[go: up one dir, main page]

CN119302616A - A sensor-based anesthesia depth monitoring method and system - Google Patents

A sensor-based anesthesia depth monitoring method and system Download PDF

Info

Publication number
CN119302616A
CN119302616A CN202411876651.7A CN202411876651A CN119302616A CN 119302616 A CN119302616 A CN 119302616A CN 202411876651 A CN202411876651 A CN 202411876651A CN 119302616 A CN119302616 A CN 119302616A
Authority
CN
China
Prior art keywords
anesthesia
target patient
medicine
preset
drug
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
Application number
CN202411876651.7A
Other languages
Chinese (zh)
Other versions
CN119302616B (en
Inventor
蔡利民
珠一暘
张焰
章陈胜
李行能
梁凡
珠淮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Yizhou Medical Technology Co ltd
Zhejiang Pearlcare Medical Technology Co ltd
Original Assignee
Zhejiang Yizhou Medical Technology Co ltd
Zhejiang Pearlcare Medical Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Yizhou Medical Technology Co ltd, Zhejiang Pearlcare Medical Technology Co ltd filed Critical Zhejiang Yizhou Medical Technology Co ltd
Priority to CN202411876651.7A priority Critical patent/CN119302616B/en
Publication of CN119302616A publication Critical patent/CN119302616A/en
Application granted granted Critical
Publication of CN119302616B publication Critical patent/CN119302616B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Medicinal Chemistry (AREA)
  • Anesthesiology (AREA)
  • Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Biophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention discloses a sensor-based anesthesia depth monitoring method and system, which relate to the technical field of anesthesia depth monitoring, and the method comprises pre-operation anesthesia preparation and intra-operation anesthesia monitoring, wherein firstly, pre-operation preparation data of a target patient is analyzed, an initial anesthesia scheme is set, secondly, initial nerve characteristic data of the target patient is collected, and the initial nerve characteristic data is analyzed based on an anesthesia initial model to judge operation starting time, and then, in the operation process, the intraoperative physiological characteristic data and the intraoperative nerve characteristic data of a target patient are collected, whether anesthesia abnormality exists or not is judged based on an intraoperative anesthesia model, if anesthesia abnormality is found, a corresponding anesthesia medicine supply changing scheme is set according to a medicine replacement model, and the method improves the anesthesia effectiveness and safety by monitoring and processing the anesthesia depth abnormality in real time.

Description

Sensor-based anesthesia depth monitoring method and system
Technical Field
The invention relates to the technical field of anesthesia depth monitoring, in particular to an anesthesia depth monitoring method and system based on a sensor.
Background
In the operation process, the anesthesiologist needs to closely monitor vital signs and anesthesia depth of the patient to ensure that the operation is performed smoothly and reduce the risk of the patient, so that the anesthesiologist needs to adjust anesthesia of the patient according to the monitoring result of the anesthesia depth monitor to improve safety and comfort of the patient during the operation.
The prior art, such as the patent application of the publication No. CN116982937A, discloses a deep learning-based perioperative anesthesia depth monitoring system, which relates to the technical field of anesthesia depth monitoring and comprises an electroencephalogram analysis module, an electrocardiogram analysis module and a deep learning model training module, wherein the electroencephalogram analysis module is used for analyzing an acquired electroencephalogram, obtaining energy of different waves by converting electroencephalogram signals into spectrograms, calculating power spectral density indexes of the electroencephalogram through the energy of the different waves, the electrocardiogram analysis module is used for obtaining energy of different frequency intervals by calculating power spectral density of the signals at each frequency point, and finally calculating the power spectral density indexes of the electrocardiogram, and the deep learning model training module is used for learning nonlinear relations between physiological signals and anesthesia depth by establishing a deep learning model and training, so as to generate anesthesia depth scores. The invention aims to monitor the anesthesia depth and vital sign index of a patient in real time, comprehensively evaluate the anesthesia depth in the perioperative period more comprehensively and ensure the safety and comfort of the patient in the operation period.
1, The above-mentioned scheme is not through carrying on the analysis to the monitoring data of the goal patient in the stage of preparing before the operation, can't carry on the suggestion to the staff when the anesthesia degree of the goal patient reaches and can't guarantee to carry on the operation in time, the patient accepts excessive anesthetic agent easily, on the one hand because the excessive anesthetic agent causes Cheng Duguo to be dark, increase the duration that the nerve of postoperative patient resumes, reduced patient's postoperative comfort in the recovery period, on the other hand because the excessive anesthetic agent can harm patient's physical health, reduced the security of anesthesia.
2. The invention only prompts when the anesthesia depth is too shallow or too deep, and does not control the anesthetic according to the physiological signal data and the nerve response data, so that on one hand, the timeliness of replacement of the anesthetic is reduced, on the other hand, the judgment is needed manually, the effectiveness of the data is reduced, and meanwhile, the invention does not consider the tolerance of a patient to the medicine according to the physiological signal data, and the medicine possibly causes abnormal physiological response when the deep anesthesia is not achieved, and can not be replaced timely, so that the safety is reduced.
Disclosure of Invention
Aiming at the technical defects, the invention aims to provide an anesthesia depth monitoring method and system based on a sensor.
In order to solve the technical problems, the invention provides a sensor-based anesthesia depth monitoring method, which comprises the following steps of firstly, pre-operation anesthesia preparation, namely collecting pre-operation preparation data of a target patient, analyzing the pre-operation preparation data of the target patient to obtain each anesthesia method of the target patient, and setting an initial anesthesia scheme of the target patient according to each anesthesia method of the target patient and historical anesthesia records in a database.
Collecting initial nerve characteristic data of a target patient, analyzing the initial nerve characteristic data of the target patient based on an anesthesia initial model, judging operation starting time, collecting the intraoperative physiological characteristic data and the intraoperative nerve characteristic data of the target patient in the operation process, analyzing the intraoperative physiological characteristic data and the intraoperative nerve characteristic data of the target patient based on an intraoperative anesthesia model, judging whether anesthesia is abnormal or not, and setting an anesthesia medicine supply changing scheme based on a medicine replacement model when the anesthesia is abnormal.
Preferably, the analysis is performed on the intraoperative physiological characteristic data and the intraoperative nerve characteristic data of the target patient, wherein the specific analysis process comprises the steps that the intraoperative physiological characteristic data of the target patient comprises the numerical value of each physiological parameter and the intraoperative forehead temperature, the intraoperative nerve characteristic data of the target patient comprises the numerical value of each electroencephalogram parameter and the frequency of the intraoperative nystagmus, the intraoperative anesthesia model comprises a physiological reaction model and a nerve reaction model, the intraoperative physiological characteristic data of the target patient is input into the physiological reaction model to obtain the output result of the intraoperative physiological reaction grade model of the target patient, the output result comprises the numerical values of 0 and 1, the intraoperative physiological characteristic data of the target patient is input into the nerve reaction model to obtain the output result of the nerve reaction model of the target patient, and the output result comprises the numerical values of-1, 0 and 1.
If the output results of the nerve response model and the physiological response model of the target patient are 0, the anesthesia in the operation is normal.
If the output result of the nerve reaction model or the physiological reaction model of the target patient is not 0, indicating that the anesthesia is abnormal during operation, wherein if the output result of the nerve reaction model of the target patient is-1 and the output result of the physiological reaction model of the target patient is 0, indicating that the anesthesia dosage is too low, the medicine dosage needs to be increased, if the output result of the nerve reaction model of the target patient is-1 and the output result of the physiological reaction model of the target patient is 1, indicating that the anesthesia medicine is intolerant, prompting a worker to replace the medicine, and if the output result of the nerve reaction model of the target patient is 1, indicating that the anesthesia dosage is excessive and the medicine dosage needs to be reduced.
Preferably, the anesthesia medicine supply changing scheme is set, and the method specifically comprises the steps of obtaining historical patient use times of each medicine used by a target patient and average use dosage of each medicine used by the target patient from a database, substituting the historical patient use times and the average use dosage of each medicine used by the target patient into a calculation formula, and obtaining the use index of each medicine used by the target patient.
If the drug supply amount of the target patient needs to be increased, the use drug with the highest use index is increased by the preset supply amount, and if the drug supply amount of the target patient needs to be decreased, the use drug with the highest use index is decreased by the preset supply amount.
If the target patient needs to be replaced by the medicine, according to an analysis method of the usage index of each usage medicine of the target patient, the usage index of each standby medicine of the target patient is obtained, the usage medicine of the minimum usage index of the target patient is recorded as the medicine to be replaced, the standby medicine of the maximum usage index of the target patient is recorded as the preset usage medicine, meanwhile, the usage data of each usage medicine is obtained from a database, the usage data of each usage medicine comprises the common usage times of each usage medicine and the medicine to be replaced, the maximum usage times of each usage medicine and the medicine to be replaced are further included, the common usage times of each usage medicine and the medicine to be replaced are further included, the maximum usage times of each usage medicine and the preset usage medicine are further included, the usage data of each usage medicine is input into a medicine replacement model, the output result of each usage medicine is obtained, the numerical value of the output result comprises-1, 0 and 1, each usage medicine output result is positive usage medicine is respectively, each usage result is respectively positive usage medicine, each usage result is respectively output is respectively preset for the preset usage reduction amount, each usage medicine to be replaced by the preset medicine is adjusted to be negative and the preset medicine to be required to be replaced, and the number of the preset medicine is adjusted to be negative and the medicine to be replaced by the preset medicine is adjusted according to the negative.
On the other hand, the invention provides a sensor-based anesthesia depth monitoring system, which comprises a preoperative anesthesia preparation module, a target patient anesthesia preparation module and a sensor-based anesthesia depth monitoring module, wherein the preoperative anesthesia preparation module is used for acquiring preoperative preparation data of the target patient, analyzing the preoperative preparation data of the target patient to obtain each anesthesia method of the target patient, and setting an initial anesthesia scheme of the target patient according to each anesthesia method of the target patient and historical anesthesia records in a database.
The intraoperative anesthesia monitoring module is used for collecting initial nerve characteristic data of a target patient, analyzing the initial nerve characteristic data of the target patient based on an anesthesia initial model, judging operation starting time, collecting intraoperative physiological characteristic data and intraoperative nerve characteristic data of the target patient in an operation process, analyzing the intraoperative physiological characteristic data and the intraoperative nerve characteristic data of the target patient based on an intraoperative anesthesia model, judging whether anesthesia is abnormal, and setting an anesthesia medicine supply changing scheme when the anesthesia is abnormal.
The method has the advantages that 1, firstly, pre-operation preparation data of a target patient are analyzed, an initial anesthesia scheme is set, secondly, initial nerve characteristic data of the target patient are collected, the initial nerve characteristic data are analyzed based on an anesthesia initial model, operation starting time is judged, then, in the operation process, the intraoperative physiological characteristic data and the intraoperative nerve characteristic data of the target patient are collected, whether anesthesia abnormality exists or not is judged based on the intraoperative anesthesia model, and if anesthesia abnormality is found, a corresponding anesthesia medicine supply changing scheme is set according to a medicine replacement model.
2. The invention monitors the physiological response data and the nerve response data of the target patient in operation, can timely identify the current abnormal anesthesia, judges the type of the abnormal anesthesia through analyzing the physiological response data and the nerve response data of the target patient, and changes the anesthesia drug supply according to the abnormal anesthesia, not only judges the anesthesia depth according to the nerve response data and changes the drug supply quantity when the anesthesia is too deep or too shallow, but also considers the tolerance of the patient to the drug according to the physiological response data, and timely changes the drug when the target patient receives the abnormal physiological response to certain drugs, thereby improving the safety of deep anesthesia and reducing the possibility of risk of the patient in the postoperative recovery period.
3. According to the invention, through analyzing the medicine usage data in the operation, the medicine replacement is carried out, the requirement of a patient on narcotics can be met, the possibility of adverse reactions in the operation is reduced, and meanwhile, the relevance of each medicine is judged through the medicine usage data, so that the medicine dosage of each medicine is adjusted step by step, the requirement on medicine replacement is met, the medicine replacement effectiveness is further improved, the monitoring data effectiveness is increased, and the safety of deep anesthesia is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of the method of the present invention.
FIG. 2 is a schematic diagram of the system structure of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
According to the method, as shown in fig. 1, the invention provides a sensor-based anesthesia depth monitoring method, which comprises the following steps of firstly, pre-operation anesthesia preparation, namely collecting pre-operation preparation data of a target patient, analyzing the pre-operation preparation data of the target patient to obtain each anesthesia method of the target patient, and setting an initial anesthesia scheme of the target patient according to each anesthesia method of the target patient and historical anesthesia records in a database.
In one embodiment, the pre-operation preparation data of the target patient is acquired, and the specific acquisition process includes that the pre-operation preparation data of the target patient includes basic body data of the target patient, abnormal body data of the target patient and operation requirements of the target patient, the basic body data of the target patient is input by the target patient, the operation requirements of the target patient are input by staff, values of various body parameters of the target patient are acquired through a medical detection instrument, intervals of abnormal values of the various body parameters are acquired from a database, if the values of certain body parameters of the target patient belong to the intervals corresponding to the abnormal values, the abnormal body parameters of the target patient are indicated, so that various abnormal body parameters are obtained, and the abnormal body data of the target patient are various abnormal body parameters.
It should be noted that, the surgical requirements of the target patient include, but are not limited to, general anesthesia or intraspinal anesthesia, medical detection instruments include, but are not limited to, a blood pressure detector and a platelet detector, and various physical parameters of the target patient include, but are not limited to, blood pressure and platelet concentration.
In one embodiment, the pre-operation preparation data of the target patient is analyzed, and the specific analysis process includes the steps of acquiring each anesthesia scheme corresponding to the operation requirement of the target patient from a database, recording each preset available anesthesia scheme of the target patient, acquiring each forbidden medicine corresponding to the abnormal body data of the target patient from the database, and if a certain preset available anesthesia scheme of the target patient does not contain any forbidden medicine, indicating that the preset available anesthesia scheme of the target patient is an anesthesia scheme to be used, thereby acquiring each anesthesia scheme to be used of the target patient.
The basic body data of the target patient comprise age, sex, weight and height of the target patient, each history anesthesia patient in the same age interval, the same sex, the same weight interval and the same height interval of the target patient is marked as each similar history anesthesia patient of the target patient, the anesthesia method of each same history anesthesia patient is obtained from a database, the historical use times of each anesthesia method are obtained through statistics, the use times of each anesthesia method to be used of the target patient are obtained from the historical use times of each anesthesia method, the anesthesia methods to be used of the target patient are ordered according to the use times, the preset number of each anesthesia method to be used is selected to be marked as each anesthesia method, and each anesthesia method of the target patient is obtained.
In a specific embodiment, setting an initial anesthesia scheme of a target patient, wherein the specific setting process comprises the steps of marking an anesthesia method with the highest use times of similar historical anesthesia patients of the target patient in the anesthesia methods of the target patient as the initial anesthesia method, acquiring a anesthesia drug supply scheme corresponding to the initial anesthesia method from a database, marking each drug in the initial anesthesia drug supply scheme as a used drug, marking each drug in the anesthesia method as a standby drug, acquiring the specificity index of each monitoring method for each used drug and each standby drug from the database, acquiring the preset operation time according to the operation requirement of the target patient, acquiring the stability index of each monitoring method for the preset operation time from the database, and substituting the specificity index of each monitoring method for each used drug, the specificity of each monitoring method for each standby drug and the stability index of each monitoring method for the preset operation time into a monitoring priority index calculation formula:
In (3) obtaining a monitoring method Priority index of (2),For the purpose of the numbering of the monitoring method,,,、AndRespectively, monitoring methodFor using medicinesSpecificity index and monitoring method of (2)For standby medicineMonitoring method for specificity and preset operation durationIs used for the stability index of (c) in the composition,In order to use the number of the medicine,,,For the number of the drug to be used,,,AndRespectively a preset standard specificity index and a standard stability index,Is a preset standard stability index which is set in advance,、AndRespectively preset weight factors of the drug specificity index to be used and the stability index,,,,And marking the monitoring method with the maximum priority index as a preset monitoring method.
It should be noted that, the anesthesia administration scheme includes, but is not limited to, the usage amount of each drug and the input rate of each drug, the stability index is the probability that the monitoring method will collect normally in the corresponding operation time period, the lower the stability index is, the more the number of times that the monitoring method will collect erroneously in the corresponding operation time period, the specificity index indicates the identification capability of the monitoring method to each drug, for example, the monitoring specificity index of the propofol drug by vital sign monitoring is 0.1, the monitoring specificity index of the propofol drug by electroencephalogram is 1.9, and the standard parameters are、AndAre all set by staff, weight factors、AndAre all set by staff, e.g.1.2,1.3,Is 0.6,Is 0.21 part,Is 0.32 and0.47.
The initial anesthesia scheme of the target patient is that the target patient is anesthetized through the initial anesthesia drug supply scheme, and meanwhile anesthesia monitoring is carried out on the target patient through a preset monitoring method.
Collecting initial nerve characteristic data of a target patient, analyzing the initial nerve characteristic data of the target patient based on an anesthesia initial model, judging operation starting time, collecting the intraoperative physiological characteristic data and the intraoperative nerve characteristic data of the target patient in the operation process, analyzing the intraoperative physiological characteristic data and the intraoperative nerve characteristic data of the target patient based on an intraoperative anesthesia model, judging whether anesthesia is abnormal or not, and setting an anesthesia medicine supply changing scheme based on a medicine replacement model when the anesthesia is abnormal.
In a specific embodiment, the collecting the initial neural characteristic data of the target patient specifically includes placing a multiparameter electroencephalogram sensor at a monitoring position of the target patient after the target patient receives the anesthetic drug, collecting brain wave images of the target patient through the multiparameter electroencephalogram sensor, obtaining initial electroencephalogram parameters from the brain wave images, collecting eye videos of the target patient through a camera, and obtaining initial nystagmus frequency from the eye videos of the target patient through machine vision.
The method comprises the steps of obtaining the usage dose and the usage rate of each medicine from an initial anesthesia medicine supply scheme, further obtaining a monitoring period corresponding to the usage dose of each medicine and a monitoring period corresponding to the usage rate of each medicine from a database, and selecting the shortest monitoring period as the monitoring period for collecting initial nerve characteristic data of a target patient.
The nerve response acquisition device is a multiparameter electroencephalogram sensor or an electroencephalogram sensor, and electroencephalogram parameters are such as average power and bispectral index of characteristic waveforms.
In one embodiment, the analysis is performed on the initial neural characteristic data of the target patient, wherein the initial neural characteristic data of the target patient comprises initial electroencephalogram parameters and initial nystagmus frequency, the initial neural characteristic data of the target patient is input into a nerve anesthesia model, an output result of the initial nerve anesthesia model of the target patient is obtained, and the output result comprises values of 0 and 1.
If the output result is 1, the initial anesthesia of the user is finished, the medicine supply is stopped, the operator is prompted to start the operation, if the output result is 0, the initial anesthesia of the user is not finished, the medicine supply is performed, the total medicine supply amount of each medicine of the user is collected, and if the total medicine supply amount of a certain medicine at present reaches the upper medicine supply limit amount of the initial anesthesia scheme, the medicine supply of the medicine is performed according to the preset medicine supply increase amount corresponding to the medicine type in the database.
It should be noted that, when the anesthesia degree of the target patient reaches the level that can perform the operation, the staff is prompted to ensure timely operation, and the medicine supply of the initial anesthesia scheme is stopped in time, so that the comfort and the safety of the patient in the recovery period after the operation are improved.
In a specific embodiment, the anesthesia initiation model expression is:
;
Wherein, Output of the initial neuroanesthesia model for the target patient,For initial electroencephalogram parametersIs a function of the number of (c),Is the number of the electroencephalogram parameters,,,For preset electroencephalogram parametersIs used as a standard value of (a),For the initial nystagmus frequency,Is a preset standard nystagmus frequency,Is a weight factor of a preset electroencephalogram parameter d,,,AndRespectively a preset weight factor of an electroencephalogram and a preset weight factor of nystagmus,,,,Is a preset standard initial anesthesia index.
Standard parameters、AndThe weight factors are the same as the standard parameter setting process、AndAre the same as the weight factor setting process described above, e.g1.3,Is 0.6,0.05 Part,Is 0.4 part,Is 0.6 and1.2.
In one embodiment, the method for acquiring the intraoperative physiological characteristic data and the intraoperative nerve characteristic data of the target patient comprises the steps of placing a multi-parameter electroencephalogram sensor at a monitoring position of the target patient after the target patient performs an operation, acquiring an electroencephalogram image of the target patient through the multi-parameter electroencephalogram sensor, acquiring each intraoperative electroencephalogram parameter from the electroencephalogram image, simultaneously acquiring an eye image of the target patient through a camera, identifying the intraoperative nystagmus frequency of the target patient from the eye image of the target patient, and simultaneously acquiring the intraoperative physiological characteristic data of the target patient through a physiological response monitoring instrument.
It should be noted that the physiological response monitoring apparatus includes, but is not limited to, a skin resistance detector, a finger arterial pressure detector, and a thermometer, and the intraoperative physiological characteristic data includes values of physiological parameters and intraoperative forehead temperature, wherein the physiological parameters include, but are not limited to, skin resistance and finger arterial pressure.
In one embodiment, the analysis is performed on the intraoperative physiological characteristic data and the intraoperative neural characteristic data of the target patient, wherein the intraoperative physiological characteristic data of the target patient comprises the numerical value of each physiological parameter and the intraoperative forehead temperature, the intraoperative neural characteristic data of the target patient comprises the numerical value of each electroencephalogram parameter and the frequency of the intraoperative nystagmus, the intraoperative anesthesia model comprises a physiological reaction model and a neural reaction model, the intraoperative physiological characteristic data of the target patient is input into the physiological reaction model to obtain the output result of the intraoperative physiological reaction grade model of the target patient, the output result comprises the numerical values of 0 and 1, the intraoperative physiological characteristic data of the target patient is input into the neural reaction model to obtain the output result of the neural reaction model of the target patient, and the output result comprises the numerical values of-1, 0 and 1.
If the output results of the nerve response model and the physiological response model of the target patient are 0, the anesthesia in the operation is normal.
If the output result of the nerve reaction model or the physiological reaction model of the target patient is not 0, indicating that the anesthesia is abnormal during operation, wherein if the output result of the nerve reaction model of the target patient is-1 and the output result of the physiological reaction model of the target patient is 0, indicating that the anesthesia dosage is too low, the medicine dosage needs to be increased, if the output result of the nerve reaction model of the target patient is-1 and the output result of the physiological reaction model of the target patient is 1, indicating that the anesthesia medicine is intolerant, prompting a worker to replace the medicine, and if the output result of the nerve reaction model of the target patient is 1, indicating that the anesthesia dosage is excessive and the medicine dosage needs to be reduced.
In one embodiment, the expression of the intraoperative anesthesia model is that the intraoperative anesthesia model comprises a physiological reaction model and a nerve reaction model, and the physiological reaction model is as follows:
;
Wherein, As a result of the output of the physiological reaction model,The value of the physiological parameter e is calculated,For the temperature of the forehead in operation,Is the number of the physiological parameter(s),,,Is a standard value of a preset physiological parameter e,Is a weight factor of a preset physiological parameter e,,,Is the preset standard intraoperative forehead temperature,AndRespectively a weight factor of a preset physiological parameter and a weight factor of forehead temperature,,,,Is a preset standard physiological response index.
Standard parameters、AndThe weight factors are the same as the standard parameter setting process、AndAre the same as the weight factor setting process described above, e.g1.3,36.5,Is 0.13 part,Is 0.35,Is 0.65 and20.46.
The neural response model is:
;
Wherein, As an output result of the neural response model,Is the value of the electroencephalogram parameter d in operation,In order to have an intra-operative nystagmus frequency,Is a standard value of a preset electroencephalogram parameter d,Is a weight factor of a preset electroencephalogram parameter d,,,Is a preset standard nystagmus frequency,AndRespectively a preset weight factor of an electroencephalogram and a preset weight factor of nystagmus,,,,AndThe lower limit and the upper limit of the preset standard intra-operative anesthesia index interval are respectively set.
Standard parametersAndAre the same as the standard parameter setting procedure described above, e.g1.32 And4.53.
In one embodiment, the anesthesia medicine supply changing scheme is specifically set by acquiring historical patient use times of each medicine used by a target patient and average use dosage of each medicine used from a database, and substituting the historical patient use times and average use dosage into a medicine use index calculation formula:
In the process, the target patient is obtained Is of the use index of (2),In order to use the number of the medicine,,,AndMedicament for use by target patientsHistorical patient number of times and use of drugsIs used in combination with the average dose of the composition,AndThe standard times and the standard dosage respectively,AndThe weight factors of the preset times of use and the weight factors of the dosage to be used are respectively,,,。
Standard parametersAndThe weight factors are the same as the standard parameter setting processAndAre the same as the weight factor setting process described above, e.g5.34,0.71,Is 0.12 and0.88.
If the drug supply amount of the target patient needs to be increased, the use drug with the highest use index is increased by the preset supply amount, and if the drug supply amount of the target patient needs to be decreased, the use drug with the highest use index is decreased by the preset supply amount.
If the target patient needs to be replaced by the medicine, according to an analysis method of the usage index of each usage medicine of the target patient, the usage index of each standby medicine of the target patient is obtained, the usage medicine of the minimum usage index of the target patient is recorded as the medicine to be replaced, the standby medicine of the maximum usage index of the target patient is recorded as the preset usage medicine, meanwhile, the usage data of each usage medicine is obtained from a database, the usage data of each usage medicine comprises the common usage times of each usage medicine and the medicine to be replaced, the maximum usage times of each usage medicine and the medicine to be replaced are further included, the common usage times of each usage medicine and the medicine to be replaced are further included, the maximum usage times of each usage medicine and the preset usage medicine are further included, the usage data of each usage medicine is input into a medicine replacement model, the output result of each usage medicine is obtained, the numerical value of the output result comprises-1, 0 and 1, each usage medicine output result is positive usage medicine is respectively, each usage result is respectively positive usage medicine, each usage result is respectively output is respectively preset for the preset usage reduction amount, each usage medicine to be replaced by the preset medicine is adjusted to be negative and the preset medicine to be required to be replaced, and the number of the preset medicine is adjusted to be negative and the medicine to be replaced by the preset medicine is adjusted according to the negative.
The preset medicine supply increment and medicine supply decrement are set by a worker, for example, 0.01 and 0.001.
In a specific embodiment, the drug replacement model expression is:
;
Wherein, For the use of drugsIs used for outputting a result of the (c),For the use of drugsThe number of times of co-use with the medicine to be replaced,For the use of drugsThe maximum dosage when the medicine is used together with the medicine to be replaced,For the use of drugsThe number of times of co-use with the preset medicine,For the use of drugsThe maximum dosage is the same with the preset medicine,AndRespectively the preset standard use times and standard maximum dosage,AndRespectively a preset weight factor of the using times and a weight factor of the maximum dosage,,,,AndThe lower limit and the upper limit of a preset standard medicine requirement index interval are respectively set.
Standard parameters、、AndThe weight factors are the same as the standard parameter setting processAndAre the same as the weight factor setting process described above, e.gIs 12,1.34,Is 0.35,0.65 Part,4.36 And8.24.
According to the invention, as shown in fig. 2, the invention provides a sensor-based anesthesia depth monitoring system, which comprises a pre-operation anesthesia preparation module, an intra-operation anesthesia monitoring module and a database.
The preoperative anesthesia preparation module is respectively connected with the intraoperative anesthesia monitoring module and the database.
The preoperative anesthesia preparation module is used for collecting preoperative preparation data of the target patient, analyzing the preoperative preparation data of the target patient to obtain each anesthesia method of the target patient, and setting an initial anesthesia scheme of the target patient according to each anesthesia method of the target patient and the historical anesthesia record in the database.
The intraoperative anesthesia monitoring module is used for collecting initial nerve characteristic data of a target patient, analyzing the initial nerve characteristic data of the target patient based on an anesthesia initial model, judging operation starting time, collecting intraoperative physiological characteristic data and intraoperative nerve characteristic data of the target patient in an operation process, analyzing the intraoperative physiological characteristic data and the intraoperative nerve characteristic data of the target patient based on an intraoperative anesthesia model, judging whether anesthesia is abnormal, and setting an anesthesia medicine supply changing scheme when the anesthesia is abnormal.
The database is used for storing historical anesthesia records, intervals of abnormal values of all physical parameters, all anesthesia schemes corresponding to operation demands of target patients, all forbidden medicines corresponding to abnormal body data of the target patients, anesthesia methods of all the same historical anesthesia patients, anesthesia medicine supply schemes corresponding to initial anesthesia methods, specificity indexes of all monitoring methods on all used medicines, specificity indexes of all monitoring methods on all standby medicines, stability indexes of all monitoring methods of preset operation time, monitoring periods corresponding to usage doses of all medicines, monitoring periods corresponding to usage rates of all medicines, preset medicine supply increment corresponding to all medicine types, historical patient usage times of all used medicines of the target patients, average usage doses of all used medicines of the target patients and usage data of all used medicines.
The foregoing is merely illustrative and explanatory of the principles of the invention, as various modifications and additions may be made to the specific embodiments described, or similar arrangements may be substituted by those skilled in the art, without departing from the principles of the invention or beyond the scope of the invention as defined in the description.

Claims (10)

1.一种基于传感器的麻醉深度监测方法，其特征在于，包括如下步骤：1. A sensor-based anesthesia depth monitoring method, characterized in that it comprises the following steps: 步骤一、术前麻醉准备：采集目标患者的术前准备数据，对目标患者的术前准备数据进行分析，得到目标患者的各麻醉方法，进而根据目标患者的各麻醉方法和数据库中的历史麻醉记录，设置目标患者的初始麻醉方案；Step 1: Preoperative anesthesia preparation: Collect the preoperative preparation data of the target patient, analyze the preoperative preparation data of the target patient, obtain the various anesthesia methods of the target patient, and then set the initial anesthesia plan of the target patient according to the various anesthesia methods of the target patient and the historical anesthesia records in the database; 步骤二、术中麻醉监测：采集目标患者的初始神经特征数据，基于麻醉初始模型，对目标患者的初始神经特征数据进行分析，判断手术开始时机，在手术过程中，采集目标患者的术中生理特征数据和术中神经特征数据，基于术中麻醉模型，对目标患者的术中生理特征数据和术中神经特征数据进行分析，判断是否麻醉异常，在麻醉异常时，基于药品更换模型，设置麻醉供药更改方案。Step 2: Intraoperative anesthesia monitoring: Collect the target patient's initial neural characteristic data, analyze the target patient's initial neural characteristic data based on the anesthesia initial model, and determine the timing of starting the operation. During the operation, collect the target patient's intraoperative physiological characteristic data and intraoperative neural characteristic data, analyze the target patient's intraoperative physiological characteristic data and intraoperative neural characteristic data based on the intraoperative anesthesia model to determine whether the anesthesia is abnormal. If the anesthesia is abnormal, set up an anesthesia drug supply change plan based on the drug replacement model. 2.根据权利要求1所述的一种基于传感器的麻醉深度监测方法，其特征在于，所述对目标患者的术前准备数据进行分析，具体分析过程如下：2. A sensor-based anesthesia depth monitoring method according to claim 1, characterized in that the preoperative preparation data of the target patient is analyzed, and the specific analysis process is as follows: 目标患者的术前准备数据包括目标患者的基本身体数据、目标患者的异常身体数据和目标患者的手术需求，从数据库中获取目标患者的手术需求对应的各麻醉方案，记为目标患者的各预设可用麻醉方案，同时从数据库中获取目标患者的异常身体数据对应的各禁用药品，若目标患者的某预设可用麻醉方案不含有任何一种禁用药品，表明目标患者的该预设可用麻醉方案为待使用麻醉方案，以此获取目标患者的各待使用麻醉方案；The preoperative preparation data of the target patient includes the basic physical data of the target patient, the abnormal physical data of the target patient and the surgical requirements of the target patient. The anesthetic schemes corresponding to the surgical requirements of the target patient are obtained from the database and recorded as the preset available anesthetic schemes of the target patient. Meanwhile, the prohibited drugs corresponding to the abnormal physical data of the target patient are obtained from the database. If a preset available anesthetic scheme of the target patient does not contain any prohibited drug, it indicates that the preset available anesthetic scheme of the target patient is the anesthetic scheme to be used, thereby obtaining the anesthetic schemes to be used of the target patient; 目标患者的基本身体数据包括目标患者的年龄、性别、体重和身高，将目标患者相同年龄区间、相同性别、相同体重区间和相同身高区间的各历史麻醉患者，记为目标患者的各同类历史麻醉患者，从数据库中获取各相同历史麻醉患者的麻醉方法，统计得到各麻醉方法历史使用次数，从各麻醉方法历史使用次数中得到目标患者的各待使用麻醉方法使用次数，将目标患者的各待使用麻醉方法按使用次数由多到少进行排序，选择前列预设数量的各待使用麻醉方法记为各麻醉方法，以此得到目标患者的各麻醉方法。The basic physical data of the target patient include the target patient's age, gender, weight and height. All historical anesthesia patients in the same age range, gender, weight range and height range as the target patient are recorded as historical anesthesia patients of the same type as the target patient. The anesthesia methods of the same historical anesthesia patients are obtained from the database, and the historical usage times of each anesthesia method are statistically obtained. The usage times of each anesthesia method to be used for the target patient are obtained from the historical usage times of each anesthesia method. The anesthesia methods to be used for the target patient are sorted from most to least according to the usage times, and the first preset number of anesthesia methods to be used are selected and recorded as the anesthesia methods, thereby obtaining the anesthesia methods for the target patient. 3.根据权利要求2所述的一种基于传感器的麻醉深度监测方法，其特征在于，所述设置目标患者的初始麻醉方案，具体设置过程如下：3. A sensor-based anesthesia depth monitoring method according to claim 2, characterized in that the initial anesthesia plan for the target patient is set in the following specific setting process: 将目标患者的各麻醉方法中目标患者的各同类历史麻醉患者使用次数最多的麻醉方法记为初始麻醉方法，从数据库中获取初始麻醉方法对应的麻药供药方案，记为初始麻醉供药方案，将初始麻醉供药方案中的各药品记为使用药品，同时将各麻醉方法中各药品记为各待用药品，从数据库中获取各监测方法对各使用药品和各待用药品的特异性指数，同时根据目标患者的手术需求得到预设手术时长，从数据库中获取预设手术时长的各监测方法的稳定性指数，将各监测方法对各使用药品的特异性指数、各监测方法对各待用药品的特异性和预设手术时长的各监测方法的稳定性指数代入监测优先指数计算公式中，得到各监测方法的优先级指数，将优先级指数最大的监测方法的记为预设监测方法；Among the anesthesia methods of the target patient, the anesthesia method that has been used the most times by the target patient's similar historical anesthesia patients is recorded as the initial anesthesia method, the anesthetic drug supply plan corresponding to the initial anesthesia method is obtained from the database and recorded as the initial anesthesia drug supply plan, each drug in the initial anesthesia drug supply plan is recorded as the used drug, and each drug in each anesthesia method is recorded as each standby drug, and the specificity index of each monitoring method for each used drug and each standby drug is obtained from the database, and the preset operation time is obtained according to the surgical requirements of the target patient, and the stability index of each monitoring method for the preset operation time is obtained from the database, and the specificity index of each monitoring method for each used drug, the specificity of each monitoring method for each standby drug and the stability index of each monitoring method for the preset operation time are substituted into the monitoring priority index calculation formula to obtain the priority index of each monitoring method, and the monitoring method with the largest priority index is recorded as the preset monitoring method; 目标患者的初始麻醉方案为：通过初始麻醉供药方案对目标患者进行麻醉，同时通过预设监测方法，对目标患者进行麻醉监测。The initial anesthesia plan for the target patient is: anesthetize the target patient through the initial anesthesia medication plan, and at the same time, monitor the anesthesia of the target patient through a preset monitoring method. 4.根据权利要求3所述的一种基于传感器的麻醉深度监测方法，其特征在于，所述对目标患者的初始神经特征数据进行分析，具体分析过程如下：4. A sensor-based anesthesia depth monitoring method according to claim 3, characterized in that the initial neural characteristic data of the target patient is analyzed, and the specific analysis process is as follows: 目标患者的初始神经特征数据包括初始各脑电图参数和初始眼球震颤频率，将目标患者的初始神经特征数据输入神经麻醉模型，得到目标患者的初始神经麻醉模型的输出结果，输出结果包括0和1的数值；The initial neural characteristic data of the target patient include initial electroencephalogram parameters and initial nystagmus frequency. The initial neural characteristic data of the target patient are input into the neural anesthesia model to obtain an output result of the initial neural anesthesia model of the target patient, and the output result includes values of 0 and 1; 若输出结果为1，表明用户的初始麻醉完成，停止供药，向工作人员提示可以开始手术，若输出结果为0，表明用户的初始麻醉未完成，进行供药，采集用户的各药品的供药总量，若当前某药品的供药总量达到初始麻醉方案的供药上限量，按数据库中该药品种类对应的预设供药增加量进行该药品的供药。If the output result is 1, it indicates that the user's initial anesthesia is completed, and the drug supply is stopped, and the staff is prompted to start the operation. If the output result is 0, it indicates that the user's initial anesthesia is not completed, and the drug supply is carried out, and the total supply of each drug of the user is collected. If the current total supply of a certain drug reaches the upper limit of the initial anesthesia plan, the drug is supplied according to the preset supply increase corresponding to the drug type in the database. 5.根据权利要求4所述的一种基于传感器的麻醉深度监测方法，其特征在于，所述麻醉初始模型表达式为：5. A sensor-based anesthesia depth monitoring method according to claim 4, characterized in that the anesthesia initial model expression is: ； ; 其中，为目标患者的初始神经麻醉模型的输出结果，为初始脑电图参数的数值，为脑电图参数的编号，，，为预设的脑电图参数的标准数值，为初始眼球震颤频率，为预设的标准眼球震颤频率，为预设的脑电图参数d的权重因子，，，和分别为预设的脑电图的权重因子和眼球震颤的权重因子，，，，为预设的标准初始麻醉指数。in, The output of the initial neuroanesthesia model for the target patient, is the initial EEG parameter The numerical value of is the number of the EEG parameter, , , Preset EEG parameters The standard value of is the initial nystagmus frequency, is the preset standard nystagmus frequency, is the weight factor of the preset EEG parameter d, , , and are the preset EEG weight factor and nystagmus weight factor, respectively. , , , It is the preset standard initial anesthetic index. 6.根据权利要求1所述的一种基于传感器的麻醉深度监测方法，其特征在于，所述对目标患者的术中生理特征数据和术中神经特征数据进行分析，具体分析过程如下：6. A sensor-based anesthesia depth monitoring method according to claim 1, characterized in that the intraoperative physiological characteristic data and intraoperative neural characteristic data of the target patient are analyzed, and the specific analysis process is as follows: 目标患者的术中生理特征数据包括各生理参数的数值和术中额头温度，目标患者的术中神经特征数据包括术中各脑电图参数的数值和术中眼球震颤频率，术中麻醉模型包括生理反应模型和神经反应模型，将目标患者的术中生理特征数据输入生理反应模型中，得到目标患者的术中生理反应等级模型的输出结果，输出结果包括0和1的数值，将目标患者的术中生理特征数据输入神经反应模型中，得到目标患者的神经反应模型的输出结果，输出结果包括-1、0和1的数值；The target patient's intraoperative physiological characteristic data include the values of various physiological parameters and the intraoperative forehead temperature; the target patient's intraoperative neural characteristic data include the values of various intraoperative electroencephalogram parameters and the intraoperative nystagmus frequency; the intraoperative anesthesia model includes a physiological response model and a neural response model; the target patient's intraoperative physiological characteristic data are input into the physiological response model to obtain the output result of the target patient's intraoperative physiological response grade model, and the output result includes the values of 0 and 1; the target patient's intraoperative physiological characteristic data are input into the neural response model to obtain the output result of the target patient's neural response model, and the output result includes the values of -1, 0 and 1; 若目标患者的神经反应模型和生理反应模型的输出结果均为0，表明术中麻醉正常；If the output results of the target patient's neural response model and physiological response model are both 0, it indicates that the intraoperative anesthesia is normal; 若目标患者的神经反应模型或生理反应模型的输出结果不为0，表明术中麻醉异常，其中，若目标患者的神经反应模型的输出结果为-1，且目标患者的生理反应模型的输出结果为0，表明麻醉药量过低，需要增加药品供药量，若目标患者的神经反应模型的输出结果为-1，且目标患者的生理反应模型的输出结果为1，表明麻醉药品存在不耐受，提示工作人员进行药品更换，若目标患者的神经反应模型的输出结果为1，表明麻醉供药过量，需要减少药品供药量。If the output result of the target patient's neural response model or physiological response model is not 0, it indicates abnormal anesthesia during surgery. If the output result of the target patient's neural response model is -1, and the output result of the target patient's physiological response model is 0, it indicates that the amount of anesthetic is too low and the drug supply needs to be increased. If the output result of the target patient's neural response model is -1, and the output result of the target patient's physiological response model is 1, it indicates that the anesthetic is intolerant, prompting the staff to change the drug. If the output result of the target patient's neural response model is 1, it indicates that the anesthetic is overdosed and the drug supply needs to be reduced. 7.根据权利要求6所述的一种基于传感器的麻醉深度监测方法，其特征在于，所述术中麻醉模型表达式为：7. A sensor-based anesthesia depth monitoring method according to claim 6, characterized in that the intraoperative anesthesia model expression is: 术中麻醉模型包括生理反应模型和神经反应模型，生理反应模型为：The intraoperative anesthesia model includes a physiological response model and a neural response model. The physiological response model is: ； ; 其中，为生理反应模型的输出结果，为生理参数e的数值，为术中额头温度，为生理参数的编号，，，为预设的生理参数e的标准数值，为预设的生理参数e的权重因子，，，为预设的标准术中额头温度，和分别为预设的生理参数的权重因子和额头温度的权重因子，，，，为预设的标准生理反应指数；in, is the output of the physiological response model, is the value of the physiological parameter e, is the forehead temperature during surgery, is the number of the physiological parameter, , , is the standard value of the preset physiological parameter e, is the weight factor of the preset physiological parameter e, , , The preset standard forehead temperature during surgery. and are the weight factors of the preset physiological parameters and the weight factors of the forehead temperature, , , , It is a preset standard physiological response index; 神经反应模型为：The neural response model is: ； ; 其中，为神经反应模型的输出结果，为术中脑电图参数d的数值，为术中眼球震颤频率，为预设的脑电图参数d的标准数值，为预设的脑电图参数d的权重因子，，，为预设的标准眼球震颤频率，和分别为预设的脑电图的权重因子和眼球震颤的权重因子，，，，和分别为预设的标准术中麻醉指数区间的下限和上限。in, is the output of the neural response model, is the value of intraoperative EEG parameter d, is the intraoperative nystagmus frequency, is the standard value of the preset EEG parameter d, is the weight factor of the preset EEG parameter d, , , is the preset standard nystagmus frequency, and are the preset EEG weight factor and nystagmus weight factor, respectively. , , , and They are respectively the lower and upper limits of the preset standard intraoperative anesthesia index range. 8.根据权利要求1所述的一种基于传感器的麻醉深度监测方法，其特征在于，所述设置麻醉供药更改方案，具体设置过程如下：8. A sensor-based anesthesia depth monitoring method according to claim 1, characterized in that the setting of the anesthesia drug supply change plan is specifically set as follows: 从数据库中获取目标患者的各使用药品的历史患者使用次数和各使用药品的平均使用剂量，代入计算公式中，得到目标患者的各使用药品的使用指数；Obtain the historical patient usage frequency and average usage dose of each drug used by the target patient from the database, substitute them into the calculation formula, and obtain the usage index of each drug used by the target patient; 若目标患者的药品供药量需要增加，则将使用指数最高的使用药品增加预设供给量，若目标患者的药品供药量需要减少，则将使用指数最高的使用药品减少预设供给量；If the target patient's drug supply needs to be increased, the drug with the highest index will be used to increase the preset supply; if the target patient's drug supply needs to be reduced, the drug with the highest index will be used to reduce the preset supply; 若目标患者需要药品更换，则根据目标患者的各使用药品的使用指数的分析方法，得到目标患者的各待用药品的使用指数，将目标患者的最小使用指数的使用药品记为需替换药品，将目标患者的最大使用指数的待用药品记为预设使用药品，同时从数据库中获取各使用药品的使用数据，各使用药品的使用数据包括各使用药品与需替换药品的共同使用次数，还包括各使用药品与需替换药品的共同使用时最大药量，还包括各使用药品与预设使用药品的共同使用次数，还包括各使用药品与预设使用药品的共同使用时最大药量，将各使用药品的使用数据输入药品更换模型，得到各使用药品的输出结果，输出结果的数值包括-1、0和1，输出结果为1的各使用药品为各正向使用药品，输出结果为-1的各使用药品为各负向使用药品，将预设使用药品替换为需替换药品，各正向使用药品按预设供药增加量进行步进调整，各负向使用药品按预设供药减少量进行步进调整。If the target patient needs to replace the medicine, then according to the analysis method of the usage index of each medicine used by the target patient, the usage index of each to-be-used medicine for the target patient is obtained, the medicine used by the target patient with the minimum usage index is recorded as the medicine to be replaced, and the to-be-used medicine with the maximum usage index of the target patient is recorded as the preset medicine. At the same time, the usage data of each medicine used is obtained from the database, and the usage data of each medicine used includes the number of times each medicine is used together with the medicine to be replaced, and also includes the maximum dosage of each medicine when used together with the medicine to be replaced, and also includes the number of times each medicine is used together with the preset medicine, and also includes the maximum dosage of each medicine when used together with the preset medicine. The usage data of each medicine used is input into the medicine replacement model to obtain the output result of each medicine used, and the value of the output result includes -1, 0 and 1. Each medicine used with an output result of 1 is a positive medicine used, and each medicine used with an output result of -1 is a negative medicine used. The preset medicine is replaced with the medicine to be replaced, and each positive medicine is step-adjusted according to the preset medicine supply increase, and each negative medicine is step-adjusted according to the preset medicine supply decrease. 9.根据权利要求8所述的一种基于传感器的麻醉深度监测方法，其特征在于，所述药品更换模型表达式为：9. A sensor-based anesthesia depth monitoring method according to claim 8, characterized in that the drug replacement model expression is: ； ; 其中，为使用药品的输出结果，为使用药品的编号，，，为使用药品与需替换药品的共同使用次数，为使用药品与需替换药品的共同使用时最大药量，为使用药品与预设使用药品的共同使用次数，为使用药品与预设使用药品的共同使用时最大药量，和分别为预设的标准使用次数和标准最大药量，和分别为预设的使用次数的权重因子和最大药量的权重因子，，，，和分别为预设的标准药品需求指数区间的下限和上限。in, For use of drugs The output result is, The number of the drug to be used. , , For use of drugs The number of times the drug is used together with the drug that needs to be replaced, For use of drugs Maximum dosage when used together with the drug to be replaced, For use of drugs The number of times the drug is used together with the intended drug. For use of drugs Maximum dosage when used with the intended medication. and They are the preset standard usage times and standard maximum dosage. and are the weight factors of the preset number of uses and the maximum dosage, respectively. , , , and They are respectively the lower and upper limits of the preset standard drug demand index range. 10.一种应用权利要求1-9任一项所述的基于传感器的麻醉深度监测方法的麻醉深度监测系统，其特征在于，包括如下模块：10. An anesthesia depth monitoring system using the sensor-based anesthesia depth monitoring method according to any one of claims 1 to 9, characterized in that it comprises the following modules: 术前麻醉准备模块，用于采集目标患者的术前准备数据，对目标患者的术前准备数据进行分析，得到目标患者的各麻醉方法，进而根据目标患者的各麻醉方法和数据库中的历史麻醉记录，设置目标患者的初始麻醉方案；The preoperative anesthesia preparation module is used to collect the preoperative preparation data of the target patient, analyze the preoperative preparation data of the target patient, obtain the various anesthesia methods of the target patient, and then set the initial anesthesia plan of the target patient according to the various anesthesia methods of the target patient and the historical anesthesia records in the database; 术中麻醉监测模块，用于采集目标患者的初始神经特征数据，基于麻醉初始模型，对目标患者的初始神经特征数据进行分析，判断手术开始时机，在手术过程中，采集目标患者的术中生理特征数据和术中神经特征数据，基于术中麻醉模型，对目标患者的术中生理特征数据和术中神经特征数据进行分析，判断是否麻醉异常，在麻醉异常时，设置麻醉供药更改方案。The intraoperative anesthesia monitoring module is used to collect the initial neural characteristic data of the target patient, analyze the initial neural characteristic data of the target patient based on the initial anesthesia model, and determine the timing of starting the operation. During the operation, the intraoperative physiological characteristic data and intraoperative neural characteristic data of the target patient are collected, and the intraoperative physiological characteristic data and intraoperative neural characteristic data of the target patient are analyzed based on the intraoperative anesthesia model to determine whether the anesthesia is abnormal. When the anesthesia is abnormal, an anesthesia drug supply change plan is set.
CN202411876651.7A 2024-12-19 2024-12-19 Sensor-based anesthesia depth monitoring method and system Active CN119302616B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411876651.7A CN119302616B (en) 2024-12-19 2024-12-19 Sensor-based anesthesia depth monitoring method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411876651.7A CN119302616B (en) 2024-12-19 2024-12-19 Sensor-based anesthesia depth monitoring method and system

Publications (2)

Publication Number Publication Date
CN119302616A true CN119302616A (en) 2025-01-14
CN119302616B CN119302616B (en) 2025-04-04

Family

ID=94183425

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411876651.7A Active CN119302616B (en) 2024-12-19 2024-12-19 Sensor-based anesthesia depth monitoring method and system

Country Status (1)

Country Link
CN (1) CN119302616B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080114212A1 (en) * 2006-10-10 2008-05-15 General Electric Company Detecting surgical phases and/or interventions
WO2014059418A1 (en) * 2012-10-12 2014-04-17 The General Hospital Corporation System and method for monitoring and controlling a state of a patient during and after administration of anesthetic compound
US20180211011A1 (en) * 2017-01-25 2018-07-26 General Electric Company Anesthesia assessment system and method for enhanced recovery after surgery qualification
CN113611382A (en) * 2021-08-06 2021-11-05 浙江海心智惠科技有限公司 An oncology medical data presentation system for preoperative visits
CN115040140A (en) * 2022-06-29 2022-09-13 燕山大学 Real-time anesthesia depth monitoring system based on deep learning
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
CN116821676A (en) * 2023-06-01 2023-09-29 黄涛 Method and system for automatically identifying anesthetic type
CN118844942A (en) * 2024-07-09 2024-10-29 中国人民解放军中部战区总医院 A perioperative anesthesia depth monitoring method and system based on deep learning

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080114212A1 (en) * 2006-10-10 2008-05-15 General Electric Company Detecting surgical phases and/or interventions
WO2014059418A1 (en) * 2012-10-12 2014-04-17 The General Hospital Corporation System and method for monitoring and controlling a state of a patient during and after administration of anesthetic compound
US20180211011A1 (en) * 2017-01-25 2018-07-26 General Electric Company Anesthesia assessment system and method for enhanced recovery after surgery qualification
CN113611382A (en) * 2021-08-06 2021-11-05 浙江海心智惠科技有限公司 An oncology medical data presentation system for preoperative visits
CN115040140A (en) * 2022-06-29 2022-09-13 燕山大学 Real-time anesthesia depth monitoring system based on deep learning
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
CN116821676A (en) * 2023-06-01 2023-09-29 黄涛 Method and system for automatically identifying anesthetic type
CN118844942A (en) * 2024-07-09 2024-10-29 中国人民解放军中部战区总医院 A perioperative anesthesia depth monitoring method and system based on deep learning

Also Published As

Publication number Publication date
CN119302616B (en) 2025-04-04

Similar Documents

Publication Publication Date Title
Chua et al. Heart rate variability can be used to estimate sleepiness-related decrements in psychomotor vigilance during total sleep deprivation
Beniczky et al. Standardized computer-based organized reporting of EEG: SCORE–Second version
EP1704819B1 (en) Determination of the anesthetic state of a patient
USRE41291E1 (en) Closed loop drug administration method and apparatus using EEG complexity for control purposes
Younes et al. Performance of a new portable wireless sleep monitor
EP2535000A1 (en) Method and system for quantifying anaesthesia or a state of vigilance
CN114177415B (en) An intelligent method and system for monitoring target control of anesthesia in the elderly based on EEG signals
CN203749411U (en) Closed-loop control injection pump device for electroencephalogram monitoring sedation depth
AU2019204679A1 (en) Anaesthesia and Consciousness Depth Monitoring System
US20140323900A1 (en) Multi-channel brain or cortical activity monitoring and method
EP1854404B1 (en) Monitoring of the state of the central nervous system of a subject
US20070010756A1 (en) Patient monitoring during drug administration
CN115813352B (en) Pupil monitoring and evaluating system for general anesthesia patient
CN114177414B (en) An intelligent method and system for target control of adult anesthesia based on EEG signal monitoring
HU215658B (en) Method and apparatus for determining the depth of anesthesia
Sinha et al. Monitoring devices for measuring the depth of anaesthesia–An overview
CN114177417B (en) Anesthesia target-control intelligent infusion pump controller based on electroencephalogram parameter feedback
CN116884605B (en) Intelligent management system for operation anesthesia information
EP1757226B1 (en) Measurement of responsiveness of a patient under anaesthesia
Ritz et al. End-tidal pCO2 in blood phobics during viewing of emotion-and disease-related films
KR20210066271A (en) Order system using medical deep learning in the field of anesthesia
Liuzzi et al. Heart rate variability for the evaluation of patients with disorders of consciousness
JP2015536693A (en) System and method for assessment of patient health based on recovery response from reduced oxygen saturation
CN116548920A (en) Anesthesia state monitoring system and method based on neural network
EP2191772A1 (en) Measurement of responsiveness of a subject

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