CN117219227A - Anesthesia administration control method and control system based on fuzzy neural network - Google Patents
Anesthesia administration control method and control system based on fuzzy neural network Download PDFInfo
- Publication number
- CN117219227A CN117219227A CN202311486130.6A CN202311486130A CN117219227A CN 117219227 A CN117219227 A CN 117219227A CN 202311486130 A CN202311486130 A CN 202311486130A CN 117219227 A CN117219227 A CN 117219227A
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- anesthetic
- neural network
- parameters
- fuzzy neural
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 40
- 206010002091 Anaesthesia Diseases 0.000 title claims abstract description 34
- 230000037005 anaesthesia Effects 0.000 title claims abstract description 34
- 230000003444 anaesthetic effect Effects 0.000 claims abstract description 54
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 230000035790 physiological processes and functions Effects 0.000 claims abstract description 12
- 230000001105 regulatory effect Effects 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 9
- 230000036772 blood pressure Effects 0.000 claims description 7
- 230000036760 body temperature Effects 0.000 claims description 7
- 210000004556 brain Anatomy 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 230000036387 respiratory rate Effects 0.000 claims description 5
- 230000001276 controlling effect Effects 0.000 claims description 3
- 201000010099 disease Diseases 0.000 claims description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 2
- 238000002347 injection Methods 0.000 claims description 2
- 239000007924 injection Substances 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 206010021118 Hypotonia Diseases 0.000 description 3
- 238000002695 general anesthesia Methods 0.000 description 3
- 230000036640 muscle relaxation Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 208000024827 Alzheimer disease Diseases 0.000 description 1
- 208000028389 Nerve injury Diseases 0.000 description 1
- 208000012902 Nervous system disease Diseases 0.000 description 1
- 208000025966 Neurological disease Diseases 0.000 description 1
- 208000026301 Postoperative Cognitive Complications Diseases 0.000 description 1
- 206010039897 Sedation Diseases 0.000 description 1
- 206010039966 Senile dementia Diseases 0.000 description 1
- 230000036592 analgesia Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008764 nerve damage Effects 0.000 description 1
- 230000036407 pain Effects 0.000 description 1
- 230000035485 pulse pressure Effects 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 230000011514 reflex Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000036280 sedation Effects 0.000 description 1
- 230000035882 stress Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The application relates to an anesthesia administration control method and system based on a fuzzy neural network, compared with the prior art: 1. according to the application, the fuzzy neural network is adopted for training, the comprehensive physiological state of a testee at the next time point is predicted, and the dosage of the anesthetic is regulated in real time according to the output parameters, so that the problems of larger error and larger noise caused by the traditional detection control method can be solved, and the dosage of the anesthetic can be accurately controlled; 2. the overall optimization parameters are set, when the overall optimization parameters reach preset parameters, the administration is stopped, the condition that the administration quantity of the anesthetic of a patient exceeds the standard caused by the continuous administration according to the current result is prevented, and meanwhile, the overall optimization parameters can be used as one of control parameters for fuzzy neural network parameter training; 3. the defect that the dosage of the anesthetic is judged according to a single physiological parameter in the prior art is avoided, and the physiological state of a patient after the anesthetic is injected is comprehensively predicted by combining a plurality of physiological parameters, so that the robustness and the accuracy of a prediction system are improved.
Description
Technical Field
The application relates to the field of anesthesia medicine, in particular to an anesthesia administration control method and system based on a fuzzy neural network.
Background
General anesthesia is a special and complex state involving many factors including sedation, analgesia, muscle relaxation, stress inhibition, etc., through the processes of general anesthesia induction, maintenance and recovery. The whole general anesthesia process is controlled by the dosage of anesthesia administration. When the anesthesia administration is insufficient, the anesthesia is too shallow, so that the pain of a patient in the operation is greatly increased, and sudden body movement is unfavorable for the normal operation. In contrast, when the amount of anesthetic administered is too large, it may cause excessive anesthesia, resulting in delayed patient recovery, postoperative cognitive dysfunction and other potential cardiovascular and cerebrovascular or neurological diseases, causing irreversible damage to the patient's body. Therefore, how to effectively detect the anesthetic state and accurately control the dosage of the anesthetic in real time in the effective detection state is a technical problem to be solved by those skilled in the art.
The traditional anesthesia state detection is based on experience judgment of an anesthesiologist, for example, whether the heart rate of a patient is normal, whether the blood pressure is low, whether the breathing is normal, whether the pupil is astigmatic, whether the body movement is moving or not, and the like, and judgment is given by combining the physiological parameter characteristics, but the index comprehensive judgment method has certain limitations and poor effect, and is difficult for a practicing doctor to operate in a short period of time. Along with the development of anesthesia, the prior art also shows higher judging methods based on brain wave analysis, nerve potential analysis or muscle relaxation state judgment and the like, and the dosage time of the anesthetic are timely controlled through the judging methods, but the methods are mainly based on the current parameter acquisition to judge the current anesthesia result, and the physiological state change and the dosage of the anesthetic of a patient in the next time period are difficult to accurately predict, so that the methods can bring larger errors and larger noise in the actual operation process, and can not accurately control the dosage of the anesthetic.
Disclosure of Invention
Aiming at the defects and problems in the background technology, the application provides an anesthesia administration control method and a control system based on a fuzzy neural network, and the specific technical scheme is as follows:
an anesthesia administration control method based on a fuzzy neural network comprises the following steps:
step S1: data acquisition and information input: starting from the injection of anesthetic by a testee, carrying out real-time data acquisition on multiple physiological indexes of the testee, and carrying out data input: the physiological indexes at least comprise brain wave frequency Phead, heart rate Pheart, respiratory rate ζ1, pulse frequency ζ2, blood pressure P and body temperature T of the front moment of the testee; the information input comprises two aspects, namely, identity information (including age, sex and disease type) of the testee and anesthetic information (including type of anesthetic and pre-use dosage));
Step S2: data preprocessing: normalizing the multiple physiological index data to obtain a data setIn particular, normalizing parametersThe method comprises the following steps:
(1)
wherein Y represents a physiological index value before normalization, X represents a physiological index after normalization, a subscript "t" represents a certain time point, and a subscript "i" represents an ith item.
Step S3: the preprocessed data set in the step S2As input parameters, the number of neurons and training times are set, and the set neurons and training times are imported into a fuzzy neural network, and training is performed based on a fuzzy prediction algorithm;
since the change of the anesthetic state with time is nonlinear, in the above step S3, in order to achieve accurate prediction, a T-S prediction model is preferable, and a fuzzy function of the nonlinear prediction in the T-S model is as follows:
(2)
in the above formula, f () and g () are smooth nonlinear functions, u is an output value in the fuzzy prediction algorithm, where the format of g () is:
(3)
step S4: normalized parameters in a datasetLearning the anesthetic dosage at the current moment, and updating various parameters of the fuzzy network;
step S5: on the basis of step S4, calculating global optimization parameter ψ, and judging whether ψ reaches a preset threshold valueAnd judging whether to administer the anesthetic at the next moment according to the result, if so, stopping injecting the anesthetic, and if not, adjusting the administration amount S according to the current global optimization parameter ψ.
(4)
In the formula, the coefficient ai is obtained by repeatedly and iteratively solving the fuzzy neural network under the condition of given initial parameters, and the psi (t) is used as a control parameter in the training process of the neural network.
The anesthesia administration control system based on the fuzzy neural network comprises a parameter acquisition module, a communication module, a calculation module, a visual input module and an administration control module, wherein the parameter acquisition module is used for acquiring physiological state parameters of a testee in real time from the administration time of a patient, the parameter acquisition module is connected with the communication module, converts multiple physiological parameters into electric signals, uploads the electric signals to the calculation module through the communication module, simultaneously, inputs identity information and anesthetic information of the testee through the visual input module, the visual input module is electrically connected with the calculation module, the identity information and the anesthetic information are stored in the calculation module, and on the basis, the calculation module performs data preprocessing and fuzzy training on the received physiological state parameters and adjusts the administration amount according to the actual output value of the fuzzy neural network.
In summary, the anesthesia administration control method and the anesthesia administration control system based on the fuzzy neural network have the following technical effects compared with the prior art:
1) According to the application, training is performed based on the fuzzy neural network, the comprehensive physiological state of a testee at the next time point is predicted, and the dosage of the anesthetic is adjusted in real time according to the output parameters obtained by the fuzzy neural network, so that the problems of larger error and larger noise caused by the traditional detection control method can be solved, and meanwhile, the dosage of the anesthetic can be accurately controlled;
2) The application sets the global optimization parameter, stops dosing when the global optimization parameter reaches the preset parameter, prevents the dosage of the anesthetic of the patient from exceeding the standard caused by continuous dosing according to the current result, and simultaneously, the global optimization parameter can be used as one of the control parameters for the fuzzy neural network parameter training;
3) The application avoids the defect that the dosage of the anesthetic is judged according to only a single physiological parameter in the prior art, and the current physiological state of the patient after the anesthetic is injected is comprehensively predicted by combining a plurality of physiological parameters, so that the robustness and the accuracy of the whole prediction system are improved.
Drawings
FIG. 1 is a flow chart of an anesthesia administration control method based on a fuzzy neural network according to the present application;
fig. 2 is a system diagram of an anesthesia administration control system based on a fuzzy neural network according to the present application.
Detailed Description
The present application will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present application, but are not intended to limit the application in any way. It should be noted that variations and modifications can be made by those skilled in the art without departing from the spirit of the application, which falls within the scope of the application.
Referring to fig. 1, a method for controlling anesthesia administration based on a fuzzy neural network includes the following steps:
step S1: data acquisition and information input: starting calculation when the anesthetic is injected into a tested person, carrying out real-time data acquisition on a plurality of physiological indexes of a patient: brain wave frequency Phead, heart rate Pheart, respiratory rate ζ1, pulse frequency ζ2, blood pressure P, body temperature T at the present moment; information entry includes two aspects: firstly, identity information (including age, sex and disease type) of a subject, and secondly, anesthetic information (including type of anesthetic, pre-dose);
It should be pointed out that, through a large number of clinical practices, the physiological parameters selected by the application are all the physiological parameters most closely corresponding to the physiological reaction after anesthetic anesthesia, and the body movement parameters are influenced by the complexity of patients (such as senile dementia, nerve injury and the like) and belong to image parameters, so that the treatment process is complex and larger noise is brought, and therefore, the physiological parameter acquisition of the scheme does not include the parameters.
Step S2: data preprocessing: normalizing the multiple physiological index data to obtain a data setSpecifically, the parameters are normalized at time t+1The method comprises the following steps:
(1)
wherein Y represents a physiological index value before normalization, X represents a physiological index after normalization, a subscript "t" represents a certain time point, and a subscript "i" represents an ith item.
Step S3: the preprocessed data set in the step S2As input parameters, the number of neurons and training times are set, and the set neurons and training times are imported into a fuzzy neural network for training;
since the change of the anesthetic state with time is nonlinear, in the step S3, in order to realize accurate prediction, the present application adopts a T-S prediction model, and the fuzzy function of the nonlinear prediction is as follows:
(2)
in the above formula, f () and g () are smooth nonlinear functions, u is an output value in the fuzzy prediction algorithm, where the format of g () is:
(3)
step S4: normalized parameters in a datasetLearning the anesthetic dosage at the current moment, and updating various parameters of the fuzzy network;
step S5: on the basis of step S4, calculating global optimization parameter ψ, and judging whether ψ reaches a preset threshold valueAnd judging whether to administer the anesthetic at the next moment according to the result, if so, stopping injecting the anesthetic, and if not, adjusting the administration amount S according to the current global optimization parameter ψ.
(4)
In the formula, the coefficient ai is obtained by repeatedly and iteratively solving the fuzzy neural network under the condition of given initial parameters, and the psi (t) is used as a control parameter in the training process of the neural network.
In the above step S3, the basic steps of the fuzzy prediction algorithm are as follows:
1) Input defining system stateAnd a domain of the output value u, a membership function and a fuzzy prediction rule, wherein the subscript "t" represents a certain time point, and the subscript "i" represents an ith physiological index;
2) Will actually inputAnd the output value u is mapped as an input in the fuzzy push theory domainAnd output of;
3) Determination ofIs a fuzzy subset of the roles of (a)Andfuzzy predictive rules for actionsFuzzy predictive rulesThe structure is the same as that of the fuzzy rule table (shown in table 1), and the fuzzy rule matrix is established by setting initial values based on the existing fuzzy rules, and the fuzzy subset is determined based on the initial valuesAnd;
4) Calculating membership value of each action ruleThe calculation is shown in formula (5):
(5)
5) Based on the step 4), performing defuzzification by using a gravity center method to obtain a fuzzy output quantityAs shown in formula (6):
(6)
in the method, in the process of the application,the value u is output for the kth rule of action.
6) Output obtained by fuzzy predictionThe actual output value u is mapped as an adjustment value of the flow difference deltas, and at the time t+1 deltas, the actual output value u has the following relationship with the fuzzy inference output value u:
(7)
(8)
wherein, each language variable value of E, EC and u is selected, the positive value is PB, the middle value is PM, the positive value is PS, the negative value is NS, the negative value is NM, the negative value is NB, and under the determination of the language variable value, the assignment of u is shown in table 1:
TABLE 1 fuzzy rule TABLE
u | PB | PM | PS | NS | NM | NB |
PB | 2 | 2 | 2 | 1 | 0 | -1 |
PM | 2 | 1 | 2 | 1 | 1 | -1 |
PS | 2 | 1 | 0 | 1 | 0 | 1 |
NS | 1 | 0 | -1 | -1 | 1 | -1 |
NM | 1 | 0 | -1 | 0 | 1 | -2 |
NB | 0 | 1 | 0 | -1 | -2 | -2 |
At time t, when ψ reaches a preset thresholdWhen the patient is in the next preset time, the patient/patient is in a complete anesthesia state, and the operation can be implemented; if ψ is not up to the preset thresholdThe dosage S is adjusted according to the actual output value u, namelyOr (b)Specifically, the fuzzy controller can input a feedback adjusting signal to an adjusting end, and the dosage of anesthetic is adjusted in real time through the micro valve/flow adjusting valve, and the adjusting process is mainly based on the acquisition of the current physiological parameters, and parameter training is carried out through the fuzzy neural network, so that the prediction of the fuzzy adjusting quantity at the next moment is realized.
In the prior art, based on brain wave analysis, nerve potential analysis or muscle relaxation state judgment, the method for controlling the dosage and the dosage time of the anesthetic by combining with a neural network algorithm or other algorithms is mainly based on the judgment of the current anesthetic result by current parameter acquisition, and obviously lacks prospective or prediction functions, firstly, the physiological state change and the anesthetic dosage of a patient in the next time period cannot be accurately predicted, and secondly, the method is mainly linear regulation (after the anesthetic is injected, the change of a plurality of physiological parameters with time is obviously nonlinear, such as the body temperature of the patient, when the anesthetic is injected to a certain extent, the parameters tend to be stable, and the body temperature cannot be reduced too low), so that the method can bring larger errors and noise in the actual operation process, and can not accurately control the dosage of the anesthetic. According to the technical scheme, the current physiological parameter information of the patient is collected, normalized and then led into a network to be subjected to fuzzy training and anti-fuzzy treatment, and finally, the fuzzy output quantity for adjusting the anesthetic dosage at the time t+1 can be obtained at the time t.
Referring to fig. 2, further, on the basis of the anesthesia administration control method based on the fuzzy neural network, an anesthesia administration control system based on the fuzzy neural network is provided, and the control system comprises a parameter acquisition module, a communication module, a calculation module, a visual input module and an administration control module, wherein the parameter acquisition module is used for acquiring physiological state parameters of a testee in real time from the time of administration of the patient, the parameter acquisition module is connected with the communication module, converts a plurality of physiological parameters into electric signals, uploads the electric signals to the calculation module through the communication module, meanwhile, identity information and anesthetic information of the testee are input through the visual input module, the visual input module is electrically connected with the calculation module, the identity information and the anesthetic information are stored in the calculation module, and on the basis, the calculation module performs data preprocessing and fuzzy training on the received physiological state parameters and adjusts the administration amount according to the actual output value of the fuzzy neural network.
The parameter acquisition module at least comprises a test chip for measuring brain wave frequency, a heart rate sensor for measuring heart rate, a sensor for measuring respiratory rate, a sphygmomanometer for measuring pulse frequency and pulse pressure band, a blood pressure meter for measuring blood pressure and a temperature sensor for measuring body temperature.
The administration control module is a micro-control valve or a flow regulating valve and is used for regulating the administration amount of the anesthetic.
It should be understood by those skilled in the art that the foregoing embodiments only describe the best mode for implementing the present application, and are not limited to the foregoing technical solutions, but other technical solutions formed by any combination of the foregoing technical features or their equivalents without departing from the basic concept of the present application, for example, technical solutions formed by replacing the foregoing technical features with technical features having similar functions of the present application, and the scope of the present application is determined by the technical solutions covered by the claims.
Claims (9)
1. An anesthesia administration control method based on a fuzzy neural network is characterized by comprising the following steps:
step S1: data acquisition and information input: starting from the injection of anesthetic by the testee, carrying out real-time data acquisition on multiple items of physiological index data of the testee, and carrying out information input;
step S2: data preprocessing: normalizing the multiple physiological index data to obtain a data setWherein, the subscript "t" represents a certain time point, and the subscript "i" represents the ith physiological index;
step S3: the preprocessed data set in the step S2As input parameters, the number of neurons and training times are set, and the set neurons and training times are imported into a fuzzy neural network, and training is performed based on a fuzzy prediction algorithm;
step S4: normalized parameters in a datasetDeep learning is carried out on the anesthetic dosage at the current moment, and various parameters of the fuzzy network are updated;
step S5: on the basis of step S4, calculating global optimization parameter ψ, and judging whether ψ reaches a preset threshold valueJudging whether to administer anesthetic at the next moment according to the result, if so, stopping injecting anesthetic, otherwise, adjusting the administration amount according to the current global optimization parameter ψS。
2. The anesthesia administration control method based on the fuzzy neural network according to claim 1, wherein in the step S1, the physiological index at least comprises brain wave frequency Phead, heart rate Pheart, respiratory rate ζ1, pulse frequency ζ2, blood pressure P and body temperature T of the subject at the current moment, and the information input comprises identity information of the subject and anesthetic information used by the subject.
3. The method for controlling the administration of anesthesia based on the fuzzy neural network according to claim 2, wherein the identity information includes age, sex and disease type, and the anesthetic information includes the type of anesthetic and the pre-dose。
4. The anesthesia administration control method based on the fuzzy neural network according to claim 1, wherein in step S2The normalization process is shown in formula (1):
(1)
wherein Y represents a physiological index value before normalization, X represents a physiological index after normalization, a subscript "t" represents a certain time point, and a subscript "i" represents an ith item.
5. The anesthesia administration control method based on the fuzzy neural network according to claim 1, wherein in the step S3, in order to realize accurate prediction, a T-S prediction model is adopted, and a fuzzy function of nonlinear prediction in the T-S prediction model is as follows:
(2)
in the above formula, f () and g () are smooth nonlinear functions, u is an output value in the fuzzy prediction algorithm, where the format of g () is:
(3)。
6. the anesthesia administration control method based on the fuzzy neural network according to claim 1, wherein the step of the fuzzy prediction algorithm in the step S3 specifically comprises:
1) Input defining system stateAnd the domain of the output value u, membership functions and fuzzy prediction rules;
2) Will actually inputAnd the output value u is mapped as input +.>And output->;
3) Determination ofIs a fuzzy subset->And->And its action fuzzy predictive rule->;
4) Calculating membership value of each action ruleThe calculation is shown in formula (5):
(5)
5) Based on the step 4), performing defuzzification by using a gravity center method to obtain a fuzzy output quantityAs in formula (6):
(6)
in the method, in the process of the application,outputting a value u for the kth action rule;
6) Output obtained by fuzzy predictionThe actual output value u is mapped as an adjustment value of the flow difference deltas, and at the time t+1 deltas, the actual output value u has the following relationship with the fuzzy inference output value u:
(7)
(8)。
7. an anesthesia administration control system based on a fuzzy neural network, which adopts the anesthesia administration control method based on the fuzzy neural network as claimed in any one of claims 1-6, and is characterized in that the control system comprises a parameter acquisition module, a communication module, a calculation module, a visual input module and an administration control module, wherein the parameter acquisition module is used for acquiring physiological state parameters of a testee in real time from the moment of administration of the patient, the parameter acquisition module is connected with the communication module, converts a plurality of physiological parameters into electric signals, the electric signals are uploaded to the calculation module through the communication module, meanwhile, identity information and anesthetic information of the testee are input through the visual input module, the visual input module is electrically connected with the calculation module, the identity information and the anesthetic information are stored in the calculation module, and on the basis, the calculation module performs data preprocessing and fuzzy training on the received physiological state parameters and adjusts the administration amount according to the actual output value of the fuzzy neural network.
8. The anesthesia administration control system based on a fuzzy neural network according to claim 7, wherein the parameter acquisition module at least comprises a test chip for measuring brain wave frequency, a heart rate sensor for measuring heart rate, a sensor for measuring respiratory rate, a sphygmomanometer for measuring pulse frequency tourniquet, blood pressure and a temperature sensor for measuring body temperature.
9. The anesthesia administration control system based on a fuzzy neural network according to claim 7, wherein the administration control module is a micro-control valve or a flow regulating valve, and the administration control module is used for regulating the administration amount of the anesthetic.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311486130.6A CN117219227B (en) | 2023-11-09 | 2023-11-09 | Anesthesia administration control system based on fuzzy neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311486130.6A CN117219227B (en) | 2023-11-09 | 2023-11-09 | Anesthesia administration control system based on fuzzy neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117219227A true CN117219227A (en) | 2023-12-12 |
CN117219227B CN117219227B (en) | 2024-01-23 |
Family
ID=89039392
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311486130.6A Active CN117219227B (en) | 2023-11-09 | 2023-11-09 | Anesthesia administration control system based on fuzzy neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117219227B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE19829018A1 (en) * | 1998-06-30 | 2000-01-13 | Markus Lendl | System for the control of the anesthesia of a patient during surgery |
US20130150748A1 (en) * | 2010-07-23 | 2013-06-13 | Quantium Medical S.L. | Apparatus for combining drug effect interaction between anaesthetics and analgesics and electroencephalogram features for precise assessment of the level of consciousness during anaesthesia |
CN103637798A (en) * | 2013-12-17 | 2014-03-19 | 山东大学齐鲁医院 | DOA (depth of anesthesia) monitoring device |
WO2015079355A1 (en) * | 2013-11-26 | 2015-06-04 | Koninklijke Philips N.V. | Methods for estimating dosage of anesthetic agent and for determining depth of anesthesia |
KR20210066271A (en) * | 2019-11-28 | 2021-06-07 | 엠텍글로벌 주식회사 | Order system using medical deep learning in the field of anesthesia |
CN116548920A (en) * | 2023-05-04 | 2023-08-08 | 上海交通大学医学院附属仁济医院 | Anesthesia state monitoring system and method based on neural network |
-
2023
- 2023-11-09 CN CN202311486130.6A patent/CN117219227B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE19829018A1 (en) * | 1998-06-30 | 2000-01-13 | Markus Lendl | System for the control of the anesthesia of a patient during surgery |
US20130150748A1 (en) * | 2010-07-23 | 2013-06-13 | Quantium Medical S.L. | Apparatus for combining drug effect interaction between anaesthetics and analgesics and electroencephalogram features for precise assessment of the level of consciousness during anaesthesia |
WO2015079355A1 (en) * | 2013-11-26 | 2015-06-04 | Koninklijke Philips N.V. | Methods for estimating dosage of anesthetic agent and for determining depth of anesthesia |
CN103637798A (en) * | 2013-12-17 | 2014-03-19 | 山东大学齐鲁医院 | DOA (depth of anesthesia) monitoring device |
KR20210066271A (en) * | 2019-11-28 | 2021-06-07 | 엠텍글로벌 주식회사 | Order system using medical deep learning in the field of anesthesia |
CN116548920A (en) * | 2023-05-04 | 2023-08-08 | 上海交通大学医学院附属仁济医院 | Anesthesia state monitoring system and method based on neural network |
Non-Patent Citations (4)
Title |
---|
丁正敏;熊冬生;王小红;钟炳艺;张兴安;: "基于模糊自适应PID控制的麻醉靶控输注智能化研究", 中国医学物理学杂志, vol. 33, no. 7, pages 726 - 732 * |
徐瑾;邓晓明;晏馥霞;: "机器学习算法在麻醉领域的应用", 中国医学科学院学报, vol. 42, no. 5, pages 696 - 701 * |
李敏;叶志前;: "基于模糊神经网络的麻醉深度的监测研究", 中国医疗器械杂志, vol. 30, no. 4, pages 253 - 255 * |
李敏;潘慧平;叶志前;: "探讨模糊神经网络在麻醉监测中的应用", 中国医疗器械信息, vol. 13, no. 9, pages 5 - 10 * |
Also Published As
Publication number | Publication date |
---|---|
CN117219227B (en) | 2024-01-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Jindal et al. | An adaptive deep learning approach for PPG-based identification | |
Mendez et al. | Sleep apnea screening by autoregressive models from a single ECG lead | |
EP3783619A1 (en) | Human body health assessment method and system based on sleep big data | |
CN110251801A (en) | A kind of eyeshade reaction type microcurrent stimulating sleeping-assisting system | |
CN110547868B (en) | Continuous anesthesia device | |
CN110289094B (en) | Expert rule-based insulin accurate administration decision method | |
CN108721048A (en) | Rehabilitation training control method, computer readable storage medium and terminal | |
CN115299881A (en) | Monitoring and regulating system and method for anesthesia maintenance period | |
CN111798956B (en) | Decision determining method, device and system for artificial intelligence anesthesia | |
KR20210066271A (en) | Order system using medical deep learning in the field of anesthesia | |
Wang et al. | Inference of brain states under anesthesia with meta learning based deep learning models | |
Fadiyah et al. | Classification of motor imagery and synchronization of post-stroke patient EEG signal | |
CN116548920A (en) | Anesthesia state monitoring system and method based on neural network | |
CN117219227B (en) | Anesthesia administration control system based on fuzzy neural network | |
CN109727670A (en) | A kind of intelligence stroke rehabilitation monitoring method and system | |
WO2021047912A1 (en) | Method for training a model usable to compute an index of nociception | |
CN116913461A (en) | Anesthesia medicine dosage prediction method based on deep learning | |
CN115282401B (en) | Intravenous infusion pump control system, intravenous infusion pump control method, and storage medium | |
WO2023123437A1 (en) | Anesthesia control system, anesthesia system, and non-transitory computer readable medium | |
CN116807392A (en) | Multimode anesthesia monitoring system | |
CN112354042A (en) | Analgesia pump flow control method and device | |
Zhang et al. | Depth of anesthesia control with fuzzy logic | |
CN113080945A (en) | Parkinson patient disease monitoring method and system | |
Vaezi et al. | AS3-SAE: Automatic Sleep Stages Scoring using Stacked Autoencoders | |
CN116705230B (en) | MDI decision system and method with insulin sensitivity adaptive estimation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |