Neural feedback training scheme automatic screening and effect suggestion method

Abstract

The invention provides a neural feedback training scheme automatic screening and effect suggestion method. The method comprises the following steps: acquiring biological data of a testee by using a brain wave collection device; wherein the brain wave collecting device comprises a household brain wave collecting device; transmitting the biological data to a brainwave database of a remote cloud system through a network; the brain wave database converts the biological data into a corresponding training parameter suggestion; and remotely feeding back the training parameter suggestions to a neural feedback training module for the testee to perform heart and brain training. Therefore, suggested training parameters are provided through a software interface, and superior and inferior brain area networks, digital therapy suggested training schemes and related health education are arranged, so that the effects of long-distance feedback and improvement of cognitive competence by brain training at home are achieved.

Description

[0001] This application claims priority to Taiwan Patent Application No. 112143313, filed on November 9, 2023. TECHNICAL FIELD

[0002] The present application relates to the technical field of neural feedback, and in particular to a method for automatically screening a neural feedback training program and providing effectiveness suggestions. BACKGROUND

[0003] Existing biofeedback training mainly uses a wireless device at the input end, such as a pair of electrode patches for comparing the brain wave changes before and after training on the three regions of the parietal lobe, a pair of electrode patches for detecting the influence of neurophysiological feedback on sensorimotor rhythm (SMR), or collecting physiological signals and uploading physiological data to a cloud platform for analysis through a wired or wireless transmission module. The individual needs to open an APP or related application program to read the physiological device during sleep in a retrospective manner. However, the existing technology usually fails to provide the subject with immediate physiological-related information such as brain waves or heart rate variability, and requires waiting for several hours to several days for interpretation.

[0004] At the same time, although the existing smart bed group health management system also collects physiological signals, it collects physiological signals during individual bed sleep. The physiological signals are uploaded to a cloud platform for analysis through a wired or wireless transmission module, and the individual needs to open a related application program to read the physiological device during sleep in a retrospective manner. The disadvantage is that the individual's physiological signals cannot be immediately calculated and fed back to the subject in real time after transmission.

[0005] In addition, although there is a functional magnetic resonance imaging feedback mechanism (Real time fMRI neurofeedback), the instrument for magnetic resonance imaging is quite expensive and is usually set up in medical institutions. The signal collection and imaging process takes more than 30 minutes, and the feedback mechanism calculation also takes more than 10 minutes, which cannot achieve remote home configuration and real-time (within 1 minute) analysis feedback. Moreover, even if feedback is obtained, the subject cannot know how to train in real time, but must provide data to professional personnel (such as doctors), and after the professional personnel make a judgment, they provide training programs and related health education, which cannot achieve remote and real-time feedback. SUMMARY

[0006] The present application aims to provide a method for automatic screening of a neural feedback training program and effectiveness suggestion. After obtaining brain wave data of a subject, a software interface is used to provide training parameters, arrange brain region networks, suggest a digital therapy training program, and provide related health education, so as to achieve remote feedback and home brain training to improve cognitive ability.

[0007] According to the above-mentioned purpose, the present application provides a method for automatic screening of a neural feedback training program and effectiveness suggestion, comprising obtaining biological data of a subject using a brain wave collection device; wherein the brain wave collection device comprises a home brain wave collection device; transmitting the biological data to a brain wave database of a remote cloud system through a network; the brain wave database converts the biological data into a corresponding training parameter suggestion; and the training parameter suggestion is remotely fed back to a neural feedback training module for the subject to perform a brain training.

[0008] In some embodiments, the home brain wave collection device is a brain wave cap (EEG Cap) or a heart rate variation cap (HRV Cap).

[0009] In some embodiments, the network is an ad-hoc network.

[0010] In some embodiments, the biological data is 19-channel brain wave data, and the training parameter suggestion is mainly converted into a standard score through at least 1 channel of brain wave data, and then listed in order according to the size of the deviation from the average.

[0011] In some embodiments, the brain wave data includes amplitude, frequency, site, and pattern characteristics.

[0012] In some embodiments, after the step of remotely feeding back the training program to the subject for brain training, an effectiveness suggestion is provided according to a result of the brain training, and the result of the brain training is transmitted back to the remote cloud system through the network.

[0013] In some embodiments, the neural feedback training module comprises a desktop computer, a notebook computer, and / or a smart mobile device.

[0014] In some embodiments, the training program includes low-resolution electromagnetic tomography (LORETA) brain region / network training and surface brain wave training.

[0015] In some embodiments, the 19-channel site is used to locate the brain activity area through brain wave characteristics, as the training parameter suggestion.

[0016] In some embodiments, in the step of converting the biological data into a corresponding training parameter suggestion in the brain wave database, it further includes a training program suggestion after the algorithm, after comparing the surface brain wave (Surface) and brain region network (Network) with the norm, the training reference suggestion refers to the priority of the training execution; also according to the neurophysiological feedback after the step of remotely feeding back the training parameter suggestion to a neural feedback training module for the subject to perform a brain training, comparing the brain wave norm to evaluate whether the brain wave or brain region is approaching balance, so as to evaluate the effectiveness suggestion.

[0017] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments listed below are described in detail with reference to the drawings. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 Flowchart of the method of automatic screening and effectiveness suggestion of the neural feedback training scheme of the present application.

[0019] Figure 2 Schematic diagram of the home brain wave collection device used in the method of automatic screening and effectiveness suggestion of the neural feedback training scheme of the present application.

[0020] Figure 3 Side view schematic diagram of the home brain wave collection device used in the method of automatic screening and effectiveness suggestion of the neural feedback training scheme of the present application.

[0021] Figure 4 Brain wave feature analysis schematic diagram of the method of automatic screening and effectiveness suggestion of the neural feedback training scheme of the present application.

[0022] Figure 5 Structural block schematic diagram of the method of automatic screening and effectiveness suggestion of the neural feedback training scheme of the present application.

[0023] SYMBOL EXPLANATION:

[0024] 100: Home brain wave collection device

[0025] 210: Subject's head top

[0026] 220: Occipital protuberance

[0027] 230: Vestibule

[0028] 240: Nasion

[0029] 300: Remote cloud system

[0030] 400: Brain wave database

[0031] 500: Neural feedback training module

[0032] 600: network

[0033] A1, A2: ear electrodes

[0034] C3, C4, CZ: electrodes

[0035] F3, F4, F7, F8, FP1, FP2, FZ: electrodes

[0036] O1, O2: electrodes

[0037] P3, P4, PZ: electrodes

[0038] T3, T4, T5, T6: electrodes

[0039] S100: method for automatic screening of neurofeedback training programs and effectiveness recommendations

[0040] S110-S150: steps DETAILED DESCRIPTION

[0041] The advantages, features and technical methods achieved by the present application will be described in more detail and more easily understood with reference to exemplary embodiments and the accompanying drawings, and the present application can be implemented in different forms, so it should not be understood as being limited to the embodiments described herein. On the contrary, those skilled in the art will appreciate the embodiments provided

[0042] To make the disclosure more thorough and complete, and to define the scope of the present application, the present application will be defined only by the appended claims.

[0043] In addition, the terms "comprise" and / or "comprising" refer to the presence of the described features, regions, integers, steps, operations, components, and / or components, but do not exclude the presence or addition of one or more other features, regions, integers, steps, operations, components, components, and / or combinations thereof.

[0044] To facilitate the understanding of the content of the present application and the effects that can be achieved, the specific embodiments listed in conjunction with the drawings are described in detail as follows.

[0045] Figure 1 The flowchart of the method for automatic screening of neurofeedback training programs and effectiveness recommendations of the present application. Figure 5 The structure block diagram of the method for automatic screening of neurofeedback training programs and effectiveness recommendations of the present application. Please refer to Figure 1 and Figure 5The method S100 of the neurofeedback training program automatic screening and effectiveness suggestion of the present application includes obtaining biological data of a subject using a brain wave collection device; wherein the brain wave collection device includes a home brain wave collection device 100 (step S110); transmitting the biological data to a brain wave database 400 of a remote cloud system 300 through a network 600 (step S120); the brain wave database 400 converts the biological data into a corresponding training parameter suggestion (step S130); and remotely feeding back the training parameter suggestion to a neurofeedback (NFB) training module 500 for the subject to perform a brain training (step S140). In some embodiments, the network 600 can be an ad-hoc network, but is not limited thereto. In some embodiments, the brain wave collection device can be a home brain wave collection device 100, but is not limited thereto, and brain wave collection devices used in other fields are also included in the protection scope of the embodiments of the present application.

[0046] In some embodiments, the method S100 of the neurofeedback training program automatic screening and effectiveness suggestion of the present application further includes providing an effectiveness suggestion according to a result of the brain training after the step of remotely feeding back the training program to the subject for brain training (step S140), and feeding back the result of the brain training to the remote cloud system through the network (step S150).

[0047] In some embodiments, in step S130, the training program suggestion after the algorithm includes, for example, surface brain wave (Surface) and brain region network (Network) comparison with the norm, and the training reference suggestion refers to the priority of the training execution. Similarly, after the neurophysiological feedback of step S140, the brain wave norm is compared to evaluate whether the brain wave or brain region is approaching balance (approaching standard Z score), so as to evaluate the effectiveness suggestion.

[0048] In some embodiments, preferably, the training parameter suggestion includes low-resolution electromagnetic tomography (LORETA) brain region / network training and surface (Surface) brain wave training.

[0049] In some embodiments, the neurofeedback training module includes a desktop computer, a notebook computer, and / or a smart mobile device, but is not limited thereto. In this way, the subject can perform "brain region training" or "brain wave training" through the neurofeedback training module.

[0050] Figure 2 The schematic diagram of the home brain wave collection device used in the method of the neurofeedback training program automatic screening and effectiveness suggestion of the present application. Figure 3FIG. 1 is a side view of a home brain wave collection device used in the method of automatic screening and effectiveness suggestion of a neural feedback training program of the present application. Please refer to Figure 2 and Figure 3 The home brain wave collection device 100 used in the method S100 of automatic screening and effectiveness suggestion of a neural feedback training program of the present application can be a brain wave cap (EEG Cap) or a heart rate variability cap (HRV Cap), and Figure 2 and Figure 3 The brain wave cap (EEG Cap) is used as an example for illustration, but is not limited thereto.

[0051] Please refer to Figure 2 and Figure 3 The home brain wave collection device 100 is worn to contact the top of the head 210, the external occipital protuberance 220, the vestibule 230 and the nasal root 240 of the subject, and includes electrodes C3, C4, P3, P4, O1, O2, FP1, FP2, FZ, CZ, PZ, T3, T4, T5, T6, F3, F4, F7, F8, and ear electrodes A1 and A2, that is, the brain wave sites and brain wave patterns of 19 channels of the above-mentioned 19 electrodes are combined to locate the brain region activity area.

[0052] Figure 4 FIG. 2 is a brain wave feature analysis diagram of the method of automatic screening and effectiveness suggestion of a neural feedback training program of the present application. In some embodiments, the brain wave sites and brain wave patterns of 19 channels of the above-mentioned home brain wave collection device are combined to locate the brain region activity area, so the biological data can be 19-channel EGG (Electroencephalography, brain wave instrument) brain wave data, and the training parameter suggestion is mainly presented in a list in order of the size of the deviation from the average after being converted into a standard score according to at least one channel of brain wave data. The brain wave data can include amplitude, frequency, site and pattern characteristics, but is not limited thereto. As shown in Figure 4 , the 19 channels of the home brain wave collection device 100 (that is, Figure 2 and Figure 3The brain wave features detected by the 19 electrodes FP1, FP2, F3, F4, F7, F8, FZ, T3, C3, CZ, C4, T4, T5, P3, PZ, P4, T6, O1, O2 include the amplitude, frequency, brain wave site (the positions of the 19 electrodes FP1, FP2, F3, F4, F7, F8, FZ, T3, C3, CZ, C4, T4, T5, P3, PZ, P4, T6, O1, O2), the amplitude, frequency, pattern, and position of the brain wave pattern, and four characteristic parameters, which form the brain wave database of different groups. The 19-channel site is the basic positioning, which can be used to analyze the brain activity area through the brain wave features, as the parameters for the above comparison and training. In this embodiment, the brain waves collected by the home brain wave collection device 100 are compared with the brain wave database 400 to obtain a basic score, as shown in FIG. 4. After comparison and analysis with the brain wave database 400, a reference point of the pointer score is generated. This reference point is also the difference compared with the norm. In the similar group (same age, same education level, same gender, etc.). Figure 4

[0053] For example, if the brain waves collected by the home brain wave collection device 100 of a certain subject are converted into a score X, but the ideal score of the subject compared with the database should be Y, then the goal of the neural feedback training process is to reduce the difference between X and Y. When the difference is reduced to a certain proportion, the subject will receive feedback information. After receiving the feedback information, the subject can perform brain wave pattern comparison again. At this time, the brain waves collected by the home brain wave collection device 100 can be converted into a new reference score X'. This X' is also compared with the database, and the new goal of the neural feedback training is to shorten the difference between X' and Y. The neural feedback training is like brain muscle training. To train a certain muscle group (biceps, six-pack, thigh muscle, etc.), the muscle endurance is X before training, but the goal is to obtain Y strength. At this time, the specific muscle group will be gradually trained until X-Y is closer and closer. For example, if the subject wants to lift a 30-kg (Y) dumbbell, but the current user can only hold up 10 kg (X). If the user can hold up 15 kg, feedback will be given (X-Y is shortened by a certain proportion). After a period of training, the user can hold up a 20-kg (X') dumbbell. At this time, the user needs to hold up a 25-kg (X'-Y is shortened by a certain proportion) dumbbell to get feedback. For example, a subject with attention deficit wants to improve concentration through brain training. Through the analysis of the collected brain waves, if it is found that the frontal lobe region of the brain is excessively activated compared with the norm, the individual can gradually reduce the difference between X and Y through feedback.

[0054] ​Specifically, the raw EEG signal, after analysis and conversion, can obtain the frequency and amplitude of the brain wave signal recorded by each electrode position over time. The brain wave recorded by a single electrode is compared with the established normative database of brain waves through analysis and conversion. According to the corresponding parameters such as gender, age, and dominant hand of the database, it can be converted into "standard score (Z score)", and the relevant position of the brain wave activity can be obtained. The calculation result value "is above or below several standard deviations of the average". The normal distribution of Z score defines the average as 0, and the standard deviation is defined as 1.

[0055] The calculation of standard Z score is: Z = (x - μ) / σ, where x is the value of the raw brain wave after analysis and conversion, μ is the average of the brain wave normative database, and σ is the standard deviation of the normative database. Z score represents the distance between the raw brain wave value and the average value of the normative database, calculated in standard deviation. After standardization, the raw score of the brain wave is lower than the average of the normative database, and the Z score is negative. After standardization, the raw score of the brain wave is higher than the average of the normative database, and the Z value is positive. After conversion, if the brain wave parameter is lower than the allowable range, it is defined as "hypo-activity"; otherwise, if it is higher than the allowable range, it is defined as "hyper-activity".

[0056] The brain wave data obtained at each site is converted and compared with the brain wave normative data. That is, each site has a corresponding brain wave database norm, which can be arranged in order according to the standard score deviation from the normal, and the training site of the surface brain wave training recommendation can be obtained. After comparing the site with the norm, if it belongs to "hypo-activity", the characteristics of the brain wave in the region are enhanced (for example: increasing amplitude or increasing the ratio of specific frequency band brain wave occurrence); otherwise, if the site is compared with the norm, if it belongs to "hyper-activity", the characteristics of the brain wave in the region are inhibited.

[0057] The brain wave evaluation analysis is from 1 to 19 electrode sites, which can be compared with the unit point brain wave norm database, so that the "surface brain wave training (Surface neurofeedback)" can be performed. After comparison, the percentage of similarity between the collected brain wave EEG and the brain wave norm database is obtained (% (or performance results, PR)), and through the conversion of Z standard score, the relative position (too high or too low) of the brain wave pattern in the norm can be known.

[0058] After the brain wave is collected, the output of the static brain wave result compared with the database is called "quantitative electroencephalography (QEEG)". However, if used for real-time neurophysiological feedback of brain waves, dynamic brain waves are calculated and analyzed, and a certain time window is taken, and with time displacement, the average and standard deviation of the brain waves recorded by each electrode position are calculated and analyzed in real time. The 19-channel site can further analyze the activity size of the brain network in real time. In order to provide feedback form control, the brain wave state of the user is provided in the form of auditory or visual feedback.

[0059] Therefore, the collected EEG brain wave data is compared with "healthy brain wave norm (health norm)" and "disease brain wave norm (clinical norm)", and the corresponding similarity percentage value or percentile is a two-dimensional concept, that is, if the brain wave is healthy, the percentage or percentile of the comparison result with the healthy brain wave norm should have a "high" similarity or correlation, and the percentage or percentile of the comparison result of the same healthy brain wave with the disease brain wave norm should have a "low" similarity or correlation.

[0060] The 19 sites are traced back to the source positioning by the brain current, so that the activity of a specific brain area or network can be known. The scalp surface (Surface) can be understood as 2D positioning, and it is also relatively shallow brain electrical activity monitoring; the neural network (Network) can be understood as 3D positioning, which can trace back to the deeper brain electrical activity. At present, 19-channel electrode sites are used for source positioning, but with the evolution of the algorithm database, in the future, <19 sites (such as single point or individual point number) can be used to accurately predict the brain region activity pattern.

[0061] According to the method S100 of the neural feedback training scheme of the present application, after obtaining the brain wave data of the subject, a software interface is used to provide training parameter suggestions (e.g., training parameter suggestions), arrange the brain region network (e.g., 19-channel brain wave data), provide digital therapy (Digital Therapy) training scheme suggestions (e.g., training scheme and heart-brain training), and provide related health education, thereby achieving the effects of remote feedback and home brain training to improve cognitive ability.

[0062] The present application discloses the best embodiments, and any local changes or modifications derived from the technical ideas of the present application are easily known by those skilled in the art without departing from the scope of the patent rights of the present application.

Claims

1. A method for automatically selecting and providing effectiveness suggestions for neurofeedback training programs, characterized in that, include: A brainwave collection device is used to acquire biological data of a subject; wherein, the brainwave collection device includes a home brainwave collection device. The biological data is transmitted via a network to a brainwave database in a remote cloud system. The brainwave database converts the biological data into a corresponding training parameter suggestion; and The training parameters are suggested to be fed back remotely to a neurofeedback training module for the subject to perform brain-mind training.

2. The method for automatically selecting and providing effectiveness suggestions for neurofeedback training programs according to claim 1, characterized in that, The home-based brainwave collection device is an EEG cap or a heart rate variability cap (HRV cap).

3. The method for automatically selecting and providing effectiveness suggestions for neurofeedback training programs according to claim 1, characterized in that, The network is an ad-hoc network.

4. The method for automatically selecting and providing effectiveness suggestions for neurofeedback training programs according to claim 1, characterized in that, The biological data is 19-channel brainwave data. The training parameters are mainly derived from brainwave data of at least 1 channel, which are converted into a standard score and then presented in a list according to the magnitude of deviation from the mean.

5. The method for automatically selecting and providing effectiveness suggestions for neurofeedback training programs according to claim 4, characterized in that, The brainwave data includes amplitude, frequency, location, and morphological features.

6. The method for automatically selecting and providing effectiveness suggestions for neurofeedback training programs according to claim 1, characterized in that, After the step of remotely feeding back the training program to the subject for mind-brain training, the method further includes providing an effectiveness suggestion based on the result of the mind-brain training, and transmitting the result of the mind-brain training back to the remote cloud system through the network.

7. The method for automatically selecting and providing effectiveness suggestions for neurofeedback training programs according to claim 1, characterized in that, The neurofeedback training module includes a desktop computer, a laptop computer, and / or a smart mobile device.

8. The method for automatically selecting and providing effectiveness suggestions for neurofeedback training programs according to claim 1, characterized in that, The training parameters suggested include low-resolution electromagnetic tomography (LORETA) brain region / network training and surface brainwave training.

9. The method for automatically selecting and providing effectiveness suggestions for neurofeedback training programs according to claim 5, characterized in that, Based on the locations of the 19 channels, brain activity areas are located and inferred through brainwave features, which serves as the suggested training parameters.

10. The method for automatically selecting and providing effectiveness suggestions for neurofeedback training programs according to claim 1, characterized in that, In the step of converting the biological data into a corresponding training parameter suggestion in the brainwave database, the algorithm-processed training program protocol suggestion is also included. After comparing the surface brainwave and brain region network according to the norm, the training reference suggestion is used to prioritize the execution of training. In addition, after the neurophysiological feedback of the step of remotely feeding the training parameter suggestion to a neurofeedback training module for the subject to perform a brain-mind training, the brainwave norm is compared to evaluate whether the brainwave or brain region is approaching balance, thereby evaluating the effectiveness of the suggestion.

Images