Anesthesia depth evaluation method, system and device and storage medium

Abstract

The invention relates to an anesthesia depth evaluation method, system and device and a storage medium. The method comprises the steps that first electroencephalogram information of a patient before anesthetic is applied and second electroencephalogram information of the patient after anesthetic is applied are obtained; determining a standard deviation unit for converting the intensity of the second electroencephalogram information into the intensity of the first electroencephalogram information, wherein the standard deviation unit represents the relationship between the first electroencephalogram information and the current change rate of the second electroencephalogram information relative to the average intensity of the first electroencephalogram information; determining target electroencephalogram information based on the standard deviation unit; determining category information of the anesthetic applied to the patient; based on the category information and the target electroencephalogram information, the anesthesia depth of the patient is determined. According to the method, the difference of different anesthetic drugs in physiological characteristics in the anesthesia state can be considered, and the judgment of the anesthesia depth of the patient is more accurate by removing the individual difference of the patient, so that the operation smoothness and the postoperative recovery effect are ensured.

Description

Description of the case

[0001] This application is a divisional application filed for a Chinese application with a filing date of July 26, 2023, application number 202310920225.8, and invention name “A method, system, device and storage medium for assessing anesthesia depth”. Technical Field

[0002] The present invention relates to the field of medical information processing, and in particular to an anesthesia depth assessment method, system, device and storage medium. Background Art

[0003] During the operation, anesthesiologists need to accurately give patients the right amount of anesthetic drugs to avoid wasting expensive anesthetic drugs and shorten the patient's stay in the recovery room after anesthesia, thereby controlling medical costs. At the same time, anesthesiologists are also required to ensure that patients lose consciousness, are painless, have muscle relaxation, and avoid awareness during the operation during general anesthesia, thereby reducing postoperative complications.

[0004] However, if the anesthesia depth given by the anesthesia depth monitoring product used by the anesthesiologist is deviated, it will be difficult for the anesthesiologist to accurately administer anesthetic drugs to the patient. Moreover, in clinical anesthesia practice, different surgical methods, different populations, and different degrees of intraoperative stimulation have different responses to anesthetic drugs.

[0005] Therefore, there is a need for an anesthesia depth assessment method that can accurately and effectively show the patient's current anesthesia depth. Summary of the invention

[0006] The purpose of the present application is to provide an anesthesia depth assessment method that can accurately and effectively show the patient's current anesthesia depth. The present application solves the problem of inaccurate anesthesia depth judgment caused by a single anesthesia depth assessment indicator.

[0007] This application is implemented as follows:

[0008] The present application provides a method for assessing the depth of anesthesia, comprising:

[0009] Acquiring first EEG information of the patient before the anesthetic is administered and second EEG information of the patient after the anesthetic is administered;

[0010] Determine target EEG information based on the first EEG information and the second EEG information;

[0011] Determining the type of anesthetic drug administered to the patient;

[0012] Based on the category information and the target EEG information, the anesthesia depth of the patient is determined.

[0013] The present application also provides an anesthesia depth assessment system, comprising:

[0014] An EEG information acquisition module, used to acquire first EEG information of a patient before an anesthetic is administered and second EEG information of the patient after an anesthetic is administered;

[0015] a target EEG information determination module, configured to determine target EEG information based on the first EEG information and the second EEG information;

[0016] A category information determination module, used to determine the category information of the anesthetic drug administered to the patient;

[0017] An anesthesia depth determination module is used to determine the anesthesia depth of the patient based on the category information and the target EEG information.

[0018] The present application also provides an anesthesia depth assessment device, comprising a processor, wherein the processor is used to execute the above-mentioned anesthesia depth assessment method.

[0019] The present application also provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the above-mentioned anesthesia depth assessment method.

[0020] The technical solution of this application has the following beneficial effects:

[0021] 1. Taking into account the differences in physiological characteristics of different anesthetic drugs under anesthesia, by eliminating individual differences of patients, the judgment of the depth of anesthesia of patients can be more accurate, so as to ensure the smooth operation and the recovery effect of patients after surgery;

[0022] 2. Automatically identifying the category information of anesthetic drugs through machine learning models can facilitate the subsequent analysis of the specific characteristics of the patient's EEG information under anesthetic drugs and improve the accuracy of the analysis results (such as the depth of anesthesia);

[0023] 3. The depth of anesthesia is obtained based on the evaluation algorithm corresponding to different anesthetic drugs, which can make the process of determining the depth of anesthesia more accurate and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0025] Figure 1 is a schematic diagram of an application scenario of an anesthesia depth assessment system according to some embodiments of this specification;

[0026] Figure 2is an exemplary flow chart of a method for assessing depth of anesthesia according to some embodiments of the present specification;

[0027] Figure 3 is an example diagram of burst suppression and complete suppression of brain waves according to some embodiments of this specification;

[0028] Figure 4 is an exemplary module diagram of an anesthesia depth assessment system according to some embodiments of this specification;

[0029] Figure 5 is a schematic diagram of an exemplary computing device on which at least a portion of an anesthesia depth assessment system may be implemented according to some embodiments of the present specification. DETAILED DESCRIPTION

[0030] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0031] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0032] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0033] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0034] In some embodiments, methods such as anesthesia sedation depth algorithm (such as BIS algorithm) can be used to evaluate the current anesthesia state based on fixed physiological indicators. However, different anesthetic drugs have different molecular mechanisms and different neural circuits, resulting in different states of consciousness change. For example, for the anesthetic drugs ketamine and nitrous oxide, although they can both change the state of consciousness, some of their physiological indicators (such as brain waves, heart rate, etc.) under anesthesia are significantly different from other anesthetic drugs. Therefore, only selecting a fixed physiological indicator to evaluate the effect of the state of consciousness has limitations.

[0035] In view of this, some embodiments of the present specification provide a method for assessing the depth of anesthesia, which combines brain wave information and the condition of anesthetic drugs to more accurately determine the patient's depth of anesthesia.

[0036] Figure 1 It is a schematic diagram of an application scenario of an anesthesia depth assessment system according to some embodiments of this specification.

[0037] like Figure 1 As shown, in some embodiments, the anesthesia depth assessment system 100 may include a brain wave acquisition device 110 , a processing device 120 , a storage device 130 , a terminal 140 , and a network 150 .

[0038] The brain wave acquisition device 110 refers to a device for a user to obtain the EEG information of a patient during anesthesia. In some embodiments, the brain wave acquisition device 110 can exchange data and / or information with other components in the anesthesia depth assessment system 100 (e.g., a processing device 120, a storage device 130, a terminal 140) through a network 150. In some embodiments, the brain wave acquisition device 110 can be directly connected to other components in the anesthesia depth assessment system 100. In some embodiments, one or more components in the anesthesia depth assessment system 100 (e.g., a processing device 120, a storage device 130, a terminal 140) can be included in the brain wave acquisition device 110.

[0039] The processing device 120 can process data and / or information obtained from other devices or system components, and execute the anesthesia depth assessment method shown in some embodiments of this specification based on these data, information and / or processing results to complete one or more functions described in some embodiments of this specification. For example, the processing device 120 can obtain pre-stored data and / or information, such as anesthetic drug categories, from the storage device 130 based on information such as the intensity (amplitude) of the patient's brain waves obtained by the brain wave acquisition device 110. In some embodiments, the processing device 120 can be used to execute the anesthesia depth assessment method shown in some embodiments of this specification.

[0040] In some embodiments, the processing device 120 may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core multi-core processing device). By way of example only, the processing device 120 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, etc., or any combination thereof.

[0041] The storage device 130 can store data or information generated by other devices. In some embodiments, the storage device 130 can store data and / or information collected by the EEG acquisition device 110. In some embodiments, the storage device 130 can store data and / or information processed by the processing device 120, for example, first EEG information, second EEG information, and target EEG information. The storage device 130 may include one or more storage components, each of which may be an independent device or part of another device. The storage device may be local or implemented through the cloud.

[0042] The terminal 140 can control the operation of the brain wave acquisition device 110. The doctor can issue an operation instruction to the brain wave acquisition device 110 through the terminal 140 so that the brain wave acquisition device 110 completes the specified operation, for example, obtains the patient's EEG information within a specific time period, etc. In some embodiments, the terminal 140 can enable the processing device 120 to perform parameter measurement as shown in some embodiments of this specification through instructions, etc. In some embodiments, the terminal 140 can receive information obtained during and / or after the processing process from the processing device 120, for example, the patient's target EEG information determined based on the first EEG information and the second EEG information. In some embodiments, the terminal 140 can output the received information, for example, the terminal 140 can output (such as display, voice broadcast, etc.) the patient's anesthesia depth. In some embodiments, the terminal 140 can be one of other devices with input and / or output functions such as a mobile device 140-1, a tablet computer 140-2, a laptop computer 140-3, a desktop computer, or any combination thereof.

[0043] The network 150 can connect the components of the system and / or connect the system with external resources. The network 150 allows the components to communicate with each other and with other parts outside the system to facilitate the exchange of data and / or information. In some embodiments, one or more components in the anesthesia depth assessment system 100 (e.g., the EEG acquisition device 110, the processing device 120, the storage device 130, the terminal 140) can send data and / or information to other components via the network 150. In some embodiments, the network 150 can be any one or more of a wired network or a wireless network.

[0044] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of this specification. For those of ordinary skill in the art, various changes and modifications may be made under the guidance of the contents of this specification. The features, structures, methods and other features of the exemplary embodiments described in this specification may be combined in various ways to obtain additional and / or alternative exemplary embodiments. For example, the processing device 120 may be based on a cloud computing platform, such as a public cloud, a private cloud, a community and a hybrid cloud. However, these changes and modifications will not deviate from the scope of this specification.

[0045] Figure 2 FIG. 1 is an exemplary flow chart of a method for assessing the depth of anesthesia according to some embodiments of the present specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 may be Figure 1 The processing device 120 in is executed.

[0046] Step 210 , obtaining first EEG information of the patient before the anesthetic is applied and second EEG information of the patient after the anesthetic is applied. In some embodiments, step 210 may be performed by the EEG information acquisition module 410 .

[0047] The first EEG information is the EEG information collected before the patient is anesthetized (ie, before the use of anesthetic drugs). In some embodiments, the EEG information of the patient within 1 to 5 minutes before anesthesia can be obtained and used as the first EEG information.

[0048] For different groups of people, the EEG information before anesthesia is different. In other words, the intensity of EEG activity is different for different people, and the intensity of EEG information representing their state of consciousness is also different. Some people can still maintain a certain subjective consciousness (such as perception of pain) when the intensity of EEG information is relatively weak. This leads to the fact that if a single physiological indicator (and the same standard) is used to judge the state of consciousness after anesthesia for different groups of people, it may be inaccurate, and even conscious patients may be judged as unconscious patients, causing harm to them, affecting postoperative recovery. Therefore, by collecting the first EEG information, individual differences of patients can be fully considered, which is convenient for the assessment of the depth of anesthesia so as to facilitate the subsequent assessment of the depth of anesthesia.

[0049] It should be noted that in order to reduce the impact of interference factors (such as the patient's emotions, state, etc.) on the first EEG information, in some embodiments, sedation (non-anesthesia) can be applied to the patient before obtaining the first EEG information, and the EEG information can be collected when the patient is calm (such as the peak fluctuation of the EEG information is within a preset range) or meets other conditions (such as the heart rate is within a preset range).

[0050] The second EEG information is the EEG information collected after the patient uses one or more anesthetic drugs. In some embodiments, it can be obtained continuously or at intervals (such as intervals of 0.1 seconds, 1 second, 10 seconds, 30 seconds, 1 minute, etc.) after the patient uses one or more anesthetic drugs. Similar to the EEG information before anesthesia, the EEG information after anesthesia is also different for different populations. Therefore, it is necessary to eliminate the individual differences of the patients and then evaluate the depth of anesthesia based on the EEG information to obtain more accurate and objective results.

[0051] In some embodiments, the first EEG information and the second EEG information may be in the form of an EEG information curve, wherein the horizontal axis represents time (unit: seconds) and the vertical axis represents signal strength (unit: μV), for example, Figure 3 The EEG information curve shown.

[0052] Step 220 , determining target EEG information based on the first EEG information and the second EEG information. In some embodiments, step 220 may be performed by the target EEG information determination module 420 .

[0053] Target EEG information is used for subsequent evaluation of the patient's anesthesia depth. Target EEG information eliminates individual differences among patients to a certain extent, reduces external interference, and can better accurately evaluate the patient's anesthesia depth.

[0054] In some embodiments, the process of determining the target EEG information can be understood as a process of eliminating the individual differences of patients. For example, since both the first EEG information and the second EEG information include the individual differences of patients, the difference between the first EEG information and the second EEG information can be directly calculated as the target EEG information.

[0055] In some embodiments, a power ratio of the second EEG information to the first EEG information may be determined, and the target EEG information may be determined based on the power ratio.

[0056] Specifically, the power ratio represents the ratio of the power of one signal segment to the power of another signal segment. In some embodiments, the signal strength of the first EEG information (also referred to as the energy of the first EEG information) can be represented as baseline. f , the signal strength of the second EEG information (also called the energy of the second EEG information) is expressed as activity tf , for the EEG information with the same signal acquisition time interval and acquisition frequency, the power ratio is equal to the energy ratio, so the power ratio can be replaced by the energy ratio and expressed as:

[0057] In some embodiments, the power ratio may be converted to decibels to obtain target EEG information. In some embodiments, the target EEG information obtained after decibel conversion may be expressed as dB. tf , based on the power ratio, it can be determined that the target EEG information can be expressed as:

[0058] In formula (1), α is a coefficient. In some embodiments, the coefficient can be set according to actual needs. For example, α=10.

[0059] In some embodiments, the target EEG information obtained based on decibel conversion can better obtain the high-frequency characteristics of the patient's EEG information. This method has great advantages for tasks that focus on weak signals (such as the high-frequency part of the EEG information). In addition, since the background noise (such as the noise caused by the device hardware) is basically unchanged in the first EEG information and the second EEG information, the first EEG information can be offset by the second EEG information during the power ratio calculation process, so this method can also eliminate most of the background noise.

[0060] In some embodiments, the intensity change ratio of the second EEG information relative to the first EEG information can be determined, and the target EEG information can be determined based on the intensity change ratio.

[0061] Specifically, the intensity change ratio refers to the ratio between the change in the intensity of the second EEG information relative to the first EEG information and the intensity of the first EEG information. In some embodiments, the intensity change ratio prctchange tf It can be expressed as:

[0062] Among them, in formula (2) represents the mean value of the signal strength in the first EEG information; β is a coefficient. In some embodiments, the coefficient can be set according to actual needs. For example, β=100.

[0063] In some embodiments, determining the target EEG information based on the intensity change ratio can better reflect the change of the second EEG information relative to the first EEG information. In addition, the method can achieve data normalization.

[0064] In some embodiments, the standard deviation unit of the intensity of the second EEG information converted to the intensity of the first EEG information may be determined, and the target EEG information may be determined based on the standard deviation unit.

[0065] Specifically, the standard deviation unit of the intensity of the second EEG information converted to the intensity of the first EEG information may represent that the energy in the second EEG information is scaled to the standard deviation unit relative to the energy in the first EEG information. In some embodiments, the standard deviation unit Z tf It can be expressed as:

[0066] Wherein, n in formula (3) represents the number of time points in the first EEG information, and the time points can be set according to actual acquisition needs.

[0067] Standard deviation unit Z tf It reflects the relationship between the current change rates of the first EEG information and the second EEG information. The target EEG information is determined by the standard deviation unit, which takes into account both the average energy of the first EEG information and the standard deviation of the first EEG information over time. It can better reflect the change of the second EEG information over time compared to the first EEG information, that is, the obtained target EEG information has better significance.

[0068] In some embodiments, a specific method for processing the first EEG information and the second EEG information to obtain the target EEG information can be determined based on the concerned frequency band of the target EEG information. For example, when the concerned frequency band of the target EEG information is a high-frequency band, a decibel conversion processing method can be used. In some embodiments, a specific method for processing the first EEG information and the second EEG information to obtain the target EEG information can be determined based on the intensity fluctuation of the acquired first EEG information. For example, when the intensity fluctuation of the first EEG information meets the preset conditions (such as the fluctuation of the peak intensity does not exceed 20%), the standard deviation unit can be used to determine the target EEG information. For another example, when the intensity fluctuation of the first EEG information does not meet the preset conditions, the intensity change ratio can be used to determine the target EEG information.

[0069] Step 230 , determining the category information of the anesthetic drug administered to the patient. In some embodiments, step 230 may be performed by the category information determination module 430 .

[0070] The category information of anesthetic drugs can be information obtained after classifying anesthetic drugs. In some embodiments, the category information of anesthetic drugs can include one or more of the information such as the name, type, measurement and batch of anesthetic drugs used by the patient. In some embodiments, the category information of anesthetic drugs can also be customized classification information based on the influence of anesthetic drugs on EEG information (for example, degree of influence, effective time, etc.). In some embodiments, the category information of anesthetic drugs can be directly input by a doctor, and in some other embodiments, the category information of anesthetic drugs can be determined based on target EEG information.

[0071] In some embodiments, the target EEG information can be processed by an anesthetic drug recognition model to determine the category information of the anesthetic drug applied to the patient. The anesthetic drug recognition model is a machine learning model obtained through training. In some embodiments, the anesthetic drug recognition model can be a neural network model, such as a convolutional neural network (CNN), a deep neural network (DNN), etc. It should be noted that in some embodiments, the first EEG information and the second EEG information can be processed by the anesthetic drug recognition model to determine the category information of the anesthetic drug. For the convenience of description, the following text takes the processing of the target EEG information and the determination of the category information of the anesthetic drug as an example.

[0072] In some embodiments, the input of the anesthetic drug recognition model may be target EEG information, and the output of the model may be category information of one or more anesthetic drugs administered to the patient.

[0073] In some embodiments, the initial anesthetic drug recognition model is trained through training samples, and the parameters of the anesthetic drug recognition model are adjusted with the goal of reducing the value of the loss function. When the value of the loss function converges or reaches a preset number of iterations, the current model can be used as the trained anesthetic drug recognition model. Among them, the loss function can be a loss function commonly used in machine learning models, which is not limited in this specification; the training samples include target EEG information measured under multiple categories of anesthetic drugs as training data, and the category information of the corresponding anesthetic drugs as labels. The training samples can be determined based on the EEG information of other different patients (such as different ages, genders, etc.) in historical anesthesia operations and the category information of the anesthetic drugs used.

[0074] The anesthetic drug recognition model obtained by training based on the EEG data of other patients can be used to identify the category information of the current patient's anesthetic drugs, which can be used as auxiliary reference information in anesthesia surgery, and provide information reference when the category information of anesthetic drugs is missing or partially missing (such as omitting a certain type of anesthetic drugs during the input process when multiple anesthetic drugs are used, or it is difficult for the operator to determine which customized classification information the anesthetic drugs belong to). In some embodiments, the category information of anesthetic drugs is customized according to the effect of anesthetic drugs on EEG information, and the category information of anesthetic drugs is automatically identified by a machine learning model, which can be more conducive to the subsequent analysis of the specific characteristics of the patient's EEG information under anesthetic drugs, and improve the accuracy of the analysis results (such as the depth of anesthesia).

[0075] Step 240 , based on the category information and the target EEG information, determine the patient's anesthesia depth. In some embodiments, step 240 may be performed by an anesthesia depth determination module 440 .

[0076] The depth of anesthesia can be a numerical value used to reflect the patient's current anesthesia state. In some embodiments, the depth of anesthesia can be a value between 1 and 100. The higher the value of the depth of anesthesia, the more awake the patient is. For example, when the patient is fully awake, the depth of anesthesia is 100; when the patient is in a completely suppressed state, the depth of anesthesia is 0.

[0077] Specifically, in order to more accurately define the depth of anesthesia, the five iconic consciousness levels during the anesthesia process can be mapped to multiple intervals of the depth of anesthesia. For example, the depth of anesthesia can be evenly divided into 10 intervals (taking the value between 1 and 100 as an example, each interval is 10 points). The patient's full consciousness can correspond to 1 interval, such as 90-100; the transition point between the presence and disappearance of the patient's consciousness can correspond to 1 interval, such as 50-60 points; the occurrence of burst suppression can correspond to 1 interval, such as 20-30; the complete suppression state or the inability to detect the patient's EEG activity can correspond to 1 interval, such as 0-10.

[0078] In some embodiments, brain waves can be divided into burst waves and suppression waves according to the amplitude. If the amplitude is below the critical value, it is a suppression wave, otherwise it is a burst wave, and the duration of both waves ranges from a few seconds to several minutes. Figure 3 , Figure 3 The EEGs in burst suppression and complete suppression states are shown in Figure 1. Burst suppression is an EEG information model in which burst waves and suppression waves alternate in the EEG. Complete suppression is when the cerebral cortex is completely suppressed, that is, the EEG waves continue to be suppression waves.

[0079] As mentioned above, different anesthetic drugs have different effects on the state of consciousness change and the EEG information. Therefore, considering the impact of different categories of anesthetic drugs, step 240 may include: determining an evaluation algorithm based on the category information; processing the target EEG information based on the evaluation algorithm to determine the patient's anesthesia depth.

[0080] In some embodiments, different types of anesthetic drugs may correspond to different evaluation algorithms. The evaluation algorithm may be a calculation formula, which may be determined based on theoretical research. The evaluation algorithm may also be a machine learning model, specifically, it may include multiple models corresponding to different types of anesthetic drugs, each of which may be obtained through training.

[0081] The input of the machine learning model is the target EEG information, and the output is the patient's anesthesia depth. The machine learning model can be obtained by training the initial model based on the training samples. The specific training method can be similar to the anesthetic drug recognition model and will not be repeated here. The training samples include the historical target EEG information of the patient in the historical anesthesia surgery with the anesthetic drug corresponding to the current machine learning model, and the label is the historical anesthesia depth corresponding to the historical target EEG information. The historical anesthesia depth can be manually determined by the doctor based on the historical target EEG information. In some embodiments, the doctor can determine the consciousness level evaluation according to the anesthesia surgery situation, and convert the consciousness level evaluation into anesthesia depth based on the method described above.

[0082] The anesthetic depth is obtained based on the evaluation algorithm corresponding to different anesthetic drugs, which can make the anesthetic depth determination process more accurate and efficient.

[0083] A patient may use multiple anesthetic drugs during an anesthesia session. In some embodiments, in response to the category information indicating multiple anesthetic drug categories, an evaluation sub-algorithm for each anesthetic drug category may be determined; and an evaluation algorithm may be determined based on the multiple evaluation sub-algorithms.

[0084] The evaluation sub-algorithm can be a calculation formula or a machine learning model. Taking the calculation formula as an example, when a patient uses three anesthetic drugs in an anesthesia, the calculation formulas corresponding to the three anesthetic drugs can be obtained as evaluation sub-algorithms respectively, and the evaluation algorithm is determined based on the three evaluation sub-algorithms. In some embodiments, the method of determining the evaluation algorithm based on multiple evaluation sub-algorithms can be to add weights to each evaluation sub-algorithm to obtain the evaluation algorithm. The weight reflects the degree of influence of the corresponding anesthetic drug on the depth of anesthesia. When multiple anesthetic drugs are used together, if a certain anesthetic drug has a greater impact on the patient's depth of anesthesia, the greater the weight. In some embodiments, the weight can be determined based on historical anesthesia surgery situations or by experimental means. Determining the evaluation algorithm through multiple sub-evaluation sub-algorithms and their corresponding weights is more suitable for occasions where multiple anesthetic drugs are shared.

[0085] For the sake of patient safety, the scenarios in which multiple anesthetic drugs are used in combination usually only include multiple conventional combinations approved by clinical trials, so algorithms corresponding to the combinations can be pre-set for the conventional combinations. In some embodiments, in response to the category information indicating multiple anesthetic drug categories, a combination algorithm is queried from a preset algorithm library based on the multiple anesthetic drug categories; and the combination algorithm is determined as an evaluation algorithm.

[0086] The preset algorithm library may include combination algorithms corresponding to the combination of multiple anesthetic drugs. The patient's anesthesia depth can be determined based on the combination algorithm. In some embodiments, the evaluation algorithm can be determined more quickly by querying the combination algorithm from the preset algorithm library.

[0087] In some embodiments, when the category information indicates multiple anesthetic drug categories, but the combination of anesthetic drugs is not in the preset algorithm library, the evaluation algorithm can be determined by separately determining the evaluation sub-algorithm for each anesthetic drug category as described above.

[0088] In some embodiments, the anesthesia depth may be determined by an anesthesia depth determination model. Specifically, in step 240, the category information and the target EEG information may be input into the anesthesia depth determination model to obtain the anesthesia depth of the patient.

[0089] In some embodiments, the anesthesia depth determination model may be a neural network model, such as a convolutional neural network (CNN), a deep neural network (DNN), etc. The input of the anesthesia depth determination model is the category information and the target EEG information, and the output is the patient's anesthesia depth. The anesthesia depth determination model may be obtained by training the initial model based on the training samples. The specific training method may be similar to that of the anesthetic drug recognition model, which will not be described in detail here.

[0090] The training samples include different computer signals from historical anesthesia operations of other different patients (such as different ages, genders, etc.) and the corresponding category information of different anesthetic drugs. The label is the historical anesthesia depth corresponding to the historical anesthesia. Similar to the previous article, the historical anesthesia depth can be manually determined by the doctor based on the historical target EEG information, or the doctor can determine the consciousness level evaluation based on the historical anesthesia operation situation and convert it into anesthesia depth based on the consciousness level evaluation.

[0091] Since patients have typical reference points during anesthesia surgery, in some embodiments, the patient's anesthesia depth can be determined based on the reference points. Specifically, determining the patient's anesthesia depth based on an evaluation algorithm to process target EEG information can include: determining the patient's characteristic reference points before and after the patient loses consciousness; using an evaluation algorithm to process the target EEG information, and determining the patient's anesthesia depth based on the characteristic reference points.

[0092] In some embodiments, the characteristic reference points before and after the loss of consciousness can be the consciousness level evaluation mentioned above. The characteristic reference points before the loss of consciousness can correspond to the transition point between full wakefulness and the presence and disappearance of patient consciousness; the characteristic reference points after the loss of consciousness can correspond to the emergence of burst suppression and the state of complete suppression or the inability to detect the patient's brain electrical activity. Based on the characteristic reference points, the patient's anesthesia depth can be evaluated according to existing standards.

[0093] The anesthesia depth assessment method provided in this manual can take into account the differences in physiological characteristics of different anesthetic drugs under anesthesia. By eliminating individual differences among patients, the anesthesia depth of patients can be judged more accurately to ensure the smooth operation and postoperative recovery effect.

[0094] In some embodiments, after determining the patient's anesthesia depth, the patient's anesthesia depth can also be output to provide a reference for the operator or doctor. For example, the patient's anesthesia depth can be displayed or reported to the operator or doctor through a device with a display function or a reporting function (such as a terminal, an electroencephalogram acquisition device, etc.).

[0095] It should be noted that the above description of the process 200 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0096] Figure 4 is an exemplary module diagram of an anesthesia depth assessment system according to some embodiments of the present specification.

[0097] In some embodiments, the anesthesia depth assessment system 400 may include an EEG information acquisition module 410 , a target EEG information determination module 420 , a category information determination module 430 , and an anesthesia depth determination module 440 .

[0098] The EEG information acquisition module 410 may be used to acquire first EEG information of a patient before an anesthetic is administered and second EEG information of a patient after an anesthetic is administered.

[0099] In some embodiments, more information about the first EEG information and the second EEG information can be found in the description of step 210, which will not be repeated here.

[0100] The target EEG information determination module 420 may be used to determine the target EEG information based on the first EEG information and the second EEG information.

[0101] In some embodiments, more information about the target EEG information can be found in the description of step 220 and will not be repeated here.

[0102] The category information determination module 430 may be used to determine category information of an anesthetic drug administered to a patient.

[0103] In some embodiments, more information about the category of anesthetic drugs can be found in the description of step 230, which will not be repeated here.

[0104] The anesthesia depth determination module 440 may be configured to determine the anesthesia depth of the patient based on the category information and the target EEG information.

[0105] In some embodiments, more details on determining the depth of anesthesia can be found in the description of step 240, which will not be repeated here.

[0106] In some embodiments, the anesthesia depth assessment system 400 may further include an output module for outputting the anesthesia depth of the patient. For example, the anesthesia depth of the patient may be displayed or reported through a display, a speaker, or other devices.

[0107] It should be understood that Figure 4 The anesthesia depth assessment system 400 and its modules shown can be implemented in various ways. It should be noted that the above description of the anesthesia depth assessment system 400 and its modules is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 4The target EEG information determination module 420 and the category information determination module 430 disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules mentioned above. For example, each module can share a storage module, or each module can have its own storage module. Such variations are within the scope of protection of this specification.

[0108] Figure 5 is a schematic diagram of an exemplary computing device on which at least a portion of an anesthesia depth assessment system may be implemented according to some embodiments of the present specification. Figure 5 As shown, computing device 500 may include processor 510 , memory 520 , input / output (I / O) 530 , and communication port 540 .

[0109] The processor 510 can execute computer instructions (e.g., program code) and perform the functions of the computing device 500 according to the techniques described in this specification. Computer instructions may include, for example, routines, programs, objects, components, data structures, processes, modules, and functions, which perform specific functions described in this specification. For example, the processor 510 can process data or information obtained from the brain wave acquisition device 110, the processing device 120, the storage device 130, the terminal 140, or any other component of the system 100. In some embodiments, the processor 510 may include one or more hardware processors, such as a microcontroller, a microprocessor, a reduced instruction set computer (RISC), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a central processing unit (CPU), a graphics processing unit (GPU), a physical processing unit (PPU), a microcontroller unit, a digital signal processor (DSP), a field programmable gate array (FPGA), an advanced RISC machine (ARM), a programmable logic device (PLD), any circuit or processor capable of performing one or more functions, etc., or a combination thereof.

[0110] For illustration purposes only, only one processor is described in the computing device 500. However, it should be noted that the computing device 500 disclosed in this specification may also include multiple processors. Therefore, the operations and / or method steps disclosed in this specification that are performed by one processor may also be performed jointly or separately by multiple processors. For example, if in this specification, the processor of the computing device 500 performs operations A and B, it should be understood that operations A and B may also be performed jointly or separately by two or more different processors in the computing device 500 (e.g., the first processor performs operation A, the second processor performs operation B, or the first processor and the second processor perform operations A and B together).

[0111] The memory 520 may store data / information obtained from any component of the brain wave acquisition device 110, the processing device 120, the storage device 130, or the terminal 140. In some embodiments, the memory 520 may include a large-capacity memory, a removable memory, a volatile read-write memory, a read-only memory, etc., or any combination thereof. For example, the large-capacity memory may include a magnetic disk, an optical disk, a solid-state drive, etc. The removable memory may include a flash drive, a floppy disk, an optical disk, a memory card, a compressed disk, a magnetic tape, etc. The volatile read-write memory may include a random access memory (RAM). The RAM may include a dynamic RAM (DRAM), a double-rate synchronous dynamic RAM (DDR SDRAM), a static RAM (SRAM), a thyristor RAM (T-RAM), and a zero-capacitor RAM (Z-RAM), etc. The ROM may include a mask ROM (MROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a compact disk ROM (CD-ROM), and a digital versatile disk ROM, etc. In some embodiments, the memory 520 may store one or more programs and / or instructions to execute the exemplary methods described in this specification.

[0112] I / O 530 may input and / or output signals, data, information, etc. In some embodiments, I / O 530 may enable a user to interact with computing device 500. In some embodiments, I / O 530 may include input devices and output devices. Exemplary input devices may include a keyboard, a mouse, a touch screen, a microphone, etc., or a combination thereof. Exemplary output devices may include a display device, a speaker, a printer, a projector, etc., or a combination thereof. Exemplary display devices may include a liquid crystal display (LCD), a light emitting diode (LED) based display, a flat panel display, a curved screen, a television device, a cathode ray tube (CRT), a touch screen screen, etc., or a combination thereof.

[0113] The communication port 540 can be connected to a network (e.g., network 150) to facilitate data communication. The communication port 540 can establish a connection between the brain wave acquisition device 110 and the processing device 120 and / or the storage device 130. The connection can be a wired connection, a wireless connection, any other communication connection that can realize data transmission and / or reception, and / or a combination of these connections. Wired connections may include, for example, cables, optical cables, telephone lines, etc., or any combination thereof. Wireless connections may include, for example, Bluetooth, Wi-Fi, wireless LAN, ZigBee, mobile networks (e.g., 3G, 4G, 5G), etc., or a combination thereof. In some embodiments, the communication port 540 may be and / or include a standardized communication port, for example, RS232, RS485, etc. In some embodiments, the communication port 240 may be a specially designed communication port.

[0114] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0115] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0116] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0117] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0118] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0119] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0120] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for assessing depth of anesthesia, comprising: Acquiring first EEG information of the patient before the anesthetic is administered and second EEG information of the patient after the anesthetic is administered; Determine a standard deviation unit for converting the intensity of the second EEG information to the intensity of the first EEG information, the standard deviation unit representing a relationship between current change rates of the first EEG information and the second EEG information relative to an average intensity of the first EEG information; Determining the target EEG information based on the standard deviation unit; Determining the type of anesthetic drug administered to the patient; Based on the category information and the target EEG information, the anesthesia depth of the patient is determined.

2. The method according to claim 1, wherein determining the anesthesia depth of the patient based on the category information and the target EEG information comprises: Based on the category information, determining an evaluation algorithm; The target EEG information is processed based on the evaluation algorithm to determine the patient's anesthesia depth.

3. The method according to claim 2, wherein determining an evaluation algorithm based on the category information comprises: In response to the category information indicating a plurality of anesthetic drug categories, determining an evaluation sub-algorithm for each anesthetic drug category; Based on the plurality of evaluation sub-algorithms, the evaluation algorithm is determined.

4. The method according to claim 2, wherein determining an evaluation algorithm based on the category information comprises: In response to the category information indicating a plurality of anesthetic drug categories, querying a combination algorithm from a preset algorithm library based on the plurality of anesthetic drug categories; The combined algorithm is determined as the evaluation algorithm.

5. The method according to claim 1, wherein determining the anesthesia depth of the patient based on the category information and the target EEG information comprises: The category information and the target EEG information are input into an anesthesia depth determination model to obtain the anesthesia depth of the patient.

6. The method of claim 2, wherein the step of processing the target EEG information based on the evaluation algorithm to determine the patient's anesthesia depth comprises: Determining characteristic reference points of the patient before and after loss of consciousness; The target EEG information is processed using the evaluation algorithm, and the anesthesia depth of the patient is determined based on the characteristic reference points.

7. The method according to claim 1, wherein determining the category information of the anesthetic drug administered to the patient comprises: The target EEG information is processed by an anesthetic drug recognition model to determine the category information of the anesthetic drug administered to the patient.

8. The method of claim 7, wherein: The method for obtaining the anesthetic drug recognition model comprises: The initial anesthetic drug recognition model is trained through training samples, and the parameters of the anesthetic drug recognition model are adjusted with the goal of reducing the value of the loss function to obtain a trained anesthetic drug recognition model; wherein the training samples include target EEG information measured under multiple categories of anesthetic drugs as training data, and the category information of the corresponding anesthetic drugs as labels.

9. An anesthesia depth assessment system, comprising: An EEG information acquisition module, used to acquire first EEG information of a patient before an anesthetic is administered and second EEG information of the patient after an anesthetic is administered; a target EEG information determination module, configured to determine a standard deviation unit for converting the intensity of the second EEG information to the intensity of the first EEG information, wherein the standard deviation unit represents a relationship between current change rates of the first EEG information and the second EEG information relative to an average intensity of the first EEG information; The target EEG information determination module is further used to determine the target EEG information based on the standard deviation unit; A category information determination module, used to determine the category information of the anesthetic drug administered to the patient; An anesthesia depth determination module is used to determine the anesthesia depth of the patient based on the category information and the target EEG information.

10. The system of claim 9, further comprising: An output module is used to output the anesthesia depth of the patient.

11. An anesthesia depth assessment device, comprising a processor, characterized in that: The processor is used to execute the anesthesia depth assessment method according to any one of claims 1 to 8.

12. A storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer executes the anesthesia depth assessment method as claimed in any one of claims 1 to 8.

Images