CN110680316B - Neural response detection method and system for unconscious patient - Google Patents
Neural response detection method and system for unconscious patient Download PDFInfo
- Publication number
- CN110680316B CN110680316B CN201911016957.4A CN201911016957A CN110680316B CN 110680316 B CN110680316 B CN 110680316B CN 201911016957 A CN201911016957 A CN 201911016957A CN 110680316 B CN110680316 B CN 110680316B
- Authority
- CN
- China
- Prior art keywords
- eeg
- sampling
- signals
- channel
- signal
- 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.)
- Active
Links
- 208000003443 Unconsciousness Diseases 0.000 title claims abstract description 67
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 230000008904 neural response Effects 0.000 title claims abstract description 39
- 238000005070 sampling Methods 0.000 claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 46
- 239000013598 vector Substances 0.000 claims description 21
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000005856 abnormality Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 abstract description 5
- 230000004044 response Effects 0.000 abstract description 3
- 230000000638 stimulation Effects 0.000 abstract description 3
- 210000004761 scalp Anatomy 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008035 nerve activity Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000011514 reflex Effects 0.000 description 2
- 208000003251 Pruritus Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000007177 brain activity Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000003710 cerebral cortex Anatomy 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 230000000926 neurological effect Effects 0.000 description 1
- 231100000862 numbness Toxicity 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4058—Detecting, measuring or recording for evaluating the nervous system for evaluating the central nervous system
- A61B5/4064—Evaluating the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Neurology (AREA)
- Psychology (AREA)
- Mathematical Physics (AREA)
- Neurosurgery (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a neural response detection method for unconscious patients, which comprises the following steps: acquiring an EEG sampling signal of the unconscious patient by utilizing an EEG cap; establishing a probability model based on the intensity of the EEG sample signals; and continuously acquiring an EEG detection signal of the unconscious patient, and judging whether the unconscious patient generates a neural response or not according to the probability model. The method can judge whether the unconscious patient has a neural response or not according to the probability model, is simple and easy to implement, does not cause damage to the patient, can be used for detecting the physiological change of the unconscious patient, judges whether the patient has a response to external stimulation or not, and further assists the treatment of doctors.
Description
Technical Field
The invention relates to the technical field of physiological electric signal sensing detection. And more particularly, to a method and system for detecting a neural response in an unconscious patient.
Background
Patients in an unconscious state cannot make behavioral responses to external stimuli, so that doctors cannot timely perceive physiological changes of the patients, and cannot judge whether a treatment method is beneficial to recovery consciousness of the patients. At present, physiological indexes for monitoring unconscious patient states comprise heart rate, respiratory rate, blood pressure and the like, when the physiological reactions of patients are not obvious, the indexes do not have obvious changes, and when the physiological indexes are obviously changed, the patients often have larger changes, so that doctors cannot timely master the physiological reactions of the patients. Compared with indexes such as blood pressure and heart rate, the brain activity can directly and quickly reflect nerve signals, and the method is suitable for monitoring the nerve activity of a patient and assisting a doctor to judge the physiological change of the patient.
The brain-computer interface (BCI) is a direct connection path established between a person and a computer, and the computer can analyze signals transmitted from the brain in real time. An electroencephalogram (EEG) based on scalp electromagnetic information is a common method for acquiring electroencephalogram signals, wherein human feelings such as itch, pain, numbness and the like are transmitted to a cerebral cortex through a nervous system to be represented in the EEG signals, and nerve activities with small intensity are also represented in the EEG signals. When the EEG signal is collected, the electrodes are only required to be placed at certain specific positions on the scalp, the device is simple, and the patient cannot be injured. At present, the brain-computer interface technology based on EEG is researched and applied more in the fields of visual stimulation, motor imagery and the like.
The EEG signal collected by the electrodes contains various interference components, the signal-to-noise ratio is low, and the fluctuation condition is difficult to directly observe, so that a proper algorithm needs to be designed to calculate the fluctuation of the EEG signal to judge whether the patient has a neural response. Currently common methods of EEG signal classification include co-spatial modes, etc. Existing classification methods require two types of data with "normal" and "abnormal" labels when classifying EEG signals in a patient. However, when a patient is unconscious, it is not possible to collect the EEG signals that are stimulated to compare with the EEG signals in the normal state, so the conventional methods cannot determine the EEG changes in unconscious patients.
Disclosure of Invention
In order to solve the problems mentioned in the background, the present invention provides, in a first aspect, a method for detecting a neural response of an unconscious patient, comprising the steps of:
acquiring an EEG sampling signal of the unconscious patient by utilizing an EEG cap;
establishing a probability model based on the intensity of the EEG sample signals;
and continuously acquiring an EEG detection signal of the unconscious patient, and judging whether the unconscious patient generates a neural response or not according to the probability model.
Optionally, said establishing a probability model based on the intensity of the EEG sample signals comprises:
filtering the EEG sample signal;
extracting sampling short signals respectively corresponding to a plurality of channels from the filtered EEG sampling signals by adopting a sliding window method;
carrying out fast discrete Fourier transform on the sampling short signal corresponding to each channel;
and establishing a probability model according to the sampling short signal corresponding to each channel after the fast discrete Fourier transform.
Optionally, the fast discrete fourier transform is performed on the sampled short signal corresponding to each channel by the following formula:
wherein,
for sampling short signals after discrete Fourier transform
I is the number of sampled short signals, j is the number of channels of the EEG sampled signal;
the sampling short signal
This is obtained by the following formula:
wherein, Δ is the length of the time window in the sliding window method, and T is the time of each sliding in the sliding window method.
Optionally, the establishing a probability model according to the sampled short signal corresponding to each channel after performing the fast discrete fourier transform includes:
obtaining the strength vectors of the sampling short signals corresponding to the same channel under n different frequencies by the following formula:
x＝(X 1 ，X 2 ，X 3 ，X 4 ，…X n ) T ，
wherein, X is the vector of the intensity of the sampling short signal corresponding to the same channel under n different frequencies, and X 1 ，X 2 ，X 3 ，X 4 ，…X n Random variables of sampling short signals corresponding to the same channel under n different frequencies;
obtaining the mean vector of the vector x of the intensities of the sampling short signals corresponding to the same channel under n different frequencies by the following formula:
μ＝(μ 1 ，μ 2 ，μ 3 ，μ 4 ，…μ n ) T ，
wherein μ is the mean vector;
obtaining the covariance of the random vector by:
c ij ＝Cov(X i ，X j )＝E{[X i -E(X i )][X j -E(X j )]}，
wherein, c ij Is the said X i And X j 1, … n;
obtaining a covariance matrix of the covariance by:
wherein, Σ is the covariance matrix;
the probabilistic model is built by:
wherein p (x) is a probability model.
Optionally, the determining whether the unconscious patient has a neurological response according to the probabilistic model comprises:
extracting detection short signals respectively corresponding to a plurality of channels from the EEG detection signal by adopting a sliding window method;
calculating and respectively calculating the probability of the occurrence of the corresponding detection short signal of each channel according to the probability model;
and judging whether the unconscious patient has a neural response or not according to the probability.
Optionally, when the frequency when the probability of the continuous occurrence of the corresponding detection short signal in one channel is lower than the preset probability is greater than the preset frequency, it indicates that the channel is abnormal;
and when the number of channels with simultaneous abnormality is larger than the preset number, judging that the unconscious patient has a neural response.
In a second aspect, the present invention provides a system for detecting a neural response in an unconscious patient, comprising:
the electroencephalogram cap module is used for acquiring an EEG sampling signal of the unconscious patient;
an establishing module for establishing a probability model based on the intensity of the EEG sample signals;
and the judgment module is used for responding to the EEG detection signal of the unconscious patient continuously acquired by the EEG cap module and judging whether the unconscious patient has a neural response or not according to the probability model.
Optionally, the establishing module is further configured to:
filtering the EEG sample signal;
extracting sampling short signals corresponding to a plurality of channels from the filtered EEG sampling signals by adopting a sliding window method;
carrying out fast discrete Fourier transform on the sampling short signal corresponding to each channel;
and establishing a probability model according to the sampling short signal corresponding to each channel after the fast discrete Fourier transform.
Optionally, the determining module is further configured to:
extracting detection short signals respectively corresponding to a plurality of channels from the EEG detection signal by adopting a sliding window method;
calculating and respectively calculating the probability of the occurrence of the corresponding detection short signal of each channel according to the probability model;
and judging whether the unconscious patient has a neural response or not according to the probability.
Optionally, when the frequency when the probability of the continuous occurrence of the corresponding detection short signal in one channel is lower than the preset probability is greater than the preset frequency, it indicates that the channel is abnormal;
and when the number of the channels which are simultaneously abnormal is larger than the preset number, judging that the unconscious patient has a neural response.
The invention has the following beneficial effects:
in conclusion, the electroencephalogram cap has the advantages of being clear in principle and simple in design, the EEG signals of the unconscious patient are obtained through the electroencephalogram cap, the probability model is further built, whether the unconscious patient has a neural response or not is judged according to the probability model, the method is simple and easy to implement, the patient is not damaged, the method can be used for detecting the physiological change of the unconscious patient, judging whether the patient has a response to external stimulation or not, and further assisting the doctor in treatment.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 illustrates a flow chart of a method for detecting a neural response in an unconscious patient, provided in accordance with an embodiment of the present invention;
fig. 2 is a block diagram illustrating a neural response detection system for an unconscious patient according to another embodiment of the present invention.
Detailed Description
In order to make the technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
One embodiment of the present invention provides a method for detecting a neural response of an unconscious patient, as shown in fig. 1, the method comprising the steps of:
s1, acquiring an EEG sampling signal of the unconscious patient by utilizing an EEG cap;
s2, establishing a probability model based on the strength of the EEG sampling signal;
s3, continuously acquiring the EEG detection signal of the unconscious patient, and judging whether the unconscious patient has a neural response according to the probability model.
Specifically, in S1 of the present embodiment, an electroencephalogram cap is used to acquire an EEG adoption signal of an unconscious patient. According to the 10-20 international electroencephalogram recording system, electrodes are attached to the scalps of unconscious patients (conductive paste and the like can be used for reducing the resistance between the electrodes and the scalps), sampled EEG signals of the unconscious patients are continuously collected for 30 minutes in a quiet environment, the number of sampling channels is 32, and the sampling frequency is 4096 Hz.
Further, in S2 of the present embodiment, the method further includes the following sub-steps:
s21, filtering the EEG sampling signal;
s22, extracting sampling short signals corresponding to a plurality of channels from the filtered EEG sampling signals by adopting a sliding window method;
s23, carrying out fast discrete Fourier transform on the sampling short signal corresponding to each channel;
and S24, establishing a probability model according to the sampling short signals corresponding to each channel after the fast discrete Fourier transform.
Specifically, in this embodiment, first, a band-pass filter with a frequency range of 8 to 32Hz is used to filter the collected EEG sampling signals, and the band-pass filter may use a second-order butterworth filter.
Secondly, after filtering is finished, because the number of sampling channels of the EEG cap is 32, sampling short signals corresponding to a plurality of channels are extracted from the EEG sampling signals after filtering by adopting a sliding window method, wherein the length of a time window adopted by the sliding window method can be 30 seconds, and the sliding time is 10 seconds each time;
then, fast discrete Fourier transform is carried out on the sampling short signal corresponding to each channel through the following formula, and the frequency spectrum of the sampling short signal is obtained
Wherein,
for sampling short signals after discrete Fourier transform
I is the number of sampled short signals, and j is the number of channels of EEG sampled signals; exemplarily, i ═ 1, … 178; j-1, … 32;
the sampling short signal
This is obtained by the following formula:
wherein, Δ is the length of the time window in the sliding window method, and T is the time of each sliding in the sliding window method;
secondly, for all the sampling short signals in the same channel, obtaining the intensity vectors of the sampling short signals corresponding to the same channel under n different frequencies according to the following formula:
x＝(X 1 ，X 2 ，X 3 ，X 4 ，…X n ) T ，
wherein, X is the vector of the intensity of the sampling short signal corresponding to the same channel under n different frequencies, and X 1 ，X 2 ，X 3 ，X 4 ，…X n The sampled short signals corresponding to the same channel are random variables at n different frequencies, where n may be 5, and the corresponding 5 different frequencies may be: 10Hz, 15Hz, 20Hz, 25Hz and 30 Hz:
then, obtaining the mean vector of the vector x of the intensities of the sampling short signals corresponding to the same channel under n different frequencies by the following formula:
μ＝(μ 1 ，μ 2 ，μ 3 ，μ 4 ，…μ n ) T ，
wherein μ is the mean vector;
further, the covariance of the random vector is obtained by:
c ij ＝Cov(X i ，X j )＝E{[X i -E(X i )][X j -E(X j )]}，
wherein, c ij Is the said X i And X j 1, … n;
further, a covariance matrix of the covariance is obtained by:
wherein, Σ is the covariance matrix;
finally, a probabilistic model is built by:
wherein p (x) is a probability model.
It should be noted that, the sliding window method is the prior art, and therefore, this embodiment does not describe this, and filtering the EEG sampling signal, extracting the EEG sampling short signal, performing fast discrete fourier transform on the EEG sampling short signal, and fitting the joint probability density function may all be performed on the GPU in parallel, so that the calculation speed can be further increased, and the work efficiency can be improved.
Further, in S3 of the present embodiment, the method further includes the following sub-steps:
s31, extracting detection short signals corresponding to a plurality of channels from the EEG detection signal by adopting a sliding window method;
s32, calculating the probability of the short detection signal corresponding to each channel according to the probability model;
and S33, judging whether the unconscious patient has a neural response or not according to the probability.
Specifically, after the probability model is established in S2, the EEG detection signal of the unconscious patient can be continuously obtained by using the electroencephalogram cap, the detection short signals corresponding to the plurality of channels are extracted from the detection signal by using the sliding window method, where, as in S2, the length of the time window used by the sliding window method may be 30 seconds, and 10 seconds are slid each time, for all the sampling short signals in the same channel, the intensities of the sampling short signals at 10Hz, 15Hz, 20Hz, 25Hz, and 30Hz are calculated according to the probability model, and the probability of the corresponding detection short signal occurring in each channel is calculated according to the probability model, so as to determine whether the unconscious patient has a neural response or not according to the probability.
In some optional implementations of this embodiment, the method further includes:
when the frequency of the channel with the corresponding detection short signal is higher than the preset frequency when the probability is lower than the preset probability, the channel is abnormal;
and when the number of channels with simultaneous abnormality is larger than the preset number, judging that the unconscious patient has a neural response.
Specifically, the preset probability, the preset number and the preset number may be set by the staff according to needs, for example, the preset probability may be set to 5%, the preset number may be set to 5, and the preset number may be set to 10, that is, if the probability that one channel has corresponding detection short signals five times in succession is lower than 5%, it indicates that the channel has a state abnormality, and when there are 10 channels in the same time that the state abnormality occurs, it indicates that the EEG signal has a significant change, and it indicates that the unconscious patient has a neural response.
In conclusion, the embodiment has the advantages of clear principle and simple design, utilizes the electroencephalogram cap to acquire the EEG signal of the unconscious patient, further establishes the probability model, judging whether the unconscious patient has a neural response according to the probability model, is simple and easy to operate, does not cause harm to the patient, can be used for detecting physiological changes of unconscious patients, judging whether the patients respond to external stimuli or not, further assisting the treatment of doctors, and, on the one hand, in order to improve the accuracy of the method, in the process of establishing the probability model, the embodiment uses a sliding window method to extract a plurality of short signals from a longer signal, so as to expand the number of samples, and uses the probability model to judge the probability of the occurrence of the abnormity, so as to reduce false alarm, on the other hand, in order to increase the operation speed, the process of establishing the probability model in the embodiment may be performed on the GPU.
Another embodiment of the present invention provides a neural response test system for an unconscious patient, as shown in fig. 2, the system comprising:
the electroencephalogram cap module is used for acquiring an EEG sampling signal of the unconscious patient;
an establishing module for establishing a probability model based on the intensity of the EEG sample signals;
and the judgment module is used for responding to the EEG detection signal of the unconscious patient continuously acquired by the EEG cap module and judging whether the unconscious patient has a neural response or not according to the probability model.
Specifically, in this embodiment, the electroencephalogram cap module can be an electroencephalogram cap, and when the electroencephalogram cap module is used specifically, by attaching the electrode to the scalp of an unconscious patient (the resistance between the electrode and the scalp can be reduced by using conductive paste and the like), the sampled EEG signals of the patient are continuously collected for 30 minutes in a quiet environment, the number of sampling channels is 32, and the sampling frequency is 4096 Hz; the establishing module and the judging module can be a GPU (graphic processing unit), and the GPU is used for parallel operation, so that the operation speed can be improved, and the cost can be reduced.
Further, the establishing module is further configured to:
filtering the EEG sample signal;
extracting sampling short signals respectively corresponding to a plurality of channels from the filtered EEG sampling signals by adopting a sliding window method;
carrying out fast discrete Fourier transform on the sampling short signal corresponding to each channel;
and establishing a probability model according to the sampling short signal corresponding to each channel after the fast discrete Fourier transform.
Further, the determining module is further configured to:
extracting detection short signals respectively corresponding to a plurality of channels from the EEG detection signal by adopting a sliding window method;
calculating the probability of the occurrence of the corresponding detection short signal of each channel according to the probability model;
and judging whether the unconscious patient has a neural response or not according to the probability.
In some optional implementations of this embodiment, the method further includes:
when the frequency of the channel with the probability of the corresponding detection short signal lower than the preset probability is larger than the preset frequency, the channel is abnormal;
and when the number of the channels which are simultaneously abnormal is larger than the preset number, judging that the unconscious patient has a neural response.
Specifically, the preset probability, the preset number and the preset number may be set by the staff according to needs, for example, the preset probability may be set to 5%, the preset number may be set to 5, and the preset number may be set to 10, that is, if the probability that one channel has corresponding detection short signals five times in succession is lower than 5%, it indicates that the channel has a state abnormality, and when there are 10 channels in the same time that the state abnormality occurs, it indicates that the EEG signal has a significant change, and it indicates that the unconscious patient has a neural response.
It should be understood that the above-mentioned embodiments of the present invention are only examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention, and it will be obvious to those skilled in the art that other variations or modifications may be made on the basis of the above description, and all embodiments may not be exhaustive, and all obvious variations or modifications may be included within the scope of the present invention.
Claims (8)
1. A method of detecting a neural response in an unconscious patient, comprising the steps of:
acquiring an EEG sampling signal of the unconscious patient by utilizing an EEG cap;
establishing a probability model based on the intensity of the EEG sample signals;
continuously acquiring an EEG detection signal of the unconscious patient, and judging whether the unconscious patient has a neural response or not according to the probability model;
said establishing a probability model based on the strengths of the EEG sample signals comprises:
filtering the EEG sample signal;
extracting sampling short signals respectively corresponding to a plurality of channels from the filtered EEG sampling signals by adopting a sliding window method;
carrying out fast discrete Fourier transform on the sampling short signal corresponding to each channel;
establishing a probability model according to the sampling short signal corresponding to each channel after the fast discrete Fourier transform;
the establishing a probability model according to the sampling short signal corresponding to each channel after the fast discrete fourier transform comprises:
obtaining the strength vectors of the sampling short signals corresponding to the same channel under n different frequencies by the following formula:
x＝(X 1 ，X 2 ，X 3 ，X 4 ，…X n ) T ，
wherein, X is the vector of the strength of the sampling short signal corresponding to the same channel under n different frequencies, and X 1 ，X 2 ，X 3 ，X 4 ，…X n Random variables of sampling short signals corresponding to the same channel under n different frequencies;
obtaining the mean vector of the vector x of the intensities of the sampling short signals corresponding to the same channel under n different frequencies by the following formula:
μ＝(μ 1 ，μ 2 ，μ 3 ，μ 4 ，…μ n ) T ，
wherein μ is the mean directionAmount, μ 1 ，μ 2 ，μ 3 ，μ 4 ，…μ n Is a random variable X 1 ，X 2 ，X 3 ，X 4 ，…X n The mean value of (a);
obtaining the covariance of the random variable by:
c ij ＝Cov(X i ，X j )＝E{[X i -E(X i )][X j -E(X j )]}，
wherein, c ij Is the said X i And X j 1, … n;
obtaining a covariance matrix of the covariance by:
wherein, Σ is the covariance matrix;
the probabilistic model is built by:
wherein p (x) is a probability model.
2. The detection method according to claim 1, wherein the fast discrete fourier transform is performed on the sampled short signal corresponding to each channel by the following formula:
wherein,
for sampling short signals after discrete Fourier transform
I is the number of sampled short signals, j is the number of channels of the EEG sampled signal;
the sampling short signal
This is obtained by the following formula:
where Δ is the length of the time window in the sliding window method, T is the time of each sliding in the sliding window method, f j (n) EEG signals collected for channel j.
3. The detection method according to claim 1, wherein the determining whether the unconscious patient has a neural response according to the probabilistic model comprises:
extracting detection short signals respectively corresponding to a plurality of channels from the EEG detection signal by adopting a sliding window method;
calculating the probability of the occurrence of the corresponding detection short signal of each channel according to the probability model;
and judging whether the unconscious patient has a neural response or not according to the probability.
4. The detection method according to claim 3,
when the frequency of the continuous occurrence of the corresponding detection short signals of one channel is lower than the preset frequency and is greater than the preset frequency, indicating that the channel is abnormal;
and when the number of the channels which are simultaneously abnormal is larger than the preset number, judging that the unconscious patient has a neural response.
5. A neural response detection system for an unconscious patient, comprising:
the electroencephalogram cap module is used for acquiring an EEG sampling signal of the unconscious patient;
an establishing module for establishing a probability model based on the intensity of the EEG sample signals;
said means for establishing a probability model based on the intensity of the EEG sample signals comprises:
filtering the EEG sample signal;
extracting sampling short signals respectively corresponding to a plurality of channels from the filtered EEG sampling signals by adopting a sliding window method;
carrying out fast discrete Fourier transform on the sampling short signal corresponding to each channel;
establishing a probability model according to the sampling short signal corresponding to each channel after the fast discrete Fourier transform;
the establishing a probability model according to the sampling short signal corresponding to each channel after the fast discrete fourier transform comprises:
obtaining the strength vectors of the sampling short signals corresponding to the same channel under n different frequencies by the following formula:
x＝(X 1 ，X 2 ，X 3 ，X 4 ，…X n ) T ，
wherein, X is the vector of the strength of the sampling short signal corresponding to the same channel under n different frequencies, and X 1 ，X 2 ，X 3 ，X 4 ，…X n Random variables of sampling short signals corresponding to the same channel under n different frequencies;
obtaining the mean vector of the vector x of the intensities of the sampling short signals corresponding to the same channel under n different frequencies by the following formula:
μ＝(μ 1 ，μ 2 ，μ 3 ，μ 4 ，…μ n ) T ，
wherein μ is the mean vector μ 1 ，μ 2 ，μ 3 ，μ 4 ，…μ n Is a random variable X 1 ，X 2 ，X 3 ，X 4 ，…X n The mean value of (a);
obtaining the covariance of the random variable by:
c ij ＝Cov(X i ，X j )＝E{[X i -E(X i )][X j -E(X j )]}，
wherein, c ij Is the said X i And X j 1, … n;
obtaining a covariance matrix of the covariance by:
wherein, Σ is the covariance matrix;
the probabilistic model is built by:
wherein p (x) is a probabilistic model;
and the judgment module is used for responding to the EEG detection signal of the unconscious patient continuously acquired by the electroencephalogram cap module and judging whether the unconscious patient generates a neural response or not according to the probability model.
6. The system of claim 5, wherein the setup module is further configured to:
filtering the EEG sample signal;
extracting sampling short signals respectively corresponding to a plurality of channels from the filtered EEG sampling signals by adopting a sliding window method;
carrying out fast discrete Fourier transform on the sampling short signal corresponding to each channel;
and establishing a probability model according to the sampling short signal corresponding to each channel after the fast discrete Fourier transform.
7. The system of claim 5, wherein the determining module is further configured to:
extracting detection short signals corresponding to a plurality of channels from the EEG detection signal by adopting a sliding window method;
calculating the probability of the occurrence of the corresponding detection short signal of each channel according to the probability model;
and judging whether the unconscious patient has a neural response or not according to the probability.
8. The system of claim 5,
when the frequency of the continuous occurrence of the corresponding detection short signals of one channel is higher than the preset frequency when the probability is lower than the preset probability, the channel is indicated to be abnormal;
and when the number of channels with simultaneous abnormality is larger than the preset number, judging that the unconscious patient has a neural response.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911016957.4A CN110680316B (en) | 2019-10-24 | 2019-10-24 | Neural response detection method and system for unconscious patient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911016957.4A CN110680316B (en) | 2019-10-24 | 2019-10-24 | Neural response detection method and system for unconscious patient |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110680316A CN110680316A (en) | 2020-01-14 |
| CN110680316B true CN110680316B (en) | 2022-08-19 |
Family
ID=69114431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911016957.4A Active CN110680316B (en) | 2019-10-24 | 2019-10-24 | Neural response detection method and system for unconscious patient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110680316B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2343706C (en) * | 2001-04-10 | 2011-12-06 | Physiometrix, Inc. | Anesthesia monitoring system based on electroencephalographic signals |
| WO2012078503A2 (en) * | 2010-12-05 | 2012-06-14 | Brown University | Methods for prediction and early detection of neurological events |
| WO2014091291A1 (en) * | 2012-12-11 | 2014-06-19 | MARUGG, James | A device and method for determining the probability of response to pain and nociception of a subject t |
| US20160324446A1 (en) * | 2013-11-05 | 2016-11-10 | The General Hospital Corporation | System and method for determining neural states from physiological measurements |
| CN110840455B (en) * | 2015-02-16 | 2022-07-19 | 内森·英特拉托 | System and method for brain activity resolution |
-
2019
- 2019-10-24 CN CN201911016957.4A patent/CN110680316B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 运动想象脑电模式的动态分类;张爽，等;《中国生物医学工程进展-2007中国生物医学工程联合学术年会论文集（下册）》;20070401;第1552-1555页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110680316A (en) | 2020-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8700141B2 (en) | Method and apparatus for automatic evoked potentials assessment | |
| US8600493B2 (en) | Method, apparatus and computer program product for automatic seizure monitoring | |
| CN113288174B (en) | Method for detecting cognitive function of schizophrenic patient | |
| WO2009064475A1 (en) | Method for real time attitude assessment | |
| US20140378859A1 (en) | Method of Multichannel Galvanic Skin Response Detection for Improving Measurement Accuracy and Noise/Artifact Rejection | |
| KR20170048638A (en) | Method and system for real-time depression detection | |
| CN110742604B (en) | Cortical electroencephalogram-based brain function positioning method under electrical stimulation of median nerve | |
| EP3335630A1 (en) | Improved signal quality index of multichannel bio-signal using riemannian geometry | |
| Li et al. | An EEG-based method for detecting drowsy driving state | |
| Patil et al. | A method for detection and reduction of stress using EEG | |
| WO2022020433A9 (en) | Seizure detection via electrooculography (eog) | |
| CN113116356B (en) | A self-awareness disorder auxiliary diagnosis system based on visual EEG signal analysis | |
| KR20170004547A (en) | Method and apparatus for extracting Brain information | |
| CN110680316B (en) | Neural response detection method and system for unconscious patient | |
| D’Mello et al. | Design and development of a Virtual Instrument for Bio-signal Acquisition and Processing using LabVIEW | |
| Radhakrishnan et al. | Investigating EEG Signals of Autistic Individuals Using Detrended Fluctuation Analysis. | |
| CN113520310A (en) | Electroencephalogram ERP-based touch information processing method | |
| CN214761119U (en) | An auxiliary diagnosis system for self-consciousness disorder based on visual EEG signal analysis | |
| CN110234272B (en) | Anesthesia stage identification and anesthesia depth calculation method and device | |
| Vadivu et al. | An Novel Versatile Inspiring Wavelet Transform and Resilient Direct Neural Network Classification Techniques for Monitoring Brain Activity System Based on EEG Signal | |
| CN120105211A (en) | A method for hazard perception and reporting via brain-computer interface | |
| Gogna et al. | Cognitive load with different origins: an EEG model-based explanation | |
| CN110269610A (en) | A kind of prior-warning device of brain electrical anomaly signal | |
| Poojitha et al. | EEG based Early Detection of Autism Using Convolutional Neural Networks | |
| Rajendran et al. | Development of single channel EEG Acquisition system for BCI applications |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |