A method and system for mental health assessment

Abstract

The application relates to a mental health state evaluation method and system, which comprises the following steps: acquiring electroencephalogram data and personal information of a person to be measured corresponding to the electroencephalogram data, wherein the electroencephalogram data are brain wave data of the person to be measured in an evaluation process; determining a mental health parameter value of the person to be measured according to the electroencephalogram data based on a preset determination rule; and determining a mental health evaluation parameter of the person to be measured according to the mental health parameter value, the personal information of the person to be measured and a pre-stored grade norm table. The application has the effects of reducing subjectivity in the evaluation process and making the evaluation result more capable of reflecting the real mental state of the person to be measured.

Description

Technical Field

[0001] This application relates to the field of mental health assessment, and in particular to a mental health assessment method and system. Background Technology

[0002] Currently, mental health assessments are usually based on scales. Participants are required to answer the questions on the scales truthfully based on their own situation. This method is highly subjective, and if the participants do not cooperate, accurate and objective evaluation results cannot be obtained.

[0003] When conducting team psychological assessments based on scales, it is necessary to go through a process of distributing scales, filling out scales, collecting scales, and then conducting centralized evaluations. The organizational process is complex and cumbersome, and the operation cycle is long. At present, there are also electronic scale systems that can distribute electronic scales through computers and organize personnel to conduct scale assessments on computers. However, such systems are still based on scales for assessment and cannot solve the problem of subjectivity in scale assessment. Summary of the Invention

[0004] In order to reduce subjectivity in the assessment process and make the assessment results more reflective of the true psychological state of the test subjects, this application provides a psychological health assessment method and system.

[0005] Firstly, this application provides a method for assessing mental health status, employing the following technical solution:

[0006] A method for assessing mental health status, the method comprising:

[0007] Obtain EEG data and the personal information of the test subject corresponding to the EEG data, wherein the EEG data is the EEG wave data of the test subject during the evaluation process;

[0008] Based on preset determination rules, the mental health parameter values ​​of the tested person are determined according to the EEG data;

[0009] The psychological health evaluation parameters of the test subjects are determined based on the values ​​of the psychological health parameters, the personal information of the test subjects, and the pre-stored level norm table.

[0010] By adopting the above technical solution, when conducting a mental health status assessment, the device collects the EEG data of the test subject. Then, based on preset determination rules, the mental health parameter values ​​of the test subject are determined according to the EEG data. Finally, based on the mental health parameter values, the test subject's personal information, and pre-stored level norm data, the mental health evaluation parameters of the test subject are determined. Using this assessment method, the test subject does not need to answer questions during the assessment process; instead, the EEG data is directly collected. This reduces the possibility of low accuracy of the assessment results due to the test subject's subjective factors, lowers the subjectivity in the assessment process, and makes the assessment results more reflective of the test subject's true mental state.

[0011] Optionally, when the EEG data comprises EEG data from multiple trainees, before determining the psychological health parameter values ​​of the test subject based on the EEG data according to a preset determination rule, the method further includes:

[0012] Obtain the timestamp information and device number corresponding to each EEG data point;

[0013] The target EEG data is determined based on the timestamp information corresponding to each EEG data, and the target EEG data is the data in the EEG data.

[0014] The subject corresponding to the target EEG data is determined based on the device number corresponding to the target EEG data.

[0015] Optionally, when the EEG data comprises EEG data from multiple trainees, the acquisition of the EEG data specifically includes:

[0016] EEG data is acquired at preset intervals, and a data acquisition command is output to the first EEG data acquisition device at this time.

[0017] Receive and store the EEG data output by the first EEG data acquisition device according to the data acquisition instruction;

[0018] The data acquisition command is output to the second EEG data acquisition device again, and the EEG data output by the second EEG data acquisition device according to the data acquisition command is received.

[0019] Data acquisition will stop once the EEG data output from the EEG acquisition device for all subjects has been obtained.

[0020] Optionally, the step of determining the mental health parameter values ​​of the test subject based on the electroencephalogram (EEG) data according to preset determination rules includes:

[0021] Identify the target EEG data contained within the EEG data;

[0022] Extract feature parameters from the target EEG data;

[0023] The first EEG feature value at each moment in the evaluation process is determined based on the preset multivariate regression equation and the feature parameters; the first EEG feature value at each moment is preprocessed and the mental health parameter value is determined based on the preprocessing result.

[0024] Optionally, the characteristic parameters include theta wave intensity, alpha wave intensity, low beta wave intensity, high beta wave intensity, and gamma wave intensity.

[0025] Optionally, determining the first EEG feature value at each moment during the evaluation process based on a preset multivariate regression equation and the feature parameters includes:

[0026] Calculate the sum of each characteristic parameter at the preset time and the difference between the intensity of the high beta wave and the intensity of the alpha wave at the preset time;

[0027] The first EEG characteristic value at the preset time is equal to the ratio of the sum of all characteristic parameters at the preset time to the difference between the high beta wave intensity and the alpha wave intensity at the preset time plus 1, where the preset time is a certain moment in the evaluation process;

[0028] Calculate the first EEG characteristic value at each moment during the assessment process.

[0029] Optionally, the step of preprocessing the first EEG feature value at each time moment and determining the mental health parameter value based on the preprocessing result includes:

[0030] Calculate the average value of the first EEG characteristic value during the assessment process to determine the second EEG characteristic value;

[0031] Determine the maximum and minimum values ​​of the second EEG characteristic parameter, and calculate the difference between the maximum and minimum values;

[0032] The ratio of the difference between the second EEG characteristic parameter corresponding to the test subject and the maximum and minimum values ​​is calculated during the assessment process; the ratio is multiplied by the first preset adjustment parameter to obtain the mental health parameter value.

[0033] Optionally, determining the mental health evaluation parameters of the test subject based on the mental health parameter values, the test subject's personal information, and a pre-stored level norm table includes:

[0034] The personal information includes gender and age;

[0035] The corresponding level norm table for the test subjects is determined based on their gender and age;

[0036] Based on the member's mental health parameter values, the corresponding level is queried in the grading norm table. The level corresponding to the mental health parameter values ​​is the mental health evaluation parameter of the tested person.

[0037] Optionally, the method further includes:

[0038] The mental health parameters of a predetermined number of people of different ages and genders were statistically analyzed.

[0039] The mental health parameter values ​​of people of the same age and gender are sorted.

[0040] Count the number of mental health parameter values ​​that are lower than each individual mental health parameter value;

[0041] The mental health evaluation parameter corresponding to the preset mental health parameter value is equal to the ratio of the number of mental health parameter values ​​less than the preset mental health parameter value to the number of people of the same age and gender, multiplied by the second preset adjustment parameter; a level norm table is formed and stored based on age, gender, each mental health parameter value and the mental health evaluation parameter corresponding to each mental health parameter value.

[0042] Secondly, this application provides a mental health status assessment system, which adopts the following technical solution:

[0043] A mental health status assessment system for performing mental health status assessment methods, comprising:

[0044] An electroencephalogram (EEG) device is used to collect brain signals from the user's scalp, process the collected brain signals into digital brain data, and output them.

[0045] The EEG exchange module is used to acquire the EEG data output by the EEG device and package and send the acquired EEG data.

[0046] The central processing module is used to receive data received from the EEG device forwarded by the EEG exchange module and to parse the EEG data.

[0047] The data analysis module is used to receive the EEG data and determine the values ​​of mental health parameters based on the EEG data;

[0048] The evaluation module is used to determine the psychological health evaluation parameters of the test subjects.

[0049] Optionally, a data recording module is provided, which is connected to the central processing module, the data analysis module, and the evaluation module respectively. The data recording module is used to store EEG data, mental health parameter values, and mental health evaluation parameters.

[0050] Optionally, it also includes: a user interaction module, which is connected to the central processing module, and is used to receive EEG data from the central processing module and display the data on the user interaction interface.

[0051] In summary, this application includes the following beneficial technical effects:

[0052] When conducting a mental health assessment, the device collects the subject's electroencephalogram (EEG) data. Based on pre-defined rules, the device determines the subject's mental health parameters using the EEG data. Then, based on these parameters, the subject's personal information, and pre-stored grading norms, the device determines the subject's mental health evaluation parameters. This assessment method eliminates the need for subjects to answer questions; instead, it directly collects their EEG data. This reduces the likelihood of subjective factors affecting the accuracy of the assessment, thus lowering the subjectivity and making the results more accurately reflect the subject's true mental state. Attached Figure Description

[0053] Figure 1 This is a system block diagram of the mental health status assessment system provided in this application.

[0054] Figure 2 This is a flowchart of the mental health status assessment method provided in this application.

[0055] Figure labeling: 10, EEG instrument; 20, EEG exchange module; 30, Central processing module; 40, User interaction module; 50, Data recording module; 60, Data analysis module; 70, Evaluation module. Detailed Implementation

[0056] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figure 1-2 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0057] This application discloses a mental health status assessment system. (Refer to...) Figure 1The mental health status assessment system includes at least one EEG device 10, an EEG exchange module 20, a central processing module 30, a user interaction module 40, a data analysis module 60, an evaluation module 70, and a data recording module 50. The EEG exchange module 20 is connected to the EEG device 10 and the central processing module 30. The central processing module 30 is also connected to the user interaction module 40, the data analysis module 60, and the data recording module 50. The data analysis module 60 is also connected to the data recording module 50 and the evaluation module 70. The evaluation module 70 is also connected to the data recording module 50.

[0058] The functions of the central processing module 30, user interaction module 40, data analysis module 60, evaluation module 70, and data recording module 50 are all implemented by a personal computer through software. The personal computer is connected to the EEG switching module 20 via a USB interface. In this embodiment, the EEG switching module 20 is a MindSwitch EEG switch.

[0059] When working, it is possible to assess the mental health status of one person or multiple people simultaneously.

[0060] When assessing the mental health status of multiple individuals simultaneously, each participant wears an EEG device 10. The user interaction module 40 displays the main interface of the software, including the software's operation interface, enabling software-based interactive functions, including keyboard and mouse operations. The operation interface includes a "Start Test" button and a "Stop Test" button. When the operator clicks the "Start Test" button, the assessment process officially begins. At this time, the user interaction module 40 plays the instructional audio and background music. Each participant, wearing the EEG device 10, performs the corresponding actions according to the instructions. Once the instructions have finished playing, the entire assessment ends.

[0061] After the assessment begins, the EEG device 10 collects EEG signals from the subject's scalp, processes the signals to form digitized EEG data, and then transmits the EEG data wirelessly to the EEG exchange module 20. The EEG exchange module 20 and multiple EEG devices 10 form a wireless transceiver network, enabling simultaneous acquisition of EEG data output from multiple EEG devices 10 via wireless communication. In other embodiments, wired communication can also be used, as long as data transmission between the EEG device 10 and the EEG exchange module 20 is possible; no limitation is imposed here. In this embodiment, the EEG device 10 is a CUBand EEG device 10, which is a portable EEG device 10 in the form of a headband.

[0062] The aforementioned system assesses the mental health status of test subjects, allowing those who do not need to participate in the assessment to answer the questions in the questionnaire truthfully based on their own circumstances. This reduces the possibility of errors in the assessment results due to non-cooperation by test subjects, minimizes subjective factors from test subjects during the assessment process, and thus improves the accuracy of the assessment results. At the same time, the system can also assess the mental health status of multiple people simultaneously, eliminating the need for processes such as distributing questionnaires, filling out questionnaires, collecting questionnaires, and then conducting centralized evaluations. This reduces the complexity of the organizational process and the operational cycle, and improves the efficiency of the assessment.

[0063] Furthermore, during the simultaneous evaluation of multiple individuals, the process by which the EEG exchange module 20 collects the EEG data acquired by the EEG device 10 is as follows: The EEG exchange module 20 periodically initiates a round of EEG data collection for team members. First, the EEG exchange module 20 sends a data acquisition command to the first EEG device, requesting it to send data. Upon receiving the command, the first EEG device packages the EEG data, the corresponding timestamp information, and the device number, and sends it to the EEG exchange module 20. The EEG exchange module 20 then transmits the data packet to the central processing module 30. The central processing module 30 parses the received data packet to obtain the EEG data of member 1, along with the corresponding timestamp information and device number, and forwards this data to the data analysis module 60. The data analysis module 60 then processes the received data... Each EEG data point, along with its timestamp and device number, is cached. The EEG exchange module 20 then sends a data acquisition command to the second EEG device. Upon receiving the command, the second EEG device packages the EEG data, its corresponding timestamp, and its device number and sends it to the exchange module 20. The exchange module 20 then forwards the received data packet to the central processing module 30. The central processing module 30 parses the received data packet from the second EEG device, extracts the EEG data, timestamp, and device number of team member 2, and forwards this data to the data analysis module 60. The data analysis module 60 caches the received data. Following this process, the exchange module 20 acquires data from all EEG devices 10 sequentially and caches the data in the data analysis module 60. After completing one round of data acquisition, the exchange module 20 stops data acquisition and outputs a completion command to the central processing module 30, marking the completion of one round of data acquisition. It then waits for the next round of acquisition to begin.

[0064] After data collection is completed, the data analysis module 60 retrieves the cached EEG data, device number, and timestamp information. It extracts the target EEG data for each subject by using the timestamp corresponding to the EEG data. The target EEG data is the EEG data with the timestamp information closest to the current time. The device number is used to identify which team member the EEG data comes from. Then, the target EEG data of each member is analyzed and calculated to obtain the mental health parameter values.

[0065] The data analysis module 60 transmits the determined mental health parameter values ​​to the evaluation module 70. The evaluation module 70 also obtains the personal information of the test subjects, including gender and age. Based on the personal information and the pre-stored grading norm table, it determines the mental health evaluation parameters and generates a mental health assessment report for each test subject based on the mental health evaluation parameters and the grading norm table.

[0066] During the assessment process, the EEG data, timestamp information and device number received by the central processing module 30, the mental health parameter values ​​determined by the data analysis module 60, and the mental health evaluation parameters determined by the evaluation module 70 are all transmitted to the data recording module 50. The data recording module 50 records these data in the file system for easy access and analysis later.

[0067] As is understood, during the evaluation process, the central processing module 30 also performs spectral analysis on the EEG data using the Fast Fourier Transform algorithm to calculate the spectral parameters of the EEG data. The central processing module 30 transmits the EEG data and spectral data of multiple individuals to the user interaction module 40. The user interaction module 40 displays the EEG data of multiple individuals in the software interface as an EEG parameter chart, shows the changing trend of the raw EEG data of multiple individuals in the form of a curve, and displays the EEG spectral graph of multiple individuals in the form of a bar chart. The software interface of the user interaction module 40 also displays the video of the evaluation process and outputs the audio.

[0068] This application also discloses a method for assessing mental health status, which is applied to the aforementioned mental health status assessment system. (Refer to...) Figure 2 Methods for assessing mental health status include:

[0069] S101: Obtain EEG data and the personal information of the test subject corresponding to the EEG data.

[0070] In this embodiment, the EEG data is the brainwave data of the test subject during the assessment process, and the personal information includes the gender and age of the test subject. The personal information of the test subject is manually entered by the staff through the user interaction module 40.

[0071] In one example, the number of people tested was 1:

[0072] Specifically, during the assessment, the EEG data output by the EEG device 10 corresponding to the test subject is collected in real time through the EEG exchange module 20, and the EEG data is forwarded to the data analysis module 60 for caching through the central processing module 30.

[0073] In another example, the number of people tested is greater than 1:

[0074] The EEG exchange module 20 collects EEG data from each subject in real time, along with the timestamp information and device number of the corresponding EEG data. The EEG exchange module 20 packages the collected EEG data, timestamp information, and device number and sends the data to the central processing module 30. The central processing module 30 receives the data packets and parses them to extract each EEG data, the corresponding device number, and the timestamp information. The data is then sent to the data analysis module 60, which caches the data.

[0075] Simultaneously, the data analysis module 60 will extract the target EEG data of each test subject through the timestamp corresponding to the EEG data. The target EEG data is the EEG data with the corresponding timestamp information closest to the current time point. The target EEG data is the EEG data used for subsequent mental health status assessment. The test subject corresponding to the target EEG data is identified according to the device number corresponding to the target EEG data.

[0076] S102: Based on preset determination rules, determine the psychological health parameter values ​​of the test subject according to EEG data.

[0077] Specifically, the EEG data used in this step is the target EEG data determined in step S102. For the target EEG data of a single member at each moment, feature parameters are extracted from the target EEG data. In this embodiment, the feature parameters include theta wave intensity, with an intensity range of 4Hz-7Hz, alpha wave intensity, with an intensity range of 8Hz-12Hz, low beta wave intensity, with an intensity range of 13Hz-17Hz, high beta wave intensity, with an intensity range of 18Hz-30Hz, and gamma wave intensity, with an intensity range of 31Hz-50Hz.

[0078] After extracting multiple feature parameters, the first EEG feature value at each time step is obtained based on five parameters—theta wave intensity, alpha wave intensity, low beta wave intensity, high beta wave intensity, and gamma wave intensity—according to a preset multivariate regression equation. The preset multivariate regression equation is as follows:

[0079]

[0080] Where A t Let θ be the first EEG characteristic value at time t. tLet α be the intensity of the theta wave at time t. t Let α be the intensity of the alpha wave at time t, and β1 be the intensity of the alpha wave at time t. t The low beta wave intensity at time t, β2 t The high beta wave intensity at time t, γ t , where are the gamma wave intensities at time t.

[0081] Based on the first EEG characteristic value of an individual member at each moment, the second EEG characteristic value of that member throughout the entire assessment process is obtained, using the following formula:

[0082]

[0083] Among them, B i A represents the second EEG feature value of the i-th member. t Let t be the first EEG characteristic value of the member at time t, and N represent the assessment duration.

[0084] The second EEG characteristic value of each member is processed to obtain the member's mental health parameter value. The processing method is as follows:

[0085]

[0086] Among them, C i B represents the psychological health parameter value of the i-th member. i B is the second EEG characteristic value of the i-th member. max B represents the maximum value of the second EEG characteristic. min M is the minimum value of the second EEG parameter, and M is the first preset adjustment parameter.

[0087] In this embodiment, B max For 2, B min The value of the first preset adjustment parameter is 0. The specific value of the first preset adjustment parameter is set by the assessor according to the actual situation. In this embodiment, M is 100, so the threshold value of the mental health parameter is 0-100.

[0088] S103: Determine the psychological health evaluation parameters of the test subject based on the psychological health parameter values, the test subject's personal information, and the pre-stored level norm table.

[0089] Specifically, the rank norm table includes gender, age, mental health parameter values, and mental health evaluation parameters, and the above data have a corresponding relationship. That is, each mental health parameter value of people of different genders in each age group corresponds to a mental health evaluation parameter. After determining the mental health parameter value of a test subject, the mental health evaluation parameter corresponding to the age, gender, and mental health parameter value of that member is queried in the rank norm table.

[0090] This embodiment also discloses the process of establishing a preset level norm table, specifically as follows: 1) Statistically analyze the mental health parameter values ​​of a preset number of people of different ages and genders; 2) Sort the mental health parameter values ​​corresponding to people of the same age and gender; 3) Count the number of mental health parameter values ​​less than each individual mental health parameter value; 4) Determine the mental health evaluation parameter corresponding to the preset mental health parameter value according to a formula, which is:

[0091]

[0092] Where, N i S represents the mental health evaluation parameter corresponding to the value i of the mental health parameter. i S represents the number of mental health parameters that are less than the preset mental health parameter value. S is the number of people in this age group and of the same gender. K is the second preset adjustment parameter. In this embodiment, the second preset adjustment parameter is set by the staff according to the actual situation. Since the threshold of the mental health evaluation parameter is 0-100 in this embodiment, K = 100.

[0093] Using the above method, the test subjects do not need to answer questions during the assessment process. Instead, their EEG data is collected directly. This reduces the possibility of low accuracy of the assessment results due to the subjective factors of the test subjects, reduces the subjectivity of the assessment process, and makes the assessment results more reflective of the test subjects' true psychological state.

[0094] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A mental health status assessment system, characterized in that: include: The system includes an electroencephalogram (EEG) device (10), an EEG communication module (20), a central processing module (30), a data analysis module (60), and an evaluation module (70). EEG device (10) is used to collect EEG signals from the user's scalp, process the collected EEG signals into digital EEG data and output them; The EEG exchange module (20) is used to acquire the EEG data output by the EEG instrument (10) and package and send the acquired EEG data. The central processing module (30) is used to receive the data received from the EEG instrument (10) forwarded by the EEG exchange module (20) and parse out the EEG data, which is the EEG data of the person being tested during the evaluation process. When the EEG data consists of EEG data from multiple trainees, the timestamp information and device number corresponding to each EEG data are obtained; The target EEG data is determined based on the timestamp information corresponding to each EEG data, and the target EEG data is the data in the EEG data. The subject corresponding to the target EEG data is determined based on the device number corresponding to the target EEG data. Identify the target EEG data contained within the EEG data; The data analysis module (60) is used to extract feature parameters from the target EEG data, including theta wave intensity, alpha wave intensity, low beta wave intensity, high beta wave intensity and gamma wave intensity. Calculate the sum of each characteristic parameter at the preset time and the difference between the intensity of the high beta wave and the intensity of the alpha wave at the preset time; The first EEG characteristic value at the preset time is equal to the ratio of the sum of all characteristic parameters at the preset time to the difference between the high beta wave intensity and the alpha wave intensity at the preset time plus 1, where the preset time is a certain moment in the evaluation process; Calculate the first EEG characteristic value at each moment during the assessment process; Calculate the average value of the first EEG characteristic value during the assessment process to determine the second EEG characteristic value; Determine the maximum and minimum values ​​of the second EEG characteristic parameter, and calculate the difference between the maximum and minimum values; Calculate the ratio of the difference between the second EEG characteristic parameter corresponding to the test subject and the maximum and minimum values ​​during the assessment process; The ratio multiplied by the first preset adjustment parameter is the value of the mental health parameter. The evaluation module (70) obtains the personal information of the test subject corresponding to the EEG data, and determines the psychological health evaluation parameters of the test subject based on the psychological health parameter values, the personal information of the test subject, and the pre-stored level norm table.

2. The mental health status assessment system according to claim 1, characterized in that: When the EEG data consists of EEG data from multiple trainees, the EEG exchange module (20) acquires the EEG data at preset intervals and outputs a data acquisition instruction to the first EEG data acquisition device. Receive and store the EEG data output by the first EEG data acquisition device according to the data acquisition instruction; The data acquisition command is output to the second EEG data acquisition device again, and the EEG data output by the second EEG data acquisition device according to the data acquisition command is received. Data acquisition will stop once the EEG data output from the EEG acquisition device for all subjects has been obtained.

3. The mental health status assessment system according to claim 1, characterized in that: The evaluation module (70) determines the psychological health evaluation parameters of the test subject based on the psychological health parameter values, the test subject's personal information, and the pre-stored level norm table, including: The personal information includes gender and age; The corresponding level norm table for the test subjects is determined based on their gender and age; Based on the mental health parameter values ​​of the test subjects, the level corresponding to the mental health parameter values ​​is looked up in the level norm table. The level corresponding to the mental health parameter values ​​is the mental health evaluation parameter of the test subjects.

4. The mental health status assessment system according to claim 1, characterized in that: Also includes: A data recording module (50) is connected to the central processing module (30), the data analysis module (60), and the evaluation module (70) respectively. The data recording module (50) is used to store EEG data, mental health parameter values, and mental health evaluation parameters. The data recording module is used for: The mental health parameters of a predetermined number of people of different ages and genders were statistically analyzed. The mental health parameter values ​​of people of the same age and gender are sorted. Count the number of mental health parameter values ​​that are lower than each individual mental health parameter value; The mental health evaluation parameter corresponding to the preset mental health parameter value is equal to the ratio of the number of mental health parameter values ​​that are less than the preset mental health parameter value to the number of people of the same age and gender, multiplied by the second preset adjustment parameter. A grading norm table is formed and stored based on age, gender, the value of each mental health parameter, and the corresponding mental health evaluation parameters.

5. The mental health status assessment system according to claim 4, characterized in that: Also includes: User interaction module (40), which is connected to the central processing module (30), is used to receive and display EEG data from the central processing module (30).

Images