CN109009099A - A kind of intelligent anesthesia system based on EEG-NIRS - Google Patents
A kind of intelligent anesthesia system based on EEG-NIRS Download PDFInfo
- Publication number
- CN109009099A CN109009099A CN201810794998.5A CN201810794998A CN109009099A CN 109009099 A CN109009099 A CN 109009099A CN 201810794998 A CN201810794998 A CN 201810794998A CN 109009099 A CN109009099 A CN 109009099A
- Authority
- CN
- China
- Prior art keywords
- anesthesia
- eeg
- nirs
- signal
- parameter
- 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
- A61B5/48—Other medical applications
- A61B5/4821—Determining level or depth of anaesthesia
-
- 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
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/6803—Head-worn items, e.g. helmets, masks, headphones or goggles
-
- 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
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
- A61M5/178—Syringes
- A61M5/20—Automatic syringes, e.g. with automatically actuated piston rod, with automatic needle injection, filling automatically
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
- A61M5/178—Syringes
- A61M5/31—Details
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2202/00—Special media to be introduced, removed or treated
- A61M2202/04—Liquids
- A61M2202/0468—Liquids non-physiological
- A61M2202/048—Anaesthetics
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2205/00—General characteristics of the apparatus
- A61M2205/33—Controlling, regulating or measuring
- A61M2205/3331—Pressure; Flow
- A61M2205/3334—Measuring or controlling the flow rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2230/00—Measuring parameters of the user
- A61M2230/04—Heartbeat characteristics, e.g. ECG, blood pressure modulation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Physics & Mathematics (AREA)
- Anesthesiology (AREA)
- Psychiatry (AREA)
- Vascular Medicine (AREA)
- Hematology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Psychology (AREA)
- Infusion, Injection, And Reservoir Apparatuses (AREA)
Abstract
The intelligent anesthesia system based on EEG-NIRS that the invention discloses a kind of, including wear-type signal acquisition module anaesthetize automatic control module, data memory module；Wear-type signal acquisition module includes near-infrared light source drive part, collecting part, control and WIFI communications portion, acquisition is synchronized to EEG signal and NIRS signal, is communicated by WIFI and pretreated EEG and NIRS signal is passed into anesthesia automatic control module；Anesthesia automatic control module has the function of dose and injection speed, deep neural network optimization, the injection of multichannel anaesthetic etc. needed for anaesthetizing index dynamic monitoring, feedback controller calculating patient；Data memory module can dynamically recording anesthesia surgery data information and key node, and be uploaded to server.The present invention acquires EEG and NIRS signal simultaneously, carries out dynamic monitoring to the indexs such as the calmness, analgesia of patient, flesh pine in art, accurately controls the infusion velocity and infusion amount of anaesthetic, medical resource utilization rate is substantially improved, reduce the use cost of Medical Devices.
Description
Technical field
The present invention relates to intelligent anesthesia control fields, more particularly to one kind to be based on EEG-NIRS signal, can be realized in art
Anaesthetize the intelligent anesthesia system of automatic and accurate administration, vital sign monitoring, safety monitoring early warning.
Background technique
At present in clinical anesthesia operation, general anesthesia operation amount is significantly increased, and Anesthetist's quantity is obvious insufficient, causes
The problem of Anesthetist operating pressure is excessive, and operation risk increases.Simultaneously as the proper operation error of manpower can not also be kept away
Exempt to cause anaesthetic and is transfused inaccurate problem.Therefore how using modern scientific and technical result reduce anesthetist workload and
Promoting arcotic infusion precision becomes very urgent.
During general anesthesia, to accomplish that the anesthesia of safe and reasonable, anesthesia depth monitoring and control are all critically important.In art
Three kinds of indexs are commonly used in anesthesia depth monitoring, i.e., calm, analgesia and degree of flaccid muscles.Therefore, calm, analgesia and flesh pine three
The monitoring divided should be the main contents of perianesthesia care anesthesia depth monitoring.For anesthesia clinically, about calmness
Study on monitoring is most, wherein it is most commonly seen universal to instruct to control different depth of anesthesia in art by BIS monitoring.In neuromuscular monitoring
Aspect understands the retarding degree and recovery using body Neuromuscular Transmission Function after muscle relaxant by related neuromuscular monitoring equipment
Situation improves the safety and reasonability of muscle relaxant clinical application.In ease pain, due to analgesic to cerebration by
Body is different from downern, and it is difficult to extract single analgesia levels from EEG.Mainly there is heart rate accordingly, with respect to analgesic monitoring
Variability (HRV), mean arterial blood pressure (MAP) etc. judge influence of the noxious stimulus to autonomic nerves system (ANS), thus in advance
Survey reaction of the body to noxious stimulation.
Although many now concerning the research in terms of Anesthesia Monitoring and closed-loop control, due to BIS, TOF, ANI etc.
The equal separate configurations of monitoring device, medical resource are anaesthetized there is no being integrated together to realize information automatic feedback and intercommunication well
The automatic control of drug is mostly single index.Simultaneously because data compatibility is poor between each monitoring device, various monitoring connecting lines
Intricate, domestic clinical operation cannot achieve various dimensions, the automatic control of multi-parameter.
Summary of the invention
It is an object of that present invention to provide a kind of indexs that can be realized to the calmness, analgesia of patient, flesh pine etc. in art
It is monitored, and accurately controls the infusion velocity and infusion amount of anaesthetic, realize and anaesthetize automatic and accurate in the art of various dimensions
The intelligent anesthesia system based on EEG-NIRS of administration.
To achieve the above object, use following technical scheme: system of the present invention includes wear-type signal acquisition mould
Block, anesthesia automatic control module, data memory module；
The wear-type signal acquisition module includes near-infrared light source drive part, collecting part, control and WIFI logical
Believe part, acquisition can be synchronized to EEG signal and NIRS signal, by the WIFI communication technology by pretreated EEG with
NIRS signal passes to anesthesia automatic control module；
The anesthesia automatic control module includes dynamic state of parameters monitoring modular and anaesthetic injection module, dynamic state of parameters inspection
Surveying module has anesthesia index extraction, anesthesia index dynamic monitoring, voice reminder, PKPD patient model, deep neural network excellent
Change function；Anaesthetic injection module includes feedback controller, parameter optimization module, RS232 serial communication, propofol Injection
Pump, Remifentanil syringe pump, atracurium syringe pump；
The data memory module can dynamically recording anesthesia surgery data information and key node, data memory module
Technology is connected with anesthesia automatic control module by wireless communication, carries out recording and storage to anesthesia data in art and is uploaded to clothes
Business device.
Further, the wear-type signal acquisition module is by electrode for encephalograms, near-infrared probe, embedded system group
At；There are three electrode for encephalograms, including one refers to pole and two collection terminals, for acquiring forehead EEG information；Near-infrared probe
It is made of two LED light tube and two reception pipes, the intensity after near infrared light net radiation for obtaining forehead；Embedded system
The amplification for the generation for being responsible for light source drive signal, brain electricity and the near infrared light strong signal of uniting and analog-to-digital conversion and anaesthesia machines people's module
Wireless communication.
Further, the anesthesia automatic control module communicates to obtain EEG/NIRS original signal by WIFI；To EEG
The feature extraction of signal obtains sedation depth index, obtains analgesia depth index to the multiscale analysis of NIRS signal, believes EEG
Number carry out spectrum analysis and quantization extract obtain degree of flaccid muscles index；By the parameter index of calm, analgesia and flesh pine in fiber crops
Insertion in liquor-saturated automatic control module is realized the calculating to anaesthetic real-time requirement amount in conjunction with feedback controller, and then is passed through
Anaesthetic injection module carries out anaesthetic injection to patient.
Further, the sedation depth parameter HLS is by the way that RPE, SFS, MPF, BetaRatio, these four refer to substantially
Mark is belonged to after being learnt by depth convolutional neural networks (CNN) in conjunction with patient's specific age, height and weight essential information
In the Sedation Scale table (HLS) of the calm index of intelligent anesthesia machine people, depth of anesthesia scores range from 0 (brain death) to 10
(completely awake), increment 0.1；Wherein, 0-3 representative anesthesia is too deep, and 3-6 represents anesthesia holddown, and 6-8 is sedation,
8-10 is waking state.The best target value anaesthetized in art is 3-6.
Further, the analgesia depth parameter NAF be by original NIRS signal carry out multi-scale wavelet decomposition and
After its inverse transformation, the details coefficients under different scale are obtained, so that HRV is obtained, MAP, HbO2 (Hb) information, then to above-mentioned
Parameter carries out feature extraction in the time domain and establishes model with parameter model Power estimation method and corresponding spectral curve is fitted,
The analgesia parameter index analgesia table of grading for belonging to intelligent anesthesia machine people is obtained by parameter testing and the determination of model order
(ALS), ALS is calculated primary every 5s, and analgesia scoring range is from -10 (very pain) to 10 (analgesias), increment 1.Most preferably
Target value is -3 to 3.
Further, the flesh pine parameter RPSD is that the frequency for being greater than 40Hz is extracted in the EEG signal of acquisition by calculating
The size of the ratio of the energy and gross energy of section and the relative power spectral density of myoelectricity component, assess patient's degree of flaccid muscles.
Further, analgesia/calmness feedback controller in the anesthesia automatic control module, present invention use analgesia/
The mode that calmness jointly controls carries out anesthesia control.From practicability and the reliability perspectives present invention using model prediction
Control；RPE parameter is obtained by anesthesia automatic control module, calm parameter HLS is calculated, then carries out downern ball note,
When waiting calmness parameter index (HLS) < 8.0, carry out having the calculated maintenance dose with human body metabolic balance of PKPD model, together
When by current physiology index, parameter index brings model predictive controller into, completes anesthesia and automatically controls；Meanwhile certainly by anesthesia
Dynamic control module obtains HRV parameter, analgesia parameter ALS is calculated, by the revision to K1, K2, by obtained dosage and physiology
Information is transmitted to analgesic injection pump, completes the administration of analgesic automatic and accurate.
Further, the flesh pine feedback controller in the anesthesia automatic control module, using based on online with offline number
According to the controller of the data-driven of fusion.In the control method of current data-driven, iterative learning controls (ILC control) energy
It is enough preferably to be controlled using online and offline data.Meanwhile ILC theory comparatively perfect, it directly approaches control signal, and
Nonparametric positive definite, it is widely used in practice.
Compared with prior art, the present invention has the advantage that
1, calm, analgesia, the multiple indexs merging monitorings of flesh pine are realized, medical resource utilization rate is significantly promoted, reduces
Medical Devices use cost.
2, using the signal collecting device and parameter index independently researched and developed, the calculation of traditional anesthesia depth monitoring index is got rid of
Method is underground and the uncertain problem of index.
3, multiple parameters carry out Anesthesia Monitoring in same equipment, assessment analgesia/calmness/flesh pine that can be more accurate
Stimulation degree.
4, the anesthesia control system that manual control is combined with automatic control mitigates the workload of anesthetist significantly, promotes hand
Art safety can will be put into prior operation decision with more energy.
Detailed description of the invention
Fig. 1 is structural framing schematic diagram of the invention.
Fig. 2 is EEG-NIRS system construction drawing of the invention.
Fig. 3 is the work flow diagram of intelligent anesthesia machine people of the invention.
Fig. 4 is Model Predictive Control schematic diagram of the invention.
Fig. 5 is downern control flow chart of the invention.
Fig. 6 is analgesic control flow chart of the invention.
Fig. 7 is data drive control schematic diagram of the invention.
Drawing reference numeral: 1- wear-type signal acquisition module, 2- anaesthetize automatic control module, 3- data memory module, 11-
EEG signal, 12-NIRS signal, 21- dynamic state of parameters monitoring modular, 221- downern (Propofol) syringe pump, 222- antalgesic
Object (Remifentanil) syringe pump, 223- muscle relaxants (atracurium) syringe pump.
Specific embodiment
The present invention will be further described with reference to the accompanying drawing:
As shown in Figure 1, the present invention includes wear-type signal acquisition module 1, automatic control module 2 is anaesthetized, data store mould
Block 3；
The wear-type signal acquisition module includes near-infrared light source drive part, collecting part, control and WIFI logical
Letter part forms, and can synchronize acquisition to EEG (11) signal and NIRS (12) signal, will be pretreated by WIFI communication
EEG and NIRS signal pass to anesthesia automatic control module.The anesthesia automatic control module includes to have anesthesia index
Extract, anaesthetize the dynamic state of parameters of the parts such as index dynamic monitoring, voice reminder, PKPD patient model, deep neural network optimization
Monitoring modular (21) has feedback controller, parameter optimization, RS232 serial communication, downern (Propofol) syringe pump
(221), analgesic (Remifentanil) syringe pump (222), the anaesthetic note of muscle relaxants (atracurium) syringe pump (223)
Penetrate module.The data memory module can dynamically recording anesthesia surgery data information and key node, and be uploaded to service
Device.
The wear-type signal acquisition module, as shown in Fig. 2, mainly by electrode for encephalograms, near-infrared probe, embedded system
System composition.There are three electrode for encephalograms, including one refers to pole, two collection terminals, for acquiring forehead EEG information；Near-infrared is visited
Head is made of two LED light tube and two reception pipes, the intensity after near infrared light net radiation for obtaining forehead；It is embedded
System is responsible for the amplification and analog-to-digital conversion and anaesthesia machines people's mould of the generation of light source drive signal, brain electricity near infrared light strong signal
Block wireless communication.
The anesthesia automatic control module includes dynamic state of parameters monitoring modular and drug injection module.As shown in figure 3, being
The workflow of intelligent anesthesia machine people.Anesthesia automatic control module communicates to obtain EEG/NIRS original signal by WIFI；It is right
The feature extraction of EEG signal obtains sedation depth index, obtains analgesia depth index to the multiscale analysis of NIRS signal, right
EEG signal carries out spectrum analysis and quantization extracts and obtains degree of flaccid muscles index.Pass through calm, analgesia and the parameter index of flesh pine
Insertion in anesthesia automatic control module realizes the calculating to anaesthetic real-time requirement amount in conjunction with feedback controller, in turn
Anaesthetic injection is carried out to patient by anaesthetic injection module.
The calm parameter index is that time domain and frequency-domain index: Renyi ordering entropy are extracted from the EEG signal of acquisition
(RPE), β ratio (BetaRatio), synchronous speed ratio (SFS), middle these four basic indexs of spectral density (MPF), in conjunction with patient
Specific age, the essential informations such as height and weight obtain belonging to intelligent fiber crops after learning by depth convolutional neural networks (CNN)
The Sedation Scale table (HLS) of the calm index of liquor-saturated robot, depth of anesthesia scoring range are (completely clear from 0 (brain death) to 10
Wake up), increment 0.1.0-3 representative anesthesia is too deep, and 3-6 represents anesthesia holddown, and 6-8 is sedation, and 8-10 is shape of regaining consciousness
State.The best target value anaesthetized in art is 3-6.
RPE specific algorithm is as follows:
In formula, pjProbability distribution is represented, a is probability selection coefficient, and m is Embedded dimensions, m！Indicate that sequencing model shares m！
Kind.
β ratio specific algorithm is as follows:
BetaRatio=log (P30-47Hz/P11-20Hz) (2)
MPF specific algorithm is as follows:
SFS specific algorithm is as follows:
SFS=log (P0.5-47Hz/P40-47Hz) (5)
The analgesia parameter index is to extract from NIRS signal to the ingredient that can embody embodiment analgesia information.?
In NIRS measuring signal, comprising pulse wave, respiratory wave, Mayer wave etc., and different waveforms is in different frequency range, so we
It can be filtered by Savitzky-Golay smoothing filter, and then obtain wave band required for us.For pulse wave,
Different people's pulse wave diversity ratios is larger, but generally lower in narcosis lower frequency, takes N=2 by experiment, can be with when L=7
It is effectively retained pulse information, while the High-frequency Interference in signal can be effectively removed.By the details coefficients of the scale 6 where heart rate
Details coefficients after (0.78-1.56HZ) proposition in scale carry out the information that inverse wavelet transform obtains the heart rate of brain, accordingly may be used
To obtain variation (HRV) situation in the segment signal comprising heart rate.The change of HbO2 and Hb relative concentration is obtained with similar mode
Change and mean arterial blood pressure (MAP) information, then to HRV, the parameters such as MAP, HbO2 (Hb) carry out feature extraction in the time domain, and
Model is established with parameter model Power estimation method and corresponding spectral curve is fitted, really by parameter testing and model order
Surely analgesia parameter index analgesia table of grading (ALS) for belonging to intelligent anesthesia machine people is obtained, ALS calculates primary, analgesia every 5s
The range that scores is from -10 (very pain) to 10 (analgesias), increment 1.Best target value is -3 to 3.Wherein about Rui Fentai
The Rapid Dose Calculation of Buddhist nun is as follows:
Doseremi=previousDoseremi×K1×K2 (6)
Wherein, DoseremiRepresent current Remifentanil dosage, previousDoseremiThe Rui Fentai once calculated before representing
The dosage of Buddhist nun, K1 is the past value of ALS and is worth proportional coefficient now, and K2 is the coefficient depending on operating stage.
The flesh pine parameter, the present invention carry out the monitoring of flesh pine degree in art by relative power spectral density (RPSD),
The size of the ratio of gross energy is accounted for, according to myoelectricity component to judge the degree of flaccid muscles of patient.The specific calculation of RSPD
It is as follows:
P () represents energy, and RPSD () represents relative power spectral density.Here f1And f2Respectively represent low frequency and height
Frequency.P (Isosorbide-5-Nitrae 7) represents EEG signal and includes five seed bandwidth (delta wave, theta wave, alpha wave, gamma from 1Hz-47Hz
Wave) energy.According to the above method, after frequency range (>=40Hz) where extracting electromyography signal, by the phase for calculating myoelectricity component
It, can accurate evaluation patient's degree of flaccid muscles to power spectral density (RPSD).
For calm and analgesic control, the present invention carries out anesthesia control in such a way that analgesia/calmness jointly controls
System.As shown in figure 4, from practicability and the reliability perspectives present invention using Model Predictive Control.Model prediction algorithm
Core be: in each sampling period, current state and prediction model based on system find out optimum control element as next
A input.By the way that optimization calculates and rolls the control action of implementation and the feedback correction of model error repeatedly online.Such as Fig. 5 institute
Show, the parameters such as RPE obtained by anesthesia automatic control module, calm parameter HLS is calculated, then carries out downern ball note,
When waiting calmness parameter index (HLS) < 8.0, carry out having the calculated maintenance dose with human body metabolic balance of PKPD model, together
When by current physiology index, parameter index brings model predictive controller into, completes anesthesia and automatically controls.Meanwhile as shown in fig. 6,
The parameters such as HRV are obtained by anesthesia automatic control module, analgesia parameter ALS are calculated, by the way that K1, the revision of K2 will be obtained
Dosage and physiologic information be transmitted to analgesic injection pump, further complete analgesic automatic and accurate administration.
For the control of muscle relaxants, the control based on the data-driven merged online with off-line data is used in the present invention
Device, as shown in Figure 7.Data drive control have ignored in controlled device Mechanism Model, directly pass through the online of controlled system
It realizes and controls with off-line data.In the control method of current data-driven, iterative learning controls (ILC control) can be preferable
Controlled using online and offline data.Meanwhile ILC theory comparatively perfect, it directly approaches control signal, and nonparametric
Positive definite, it is widely used in practice.
The anaesthetic injection module is mainly made of three independent syringe pumps, complete by anesthesia automatic control module
Pairs of downern (Propofol), analgesic (Remifentanil), the infusion velocity of muscle relaxants (atracurium) and infusion agent
The control of amount.Each independent syringe pump (includes by LCD LCD screen display device, syringe piston pushrod movement driving device
Stepper motor, lead screw gear and driver circuit), syringe pump embedded system, state monitoring apparatus and power supply device
It is formed Deng part.Real-time medication infusion rate is calculated by anesthesia automatic control module, control drug injection system carries out certainly
Dynamic accurate administration.
The data memory module is mainly to data progress recording and storage is anaesthetized in art, to carry out anesthesia algorithm
It updates and improves.
Embodiment described above only describe the preferred embodiments of the invention, not to model of the invention
It encloses and is defined, without departing from the spirit of the design of the present invention, those of ordinary skill in the art are to technical side of the invention
The various changes and improvements that case is made should all be fallen into the protection scope that claims of the present invention determines.
Claims (8)
1. a kind of intelligent anesthesia system based on EEG-NIRS, it is characterised in that: the system comprises wear-type signal acquisition moulds
Block, anesthesia automatic control module, data memory module；
The wear-type signal acquisition module includes near-infrared light source drive part, collecting part, control and WIFI communication unit
Point, acquisition can be synchronized to EEG signal and NIRS signal, by the WIFI communication technology by pretreated EEG and NIRS
Signal passes to anesthesia automatic control module；
The anesthesia automatic control module includes dynamic state of parameters monitoring modular and anaesthetic injection module, and dynamic state of parameters detects mould
There is block anesthesia index extraction, anesthesia index dynamic monitoring, voice reminder, PKPD patient model, deep neural network to optimize function
Energy；Anaesthetic injection module include feedback controller, parameter optimization module, RS232 serial communication, propofol Injection pump, it is auspicious
Fentanyl syringe pump, atracurium syringe pump；
The data memory module can dynamically recording anesthesia surgery data information and key node, data memory module passes through
Wireless communication technique is connected with anesthesia automatic control module, carries out recording and storage to anesthesia data in art and is uploaded to service
Device.
2. a kind of intelligent anesthesia system based on EEG-NIRS according to claim 1, it is characterised in that: described wears
Formula signal acquisition module is made of electrode for encephalograms, near-infrared probe, embedded system；There are three electrode for encephalograms, including a ginseng
Pole and two collection terminals are examined, for acquiring forehead EEG information；Near-infrared probe is by two LED light tube and two reception pipe groups
At the intensity after near infrared light net radiation for obtaining forehead；Embedded system is responsible for the generation of light source drive signal, brain electricity
Amplification and analog-to-digital conversion and anaesthesia machines people's module near infrared light strong signal wirelessly communicate.
3. a kind of intelligent anesthesia system based on EEG-NIRS according to claim 1, it is characterised in that: the anesthesia
Automatic control module communicates to obtain EEG/NIRS original signal by WIFI；Sedation depth is obtained to the feature extraction of EEG signal
Index obtains analgesia depth index to the multiscale analysis of NIRS signal, carries out spectrum analysis to EEG signal and quantization is extracted
To degree of flaccid muscles index；The insertion in automatic control module is being anaesthetized by the parameter index of calm, analgesia and flesh pine, in conjunction with
Feedback controller realizes the calculating to anaesthetic real-time requirement amount, and then carries out fiber crops to patient by anaesthetic injection module
Liquor-saturated drug injection.
4. a kind of intelligent anesthesia system based on EEG-NIRS according to claim 3, it is characterised in that: described calm deep
Degree parameter HLS be by RPE, SFS, MPF, BetaRatio these four basic indexs, in conjunction with patient's specific age, height
Weight essential information obtains the calm index for belonging to intelligent anesthesia machine people after learning by depth convolutional neural networks (CNN)
Sedation Scale table (HLS), depth of anesthesia score range from 0 (brain death) to 10 (completely awake), increment 0.1；Wherein, 0-
3 representative anesthesia are too deep, and 3-6 represents anesthesia holddown, and 6-8 is sedation, and 8-10 is waking state.
5. a kind of intelligent anesthesia system based on EEG-NIRS according to claim 3, it is characterised in that: the analgesia is deep
Degree parameter NAF be by carrying out multi-scale wavelet decomposition and its inverse transformation to original NIRS signal after, obtain under different scale
Details coefficients, to obtain HRV, then MAP, HbO2 (Hb) information carries out feature extraction simultaneously in the time domain to above-mentioned parameter
Model is established with parameter model Power estimation method and corresponding spectral curve is fitted, really by parameter testing and model order
Surely analgesia parameter index analgesia table of grading (ALS) for belonging to intelligent anesthesia machine people is obtained, ALS calculates primary, analgesia every 5s
The range that scores is from -10 (very pain) to 10 (analgesias), increment 1.
6. a kind of intelligent anesthesia system based on EEG-NIRS according to claim 3, it is characterised in that: the flesh pine ginseng
Number RPSD be by calculate in the EEG signal of acquisition extract greater than 40Hz frequency range energy and gross energy ratio it is big
Small and myoelectricity component relative power spectral density assesses patient's degree of flaccid muscles.
7. a kind of intelligent anesthesia system based on EEG-NIRS according to claim 3, it is characterised in that: the anesthesia is certainly
Analgesia/calmness feedback controller in dynamic control module obtains RPE parameter by anesthesia automatic control module, calculates calmness
Then parameter HLS carries out downern ball note, when waiting calmness parameter index (HLS) < 8.0, carried out PKPD model and calculated
The maintenance dose with human body metabolic balance, while by current physiology index, parameter index brings model predictive controller into, completes
Anesthesia automatically controls；Meanwhile by anesthesia automatic control module obtain HRV parameter, calculate analgesia parameter ALS, by K1,
Obtained dosage and physiologic information are transmitted to analgesic injection pump, complete the administration of analgesic automatic and accurate by the revision of K2.
8. a kind of intelligent anesthesia system based on EEG-NIRS according to claim 3, it is characterised in that: the anesthesia is certainly
Flesh pine feedback controller in dynamic control module, using the controller based on the data-driven merged online with off-line data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810794998.5A CN109009099A (en) | 2018-07-19 | 2018-07-19 | A kind of intelligent anesthesia system based on EEG-NIRS |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810794998.5A CN109009099A (en) | 2018-07-19 | 2018-07-19 | A kind of intelligent anesthesia system based on EEG-NIRS |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109009099A true CN109009099A (en) | 2018-12-18 |
Family
ID=64642319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810794998.5A Pending CN109009099A (en) | 2018-07-19 | 2018-07-19 | A kind of intelligent anesthesia system based on EEG-NIRS |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109009099A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110193113A (en) * | 2019-05-30 | 2019-09-03 | 北京易飞华通科技开发有限公司 | Multi-channel intelligent drug delivery system |
| CN110232961A (en) * | 2019-06-10 | 2019-09-13 | 上海电机学院 | A kind of speech recognition intelligent anesthesia system based on big data |
| CN110237362A (en) * | 2019-06-19 | 2019-09-17 | 四川大学华西第二医院 | A kind of inhibiting pain in parturition method and analgesic apparatus |
| CN110547868A (en) * | 2019-09-05 | 2019-12-10 | 栾其友 | Continuous anesthesia device |
| CN111508581A (en) * | 2020-04-23 | 2020-08-07 | 张琦 | Hospital anesthesia treatment management system |
| CN112006659A (en) * | 2020-08-21 | 2020-12-01 | 思澜科技（成都）有限公司 | Anesthesia state monitoring method and device |
| CN112037901A (en) * | 2020-06-14 | 2020-12-04 | 深圳市前海澳威智控科技有限责任公司 | Intelligent pain management system and management method |
| CN112057700A (en) * | 2020-09-04 | 2020-12-11 | 深圳市威浩康医疗器械有限公司 | System, device and storage medium for determining base consciousness value in anesthesia maintenance period |
| CN112138245A (en) * | 2020-09-27 | 2020-12-29 | 北京医院 | Self-feedback pain relieving system |
| CN112354042A (en) * | 2020-12-01 | 2021-02-12 | 南通市肿瘤医院 | Analgesia pump flow control method and device |
| CN112438701A (en) * | 2019-08-16 | 2021-03-05 | 浙江象立医疗科技有限公司 | Method for detecting blood parameters and electrophysiological parameters based on photoelectric fusion |
| CN112675384A (en) * | 2020-11-19 | 2021-04-20 | 联赢医疗科技有限公司 | Automatic anesthesia robot of dosing |
| CN113069081A (en) * | 2021-03-22 | 2021-07-06 | 山西三友和智慧信息技术股份有限公司 | Pain detection method based on improved Bi-LSTM and fNIRS |
| CN113440690A (en) * | 2021-08-03 | 2021-09-28 | 复旦大学 | Intelligent quantitative drug administration electric needle injection device based on electromyographic signal feedback |
| CN115105681A (en) * | 2022-06-24 | 2022-09-27 | 纽锐思(苏州)医疗科技有限公司 | Anesthesia closed-loop infusion system based on multi-modal physiological indexes |
| JP2023518363A (en) * | 2020-03-16 | 2023-05-01 | コーニンクレッカ フィリップス エヌ ヴェ | Macro/microstructure of sleep and similar states of consciousness to optimize pain therapy |
| CN116452101A (en) * | 2023-06-09 | 2023-07-18 | 淄博市中心医院 | Intelligent anesthesia department medicine distribution charging method and system |
| CN116491898A (en) * | 2023-04-06 | 2023-07-28 | 深圳市威浩康医疗器械有限公司 | Intelligent anesthesia target control device suitable for surgical operation and administration method |
| CN117797406A (en) * | 2024-02-22 | 2024-04-02 | 中国人民解放军空军军医大学 | Closed loop percutaneous acupoint electro-stimulation sedation method and system |
| CN118178785A (en) * | 2024-04-18 | 2024-06-14 | 首都医科大学宣武医院 | Analgesic administration regulation and control system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103432651A (en) * | 2012-12-31 | 2013-12-11 | 南京理工大学 | Closed-loop intelligent anesthesia control system |
-
2018
- 2018-07-19 CN CN201810794998.5A patent/CN109009099A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103432651A (en) * | 2012-12-31 | 2013-12-11 | 南京理工大学 | Closed-loop intelligent anesthesia control system |
Non-Patent Citations (1)
| Title |
|---|
| 梁振虎等: "《2017中国自动化大会（CAC 2017）》", 22 October 2017 * |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110193113A (en) * | 2019-05-30 | 2019-09-03 | 北京易飞华通科技开发有限公司 | Multi-channel intelligent drug delivery system |
| CN110232961A (en) * | 2019-06-10 | 2019-09-13 | 上海电机学院 | A kind of speech recognition intelligent anesthesia system based on big data |
| CN110237362A (en) * | 2019-06-19 | 2019-09-17 | 四川大学华西第二医院 | A kind of inhibiting pain in parturition method and analgesic apparatus |
| CN112438701A (en) * | 2019-08-16 | 2021-03-05 | 浙江象立医疗科技有限公司 | Method for detecting blood parameters and electrophysiological parameters based on photoelectric fusion |
| CN110547868A (en) * | 2019-09-05 | 2019-12-10 | 栾其友 | Continuous anesthesia device |
| CN110547868B (en) * | 2019-09-05 | 2020-06-09 | 方磊 | Continuous anesthesia device |
| JP7462786B2 (en) | 2020-03-16 | 2024-04-05 | コーニンクレッカ フィリップス エヌ ヴェ | Macro/Micro-structure of Sleep and Similar States of Consciousness for Optimizing Pain Treatment |
| JP2023518363A (en) * | 2020-03-16 | 2023-05-01 | コーニンクレッカ フィリップス エヌ ヴェ | Macro/microstructure of sleep and similar states of consciousness to optimize pain therapy |
| CN111508581A (en) * | 2020-04-23 | 2020-08-07 | 张琦 | Hospital anesthesia treatment management system |
| CN112037901A (en) * | 2020-06-14 | 2020-12-04 | 深圳市前海澳威智控科技有限责任公司 | Intelligent pain management system and management method |
| CN112006659A (en) * | 2020-08-21 | 2020-12-01 | 思澜科技（成都）有限公司 | Anesthesia state monitoring method and device |
| CN112006659B (en) * | 2020-08-21 | 2022-08-05 | 思澜科技（成都）有限公司 | Anesthesia state monitoring method and device |
| CN112057700A (en) * | 2020-09-04 | 2020-12-11 | 深圳市威浩康医疗器械有限公司 | System, device and storage medium for determining base consciousness value in anesthesia maintenance period |
| CN112138245A (en) * | 2020-09-27 | 2020-12-29 | 北京医院 | Self-feedback pain relieving system |
| CN112675384B (en) * | 2020-11-19 | 2021-09-21 | 联赢医疗科技有限公司 | Automatic anesthesia robot of dosing |
| CN112675384A (en) * | 2020-11-19 | 2021-04-20 | 联赢医疗科技有限公司 | Automatic anesthesia robot of dosing |
| CN112354042A (en) * | 2020-12-01 | 2021-02-12 | 南通市肿瘤医院 | Analgesia pump flow control method and device |
| CN113069081B (en) * | 2021-03-22 | 2023-04-07 | 山西三友和智慧信息技术股份有限公司 | Pain detection method based on improved Bi-LSTM and fNIRS |
| CN113069081A (en) * | 2021-03-22 | 2021-07-06 | 山西三友和智慧信息技术股份有限公司 | Pain detection method based on improved Bi-LSTM and fNIRS |
| CN113440690A (en) * | 2021-08-03 | 2021-09-28 | 复旦大学 | Intelligent quantitative drug administration electric needle injection device based on electromyographic signal feedback |
| CN115105681A (en) * | 2022-06-24 | 2022-09-27 | 纽锐思(苏州)医疗科技有限公司 | Anesthesia closed-loop infusion system based on multi-modal physiological indexes |
| CN115105681B (en) * | 2022-06-24 | 2024-05-24 | 纽锐思(苏州)医疗科技有限公司 | Anesthesia closed-loop infusion system based on multi-mode physiological indexes |
| CN116491898A (en) * | 2023-04-06 | 2023-07-28 | 深圳市威浩康医疗器械有限公司 | Intelligent anesthesia target control device suitable for surgical operation and administration method |
| CN116491898B (en) * | 2023-04-06 | 2024-05-28 | 深圳市威浩康医疗器械有限公司 | Intelligent anesthesia target control device suitable for surgical operation and administration method |
| CN116452101A (en) * | 2023-06-09 | 2023-07-18 | 淄博市中心医院 | Intelligent anesthesia department medicine distribution charging method and system |
| CN116452101B (en) * | 2023-06-09 | 2023-08-25 | 淄博市中心医院 | Intelligent anesthesia department medicine distribution charging method and system |
| CN117797406A (en) * | 2024-02-22 | 2024-04-02 | 中国人民解放军空军军医大学 | Closed loop percutaneous acupoint electro-stimulation sedation method and system |
| CN118178785A (en) * | 2024-04-18 | 2024-06-14 | 首都医科大学宣武医院 | Analgesic administration regulation and control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109009099A (en) | A kind of intelligent anesthesia system based on EEG-NIRS | |
| CN109308940A (en) | Cardiopulmonary exercise assessment and training integral system | |
| CN106874699A (en) | It is a kind of based on the health management system arranged of iOS platforms | |
| CN109360647A (en) | A kind of Chinese medicine diagnosis and therapy system based on artificial intelligence | |
| CN207012242U (en) | Integral intelligent anaesthesia machines people | |
| CN105023073A (en) | Hospital intelligence assessment triage system based on artificial neural network | |
| CN206714993U (en) | Intelligent anesthesia machine people | |
| CN201060561Y (en) | Biofeedback mental state regulation and auxiliary learning machine | |
| CN108325020B (en) | Vein anesthesia multi-parameter index closed-loop monitoring system | |
| CN204189169U (en) | A kind of intelligent medical office management system based on living things feature recognition | |
| CN108847274A (en) | A kind of vital sign data processing method and system based on cloud platform | |
| CN110232961A (en) | A kind of speech recognition intelligent anesthesia system based on big data | |
| CN111798956B (en) | Decision determining method, device and system for artificial intelligence anesthesia | |
| CN110193113A (en) | Multi-channel intelligent drug delivery system | |
| DE102012003509A1 (en) | ventilation system | |
| CN104869897A (en) | System and method for monitoring and controlling a state of a patient during and after administration of anesthetic compound | |
| CN113035353A (en) | Digital twin health management system | |
| CN110827950B (en) | Method for determining dosage of anesthetic, method for training model, and model | |
| CN114177414A (en) | Intelligent adult anesthesia target control method and system based on electroencephalogram signal monitoring | |
| US20220172721A1 (en) | Medical device and medical device system | |
| WO2023123437A1 (en) | Anesthesia control system, anesthesia system, and non-transitory computer readable medium | |
| US12053295B2 (en) | Tracking nociception under anesthesia using a multimodal metric | |
| CN109714419A (en) | A kind of vehicle-mounted health detection system and its method | |
| CN116747377B (en) | Closed-loop intelligent anesthesia control system | |
| CN2873238Y (en) | Intelligent full vein anaesthesia machine |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181218 |
|
| WD01 | Invention patent application deemed withdrawn after publication |