CN107468243A - A kind of method and device for assessing stupor degree - Google Patents
A kind of method and device for assessing stupor degree Download PDFInfo
- Publication number
- CN107468243A CN107468243A CN201710778478.0A CN201710778478A CN107468243A CN 107468243 A CN107468243 A CN 107468243A CN 201710778478 A CN201710778478 A CN 201710778478A CN 107468243 A CN107468243 A CN 107468243A
- Authority
- CN
- China
- Prior art keywords
- stupor
- eeg signals
- prognosis
- degree
- coma
- 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
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
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
- A61B5/0004—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by the type of physiological signal transmitted
- A61B5/0006—ECG or EEG signals
-
- 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
- A61B5/72—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
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- 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
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- 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
-
- 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
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Power Engineering (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention provides a kind of method and device for assessing stupor degree, this method includes：Obtain the eeg data of coma patient；Eeg data is pre-processed, obtains pure EEG signals；According to pure EEG signals, stupor degree corresponding to coma patient is assessed.The present invention the automatic stupor degree for assessing coma patient, reduces the manual intervention during stupor scale evaluation according to the pure EEG signals of coma patient, evaluation process is avoided to be influenceed by the subjective factor of medical personnel, avoid artificially judging by accident, reduce assessment errors, improve and assess accuracy.Sample entropy is applied to and assessed in stupor degree, sample entropy corresponding to pure EEG signals is calculated, stupor degree is assessed according to the threshold range where the sample entropy, the quantitative evaluation to degree of going into a coma is realized, greatly improves assessment efficiency.Automatic Index for diagnosis is carried out according to pure EEG signals simultaneously, sample entropy is applied in the Index for diagnosis of coma patient, improves the efficiency and accuracy of Index for diagnosis.
Description
Technical field
The present invention relates to technical field of data processing, in particular to a kind of method and device for assessing stupor degree.
Background technology
Stupor is a type of the complete loss of consciousness, is critical illness clinically.Go into a coma the time, carry to shorten patient
The survival rate of high coma patient, it is thus necessary to determine that stupor degree, prognosis situation and current state of coma patient etc..
Currently, the stupor degree of patient is medically assessed usually using Glasgow coma score mode.Glasgow
The assessment of stupor index has three eye opening reaction, language response and limb motion aspects, and the assessment fraction in terms of these three is added
It is final stupor index with obtained total score.It is to pass through observation and medical personnel carry out the test of this three aspect to patient
Sick person's development makes a decision, therefore is easily influenceed by medical personnel's subjective factor, causes to judge by accident, and accuracy is very low,
The truth of patient's stupor degree can not be reflected strictly according to the facts.
The content of the invention
In view of this, the purpose of the embodiment of the present invention is to provide a kind of method and device for assessing stupor degree, with solution
Certainly problems with existing for prior art：Currently made a decision by medical personnel by observing disease person's development, easily by medical care people
Member's subjective factor influences, and causes to judge by accident, accuracy is very low, it is impossible to reflects the truth of patient's stupor degree strictly according to the facts.
In a first aspect, the embodiments of the invention provide a kind of method for assessing stupor degree, methods described includes：
Obtain the eeg data of coma patient；
The eeg data is pre-processed, obtains pure EEG signals；
According to the pure EEG signals, stupor degree corresponding to the coma patient is assessed.
With reference in a first aspect, the embodiments of the invention provide the possible implementation of the first of above-mentioned first aspect, its
In, it is described that the eeg data is pre-processed, pure EEG signals are obtained, including：
Remove linear trend, DC component and the Hz noise in the eeg data；
To going the eeg data after division operation to carry out the filtering process of predeterminated frequency scope；
Eye electricity data are rejected from the eeg data after filtering process, and carry out Noise Elimination from Wavelet Transform, are obtained pure
EEG signals.
With reference in a first aspect, the embodiments of the invention provide the possible implementation of second of above-mentioned first aspect, its
In, it is described according to the pure EEG signals, stupor degree corresponding to the coma patient is assessed, including：
According to the pure EEG signals, stupor sample entropy corresponding to the coma patient is calculated；
Determine the stupor threshold range residing for the stupor sample entropy；
Stupor degree corresponding to the stupor threshold range is defined as degree of being gone into a coma corresponding to the coma patient.
With reference in a first aspect, the embodiments of the invention provide the possible implementation of the third of above-mentioned first aspect, its
In, it is described according to the pure EEG signals, stupor degree corresponding to the coma patient is assessed, including：
According to the pure EEG signals, stupor sample entropy corresponding to signal energy and the coma patient is calculated；
The signal energy is obtained in time domain and the characteristic distributions of frequency domain；
Electroencephalogram corresponding to drawing the pure EEG signals, extract the wave character of the electroencephalogram；
The pure EEG signals and default normal EEG signals are contrasted, obtain comparative result；
According to stupor sample entropy, the characteristic distributions, the wave character and the comparative result, described in assessment
Stupor degree corresponding to coma patient.
With reference in a first aspect, the embodiments of the invention provide the possible implementation of the 4th of above-mentioned first aspect kind, its
In, it is described according to the pure EEG signals, stupor degree corresponding to the coma patient is assessed, including：
According to the pure EEG signals, stupor sample entropy corresponding to signal energy and the coma patient is calculated；
Electroencephalogram corresponding to the pure EEG signals is drawn, the amplitude and frequency of wave band are extracted from the electroencephalogram；
By the stupor of the stupor sample entropy, the signal energy, the amplitude and frequency input training in advance
Machine learning model, obtain stupor degree corresponding to the coma patient.
With reference in a first aspect, the embodiments of the invention provide the possible implementation of the 5th of above-mentioned first aspect kind, its
In, methods described also includes：
According to the pure EEG signals, prognosis sample entropy corresponding to the coma patient is calculated；
Determine the prognosis threshold range residing for the prognosis sample entropy；
Prognosis classification corresponding to the prognosis threshold range is defined as prognosis classification corresponding to the coma patient.
With reference to the third possible implementation of first aspect, the embodiments of the invention provide the of above-mentioned first aspect
Six kinds of possible implementations, wherein, after stupor degree corresponding to the assessment coma patient, in addition to：
According to the pure EEG signals, prognosis sample entropy corresponding to the coma patient is calculated；
Extract the sleep spindle that the pure EEG signals include；
According to prognosis sample entropy, the signal energy, the amplitude, the frequency and the sleep spindle,
Prognosis classification corresponding to the coma patient is assessed by the prognosis machine learning model of training in advance.
With reference in a first aspect, the embodiments of the invention provide the possible implementation of the 7th of above-mentioned first aspect kind, its
In, after stupor degree corresponding to the assessment coma patient, in addition to：
Show the stupor degree, the prognosis classification, electroencephalogram and each wave band figure corresponding to the coma patient.
Second aspect, the embodiments of the invention provide a kind of device for assessing stupor degree, described device includes：
Acquisition module, for obtaining the eeg data of coma patient；
Pretreatment module, for being pre-processed to the eeg data, obtain pure EEG signals；
Evaluation module, for according to the pure EEG signals, assessing stupor degree corresponding to the coma patient.
With reference to second aspect, the embodiments of the invention provide the possible implementation of the first of above-mentioned second aspect, its
In, described device also includes：
Prognostic module, for according to the pure EEG signals, calculating prognosis sample entropy corresponding to the coma patient；
Determine the prognosis threshold range residing for the prognosis sample entropy；Prognosis classification corresponding to the prognosis threshold range is defined as
Prognosis classification corresponding to the coma patient.
In embodiments of the present invention, the eeg data of coma patient is obtained；Eeg data is pre-processed, obtained pure
EEG signals；According to pure EEG signals, stupor degree corresponding to coma patient is assessed.The present invention is according to the pure of coma patient
EEG signals, the automatic stupor degree for assessing coma patient, the manual intervention during stupor scale evaluation is reduced, avoids assessing
Process is influenceed by the subjective factor of medical personnel, avoids artificially judging by accident, reduces assessment errors, is improved and is assessed accuracy.By sample
Entropy, which is applied to, to be assessed in stupor degree, sample entropy corresponding to pure EEG signals is calculated, according to where the sample entropy
Threshold range assesses stupor degree, realizes the quantitative evaluation to degree of going into a coma, greatly improves assessment efficiency.Simultaneously according to pure
EEG signals carry out automatic Index for diagnosis, and sample entropy is applied in the Index for diagnosis of coma patient, improves Index for diagnosis
Efficiency and accuracy.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by embodiment it is required use it is attached
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, therefore be not construed as pair
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to this
A little accompanying drawings obtain other related accompanying drawings.
Fig. 1 shows the hardware configuration signal that the method for the assessment stupor degree that the embodiment of the present invention 1 is provided is based on
Figure；
Fig. 2 shows a kind of method flow diagram for assessment stupor degree that the embodiment of the present invention is provided；
Fig. 3 shows a kind of bottom current for being used to assess the application program of stupor degree that the embodiment of the present invention 1 is provided
Journey schematic diagram；
Fig. 4 shows that the another kind that the embodiment of the present invention 1 is provided is used for the bottom for assessing the application program of stupor degree
Schematic flow sheet；
Fig. 5 shows a kind of apparatus structure schematic diagram for assessment stupor degree that the embodiment of the present invention 2 is provided.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
Middle accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only
It is part of the embodiment of the present invention, rather than whole embodiments.The present invention being generally described and illustrated herein in the accompanying drawings is real
Applying the component of example can be configured to arrange and design with a variety of.Therefore, it is of the invention to what is provided in the accompanying drawings below
The detailed description of embodiment is not intended to limit the scope of claimed invention, but is merely representative of the selected reality of the present invention
Apply example.Based on embodiments of the invention, institute that those skilled in the art are obtained on the premise of creative work is not made
There is other embodiment, belong to the scope of protection of the invention.
In view of currently employed Glasgow coma score mode, sentenced by medical personnel by observing disease person's development to do
It is disconnected, easily influenceed by medical personnel's subjective factor, cause to judge by accident, accuracy is very low, it is impossible to reflect the true of patient's stupor degree strictly according to the facts
Truth condition.Similarly, the accuracy for carrying out Index for diagnosis to coma patient using Glasgow coma score mode is also very low.Base
In this, the embodiments of the invention provide a kind of method and device for assessing stupor degree, it is described below by embodiment.
Embodiment 1
The embodiments of the invention provide a kind of method for assessing stupor degree.Stupor is a species of the complete loss of consciousness
Type, it is critical illness clinically.The generation of stupor, prompt the Cerebral cortex function of patient that there occurs serious hindrance.Medically by dusk
The degree of fan is divided into：Slight stupor, coma in moderate depth, excessively severe coma, stupor.The embodiment of the present invention is by using coma patient
EEG signals, the automatic stupor degree for assessing coma patient, and carry out Index for diagnosis to coma patient improves stupor degree
The accuracy and efficiency of assessment.
As shown in figure 1, the hardware system that the embodiment of the present invention is based on includes brain wave acquisition equipment and assesses terminal.Brain electricity
Collecting device includes acquisition module, eeg data processing module, data transmission blocks and power module.Power module includes electricity
Pond, power switch and capacity prompt lamp, battery provide voltage-stabilized power supply to each part of brain wave acquisition equipment.Capacity prompt lamp carries
Show whether current electric quantity is sufficient, battery capacity indication lamp prompting green during such as electricity abundance, prompting is red during not enough power supply.
Wherein, acquisition module includes acquisition electrode and reference electrode.Acquisition electrode is prolongable, can such as be opened up from 1
Open up to 20, and acquisition electrode is detachable movable, can be according to requirements such as the differences of pickup area come mobile collection
Electrode.In embodiments of the present invention, for acquisition electrode using claw electrode, the main material of claw electrode is can 3D (three-dimensional)
The silicon class material of printing, there is good elasticity.Claw electrode can easily be pressed against domsiekte by brain electricity cap when in use
On the scalp of people, it is in close contact with scalp and avoids hair.Simultaneously claw electrode each pawl point it is silver-plated, and with claw electrode
Conductive material skeleton in pawl is connected, and has good electric conductivity.Claw electrode coordinates the input impedance of follow up amplifier superelevation,
It sharp can experience the tiny change of brain electricity.Reference electrode is 2 circular button electrodes, and stupor is separately fixed at by ear clip
The left and right ear-lobe of patient.
It is when gathering the eeg data of coma patient by above-mentioned acquisition electrode, brain wave acquisition equipment and above-mentioned assessment is whole
Hold wired connection or wireless connection.Then acquisition electrode is contacted into connection with the scalp of coma patient, and reference electrode is fixed
On the ear-lobe of coma patient.Badly led during eeg data is gathered, it is necessary to reject, i.e. removal is connected unstable with scalp
Acquisition electrode, or without connection on electrode.For connecting good acquisition electrode, it is pre- that brain wave acquisition equipment sends first
If order to terminal.For connecting unstable acquisition electrode, brain wave acquisition equipment sends the second pre-set commands to terminal.Terminal
Ordered according to what brain wave acquisition equipment was sent to determine the connection of each acquisition electrode, and it is unstable to prompt user to adjust connection
Acquisition electrode.For example, in no connection or connecting unstable acquisition electrode, terminal display is red；It is good for connecting
Good acquisition electrode, terminal display green.When user sees that some electrode corresponds to red, the electrode is adjusted, until the electrode
Connection is good.Above-mentioned first pre-set commands can be that numeral 0 is ordered, and above-mentioned second pre-set commands can be non-zero order.
The eeg data processing module that brain wave acquisition equipment includes includes amplifying circuit, filter circuit and A/D change-over circuits.
Because EEG signals frequency is very low, amplifying circuit causes EEG signals also to have very high input impedance in low frequency, so as to have
There is stronger AC coupled ability, higher common-mode rejection ratio can be provided in the case where suppressing DC influence.Amplifying circuit
Can be pre-differential amplifier circuit, voltage amplifier circuit or low-frequency amplifier circuit.
After acquisition electrode collects the EEG signals of coma patient, it will be amplified in EEG signals input amplifying circuit,
Then EEG signals are filtered by filter circuit, reduce interference of the noise to EEG signals, improve the noise of EEG signals
Than.The frequency range of EEG signals is 0.5Hz~35Hz, and filter circuit is filtered with Butterworth band logical respectively in the embodiment of the present invention
Ripple device, notch filter, remove High-frequency Interference, low-frequency disturbance and 50Hz Hz noises beyond EEG signals.
After being filtered by filter circuit to eeg data, EEG signals are converted to by digital letter by A/D change-over circuits
Number.And A/D change-over circuits it is sampled, keep, quantify and coding, when time, amplitude continuously being simulated into EEG signals being converted to
Between the digital brain electrical signal discrete with amplitude.The number of the A/D change-over circuits discrete brain electricity digital signal value of output per second is 512
Point, the i.e. sample frequency of brain wave acquisition equipment are 512Hz.
The data transmission blocks that brain wave acquisition equipment includes are mainly comprising management control chip and less radio-frequency transmitter.Pipe
Reason control chip in addition to communicating with one another between control each part of brain wave acquisition equipment, also with less radio-frequency transmitter company
Connect, and control less radio-frequency transmitter interim data, the EEG signals of the digital form received are transferred to less radio-frequency hair
Device is sent, assessment terminal is sent to by less radio-frequency transmitter.
Brain wave acquisition equipment collects the eeg data of coma patient, and the eeg data of collection is amplified and filtered
Ripple, after then eeg data that eeg data is converted to digital form, eeg data is transferred to assessment terminal.Assess terminal
The as executive agent of the embodiment of the present invention, as shown in Fig. 2 assessing terminal, 101-103 operation is automatic as follows
Assess the stupor degree of coma patient.
Step 101：Obtain the eeg data of coma patient.
Assess terminal and obtain eeg data from brain wave acquisition equipment.After getting eeg data, terminal is assessed also by brain electricity
Data storage is stored under some file path in database, or by eeg data, and eeg data is carried out for the later stage
Analyzed under non real-time line.
Step 102：Eeg data is pre-processed, obtains pure EEG signals.
Although brain wave acquisition equipment such as is exaggerated, filtered at the processing to the EEG signals collected, it is suppressed that some are made an uproar
Acoustic jamming, but some noises and interference are inevitably still mixed into EEG signals, so assessing terminal gets brain electricity number
According to rear, eeg data is pre-processed first, further removes noise, interference, to obtain pure EEG signals, specific bag
Include：
Remove linear trend, DC component and the Hz noise in eeg data；To going the eeg data after division operation to enter
The filtering process of row predeterminated frequency scope；Eye electricity data are rejected from the eeg data after filtering process, and carry out wavelet transformation
Denoising, obtain pure EEG signals.
In the embodiment of the present invention, Hz noise is removed using 50Hz bandstop filters.Using bandpass filter to above-mentioned
The EEG signals for removing linear trend are filtered processing, and 0.5Hz-30Hz filter is such as carried out using Butterworth bandpass filter
Ripple.Using soft-threshold function to removing linear trend, filtering and the EEG signals progress Noise Elimination from Wavelet Transform for rejecting eye electricity data
The interference of high-frequency noise is removed, finally gives pure EEG signals.
Step 103：According to pure EEG signals, stupor degree corresponding to coma patient is assessed.
In embodiments of the present invention, go into a coma for slight stupor, coma in moderate depth, severe coma and excessively that these are different
Stupor degree, it is respectively arranged with stupor threshold range corresponding to each stupor degree.Terminal is assessed according to pure EEG signals, meter
Calculate stupor sample entropy corresponding to coma patient.The stupor threshold range residing for the stupor sample entropy is determined, by what is determined
Stupor degree corresponding to stupor threshold range is defined as stupor degree corresponding to coma patient.
In order to further improve the accuracy for assessing stupor degree, gone into a coma except above-mentioned according only to stupor sample entropy to assess
Outside the mode of degree, the stupor of the comprehensive assessment coma patient such as signal energy and each wave band feature herein in connection with pure EEG signals
Degree, specifically include：
According to pure EEG signals, stupor sample entropy corresponding to signal energy and coma patient is calculated；Obtain signal energy
Amount is in time domain and the characteristic distributions of frequency domain；Electroencephalogram corresponding to drawing pure EEG signals, extract the wave character of electroencephalogram；Will
Pure EEG signals contrast with default normal EEG signals, obtain comparative result；According to stupor sample entropy, point of signal energy
Cloth feature, wave character and the comparative result between default normal EEG signals, assess stupor degree corresponding to coma patient.
The wave character for the electroencephalogram that said extracted goes out includes the wave character of each wave band, if the pure brain of coma patient
Electric signal includes sleep spindle, then also includes the feature of sleep spindle in the wave character extracted.
Assess terminal and the electroencephalogram of coma patient drawn according to pure EEG signals, determine be in coma patient EEG signals
It is no to include sleep spindle, if it is, extracting sleep spindle from pure EEG signals.If from the pure brain of coma patient
Sleep spindle is extracted in electric signal, and sleep spindle symmetrically occurs, then show the stupor degree of coma patient compared with
Gently, degree of awakening is higher.In addition, extract the wave character of each wave band respectively from pure EEG signals, each wave band of extraction
Including：The α ripples and frequency that θ ripples that δ ripples that frequency is 0.5~3Hz, frequency are 4~7Hz, frequency are 8~13Hz be 14~
30Hz β ripples.In most cases, electroencephalogram changes has good correlation with the degree of injury of brain function, can reflect
The depth of stupor and the degree of injury of brain function.After extracting above-mentioned each wave band, record θ ripples, the frequency of occurrences of δ ripples, θ is calculated
The wave amplitude of ripple, δ ripples, wave amplitude size are eeg data size, and θ ripples, the frequency of occurrences of δ ripples are slower, and wave amplitude is more low, degree of going into a coma
It is deeper.In embodiments of the present invention, amplitude thresholds scope corresponding to each different stupor degree is also set respectively.Calculate domsiekte
The θ of people involves δ ripple brain electricity amplitude sizes, judges the amplitude thresholds scope where brain electricity amplitude, and the amplitude thresholds scope is corresponding
Stupor degree be defined as stupor degree corresponding to coma patient.
Lower in energy corresponding to time domain and frequency domain HFS, then degree of going into a coma is deeper, as corresponding to α ripples or beta band
Energy is lower, then degree of going into a coma is deeper.In embodiments of the present invention, energy cut-off corresponding to each different stupor degree is set respectively
Value, the energy value of EEG signals is calculated, the energy threshold contrast corresponding with each stupor degree of the energy value of calculating is assessed
Go out the stupor degree of coma patient.
The signal energy that terminal also calculates pure EEG signals is assessed, and signal Analysis energy is in the distribution of time domain and frequency domain
Feature.And the wave character of the wave character of each wave band of coma patient and each wave band for presetting normal EEG signals is entered
Row compares, and comparative result is obtained, according to the stupor degree of the comparative result aided assessment coma patient.Above-mentioned default normal brain activity electricity
Signal can be the EEG signals of clear-headed normal person.
In the manner described above by sample entropy of going into a coma, signal energy in time domain and the characteristic distributions of frequency domain, wave character
And the stupor degree of patient can be evaluated respectively with presetting the comparative result between normal EEG signals, so evaluate respectively
Stupor degree may be identical, it is also possible to differ.When the stupor degree all same evaluated respectively, the stupor degree is
The stupor degree finally evaluated.When the stupor degree evaluated respectively differs, by the multiple stupor degree evaluated
The most stupor degree of same number is defined as final stupor degree, and such as evaluating stupor degree according to stupor sample entropy is
Slight stupor, the stupor degree evaluated according to the characteristic distributions of signal energy is slight stupor, is evaluated according to wave character
Stupor degree be coma in moderate depth, then slight stupor is defined as the stupor degree of the coma patient.If evaluate respectively
Stupor degree is different, can not determine the most stupor degree of same number, then will be evaluated according to stupor sample entropy
Stupor degree be defined as final stupor degree.
In embodiments of the present invention, in addition to assessing stupor degree except through the above way, a large amount of brains can also be used in advance
Electric sample data trains the stupor machine learning model for assessing stupor degree automatically.Go into a coma machine learning model it is specific
Training can be trained in a manner of trade-off decision tree or SVMs.With the stupor machine learning model based on decision Tree algorithms
Exemplified by training：
First, the eeg data of the patient of different stupor degree is gathered, calculates stupor Sample Entropy, letter corresponding to eeg data
Number energy, amplitude and frequency, the eigenmatrix by the data preparation being calculated into m*n.Wherein, m is patient's number, and n is characterized
Number.Encoded simultaneously for different stupor degree, such as slight stupor is classification 0, and coma in moderate depth is classification 1, and severe is confused
It is confused as classification 2, excessively stupor is classification 3, by that analogy.So obtain m*1 classification matrix.Decision tree is to represent training sample
Single node (root node) start, by choose most have classification capacity attribute be used as cut-point, according to current decision node
The difference of attribute value, current sample data is divided into some subsets, the sample with the characteristic value of same range forms one
Branch, if sample, the node turns into leaf all if same class, and is marked with such.Selected in the node split of decision tree
During feature, there is that many indexes are available, such as Gini coefficient, information gain.Decision Tree algorithms are selected in each division
That feature of best results in currently available feature is taken to be separated.It is determined that after division index, decision tree can be from root section
Point starts continuous iteration division, the stop condition until meeting algorithm.
The stupor machine learning model trained can regard a binary tree as, and all training are contained in root node
Sample, new samples are in prediction, and since root node, which height section entered according to the scope selection of the characteristic value of new samples
Point, for example, new samples energy value be more than training when selected split values, then new samples enter right side child node, if being less than,
Then enter left side child node, since root node, the judgement of new node step by step, be finally included into a leaf node, should
Training sample in node is entirely a classification, for example the training sample in the node is entirely severe coma, then this is new
Sample is also predicted to be severe coma.
After training stupor machine learning model through the above way, when carrying out stupor scale evaluation to coma patient,
According to pure EEG signals, stupor sample entropy corresponding to signal energy and coma patient is calculated.Draw pure EEG signals pair
The electroencephalogram answered, the amplitude and frequency of wave band are extracted from electroencephalogram.By sample entropy, the signal energy of being gone into a coma corresponding to coma patient
In the stupor machine learning model of amount, amplitude and frequency input training in advance, assessed automatically by stupor machine learning model and defeated
Go out stupor degree corresponding to the coma patient.The result of machine learning model of going into a coma output can be 0,1,2 or 3, represent respectively
Slight stupor, coma in moderate depth, excessively severe coma, stupor.
In embodiments of the present invention, comprehensive stupor sample entropy, signal energy are in time domain and the characteristic distributions of frequency domain, waveform
Feature and assess the stupor degree of coma patient presetting the comparative result between normal EEG signals, substantially increase assessment
Accuracy.
In embodiments of the present invention, while assessing the stupor degree of coma patient, the prognosis feelings to coma patient are also needed
Condition is judged that prognosis situation is used for the possibility course of disease and final result for predicting coma patient.By prognosis situation in the embodiment of the present invention
5 grades are divided into, one-level represents clear-headed, resumed work；Two level is residual in representing, life can take care of oneself；Three-level represents that weight is residual, life
Need other people to look after；Level Four represents stupor or vegetative state；Pyatyi represents dead.Wherein, firsts and seconds is prognosis bona, three
Level, level Four and Pyatyi are prognosis mala.The embodiment of the present invention is respectively provided with prognosis threshold range corresponding to each prognosis classification.
Terminal is assessed according to pure EEG signals, calculates prognosis sample entropy corresponding to coma patient；Determine prognosis sample
Prognosis threshold range residing for entropy；Prognosis corresponding to the prognosis threshold range of determination is defined as corresponding to coma patient
Prognosis.
, can also be after the stupor degree of coma patient be evaluated, with reference to the stupor degree of assessment in the embodiment of the present invention
To carry out Index for diagnosis, stupor degree is deeper, then the prognosis rank judged is higher., can be with root when carrying out Index for diagnosis
According to stupor degree, signal energy in time domain and the characteristic distributions of frequency domain, the wave character of coma patient EEG signals and with presetting
Comparative result between normal EEG signals, it is comprehensive to carry out Index for diagnosis.
If the wave character of coma patient EEG signals shown in popularity-high-amplitude θ ripples, δ ripples activity, paroxysmal θ
Ripple, the activity of δ ripples, then be shown to be a kind of waking response, prognosis is all right.And what sleep cycle and above-mentioned wave character included sleeps
The symmetrical appearance of dormancy spindle wave also shows the increase of electroencephalogram arousal degree, and the presence of this reaction prompts prognosis relatively preferable.Slow Wave
During stupor, there is the degree of slow wave, including frequency, index and the popularity of distribution, have substantial connection with the degree of the disturbance of consciousness.
Frequency is very fast, and wave amplitude is higher, prompts prognosis bona；Frequency is slower, and wave amplitude is more low, prompts the degree of stupor deeper, and E.E.G
In the then prompting prognosis mala of suppression, flat ripple or " outburst-suppression " wave mode.
In embodiments of the present invention, can also be in advance in addition to the prognosis classification to judge coma patient through the above way
The prognosis machine learning model for automatic decision prognosis classification is trained using a large amount of brain electricity sample datas.In training prognosis machine
During device learning model, according to brain electricity sample data, signal energy and prognosis sample entropy are calculated.It is corresponding to draw brain electricity sample data
Electroencephalogram, the amplitude and frequency of wave band are extracted from electroencephalogram, and carries the sleep spindle that brain electricity sample data includes.
According to signal energy, prognosis sample entropy, amplitude, frequency and the sleep spindle being calculated, according to the above-mentioned stupor machine of training
The same way of device learning model trains prognosis machine learning model, will not be repeated here.Prognosis is being carried out to coma patient
When grade judges, according to pure EEG signals, stupor sample entropy corresponding to signal energy and coma patient is calculated；Draw pure
Electroencephalogram corresponding to EEG signals, the amplitude and frequency of wave band are extracted from electroencephalogram；Extract what pure EEG signals included
Sleep spindle.By above-mentioned prognosis sample entropy, signal energy, amplitude, frequency and with sleep spindle input training in advance
In prognosis machine learning model, as prognosis machine learning model automatic decision and export the coma patient corresponding to prognosis classification.
The result of prognosis machine learning model output can be 0,1,2,3 or 4, represent a prognosis classification for arriving Pyatyi respectively.
It is also aobvious after the stupor degree and the prognosis classification that evaluate coma patient through the above way in the embodiment of the present invention
Show the stupor degree, prognosis classification, electroencephalogram and each wave band figure corresponding to coma patient.Show the assessment report of coma patient
Accuse, the assessment report includes electroencephalogram and each wave band figure etc. corresponding to stupor degree, prognosis classification, coma patient.
In embodiments of the present invention, the application program being provided with terminal for assessing stupor degree is assessed, as shown in Figure 3
The application program bottom layer realization flow, the application program include initial data preserving module, pretreatment module, data analysis
Module and display object module.Initial data preserving module is used for the eeg data that storing step 101 is got, under line
Non real-time nature is analyzed.Pretreatment module is used to be removed line to the eeg data of coma patient by the operation of step 102
Property trend, filtering, remove eye electricity data and Noise Elimination from Wavelet Transform, obtain pure EEG signals.Data analysis module is used to pass through
The stupor degree and prognosis classification of coma patient are assessed in the operation of step 103 according to pure EEG signals.Show that object module is used
In the assessment report of display coma patient, the assessment report includes stupor degree, prognosis classification and electroencephalogram of coma patient etc..
In embodiments of the present invention, when use stupor machine learning model carries out stupor scale evaluation, and use prognosis machine
When device learning model carries out Index for diagnosis, the bottom layer realization flow of above-mentioned application program is as shown in figure 4, the application program includes original
Beginning data storage module, pretreatment module, characteristic extracting module, stupor machine learning model, prognosis machine learning model and aobvious
Show object module.Initial data preserving module is used for the eeg data that storing step 101 is got, for non real-time nature under line
Analysis.Pretreatment module is used to be removed the eeg data of coma patient linear trend, filter by the operation of step 102
Ripple, eye electricity data and Noise Elimination from Wavelet Transform are removed, obtain pure EEG signals.Characteristic extracting module is used to extract pure brain telecommunications
The feature such as Sample Entropy, energy, amplitude, frequency or sleep spindle corresponding to number.Machine learning model of going into a coma is used for according to feature
The feature evaluation of extraction module extraction goes out the stupor degree of coma patient.Prognosis machine learning model is used for according to feature extraction mould
The feature of block extraction judges the prognosis classification of coma patient.Display object module is used for the assessment report for showing coma patient,
The assessment report includes stupor degree, prognosis classification and electroencephalogram of coma patient etc..
It is the newly-built assessment engineering of coma patient, newly when by the stupor degree of above-mentioned application assessment patient
Build when assessing engineering, it is necessary to fill in the personal information such as the name of coma patient, sex, age.Assessing can be automatic after engineering has been built
Default directory, including above-mentioned personal information, newly-built time are saved in, it is silent that the assessment engineering subsequently has renewal also to automatically save this
Recognize catalogue.It can also be deleted having assessed engineering or the operation such as renaming.It is newly-built assessment engineering do not influence before other
Assess the presence of engineering.All assessment engineerings are shown in engineering list, and when needing to monitor some coma patient, clicking on should
Engineering is assessed corresponding to coma patient to start to assess the coma patient.
Above-mentioned application program also provides selection function, and user can select to need the brain electricity spy analyzed by the selection function
The algorithm levied or be related to, such as select pretreated AEEG, disease is shown according to stupor sample entropy and comparative result
People's stupor degree and prognosis classification, extraction sleep spindle result and analysis result, display each wave band, time frequency analysis figure and analysis
As a result etc..
When assessing the stupor degree of coma patient by method provided in an embodiment of the present invention, by brain wave acquisition equipment bag
The acquisition electrode and reference electrode included is to patient with good, i.e., acquisition electrode is placed in correctly collection position, two reference electrodes
Left and right ear-lobe is separately fixed at clip.Then the above-mentioned application program assessed and installed in terminal is opened, brain wave acquisition is opened and sets
Standby power switch, brain wave acquisition equipment start to gather the EEG signals of coma patient, and the EEG signals of collection are amplified, filter
Assessment terminal is uploaded to by data transmission blocks after the preliminary treatments such as ripple, analog-to-digital conversion, terminal is assessed and receives coma patient
Eeg data, pre-processed in above-mentioned application program, analyze and obtain a result and visualize.
In embodiments of the present invention, the eeg data of coma patient is obtained；Eeg data is pre-processed, obtained pure
EEG signals；According to pure EEG signals, stupor degree corresponding to coma patient is assessed.The present invention is according to the pure of coma patient
EEG signals, the automatic stupor degree for assessing coma patient, the manual intervention during stupor scale evaluation is reduced, avoids assessing
Process is influenceed by the subjective factor of medical personnel, avoids artificially judging by accident, reduces assessment errors, is improved and is assessed accuracy.By sample
Entropy, which is applied to, to be assessed in stupor degree, sample entropy corresponding to pure EEG signals is calculated, according to where the sample entropy
Threshold range assesses stupor degree, realizes the quantitative evaluation to degree of going into a coma, greatly improves assessment efficiency.Simultaneously according to pure
EEG signals carry out automatic Index for diagnosis, and sample entropy is applied in the Index for diagnosis of coma patient, improves Index for diagnosis
Efficiency and accuracy.
Embodiment 2
Referring to Fig. 5, the embodiments of the invention provide a kind of device for assessing stupor degree, the device is used to perform above-mentioned reality
The method for applying the assessment stupor degree that example 1 is provided, the device include：
Acquisition module 20, for obtaining the eeg data of coma patient；
Pretreatment module 21, for being pre-processed to eeg data, obtain pure EEG signals；
Evaluation module 22, for according to pure EEG signals, assessing stupor degree corresponding to coma patient.
Above-mentioned evaluation module 22 includes：
Computing unit, for according to pure EEG signals, calculating stupor sample entropy corresponding to coma patient；
Determining unit, for determining the stupor threshold range residing for stupor sample entropy；It will go into a coma corresponding to threshold range
Stupor degree is defined as stupor degree corresponding to coma patient.
In order to further improve the accuracy for assessing stupor degree, evaluation module 22 is removed according only to stupor sample entropy to comment
Estimate outside stupor degree, gone into a coma herein in connection with comprehensive assessments such as the electrical energy of brain of pure EEG signals, signal energy and each wave band features
The stupor degree of patient.Specifically, above-mentioned evaluation module 22 is used to, according to pure EEG signals, calculate signal energy and domsiekte
Stupor sample entropy corresponding to people；Signal energy is obtained in time domain and the characteristic distributions of frequency domain；It is corresponding to draw pure EEG signals
Electroencephalogram, extract the wave character of electroencephalogram；Pure EEG signals and default normal EEG signals are contrasted, obtain comparing knot
Fruit；According to stupor sample entropy, characteristic distributions, wave character and comparative result, stupor degree corresponding to coma patient is assessed.
In embodiments of the present invention, above-mentioned evaluation module 22, be additionally operable to according to pure EEG signals, calculate signal energy and
Stupor sample entropy corresponding to coma patient；Electroencephalogram corresponding to pure EEG signals is drawn, wave band is extracted from electroencephalogram
Amplitude and frequency；Go into a coma sample entropy, signal energy, amplitude and frequency are inputted to the stupor machine learning model of training in advance,
Obtain stupor degree corresponding to coma patient.
Above-mentioned pretreatment module 21, for removing the linear trend in eeg data；To removing the eeg data after division operation
Carry out the filtering process of predeterminated frequency scope；Eye electricity data are rejected from the eeg data after filtering process, and carry out small echo change
Denoising is changed, obtains pure EEG signals.
In embodiments of the present invention, the device also includes：Prognostic module, for according to pure EEG signals, calculating stupor
Prognosis sample entropy corresponding to patient；Determine the prognosis threshold range residing for prognosis sample entropy；Prognosis threshold range is corresponding
Prognosis classification be defined as prognosis classification corresponding to coma patient.
In the embodiment of the present invention, prognostic module can also after evaluation module 22 evaluates the stupor degree of coma patient,
Index for diagnosis is carried out with reference to the stupor degree of assessment, stupor degree is deeper, then the prognosis rank judged is higher.Above-mentioned prognosis
Module, be additionally operable to according to stupor degree, signal energy time domain and the characteristic distributions of frequency domain, wave character and with default normal brain activity
Comparative result between electric signal, assess prognosis classification corresponding to coma patient.
Prognostic module, it is additionally operable to, according to pure EEG signals, calculate prognosis sample entropy corresponding to coma patient；Extract pure
The sleep spindle that net EEG signals include；According to prognosis sample entropy, signal energy, above-mentioned amplitude, said frequencies and sleep
Dormancy spindle wave, prognosis classification corresponding to coma patient is assessed by the prognosis machine learning model of training in advance.
Also include in the embodiment of the present invention, display module, for showing that stupor degree, prognosis classification, coma patient are corresponding
Electroencephalogram and each wave band figure.
In embodiments of the present invention, the eeg data of coma patient is obtained；Eeg data is pre-processed, obtained pure
EEG signals；According to pure EEG signals, stupor degree corresponding to coma patient is assessed.The present invention is according to the pure of coma patient
EEG signals, the automatic stupor degree for assessing coma patient, the manual intervention during stupor scale evaluation is reduced, avoids assessing
Process is influenceed by the subjective factor of medical personnel, avoids artificially judging by accident, reduces assessment errors, is improved and is assessed accuracy.By sample
Entropy, which is applied to, to be assessed in stupor degree, sample entropy corresponding to pure EEG signals is calculated, according to where the sample entropy
Threshold range assesses stupor degree, realizes the quantitative evaluation to degree of going into a coma, greatly improves assessment efficiency.Simultaneously according to pure
EEG signals carry out automatic Index for diagnosis, and sample entropy is applied in the Index for diagnosis of coma patient, improves Index for diagnosis
Efficiency and accuracy.
The device for the assessment stupor degree that the embodiment of the present invention is provided can be specific hardware or installation in equipment
In the software in equipment or firmware etc..The device that the embodiment of the present invention is provided, its realization principle and caused technique effect and
Preceding method embodiment is identical, and to briefly describe, device embodiment part does not refer to part, refers in preceding method embodiment
Corresponding contents.It is apparent to those skilled in the art that for convenience and simplicity of description, described above is
The specific work process of system, device and unit, may be referred to the corresponding process in above method embodiment, no longer superfluous herein
State.
In embodiment provided by the present invention, it should be understood that disclosed apparatus and method, can be by others side
Formula is realized.Device embodiment described above is only schematical, for example, the division of the unit, only one kind are patrolled
Function division is collected, there can be other dividing mode when actually realizing, in another example, multiple units or component can combine or can
To be integrated into another system, or some features can be ignored, or not perform.Another, shown or discussed is mutual
Coupling or direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, device or unit
Connect, can be electrical, mechanical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in embodiment provided by the invention can be integrated in a processing unit, also may be used
To be that unit is individually physically present, can also two or more units it is integrated in a unit.
If the function is realized in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention.
And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
It should be noted that：Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined, then it further need not be defined and explained in subsequent accompanying drawing in individual accompanying drawing, in addition, term " the
One ", " second ", " the 3rd " etc. are only used for distinguishing description, and it is not intended that instruction or hint relative importance.
Finally it should be noted that：Embodiment described above, it is only the embodiment of the present invention, to illustrate the present invention
Technical scheme, rather than its limitations, protection scope of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, it will be understood by those within the art that：Any one skilled in the art
The invention discloses technical scope in, it can still modify to the technical scheme described in previous embodiment or can be light
Change is readily conceivable that, or equivalent substitution is carried out to which part technical characteristic；And these modifications, change or replacement, do not make
The essence of appropriate technical solution departs from the spirit and scope of technical scheme of the embodiment of the present invention.The protection in the present invention should all be covered
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
- A kind of 1. method for assessing stupor degree, it is characterised in that methods described includes：Obtain the eeg data of coma patient；The eeg data is pre-processed, obtains pure EEG signals；According to the pure EEG signals, stupor degree corresponding to the coma patient is assessed.
- 2. according to the method for claim 1, it is characterised in that it is described that the eeg data is pre-processed, obtain pure Net EEG signals, including：Remove linear trend, DC component and the Hz noise in the eeg data；To going the eeg data after division operation to carry out the filtering process of predeterminated frequency scope；Eye electricity data are rejected from the eeg data after filtering process, and carry out Noise Elimination from Wavelet Transform, obtain pure brain electricity Signal.
- 3. according to the method for claim 1, it is characterised in that it is described according to the pure EEG signals, assess the dusk Stupor degree corresponding to patient is confused, including：According to the pure EEG signals, stupor sample entropy corresponding to the coma patient is calculated；Determine the stupor threshold range residing for the stupor sample entropy；Stupor degree corresponding to the stupor threshold range is defined as degree of being gone into a coma corresponding to the coma patient.
- 4. according to the method for claim 1, it is characterised in that it is described according to the pure EEG signals, assess the dusk Stupor degree corresponding to patient is confused, including：According to the pure EEG signals, stupor sample entropy corresponding to signal energy and the coma patient is calculated；The signal energy is obtained in time domain and the characteristic distributions of frequency domain；Electroencephalogram corresponding to drawing the pure EEG signals, extract the wave character of the electroencephalogram；The pure EEG signals and default normal EEG signals are contrasted, obtain comparative result；According to stupor sample entropy, the characteristic distributions, the wave character and the comparative result, the stupor is assessed Stupor degree corresponding to patient.
- 5. according to the method for claim 1, it is characterised in that it is described according to the pure EEG signals, assess the dusk Stupor degree corresponding to patient is confused, including：According to the pure EEG signals, stupor sample entropy corresponding to signal energy and the coma patient is calculated；Electroencephalogram corresponding to the pure EEG signals is drawn, the amplitude and frequency of wave band are extracted from the electroencephalogram；By the stupor machine of the stupor sample entropy, the signal energy, the amplitude and frequency input training in advance Learning model, obtain stupor degree corresponding to the coma patient.
- 6. according to the method for claim 1, it is characterised in that methods described also includes：According to the pure EEG signals, prognosis sample entropy corresponding to the coma patient is calculated；Determine the prognosis threshold range residing for the prognosis sample entropy；Prognosis classification corresponding to the prognosis threshold range is defined as prognosis classification corresponding to the coma patient.
- 7. according to the method for claim 5, it is characterised in that it is described assess stupor degree corresponding to the coma patient it Afterwards, in addition to：According to the pure EEG signals, prognosis sample entropy corresponding to the coma patient is calculated；Extract the sleep spindle that the pure EEG signals include；According to prognosis sample entropy, the signal energy, the amplitude, the frequency and the sleep spindle, pass through The prognosis machine learning model of training in advance assesses prognosis classification corresponding to the coma patient.
- 8. according to the method described in any one of claim 6 or 7, it is characterised in that described to assess corresponding to the coma patient After stupor degree, in addition to：Show the stupor degree, the prognosis classification, electroencephalogram and each wave band figure corresponding to the coma patient.
- 9. a kind of device for assessing stupor degree, it is characterised in that described device includes：Acquisition module, for obtaining the eeg data of coma patient；Pretreatment module, for being pre-processed to the eeg data, obtain pure EEG signals；Evaluation module, for according to the pure EEG signals, assessing stupor degree corresponding to the coma patient.
- 10. device according to claim 9, it is characterised in that described device also includes：Prognostic module, for according to the pure EEG signals, calculating prognosis sample entropy corresponding to the coma patient；It is determined that Prognosis threshold range residing for the prognosis sample entropy；Prognosis classification corresponding to the prognosis threshold range is defined as described Prognosis classification corresponding to coma patient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710778478.0A CN107468243A (en) | 2017-09-01 | 2017-09-01 | A kind of method and device for assessing stupor degree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710778478.0A CN107468243A (en) | 2017-09-01 | 2017-09-01 | A kind of method and device for assessing stupor degree |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107468243A true CN107468243A (en) | 2017-12-15 |
Family
ID=60604575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710778478.0A Pending CN107468243A (en) | 2017-09-01 | 2017-09-01 | A kind of method and device for assessing stupor degree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107468243A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256460A (en) * | 2018-01-11 | 2018-07-06 | 中国科学院上海微系统与信息技术研究所 | Prediagnosis method/system, computer readable storage medium and the equipment of potential patient |
| CN108742606A (en) * | 2018-06-25 | 2018-11-06 | 苏州大学 | Coma patient prognostic evaluation device |
| CN109199371A (en) * | 2018-09-29 | 2019-01-15 | 北京机械设备研究所 | A kind of wearable brain electricity acquisition device |
| CN109247935A (en) * | 2018-10-31 | 2019-01-22 | 山东大学 | A kind of During Night Time parahypnosis condition monitoring system and method |
| CN109893125A (en) * | 2019-03-18 | 2019-06-18 | 杭州电子科技大学 | A kind of brain comatose state recognition methods based on brain area information exchange |
| CN110265143A (en) * | 2019-06-18 | 2019-09-20 | 福州大学 | Intelligent auxiliary diagnosis system based on electroencephalogram |
| CN110338787A (en) * | 2019-07-15 | 2019-10-18 | 燕山大学 | A kind of analysis method of pair of static EEG signals |
| CN110710956A (en) * | 2019-10-21 | 2020-01-21 | 广州市花都区人民医院 | Prognosis evaluation method and evaluation system for coma patient |
| CN111012341A (en) * | 2020-01-08 | 2020-04-17 | 东南大学 | Artifact removal and electroencephalogram signal quality evaluation method based on wearable electroencephalogram equipment |
| KR102308844B1 (en) * | 2021-03-22 | 2021-10-06 | 주식회사 아이메디신 | Method, server and computer program for predicting coma patient's prognosis using artificial intelligence model |
| CN114435373A (en) * | 2022-03-16 | 2022-05-06 | 一汽解放汽车有限公司 | Fatigue driving detection method, device, computer equipment and storage medium |
| CN117064409A (en) * | 2023-10-12 | 2023-11-17 | 杭州般意科技有限公司 | Method, device and terminal for evaluating transcranial direct current intervention stimulation effect in real time |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105147281A (en) * | 2015-08-25 | 2015-12-16 | 上海医疗器械高等专科学校 | Portable stimulating, awaking and evaluating system for disturbance of consciousness |
-
2017
- 2017-09-01 CN CN201710778478.0A patent/CN107468243A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105147281A (en) * | 2015-08-25 | 2015-12-16 | 上海医疗器械高等专科学校 | Portable stimulating, awaking and evaluating system for disturbance of consciousness |
Non-Patent Citations (2)
| Title |
|---|
| 梁静坤: "《基于想象驾驶行为的脑机接口控制》", 31 December 2015 * |
| 邱志斌: "不同程度意识障碍患者间的脑电信号对比分析研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256460B (en) * | 2018-01-11 | 2022-01-18 | 中国科学院上海微系统与信息技术研究所 | Method/system, computer storage medium and apparatus for early prognosis of potential patient |
| CN108256460A (en) * | 2018-01-11 | 2018-07-06 | 中国科学院上海微系统与信息技术研究所 | Prediagnosis method/system, computer readable storage medium and the equipment of potential patient |
| CN108742606A (en) * | 2018-06-25 | 2018-11-06 | 苏州大学 | Coma patient prognostic evaluation device |
| CN109199371A (en) * | 2018-09-29 | 2019-01-15 | 北京机械设备研究所 | A kind of wearable brain electricity acquisition device |
| CN109247935A (en) * | 2018-10-31 | 2019-01-22 | 山东大学 | A kind of During Night Time parahypnosis condition monitoring system and method |
| CN109893125A (en) * | 2019-03-18 | 2019-06-18 | 杭州电子科技大学 | A kind of brain comatose state recognition methods based on brain area information exchange |
| CN110265143A (en) * | 2019-06-18 | 2019-09-20 | 福州大学 | Intelligent auxiliary diagnosis system based on electroencephalogram |
| CN110265143B (en) * | 2019-06-18 | 2022-05-13 | 福州大学 | Intelligent auxiliary diagnosis system based on electroencephalogram |
| CN110338787A (en) * | 2019-07-15 | 2019-10-18 | 燕山大学 | A kind of analysis method of pair of static EEG signals |
| CN110710956A (en) * | 2019-10-21 | 2020-01-21 | 广州市花都区人民医院 | Prognosis evaluation method and evaluation system for coma patient |
| CN111012341A (en) * | 2020-01-08 | 2020-04-17 | 东南大学 | Artifact removal and electroencephalogram signal quality evaluation method based on wearable electroencephalogram equipment |
| CN111012341B (en) * | 2020-01-08 | 2022-04-22 | 东南大学 | Artifact removal and electroencephalogram signal quality evaluation method based on wearable electroencephalogram equipment |
| KR102308844B1 (en) * | 2021-03-22 | 2021-10-06 | 주식회사 아이메디신 | Method, server and computer program for predicting coma patient's prognosis using artificial intelligence model |
| CN114435373A (en) * | 2022-03-16 | 2022-05-06 | 一汽解放汽车有限公司 | Fatigue driving detection method, device, computer equipment and storage medium |
| CN114435373B (en) * | 2022-03-16 | 2023-12-22 | 一汽解放汽车有限公司 | Fatigue driving detection method, device, computer equipment and storage medium |
| CN117064409A (en) * | 2023-10-12 | 2023-11-17 | 杭州般意科技有限公司 | Method, device and terminal for evaluating transcranial direct current intervention stimulation effect in real time |
| CN117064409B (en) * | 2023-10-12 | 2024-01-30 | 深圳般意科技有限公司 | Method, device and terminal for evaluating transcranial direct current intervention stimulation effect in real time |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107468243A (en) | A kind of method and device for assessing stupor degree | |
| Sangaiah et al. | An intelligent learning approach for improving ECG signal classification and arrhythmia analysis | |
| CN106821376B (en) | epileptic seizure early warning system based on deep learning algorithm | |
| CN111012341B (en) | Artifact removal and electroencephalogram signal quality evaluation method based on wearable electroencephalogram equipment | |
| CN110353702A (en) | A kind of emotion identification method and system based on shallow-layer convolutional neural networks | |
| CN109620211A (en) | A kind of intelligent abnormal electrocardiogram aided diagnosis method based on deep learning | |
| CN110604565A (en) | Brain health screening method based on portable EEG equipment | |
| CN111466876B (en) | Alzheimer's disease auxiliary diagnosis system based on fNIRS and graph neural network | |
| CN106236027B (en) | Depressed crowd's decision method that a kind of brain electricity is combined with temperature | |
| CN107595243A (en) | A kind of illness appraisal procedure and terminal device | |
| CN111544015B (en) | Cognitive power-based control work efficiency analysis method, device and system | |
| CN105942974A (en) | Sleep analysis method and system based on low frequency electroencephalogram | |
| CN111598451B (en) | Control work efficiency analysis method, device and system based on task execution capacity | |
| CN110477909B (en) | Gender classification method based on resting electroencephalogram data | |
| CN109044280B (en) | Sleep staging method and related equipment | |
| CN106725452A (en) | Based on the EEG signal identification method that emotion induces | |
| CN112488002B (en) | Emotion recognition method and system based on N170 | |
| CN110353704B (en) | Emotion evaluation method and device based on wearable electrocardiogram monitoring | |
| CN113723557A (en) | Depression electroencephalogram classification system based on multiband time-space convolution network | |
| CN106510702A (en) | Auditory sense attention characteristic extraction and recognition system and method based on middle latency auditory evoked potential | |
| CN115281685A (en) | Sleep stage identification method and device based on anomaly detection and computer readable storage medium | |
| CN108143412A (en) | A kind of control method of children's brain electricity mood analysis, apparatus and system | |
| AU2020103949A4 (en) | EEG Signal Mixed Noise Processing Method, Equipment and Storage Medium | |
| CN112438741B (en) | Driving state detection method and system based on electroencephalogram feature transfer learning | |
| CN113491506A (en) | Electroencephalogram signal processing method and device based on deep convolutional network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171215 |