

[0092] In this embodiment, for each balance function-related indicator, the difference between the data corresponding to the balance function-related indicator in the second gait test data and the data corresponding to the balance function-related indicator in the first gait test data is calculated; and the ratio between the difference and the data corresponding to the balance function-related indicator in the first gait test data is calculated to obtain a first improvement rate corresponding to the balance function-related indicator. Each balance function-related indicator corresponds to a first improvement rate.

[0093] In this embodiment, for the balance function related indicator m, the first improvement rate corresponding to the balance function related indicator m can be calculated using the following formula:

[0094]

[0095] Among them, h m represents the first improvement rate corresponding to the balance function related index m; b m represents the data corresponding to the balance function related index m in the second gait test data; a m Represents the data corresponding to the balance function related index m in the first step test data.

[0096] S103: Inputting the first gait test data, the second gait test data, the third gait test data and the first lifting rate into a balance function evaluation model, and outputting an evaluation result for characterizing the balance function of the patient to be evaluated through the balance function evaluation model.

[0097] In this embodiment, the first gait test data, the second gait test data, the third gait test data and the first improvement rate corresponding to each balance function related indicator are input into the balance function evaluation model, and the balance function of the patient to be evaluated is evaluated by the balance function evaluation model to obtain an evaluation result, wherein the evaluation result can be a score of the balance function.

[0098] In a possible implementation, when executing step S103, the following steps S1031-S1033 may be specifically performed:

[0099] S1031: Inputting the first step test feature used to characterize the first step test data into the gait test model, and outputting the target gait test score through the gait test model.

[0100] In this embodiment, the first gait test feature is extracted from the first gait test data, the second gait test feature is extracted from the second gait test data, the third gait test feature is extracted from the third gait test data, and the first lift rate feature is extracted from the first lift rate.

[0101] The first gait test feature is input into the trained gait test model to obtain the target gait test score for the patient to be evaluated. The maximum target gait test score is 12 points.

[0102] S1032: Input the second gait test feature for characterizing the second gait test data, the third gait test feature for characterizing the third gait test data, and the first improvement rate feature for characterizing the first improvement rate into the balance test model, and output the target balance test score through the balance test model.

[0103] The second gait test feature, the third gait test feature, and each first lift rate feature are input into the trained balance test model to obtain a target balance test score for the patient to be evaluated, where the maximum score for the target balance test score is 16 points.

[0104] S1033: Calculate the sum of the target gait test score and the target balance test score to obtain an evaluation result.

[0105] In this embodiment, the evaluation result is specifically an evaluation score of the balance function of the patient to be evaluated, with a full score of 28 points.

[0106] In a possible implementation, after obtaining the evaluation result, the following steps may be performed:

[0107] S1041: When the patient to be evaluated is being evaluated for the first time, the balance function training content required for the patient to be evaluated is determined based on the evaluation results.

[0108] In this embodiment, when the patient being evaluated is undergoing a first evaluation, the balance function training content required for the patient is determined based on the target gait test score and target balance test score included in the evaluation results, as well as the patient's demographic information (gender, age, and education level). For example, when the target gait test score is below a first preset threshold, the balance function training content includes gait training, and when the target balance test score is below a second preset threshold, the balance function training content includes balance training.

[0109] S1042: When the patient to be evaluated is not being evaluated for the first time, the balance function training content determined for the patient to be evaluated at the historical moment is adjusted according to the evaluation result and the historical evaluation result to obtain new balance function training content.

[0110] In this embodiment, when the patient being evaluated is not being evaluated for the first time, the balance function training content determined for the patient being evaluated at the time of evaluation is adjusted based on the target gait test score and target balance test score included in the evaluation result, the target gait test score and target balance test score included in the historical evaluation result, and the demographic information (gender, age, and education level) of the patient being evaluated, thereby obtaining a new balance function training content. The historical evaluation result is the evaluation result determined for the patient being evaluated at the time of evaluation.

[0111] For example, when the target gait test score in the evaluation results of the patient to be evaluated is higher than the target gait test score in the historical evaluation results, it means that the gait ability of the patient to be evaluated is in an improved state. At this time, the training content of the gait training part in the balance function training content determined for the patient to be evaluated at the historical moment can be reduced.

[0112] When the target balance test score in the assessment result of the patient to be assessed is lower than the target balance test score in the historical assessment result, it means that the balance ability of the patient to be assessed is getting worse. At this time, the training content for the balance training part of the balance function training content determined for the patient to be assessed at the historical moment can be increased.

[0113] In a possible implementation, the gait test model is obtained by training the first regression model, and the balance test model is obtained by training the second regression model. The specific training process is as follows:

[0114] Obtaining first sample gait test data corresponding to the balance function-related indicators of the training sample patient when performing the first gait test, second sample gait test data corresponding to the balance function-related indicators when performing the second gait test, third sample gait test data corresponding to the balance function-related indicators when performing the dual-task gait test, and the actual balance test score and actual gait test score of the training sample patient;

[0115] For the same balance function-related indicator, calculating a second improvement rate of the second sample gait test data relative to the first sample gait test data;

[0116] Inputting a first sample gait test feature for characterizing the first sample gait test data into a first regression model to be trained, and outputting a predicted gait test score through the first regression model;

[0117] Inputting the second sample gait test feature for characterizing the second sample gait test data, the third sample gait test feature for characterizing the third sample gait test data, and the second improvement rate feature for characterizing the second improvement rate into a second regression model to be trained, and outputting a predicted balance test score through the second regression model;

[0118] According to the actual gait test scores and the predicted gait test scores, the first regression model is trained. When the training cutoff condition is reached, the training is stopped to obtain the gait test model after the training is completed;

[0119] The second regression model is trained according to the real balance test scores and the predicted balance test scores. When the training cutoff condition is reached, the training is stopped to obtain the balance test model after the training is completed.

[0120] In one possible implementation, after the balance test model and the gait test model are trained, that is, after the balance function assessment model is trained, the trained balance function assessment model may be evaluated in the following manner to assess the accuracy of the balance function assessment model:

[0121] Obtaining fourth gait test data corresponding to the balance function-related index of the test patient when performing the first gait test, fifth gait test data corresponding to the balance function-related index when performing the second gait test, sixth gait test data corresponding to the balance function-related index when performing the dual-task gait test, and the actual assessment score of the test patient;

[0122] For the same balance function-related indicator, calculating a third improvement rate of the fifth gait test data relative to the fourth gait test data;

[0123] inputting the fourth gait test data, the fifth gait test data, the sixth gait test data, and the third lifting rate into a balance function assessment model, and outputting a test assessment score for characterizing the balance function of the test patient through the balance function assessment model;

[0124] Based on the real evaluation score and the test evaluation score, the model evaluation parameters used to characterize the accuracy of the model evaluation are calculated; the model evaluation parameters include any one or more of the following: mean absolute error, mean absolute percentage error, mean square error, root mean square error, and determination coefficient.

[0125] In this embodiment, the smaller the model evaluation parameter, that is, the smaller the error, the higher the accuracy of the balance function evaluation model.

[0126] Example 2:

[0127] Based on the same technical concept, the present application also provides a balance function evaluation device, Figure 3 FIG. 1 shows a structural diagram of a balance function evaluation device provided in an embodiment of the present application. Figure 3 As shown, the device includes:

[0128] The acquisition module 301 is used to acquire first gait test data corresponding to the balance function-related index when the patient to be evaluated performs the first gait test, second gait test data corresponding to the balance function-related index when the patient to be evaluated performs the second gait test, and third gait test data corresponding to the balance function-related index when the patient to be evaluated performs the dual-task gait test;

[0129] A calculation module 302 is configured to calculate a first improvement rate of the second gait test data relative to the first gait test data for the same balance function related index;

[0130] The input module 303 is used to input the first gait test data, the second gait test data, the third gait test data and the first lifting rate into the balance function evaluation model, and output the evaluation result used to characterize the balance function of the patient to be evaluated through the balance function evaluation model.

[0131] Optionally, the balance function-related indicators include any one or more of the following: step speed, stride length, step height, step width, stance phase, swing phase, double support phase, stride speed, swing speed, completion time and turn time.

[0132] Optionally, when the calculation module 302 is used to calculate the first improvement rate of the second gait test data relative to the first gait test data for the same balance function-related indicator, it is specifically used to:

[0133] For the same balance function related index, calculating the difference between the second gait test data and the first gait test data corresponding to the balance function related index;

[0134] The ratio between the difference and the first posture test data corresponding to the balance function related index is calculated to obtain the first improvement rate.

[0135] Optionally, the balance function assessment model includes a gait test model and a balance test model;

[0136] The input module 303 is used to input the first gait test data, the second gait test data, the third gait test data, and the first lift rate into the balance function evaluation model, and output an evaluation result representing the balance function of the patient to be evaluated through the balance function evaluation model, specifically for:

[0137] inputting a first step test feature for characterizing the first step test data into the gait test model, and outputting a target gait test score through the gait test model;

[0138] inputting a second gait test feature for characterizing the second gait test data, a third gait test feature for characterizing the third gait test data, and a first lift rate feature for characterizing the first lift rate into the balance test model, and outputting a target balance test score through the balance test model;

[0139] The sum of the target gait test score and the target balance test score is calculated to obtain the evaluation result.

[0140] Optionally, the device further includes:

[0141] A determination module is used to determine the balance function training content required for the patient to be evaluated based on the evaluation result when the patient to be evaluated is being evaluated for the first time;

[0142] The adjustment module is used to adjust the balance function training content determined at a historical moment for the patient to be evaluated according to the evaluation result and the historical evaluation result when the patient to be evaluated is not being evaluated for the first time, so as to obtain new balance function training content.

[0143] Optionally, the device further includes a training module, and the training model is used to:

[0144] Obtaining first sample gait test data corresponding to the balance function-related index of the training sample patient when performing the first gait test, second sample gait test data corresponding to the balance function-related index when performing the second gait test, third sample gait test data corresponding to the balance function-related index when performing the dual-task gait test, and the actual balance test score and actual gait test score of the training sample patient;

[0145] For the same balance function-related indicator, calculating a second improvement rate of the second sample gait test data relative to the first sample gait test data;

[0146] Inputting a first sample gait test feature for characterizing the first sample gait test data into a first regression model to be trained, and outputting a predicted gait test score through the first regression model;

[0147] inputting a second sample gait test feature for characterizing the second sample gait test data, a third sample gait test feature for characterizing the third sample gait test data, and a second lift rate feature for characterizing the second lift rate into a second regression model to be trained, and outputting a predicted balance test score through the second regression model;

[0148] Training the first regression model according to the actual gait test score and the predicted gait test score, and stopping the training when a training cutoff condition is reached, thereby obtaining the gait test model after training;

[0149] The second regression model is trained according to the true balance test score and the predicted balance test score. When a training cutoff condition is reached, the training is stopped to obtain the balance test model after training.

[0150] Optionally, the device further includes a model evaluation module, wherein the model evaluation module is used to:

[0151] Obtaining fourth gait test data corresponding to the balance function-related index of the test patient when performing the first gait test, fifth gait test data corresponding to the balance function-related index when performing the second gait test, sixth gait test data corresponding to the balance function-related index when performing the dual-task gait test, and a true assessment score of the test patient;

[0152] For the same balance function-related indicator, calculating a third improvement rate of the fifth gait test data relative to the fourth gait test data;

[0153] inputting the fourth gait test data, the fifth gait test data, the sixth gait test data, and the third improvement rate into the balance function assessment model, and outputting a test assessment score for characterizing the balance function of the test patient through the balance function assessment model;

[0154] Based on the real evaluation score and the test evaluation score, the model evaluation parameters used to characterize the accuracy of the user model evaluation are calculated; the model evaluation parameters include any one or more of the following: mean absolute error, mean absolute percentage error, mean square error, root mean square error, and determination coefficient.

[0155] Example 3:

[0156] Figure 4 A structural diagram of an electronic device provided in an embodiment of the present application includes: a processor 401, a memory 402 and a bus 403, wherein the memory 402 stores machine-readable instructions executable by the processor 401. When the electronic device runs the above-mentioned information processing method, the processor 401 communicates with the memory 402 through the bus 403, and the processor 401 executes the machine-readable instructions to perform the method steps described in Example 1.

[0157] Example 4:

[0158] The fourth embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method steps described in the first embodiment are executed.

[0159] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, electronic devices, and computer-readable storage media can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0160] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection of some communication interface, device or unit, which can be electrical, mechanical or other forms.

[0161] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0162] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0163] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0164] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The scope of protection of the present application is not limited thereto. Although the present application has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present application, or perform equivalent replacements for some of the technical features thereof. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection of the claims.

Claims

1. A method for evaluating balance function, characterized in that: include: Collect the first gait test data corresponding to the balance function-related indicators of the patient to be evaluated when performing the first gait test, the second gait test data corresponding to the balance function-related indicators when performing the second gait test, and the third gait test data corresponding to the balance function-related indicators when performing the dual-task gait test; the walking speed required in the second gait test is greater than the walking speed required in the first gait test; the dual-task gait test requires cognitive testing to be performed simultaneously with the first gait test; For the same balance function related index, calculating a first improvement rate of the second gait test data relative to the first gait test data; inputting the first gait test data, the second gait test data, the third gait test data, and the first lifting rate into a balance function evaluation model, and outputting an evaluation result for characterizing the balance function of the patient to be evaluated through the balance function evaluation model; The balance function evaluation model includes a gait test model and a balance test model; the first gait test data, the second gait test data, the third gait test data, and the first lift rate are input into the balance function evaluation model, and the balance function evaluation model outputs an evaluation result for characterizing the balance function of the patient to be evaluated, including: inputting a first step test feature for characterizing the first step test data into the gait test model, and outputting a target gait test score through the gait test model; inputting a second gait test feature for characterizing the second gait test data, a third gait test feature for characterizing the third gait test data, and a first lift rate feature for characterizing the first lift rate into the balance test model, and outputting a target balance test score through the balance test model; The sum of the target gait test score and the target balance test score is calculated to obtain the evaluation result.

2. The method according to claim 1, characterized in that The balance function related indicators include any one or more of the following: step speed, stride length, step height, step width, stance phase, swing phase, double support phase, stride speed, swing speed, completion time and turn time.

3. The method according to claim 1, characterized in that Calculating a first improvement rate of the second gait test data relative to the first gait test data for the same balance function-related indicator includes: For the same balance function related index, calculating the difference between the second gait test data and the first gait test data corresponding to the balance function related index; The ratio between the difference and the first posture test data corresponding to the balance function related index is calculated to obtain the first improvement rate.

4. The method according to claim 1, characterized in that After obtaining the evaluation result, the method further includes: When the patient to be evaluated is being evaluated for the first time, determining the balance function training content required for the patient to be evaluated based on the evaluation result; When the patient to be evaluated is not being evaluated for the first time, the balance function training content determined for the patient to be evaluated at a historical moment is adjusted according to the evaluation result and historical evaluation results to obtain new balance function training content.

5. The method according to claim 1, characterized in that: The gait test model and the balance test model are trained in the following manner: Obtaining first sample gait test data corresponding to the balance function-related index of the training sample patient when performing the first gait test, second sample gait test data corresponding to the balance function-related index when performing the second gait test, third sample gait test data corresponding to the balance function-related index when performing the dual-task gait test, and the actual balance test score and actual gait test score of the training sample patient; For the same balance function-related indicator, calculating a second improvement rate of the second sample gait test data relative to the first sample gait test data; Inputting a first sample gait test feature for characterizing the first sample gait test data into a first regression model to be trained, and outputting a predicted gait test score through the first regression model; inputting a second sample gait test feature for characterizing the second sample gait test data, a third sample gait test feature for characterizing the third sample gait test data, and a second lift rate feature for characterizing the second lift rate into a second regression model to be trained, and outputting a predicted balance test score through the second regression model; Training the first regression model according to the actual gait test score and the predicted gait test score, and stopping the training when a training cutoff condition is reached, thereby obtaining the gait test model after training; The second regression model is trained according to the true balance test score and the predicted balance test score. When a training cutoff condition is reached, the training is stopped to obtain the balance test model after training.

6. The method according to claim 1, characterized in that After obtaining the trained balance function assessment model, the method further includes: Obtaining fourth gait test data corresponding to the balance function-related index of the test patient when performing the first gait test, fifth gait test data corresponding to the balance function-related index when performing the second gait test, sixth gait test data corresponding to the balance function-related index when performing the dual-task gait test, and a true assessment score of the test patient; For the same balance function-related indicator, calculating a third improvement rate of the fifth gait test data relative to the fourth gait test data; inputting the fourth gait test data, the fifth gait test data, the sixth gait test data, and the third improvement rate into the balance function assessment model, and outputting a test assessment score for characterizing the balance function of the test patient through the balance function assessment model; Based on the real evaluation score and the test evaluation score, the model evaluation parameters used to characterize the accuracy of the user model evaluation are calculated; the model evaluation parameters include any one or more of the following: mean absolute error, mean absolute percentage error, mean square error, root mean square error, and determination coefficient.

7. A balance function assessment device, characterized in that: include: an acquisition module for acquiring first gait test data corresponding to balance function-related indicators of the patient to be evaluated when performing the first gait test, second gait test data corresponding to balance function-related indicators when performing the second gait test, and third gait test data corresponding to balance function-related indicators when performing the dual-task gait test; the walking speed required in the second gait test is greater than the walking speed required in the first gait test; the dual-task gait test requires cognitive testing to be performed simultaneously with the first gait test; a calculation module, configured to calculate, for the same balance function-related index, a first improvement rate of the second gait test data relative to the first gait test data; an input module, configured to input the first gait test data, the second gait test data, the third gait test data, and the first lift rate into a balance function evaluation model, and output an evaluation result representing the balance function of the patient to be evaluated through the balance function evaluation model; The balance function evaluation model includes a gait test model and a balance test model; the input module is used to input the first gait test data, the second gait test data, the third gait test data, and the first lift rate into the balance function evaluation model, and output an evaluation result for characterizing the balance function of the patient to be evaluated through the balance function evaluation model, specifically for: inputting a first step test feature for characterizing the first step test data into the gait test model, and outputting a target gait test score through the gait test model; inputting a second gait test feature for characterizing the second gait test data, a third gait test feature for characterizing the third gait test data, and a first lift rate feature for characterizing the first lift rate into the balance test model, and outputting a target balance test score through the balance test model; The sum of the target gait test score and the target balance test score is calculated to obtain the evaluation result.

8. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method according to any one of claims 1 to 6 are performed.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the method according to any one of claims 1 to 6.

Images