CN114431856A - Neural feedback rehabilitation training system - Google Patents
Neural feedback rehabilitation training system Download PDFInfo
- Publication number
- CN114431856A CN114431856A CN202210106637.3A CN202210106637A CN114431856A CN 114431856 A CN114431856 A CN 114431856A CN 202210106637 A CN202210106637 A CN 202210106637A CN 114431856 A CN114431856 A CN 114431856A
- Authority
- CN
- China
- Prior art keywords
- training
- curve
- target patient
- information
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 171
- 230000001537 neural effect Effects 0.000 title description 4
- 230000002159 abnormal effect Effects 0.000 claims abstract description 49
- 108010064719 Oxyhemoglobins Proteins 0.000 claims abstract description 40
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims abstract description 24
- 239000008280 blood Substances 0.000 claims abstract description 24
- 210000004369 blood Anatomy 0.000 claims abstract description 24
- 229910052760 oxygen Inorganic materials 0.000 claims abstract description 24
- 239000001301 oxygen Substances 0.000 claims abstract description 24
- 230000008859 change Effects 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 22
- 239000000203 mixture Substances 0.000 claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 15
- 230000008569 process Effects 0.000 claims abstract description 7
- 230000000638 stimulation Effects 0.000 claims description 14
- 108010054147 Hemoglobins Proteins 0.000 claims description 12
- 102000001554 Hemoglobins Human genes 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 8
- 239000000126 substance Substances 0.000 claims description 7
- 230000010354 integration Effects 0.000 claims description 5
- 210000003710 cerebral cortex Anatomy 0.000 claims description 4
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 230000000284 resting effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 13
- 210000005036 nerve Anatomy 0.000 abstract description 5
- 210000004556 brain Anatomy 0.000 description 7
- 208000006011 Stroke Diseases 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 206010008190 Cerebrovascular accident Diseases 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 230000002490 cerebral effect Effects 0.000 description 3
- 208000026106 cerebrovascular disease Diseases 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 230000001020 rhythmical effect Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000002835 absorbance Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 235000013405 beer Nutrition 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000003702 neurovascular coupling effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010001497 Agitation Diseases 0.000 description 1
- 208000016988 Hemorrhagic Stroke Diseases 0.000 description 1
- 208000032382 Ischaemic stroke Diseases 0.000 description 1
- 208000030886 Traumatic Brain injury Diseases 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 230000007177 brain activity Effects 0.000 description 1
- 210000005013 brain tissue Anatomy 0.000 description 1
- 230000001054 cortical effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 208000035474 group of disease Diseases 0.000 description 1
- 208000020658 intracerebral hemorrhage Diseases 0.000 description 1
- 230000000302 ischemic effect Effects 0.000 description 1
- 230000008338 local blood flow Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007659 motor function Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000007634 remodeling Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 210000004761 scalp Anatomy 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000000451 tissue damage Effects 0.000 description 1
- 231100000827 tissue damage Toxicity 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
- A61B5/14553—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases specially adapted for cerebral tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/7405—Details of notification to user or communication with user or patient ; user input means using sound
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/7455—Details of notification to user or communication with user or patient ; user input means characterised by tactile indication, e.g. vibration or electrical stimulation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N1/00—Electrotherapy; Circuits therefor
- A61N1/18—Applying electric currents by contact electrodes
- A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
- A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
- A61N1/36003—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation of motor muscles, e.g. for walking assistance
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N1/00—Electrotherapy; Circuits therefor
- A61N1/18—Applying electric currents by contact electrodes
- A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
- A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
- A61N1/36014—External stimulators, e.g. with patch electrodes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N1/00—Electrotherapy; Circuits therefor
- A61N1/18—Applying electric currents by contact electrodes
- A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
- A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
- A61N1/36014—External stimulators, e.g. with patch electrodes
- A61N1/3603—Control systems
- A61N1/36031—Control systems using physiological parameters for adjustment
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Veterinary Medicine (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Physiology (AREA)
- Rehabilitation Tools (AREA)
- Physical Education & Sports Medicine (AREA)
- Neurology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Optics & Photonics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a nerve feedback rehabilitation training system, which relates to the technical field of medical systems and comprises the following components: the input module is used for acquiring medical record information of a target patient and a corresponding training scheme; the acquisition module is used for acquiring blood oxygen information of a target patient in real time in the process of executing the training scheme; the processing module is used for generating a training curve of oxyhemoglobin content change according to the blood oxygen information; the monitoring module is used for monitoring and judging whether the training of the target patient is abnormal or not according to the training curve and preset parameters, and generating abnormal information when the training of the target patient is abnormal; the display module is used for displaying the training curve, displaying the reference curve according to the abnormal information so as to facilitate the target patient to finish the training scheme according to the reference curve in a self-adaptive adjustment mode; wherein the reference curve is generated by a gaussian mixture model. The invention displays the reference curve on the display module, so that the target patient can adaptively adjust and finish the training scheme according to the reference curve, and the rehabilitation effect of the training is improved.
Description
Technical Field
The invention relates to the technical field of medical systems, in particular to a nerve feedback rehabilitation training system.
Background
"cerebral apoplexy" (or "stroke") also known as "stroke" or "cerebrovascular accident" (CVA). Is an acute cerebrovascular disease, which is a group of diseases causing brain tissue damage due to sudden rupture of cerebral vessels or failure of blood flow into the brain due to vessel occlusion, including ischemic and hemorrhagic stroke.
The rehabilitation training system is used for receiving the concentrated law rehabilitation training in the early stage of the attack of cerebral apoplexy and the like, and is very important for remodeling the body function of a patient and reducing disability. In the rehabilitation process, the training of long-term regular limb rehabilitation, speech rehabilitation and the like can help the corresponding brain area of the patient to generate plasticity change, and the autonomous activity of the patient is improved. In particular, related studies have shown that motor function rehabilitation can be promoted by increasing focal lateral cortical excitability.
At present, the sequelae caused by brain trauma are usually rehabilitated and trained by a nerve feedback training method, the nerve feedback training is different from the driven limb training and speech training, and the nerve feedback training adopts a biological feedback method; brain signals of an individual are acquired through electroencephalogram, functional magnetic resonance and other equipment and are presented to the individual in an image or other mode, so that the patient is trained to carry out a method for self-learning to adjust the brain activity intensity according to requirements to accelerate recovery.
However, the electroencephalogram has low spatial resolution, is not favorable for locating corresponding brain regions, is easily interfered by motion artifacts, and the acquired signals are difficult to decode to obtain the real intention of the target. The magnetoencephalogram and the functional magnetic resonance equipment are high in manufacturing cost and large in size, and cannot be suitable for long-term home rehabilitation.
There is therefore a need for an improved rehabilitation training system.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention aims to provide a neurofeedback rehabilitation training system for solving the problem of the prior art that a target patient cannot autonomously and efficiently complete a training scheme.
To achieve the above and other related objects, the present invention provides a neurofeedback rehabilitation training system, comprising: the input module is used for acquiring medical record information of a target patient and a corresponding training scheme; the acquisition module is used for acquiring blood oxygen information of a target patient in the process of executing the training scheme in real time; the processing module is used for generating a training curve of oxyhemoglobin content change according to the blood oxygen information; the monitoring module is used for monitoring and judging whether the training of the target patient is abnormal or not according to the training curve and preset parameters, and generating abnormal information when the training of the target patient is abnormal; the display module is used for displaying the training curve and displaying a reference curve according to the abnormal information so as to facilitate a target patient to finish the training scheme according to the reference curve in a self-adaptive adjustment mode; wherein the reference curve is generated by a Gaussian mixture model.
In an embodiment of the present invention, the acquisition module includes: a light source unit for emitting near-infrared light toward a head of a target patient; the detector unit is used for receiving the near-infrared light rays reflected by the cerebral cortex from the light source unit and generating light intensity signals; and the processing unit is used for calculating the blood oxygen information according to the light intensity signal, wherein the blood oxygen information comprises the content of oxyhemoglobin.
In an embodiment of the present invention, the processing module includes: the recording unit is used for recording the blood oxygen information acquired by the acquisition module in real time; and the filtering unit is used for filtering the blood oxygen information to obtain the training curve, and the training curve is a curve of the concentration of oxyhemoglobin changing along with time.
In an embodiment of the present invention, the monitoring module includes: the deviation calculating unit is used for calculating a deviation value between a training section and a rest section in the training curve; and the comparison unit is used for comparing the deviation value with a preset variance threshold value, and when the deviation value is smaller than the preset variance threshold value, judging that the training is abnormal and generating abnormal information.
In an embodiment of the invention, the deviation value is a ratio of variances of concentration values of oxygenated hemoglobin in a training segment and a rest segment of the training curve.
In an embodiment of the present invention, the monitoring module further includes: the statistical unit is used for counting the generation quantity of the abnormal information in preset time; and the judging unit is used for comparing the generated quantity of the abnormal information with a preset quantity threshold value, and generating the abnormal information and giving an alarm when the generated quantity is greater than the preset quantity threshold value.
In an embodiment of the present invention, the apparatus further includes an auxiliary module, which is started according to the abnormal information; the auxiliary module generates sound information so as to facilitate the target patient to finish the training scheme according to the sound information in a self-adaptive adjustment mode; and/or the auxiliary module sends out electrical stimulation to act on the focus of the target patient, and the target patient is assisted to complete the training scheme through external stimulation.
In an embodiment of the present invention, the step of generating the reference curve includes: obtaining a profile of the change in oxyhemoglobin concentration during the performance of the training regimen for a plurality of normal subjects; respectively calculating Gaussian distribution density according to the change curves; synthesizing the plurality of Gaussian distribution densities into a Gaussian mixture model; generating the reference curve from the Gaussian mixture model by Gaussian mixture regression.
In an embodiment of the present invention, the step of obtaining a variation curve of oxyhemoglobin concentration during the training regimen for a plurality of normal subjects further comprises:
the plurality of the change curves are respectively normalized by a z-score method:
wherein the content of the first and second substances,
a curve normalized for the oxyhemoglobin concentration of an nth normal subject; xnIs the variation curve of the nth normal subject; mu.snOxyhemoglobin concentration for the nth normal subjectThe mean value of (a); sigmanIs the standard deviation of the oxyhemoglobin concentration of the nth normal subject.
In an embodiment of the present invention, the gaussian mixture regression algorithm is:
wherein the content of the first and second substances,
is the concentration value of oxygenated hemoglobin in the reference curve; t is time; p is a radical ofk(t) is a gaussian model of integration of oxyhemoglobin concentration data for n normal subjects, wherein K is 1, 2, 3, 4, 5 … … K; p (t) is a Gaussian mixture model consisting of k Gaussian models; k is the number of Gaussian models;
an estimate of the value of oxyhemoglobin concentration for the kth gaussian model; mu.s0Mean value of oxygenated hemoglobin concentration for a resting segment of a target patient during execution of a training regimen; alpha (alpha) ("alpha")kIs the weight of the kth gaussian model.
The neural feedback rehabilitation training system provided by the invention can reduce the training difficulty of a target patient to a certain extent; specifically, in the process of executing the training scheme by the target patient, the oxyhemoglobin content of the focus corresponding to the brain of the target patient is detected in real time to generate a training curve, the training curve is analyzed, whether the training of the target patient is abnormal or not is judged, if the training is abnormal, the display module displays the reference curve according to abnormal information, so that the target patient, a doctor or a rehabilitee can visually know the training state and effect of the target patient, the target patient can be adaptively adjusted according to the reference curve by displaying the reference curve to complete the training scheme, the difficulty of training can be reduced to a certain extent by generating the reference curve, and the rehabilitation effect obtained after the target patient executes the training scheme is improved; in addition, after the target patient is abnormal in training, the training and guiding of the target patient are performed by rhythmic sound and/or periodic low-frequency electrical stimulation through the sound guiding unit and the electrical stimulation guiding unit in the auxiliary module, so that the target patient is helped to efficiently complete a training scheme, and an expected rehabilitation training effect is achieved.
Drawings
FIG. 1 is a schematic system diagram illustrating a neurofeedback rehabilitation training system according to an embodiment of the present invention;
FIG. 2 is a detailed system diagram of a neurofeedback rehabilitation training system according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating steps of generating a reference curve in an embodiment of a neurofeedback rehabilitation training system according to the present invention.
Description of the element reference numerals
100. An input module; 200. an acquisition module; 210. a light source unit; 220. a detector unit; 230. a processing unit; 300. a processing module; 310. a recording unit; 320. a filtering unit; 400. a monitoring module; 410. a deviation calculation unit; 420. a comparison unit; 430. a counting unit; 440. a judgment unit; 500. a display module; 600. an auxiliary module; 610. a sound guide unit; 620. an electrical stimulation guiding unit.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the features in the following embodiments and examples may be combined with each other without conflict. It is also to be understood that the terminology used in the examples is for the purpose of describing particular embodiments only, and is not intended to limit the scope of the present invention. Test methods in which specific conditions are not specified in the following examples are generally carried out under conventional conditions or under conditions recommended by the respective manufacturers.
Please refer to fig. 1 to 3. It should be understood that the structures, ratios, sizes, and the like shown in the drawings and described in the specification are only used for matching with the disclosure of the specification, so as to be understood and read by those skilled in the art, and are not used to limit the conditions under which the present invention can be implemented, so that the present invention has no technical significance, and any structural modification, ratio relationship change, or size adjustment should still fall within the scope of the present invention without affecting the efficacy and the achievable purpose of the present invention. In addition, the terms "upper", "lower", "left", "right", "middle" and "one" used in the present specification are used for clarity of description, and are not intended to limit the scope of the present invention, and the relative relationship between the terms and the terms may be changed or adjusted without substantial change in the technical content.
Referring to fig. 1 and 2, the present invention provides a neurofeedback rehabilitation training system, which includes an input module 100, an acquisition module 200, a processing module 300, a monitoring module 400, a display module 500, and an auxiliary module 600. The input module 100 is configured to obtain medical record information of a target patient and a corresponding training scheme; the acquisition module 200 is used for acquiring blood oxygen information of a target patient in real time during the process of executing a training scheme; the processing module 300 is configured to generate a training curve of oxyhemoglobin content variation according to the blood oxygen information; the monitoring module 400 is configured to monitor and determine whether training of the target patient is abnormal according to the training curve and preset parameters, and generate abnormal information when the training is abnormal; the display module 500 is configured to display a training curve, display a reference curve according to the abnormal information, so as to facilitate a target patient to complete a training scheme according to adaptive adjustment of the reference curve, and generate the reference curve through a gaussian mixture model; the assistance module 600 is activated based on the abnormality information and is used to assist the target patient in completing the training regimen.
Referring to fig. 1 and 2, in the course of performing neuro-feedback rehabilitation training on a target patient, a doctor or a rehabilitee diagnoses the target patient and obtains medical record information of the target patient; the doctor or the rehabilitation engineer selects a corresponding training scheme according to the medical record information of the target patient, and inputs the medical record information and the training scheme into the display module 500 through the input module 100. It should be noted that the medical record information includes the name, age, sex, attack time, training times, physical parameters, etc. of the target patient; the training scheme includes specific training content, training time and training period, wherein one training period includes a training section and a rest section, and the time of the training section and the rest section can be set according to the actual illness state of the target patient, as an example, in this embodiment, the time of the training section and the rest section is 20 seconds.
Referring to fig. 1 and fig. 2, in the present embodiment, the collecting module 200 includes a light source unit 210, a detector unit 220, and a processing unit 230. The light source unit 210 and the detector unit 220 are both mounted on the testing cap, wherein the light source unit 210 is attached to the scalp of the target patient, and the light source unit 210 emits near-infrared light toward the head of the target patient, it should be noted that the light source unit 210 includes two independent light sources, each light source can emit near-infrared light with a wavelength of 600-900 nm, and the wavelengths of the near-infrared light emitted by the two light sources are different.
The detector unit 220 can receive the near-infrared light reflected by the cerebral cortex, and analyze the light intensity of the received near-infrared light to generate a light intensity signal, it should be noted that the detector unit 220 includes six independent detectors, and each light source is paired with three detectors, the three detectors surround the corresponding light source, and the distance between the three detectors and the corresponding light source is 3-5 cm.
The processing unit 230 calculates the blood oxygen information according to the light intensity signal, and the blood oxygen information includes the content of oxyhemoglobin, it should be noted that, in the embodiment, the processing unit 230 uses a DSP chip as a main calculation tool, and the processing unit 230 is based on the neurovascular coupling hypothesis and based on the principle of the neurovascular coupling hypothesisThe Beer-Lambert law (Beer's law) calculates the local blood flow and the local blood oxygen increase (i.e. the content of oxyhemoglobin) of the corresponding brain area of the target patient; Beer-Lambert law of
Wherein A is the absorbance and T is the transmittance (the intensity of emitted light l)1And the intensity of incident light l0Ratio of incident light intensity l0The intensity of the near infrared light emitted from the light source unit 210), K is the molar absorption coefficient (selected according to the nature of the light absorbing substance and the wavelength of the incident light), b is the thickness of the absorbing layer (thickness of the cerebral cortex of the target patient), unit: cm; c is the concentration, unit of light absorbing species: mol/L; it should be noted that the Beer-Lambert law (Beer's law) is applicable to the range of absorbance A between 0.2 and 0.8.
Further, the acquisition module 200 further includes a wireless transmission unit (not shown), the wireless transmission unit corresponds to the six detectors one to one and is configured to transmit the blood oxygen information calculated by the processing unit 230, and the wireless transmission unit transmits the blood oxygen information calculated by the processing unit from the light intensity signals acquired by the six detectors to the processing module 300 at a frequency of 10Hz through a bluetooth protocol.
Referring to fig. 1 and fig. 2, in the present embodiment, the processing module 300 includes a recording unit 310 and a filtering unit 320. The recording unit 310 records the blood oxygen information calculated by the processing unit 230 in the acquisition module 200 in real time, and it should be noted that the recording unit 310 receives the blood oxygen information corresponding to the 10Hz frequency sent by the wireless transmission unit 240 through the bluetooth protocol. The filtering unit 320 is configured to filter the blood oxygen information to obtain a smooth training curve, where the training curve is a curve of the concentration of oxyhemoglobin changing with time; it should be noted that, in the present embodiment, the filtering unit 320 is a kalman filter.
Referring to fig. 1 and fig. 2, in the present embodiment, the monitoring module 400 includes a deviation calculating unit 410, a comparing unit 420, a counting unit 430 and a determining unit 440. The deviation calculating unit 410 is configured to calculate a deviation value between a training segment and a rest segment in the training curve, where it should be noted that, since the training scheme is trained according to a time period, the training curve obtained by executing the training scheme has periodicity, and one period of the training curve includes the training segment and the rest segment, that is, the deviation value is a ratio of variances of concentration values of oxyhemoglobin in the training segment and the rest segment in the training curve.
The comparing unit 420 is configured to compare the deviation value with a preset variance threshold, and when the deviation value is equal to or greater than the preset deviation value, determine that the training is normal, and then normally execute the training scheme; when the deviation value is smaller than a preset variance threshold value, judging that the training is abnormal, and generating abnormal information; note that, in this embodiment, the preset variance threshold is 2.
The counting unit 430 is configured to count the number of abnormal information generated within a preset time (preset continuous period); the judging unit 440 is configured to compare the generated number of abnormal information with a preset number threshold, and when the generated number of abnormal information is smaller than the preset number threshold, consider that training is normal, and normally execute the training scheme; and when the generation quantity of the abnormal information is greater than a preset quantity threshold value, considering that the training is abnormal, generating abnormal information and giving an alarm. It should be noted that, in this embodiment, the preset time (preset continuous period) is three continuous training periods, and the preset number threshold is 3.
Referring to fig. 1 and fig. 2, in the present embodiment, the display module 500 may play the training program set for the target patient before the target patient executes the training program, and at this time, the content displayed by the display module 500 mainly includes the specific motion of the training, the specific rhythm of the motion execution, and the like; when the target patient is in the training state, the target patient can move according to the content displayed by the display module 500, and in addition, the display module 500 displays the training curve of the target patient in real time, so that the target patient, a doctor or a rehabilitation teacher can visually know the training state and the effect of the target patient. After the target patient executes the training scheme for a certain time (period), if the relevant parameters monitored by the monitoring module 400 are normal, the training effect of the target patient is good, and the training scheme is continuously executed; if the relevant parameters monitored by the monitoring module 400 are abnormal, abnormal information is generated and an alarm is given, at this time, the display module 500 displays a reference curve according to the abnormal information, the target patient can be adaptively adjusted according to the reference curve so as to complete the training scheme, the generation of the reference curve can reduce the training difficulty to a certain extent, and the rehabilitation effect obtained after the target patient executes the training scheme is improved.
It should be noted that the alarm modes mainly include visual alarm, sound alarm and vibration alarm; the visual alarm is that the display module 500 reminds a target patient, a doctor or a rehabilitation teacher in the modes of warning signs appearing according to abnormal information, color change of a user interface and the like; the sound alarm is to give out alarm sound through components such as a sound box, a metronome and the like to remind a target patient, a doctor or a rehabilitation teacher; the vibrations are reported to the police and are warned the target patient for the sense of vibration that sends through devices such as bracelet.
Referring to fig. 3, in the present embodiment, the step of generating the reference curve includes:
step S100, obtaining a variation curve of the concentration of oxygenated hemoglobin of a plurality of normal subjects during the execution of the training scheme.
A plurality of normal subjects were first acquired and recorded as { X ] oxygenated hemoglobin concentration profiles in the performance of the training regimennWhere n is the number of normal subjects; it should be noted that the normal subjects should have sex, age, weight and other parameters similar to those of the target patients. It should be noted that, since the training program is trained according to a time period, the variation curve obtained by the normal subject in executing the training program has periodicity, and one period of the variation curve includes a training segment and a rest segment.
Further, the step of obtaining a variation curve of the oxyhemoglobin concentration of the plurality of normal subjects during the execution of the training regimen further comprises, due to factors such as individual differences of the normal subjects or different acquired channels: step S110, respectively carrying out standardization processing on the plurality of change curves by a z-score method; specifically, the z-score method is as follows:
wherein the content of the first and second substances,
a curve normalized for the oxyhemoglobin concentration of an nth normal subject; xnIs the variation curve of the nth normal subject; mu.snIs the mean of the oxyhemoglobin concentration of the nth normal subject; sigmanIs the standard deviation of the oxyhemoglobin concentration of the nth normal subject.
And step S200, respectively calculating Gaussian distribution density according to the plurality of change curves.
Dividing the change curve into a training section and a rest section according to a cycle; modeling a plurality of change curves aiming at each training section and each rest section to generate a change relation (Gaussian model) of the concentration value x of oxygenated hemoglobin of each training section and each rest section and time t, wherein the change relations (Gaussian models) obey a lower Gaussian distribution density function; the specific gaussian distribution density function is:
wherein p isk(t) is a gaussian model of integration of oxyhemoglobin concentration data for n normal subjects, wherein K is 1, 2, 3, 4, 5 … … K; x is the number ofnA concentration value of oxygenated hemoglobin for an nth normal subject; t is time; μ is the mean of the oxygenated hemoglobin concentrations of n normal subjects; Σ is a covariance matrix of oxyhemoglobin concentrations of n normal subjects; .
Further, the parameters μ, Σ are estimated by an Expectation Maximization (EM) algorithm, and the specific calculation formula is as follows:
θ＝(αk,μk,∑k)；
wherein alpha iskIs the weight of the kth Gaussian model; mu.sk(ii) expectation for kth gaussian model; sigmakCovariance of oxyhemoglobin concentration for kth gaussian model; mu.st,kThe mean value of the test time t of the kth Gaussian model; mu.sx,kMean value of oxyhemoglobin concentration for kth gaussian model; sigmatt,kIs the covariance between time t and time t in the kth Gaussian model; sigmatx,kIs the covariance between time t and concentration value x in the kth gaussian model; sigmaxt,kIs the covariance between the concentration value x and time t in the kth Gaussian model; sigmaxx,kIs the concentration value x in the kth gaussian model and the covariance between the concentration values x.
And step S300, synthesizing the plurality of Gaussian distribution densities into a Gaussian mixture model.
For a gaussian mixture model containing k gaussian models, it can be expressed as:
wherein t is time; p is a radical ofk(t) is a gaussian model of integration of oxyhemoglobin concentration data for n normal subjects, wherein K is 1, 2, 3, 4, 5 … … K; alpha is alphakIs the weight of the kth Gaussian model; k is the number of Gaussian models.
In the present embodiment, the number of normal subjects is selected to be three in consideration of the complexity of data and calculation. In the method for iteratively updating the parameters theta of the Gaussian mixture model by an expectation-maximization (EM) algorithm, firstly, parameter initialization is carried out, and in step E, the possibility that each datum comes from the nth change curve is calculated according to the current parameters; in step M, the update iteration parameter θ ═ αk,μk,∑k) And repeating the step E and the step M until the parameter theta converges.
And S400, generating a reference curve by the Gaussian mixture model through Gaussian mixture regression.
Patient-oriented reference curves are regressed by Gaussian mixture (Gau)ssian texture Regression), and at any time t, the gaussian distribution mean value to which the corresponding concentration change obeys
The specific calculation formula is as follows:
wherein the content of the first and second substances,
is the concentration value of oxygenated hemoglobin in the reference curve; t is time; p is a radical ofk(t) is a gaussian model of integration of oxyhemoglobin concentration data for n normal subjects, wherein K is 1, 2, 3, 4, 5 … … K; p (t) is a Gaussian mixture model consisting of k Gaussian models; k is the number of Gaussian models;
an estimate of the value of oxyhemoglobin concentration for the kth gaussian model; mu.sx,kMean value of the oxyhemoglobin concentration values for the kth gaussian model;
an estimate of the value of oxyhemoglobin concentration for the kth gaussian model; mu.st,kIs the mean value of time t in the kth Gaussian model; sigmatt,kIs the covariance between time t and time t in the kth Gaussian model; alpha is alphakIs the weight of the kth normal subject.
Referring to fig. 1 and 2, the auxiliary module 600 includes a sound guide unit 610 and an electrical stimulation guide unit 620. The voice guidance unit 610 generates voice information according to the abnormal information, and the target patient can perform adaptive adjustment according to the voice information to complete the training scheme; it should be noted that, in this embodiment, the sound guiding unit may be a metronome, and the sound guiding unit may generate rhythmic sound according to the abnormal information to help improve the motor imagery ability of the target patient, so as to improve the effect of self-regulation training. The electrical stimulation guiding unit 620 may stimulate the limbs of the target patient corresponding to the training regimen by periodic low-frequency electrical stimulation when the target patient cannot effectively complete the training regimen, thereby activating muscle activity of the target patient by external stimulation and helping the target patient complete the training regimen by using a physical means; the periodicity, frequency, intensity, and other parameters of the electrical stimulation may be set according to the actual condition of the target patient.
The processor may be a general-purpose processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; or a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component; the Memory may include a Random Access Memory (RAM), and may further include a Non-volatile Memory (Non-volatile Memory), such as at least one disk Memory.
In conclusion, in the neural feedback rehabilitation training system, the training difficulty of the target patient can be reduced to a certain extent; specifically, in the process of executing the training scheme by the target patient, the oxyhemoglobin content of the focus corresponding to the brain of the target patient is collected in real time to generate a training curve, the training curve is analyzed, whether the training of the target patient is abnormal or not is judged, if the training is abnormal, the display module 500 displays the reference curve according to the abnormal information, so that the target patient, a doctor or a rehabilitee can visually know the training state and effect of the target patient, the target patient can be adaptively adjusted according to the reference curve by displaying the reference curve to complete the training scheme, the difficulty of training can be reduced to a certain extent by generating the reference curve, and the rehabilitation effect obtained after the target patient executes the training scheme is improved; in addition, after the training abnormality of the target patient occurs, the invention also performs training guidance on the target patient by rhythmic sound and/or periodic low-frequency electrical stimulation through the sound guidance unit 610 and the electrical stimulation guidance unit 620 in the auxiliary module 600, so as to help the target patient to complete the training scheme efficiently. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A neurofeedback rehabilitation training system, comprising:
the input module is used for acquiring medical record information of a target patient and a corresponding training scheme;
the acquisition module is used for acquiring blood oxygen information of a target patient in the process of executing the training scheme in real time;
the processing module is used for generating a training curve of oxyhemoglobin content change according to the blood oxygen information;
the monitoring module is used for monitoring and judging whether the training of the target patient is abnormal or not according to the training curve and preset parameters, and generating abnormal information when the training of the target patient is abnormal;
the display module is used for displaying the training curve and displaying a reference curve according to the abnormal information so as to facilitate a target patient to finish the training scheme according to the reference curve in a self-adaptive adjustment mode;
wherein the reference curve is generated by a Gaussian mixture model.
2. The neurofeedback rehabilitation training system of claim 1, wherein: the acquisition module comprises:
a light source unit for emitting near-infrared light toward a head of a target patient;
the detector unit is used for receiving the near-infrared light rays reflected by the cerebral cortex from the light source unit and generating light intensity signals;
and the processing unit is used for calculating the blood oxygen information according to the light intensity signal, wherein the blood oxygen information comprises the content of oxyhemoglobin.
3. The neurofeedback rehabilitation training system of claim 1, wherein: the processing module comprises:
the recording unit is used for recording the blood oxygen information acquired by the acquisition module in real time;
and the filtering unit is used for filtering the blood oxygen information to obtain the training curve, and the training curve is a curve of the concentration of the oxyhemoglobin changing along with time.
4. The neurofeedback rehabilitation training system of claim 1, wherein: the monitoring module includes:
the deviation calculating unit is used for calculating a deviation value between a training section and a rest section in the training curve;
and the comparison unit is used for comparing the deviation value with a preset variance threshold value, and when the deviation value is smaller than the preset variance threshold value, judging that the training is abnormal and generating abnormal information.
5. The neurofeedback rehabilitation training system of claim 4, wherein: the deviation value is a ratio of variances of concentration values of oxygenated hemoglobin of a training segment and a rest segment in the training curve.
6. The neurofeedback rehabilitation training system of claim 4, wherein: the monitoring module further comprises:
the statistic unit is used for counting the generation quantity of the abnormal information in preset time;
and the judging unit is used for comparing the generated quantity of the abnormal information with a preset quantity threshold value, and generating the abnormal information and giving an alarm when the generated quantity is greater than the preset quantity threshold value.
7. The neurofeedback rehabilitation training system of claim 1, wherein: the auxiliary module is started according to the abnormal information;
the auxiliary module generates sound information so as to facilitate the target patient to finish the training scheme according to the sound information in a self-adaptive adjustment mode;
and/or the auxiliary module sends out electric stimulation to act on the affected side limb of the target patient, and the target patient is assisted to complete the training scheme through external stimulation.
8. The neurofeedback rehabilitation training system of claim 1, wherein: the step of generating the reference curve comprises:
obtaining a profile of the change in oxyhemoglobin concentration during the performance of the training regimen for a plurality of normal subjects;
respectively calculating Gaussian distribution density according to the change curves;
synthesizing the plurality of Gaussian distribution densities into a Gaussian mixture model;
and generating the reference curve by combining the Gaussian mixture model with the training curve and Gaussian mixture regression.
9. The neurofeedback rehabilitation training system of claim 8, wherein: the step of obtaining a profile of the change in oxyhemoglobin concentration during the performance of the training regimen for a plurality of normal subjects further comprises:
the plurality of the change curves are respectively normalized by a z-score method:
wherein the content of the first and second substances,
a curve normalized for the oxyhemoglobin concentration of an nth normal subject; xnIs the variation curve of the nth normal subject; mu.snIs the mean of the oxyhemoglobin concentration of the nth normal subject; sigmanIs the standard deviation of the oxyhemoglobin concentration of the nth normal subject.
10. The neurofeedback rehabilitation training system of claim 8, wherein: the Gaussian mixture regression algorithm is as follows:
wherein the content of the first and second substances,
is the concentration value of oxygenated hemoglobin in the reference curve; t is time; p is a radical ofk(t) is a gaussian model of integration of oxyhemoglobin concentration data for n normal subjects, wherein K is 1, 2, 3, 4, 5 … … K; p (t) is a Gaussian mixture model consisting of k Gaussian models; k is the number of Gaussian models;
an estimate of the value of oxyhemoglobin concentration for the kth gaussian model; mu.s0Mean value of oxygenated hemoglobin concentration for a resting segment of a target patient during execution of a training regimen; alpha (alpha) ("alpha")kIs the weight of the kth gaussian model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210106637.3A CN114431856A (en) | 2022-01-28 | 2022-01-28 | Neural feedback rehabilitation training system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210106637.3A CN114431856A (en) | 2022-01-28 | 2022-01-28 | Neural feedback rehabilitation training system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114431856A true CN114431856A (en) | 2022-05-06 |
Family
ID=81372216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210106637.3A Pending CN114431856A (en) | 2022-01-28 | 2022-01-28 | Neural feedback rehabilitation training system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114431856A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103301002A (en) * | 2013-06-20 | 2013-09-18 | 北京师范大学 | Central-peripheral nerve recovery training method and system based on optical brain imaging |
| CN108982732A (en) * | 2018-08-23 | 2018-12-11 | 西南科技大学 | A kind of efficient liquid phase glycosylated hemoglobin chromatographic peak area recognition methods |
| CN111816309A (en) * | 2020-07-13 | 2020-10-23 | 国家康复辅具研究中心 | Rehabilitation training prescription self-adaptive recommendation method and system based on deep reinforcement learning |
| CN212438586U (en) * | 2020-04-15 | 2021-02-02 | 中科搏锐（北京）科技有限公司 | Anesthesia and consciousness depth monitoring system |
| CN113180650A (en) * | 2021-01-25 | 2021-07-30 | 北京不器科技发展有限公司 | Near-infrared brain imaging atlas identification method |
| CN113419020A (en) * | 2021-06-30 | 2021-09-21 | 成都师范学院 | Glycated hemoglobin overlapping peak recognition method, apparatus, system, device, and medium |
| CN113925465A (en) * | 2021-10-20 | 2022-01-14 | 佛山科学技术学院 | Rehabilitation training evaluation method and system based on muscle oxygen feedback information |
-
2022
- 2022-01-28 CN CN202210106637.3A patent/CN114431856A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103301002A (en) * | 2013-06-20 | 2013-09-18 | 北京师范大学 | Central-peripheral nerve recovery training method and system based on optical brain imaging |
| CN108982732A (en) * | 2018-08-23 | 2018-12-11 | 西南科技大学 | A kind of efficient liquid phase glycosylated hemoglobin chromatographic peak area recognition methods |
| CN212438586U (en) * | 2020-04-15 | 2021-02-02 | 中科搏锐（北京）科技有限公司 | Anesthesia and consciousness depth monitoring system |
| CN111816309A (en) * | 2020-07-13 | 2020-10-23 | 国家康复辅具研究中心 | Rehabilitation training prescription self-adaptive recommendation method and system based on deep reinforcement learning |
| CN113180650A (en) * | 2021-01-25 | 2021-07-30 | 北京不器科技发展有限公司 | Near-infrared brain imaging atlas identification method |
| CN113419020A (en) * | 2021-06-30 | 2021-09-21 | 成都师范学院 | Glycated hemoglobin overlapping peak recognition method, apparatus, system, device, and medium |
| CN113925465A (en) * | 2021-10-20 | 2022-01-14 | 佛山科学技术学院 | Rehabilitation training evaluation method and system based on muscle oxygen feedback information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240062671A1 (en) | Simulator and simulation system for brain training based on behavior modeling | |
| US11407422B2 (en) | Operation appropriateness determination system, method for determining operation appropriateness, and non-transitory computer readable medium storing program for determining operation appropriateness | |
| US8986207B2 (en) | Systems and methods for providing sensor arrays for detecting physiological characteristics | |
| US20160367198A1 (en) | Apparatus and method for detecting and removing artifacts in optically acquired biological signals | |
| JP4991431B2 (en) | External environment control device based on brain function measurement | |
| US20140316218A1 (en) | Systems and methods for monitoring brain metabolism and activity using electroencephalogram and optical imaging | |
| US20110319724A1 (en) | Methods and systems for non-invasive, internal hemorrhage detection | |
| Tsunashima et al. | Measurement of brain function using near-infrared spectroscopy (NIRS) | |
| US20230172565A1 (en) | Systems, devices, and methods for developing a model for use when performing oximetry and/or pulse oximetry and systems, devices, and methods for using a fetal oximetry model to determine a fetal oximetry value | |
| JP7316574B2 (en) | Work adequacy judgment system | |
| US9770210B2 (en) | Systems and methods for analyzing a physiological sensor signal | |
| Son et al. | Human performance assessment using fNIR | |
| CN114431856A (en) | Neural feedback rehabilitation training system | |
| Geman et al. | Parkinson’s disease assessment using fuzzy expert system and nonlinear dynamics | |
| Rahman et al. | Evaluating the connectivity of motor area with prefrontal cortex by fNIR spectroscopy | |
| Hasanpoor et al. | Stress assessment with convolutional neural network using PPG signals | |
| JP6008099B2 (en) | Brain activity state analysis device, brain activity state analysis method, and brain activity state analysis program | |
| Ray et al. | DeepPulse: An Uncertainty-aware Deep Neural Network for Heart Rate Estimations from Wrist-worn Photoplethysmography | |
| US11839471B2 (en) | Autoregulation monitoring using deep learning | |
| Xu et al. | A Subject-Specific Attention Index Based on the Weighted Spectral Power | |
| Gupta | Complexity Reduction for Near Real-Time High Dimensional Filtering and Estimation Applied to Biological Signals | |
| MIGLIORINI et al. | Time-frequency analysis of the ballistocardiogram for sleep staging | |
| WO2023183621A1 (en) | Systems, devices, and methods for determining an oximetry value using an oximetry model | |
| Usoro | Information Theoretic EEG Analysis of Children with Severe Disabilities in Response to Power Mobility Training: A Pilot Study | |
| WO2021207138A1 (en) | Contactless vital sign monitoring of multiple subjects in real-time |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |