Anesthesia-assisted awakening method, control center and equipment based on EEG data analysis

Abstract

The present invention relates to the field of artificial intelligence, and specifically to an anesthesia-assisted awakening method, control center and equipment based on EEG data analysis, with the purpose of improving the control accuracy of an anesthesia-assisted awakening device. The anesthesia-assisted awakening method based on EEG data analysis proposed in the present invention is suitable for a control center, including: obtaining the patient's EEG data and other physiological data; determining the patient's current consciousness category based on the EEG data and other physiological data; determining the current control strategy based on the mapping relationship between preset time nodes, consciousness categories and control strategies; and controlling the anesthesia-assisted awakening device to perform corresponding operations according to the current control strategy. The present invention realizes the intelligent control of the anesthesia-assisted awakening device, gets rid of the dependence on the doctor's experience, and improves the control accuracy.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to an anesthesia-assisted awakening method, a control center and equipment based on electroencephalogram data analysis. Background Art

[0002] After a doctor performs a general anesthesia surgery on a patient, he or she needs to wake the patient up in time to ensure the patient's safety and health.

[0003] In the prior art, the anesthesia awakening device is worn on the patient in advance, and then the medical staff manually operates the anesthesia awakening device to achieve anesthesia awakening. For example, some anesthesia awakening devices can wake up the patient by activating the voice module and the massage module to implement voice broadcast and massage the patient. When anesthesia awakening is required, the medical staff needs to manually activate the voice module and the massage module. Therefore, the control accuracy of the anesthesia awakening device depends largely on the experience of the medical staff. Summary of the invention

[0004] In order to solve the above problems in the prior art, the present invention proposes an anesthesia-assisted awakening method, a control center and equipment based on EEG data analysis, which improves the control accuracy of the anesthesia-assisted awakening device.

[0005] In a first aspect of the present invention, an anesthesia-assisted awakening method based on EEG data analysis is proposed, the method being applicable to a control center, and the method comprising:

[0006] Obtain the patient's EEG data and other physiological data;

[0007] Determining the patient's current consciousness category based on the EEG data and the other physiological data;

[0008] Determine the current control strategy based on the mapping relationship between the preset time node, awareness category and control strategy;

[0009] Controlling the anesthesia auxiliary awakening device to perform corresponding operations according to the current control strategy;

[0010] in,

[0011] The EEG data includes: all whole-brain EEGs from the time point of anesthetic administration to the current time point and the corresponding acquisition time points;

[0012] The other physiological data include: all blood pressure data, heart rate data and / or eye movement data from the time point of anesthetic administration to the current time point.

[0013] Preferably, determining the patient's current consciousness category based on the EEG data and the other physiological data includes:

[0014] Using a spatiotemporal feature extraction network to extract the spatiotemporal features of the EEG data;

[0015] Inputting the EEG spatiotemporal features into a consciousness classification model and outputting a first category;

[0016] Determine a corresponding consciousness category according to the other physiological data to obtain a second category;

[0017] Determine whether the first category is the same as the second category; if they are the same, determine the first category as the patient's current consciousness category; otherwise,

[0018] Calculating the credibility of the EEG data;

[0019] Determine whether the credibility is higher than a preset threshold; if so, determine the first category as the patient's current consciousness category; otherwise, re-determine the second category and determine the second category as the patient's current consciousness category.

[0020] Preferably, determining the corresponding consciousness category according to the other physiological data to obtain the second category includes:

[0021] Determine the consciousness category corresponding to each current physiological data of the patient according to the mapping relationship between the other physiological data and the preset numerical range of each physiological data and the consciousness category;

[0022] The second category is determined according to the consciousness category corresponding to each current physiological data of the patient.

[0023] Preferably, the calculating the credibility of the EEG data comprises:

[0024] Assessing the integrity of the EEG data based on the continuity of the acquisition time points in the EEG data;

[0025] The credibility of the EEG data is determined based on the integrity assessment result.

[0026] Preferably, the re-determining the second category and determining the second category as the patient's current consciousness category comprises:

[0027] Screening the other physiological data based on the completeness of the data;

[0028] Determine the consciousness category corresponding to each current physiological data of the patient according to the filtered other physiological data and the mapping relationship between the preset numerical range of each physiological data and the consciousness category;

[0029] re-determining the second category according to the consciousness category corresponding to each current physiological data of the patient;

[0030] The re-determined second category is used as the patient's current consciousness category.

[0031] Preferably, determining the current control strategy according to the mapping relationship between the preset time node, consciousness category and control strategy includes:

[0032] If the current time node is an anesthesia time node, and the patient's current consciousness category is awake, then determining that the current control strategy is an anesthesia control strategy;

[0033] The controlling the anesthesia auxiliary awakening device to perform corresponding operations according to the current control strategy includes:

[0034] The anesthesia auxiliary awakening device is controlled to play designated audio for calming and soothing according to the anesthesia control strategy.

[0035] Preferably, determining the current control strategy according to the mapping relationship between the preset time node, consciousness category and control strategy includes:

[0036] If the current time node is a wake-up time node, and the patient's current consciousness category is to be awakened, then determining that the current control strategy is a wake-up control strategy;

[0037] The controlling the anesthesia auxiliary awakening device to perform corresponding operations according to the current control strategy includes:

[0038] The anesthesia auxiliary awakening device is controlled to play a specified awakening audio and / or trigger a specified physical stimulation according to the awakening control strategy.

[0039] Preferably, before the operation, the patient wears the anesthesia auxiliary awakening device, the EEG acquisition device and other physiological parameter acquisition devices in advance; wherein the anesthesia auxiliary awakening device, the EEG acquisition device and the other physiological parameter acquisition devices are connected to the control center;

[0040] The method further comprises:

[0041] The EEG data and various other physiological data are associated with each other according to time and displayed visually in real time.

[0042] According to a second aspect of the present invention, a control center is provided, comprising a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the method described above.

[0043] According to a third aspect of the present invention, a storage device is provided, storing a computer program that can be loaded by a processor and execute the method described above.

[0044] The present invention has the following beneficial effects:

[0045] The anesthesia-assisted awakening method based on EEG data analysis proposed by the present invention obtains the patient's EEG data and other physiological data, and determines the patient's current consciousness category based on the acquired data, and then determines the current control strategy based on the mapping relationship between the preset time node, consciousness category and control strategy, and finally controls the anesthesia-assisted awakening device to perform corresponding operations according to the current control strategy. By adopting the above means, the present invention realizes the intelligent control of the anesthesia-assisted awakening device, gets rid of the dependence on the doctor's experience, and improves the control accuracy.

[0046] When judging the patient's current category of consciousness, EEG data and other physiological data are taken into account to draw a comprehensive conclusion, so as to better grasp the control timing of the anesthesia-assisted awakening device. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the main steps of Embodiment 1 of the anesthesia-assisted awakening method based on EEG data analysis of the present invention;

[0048] Figure 2 It is a schematic diagram of the main steps of Example 2 of the anesthesia-assisted awakening method based on EEG data analysis of the present invention. DETAILED DESCRIPTION

[0049] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] It should be noted that, in the description of the present invention, the terms "first" and "second" are only for the convenience of description, and do not indicate or imply the relative importance of the devices, elements or parameters, and therefore cannot be understood as limiting the present invention. In addition, the term "and / or" in the present invention is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally indicates that the associated objects before and after are in an "or" relationship.

[0052] Before the operation, the patient needs to wear an anesthesia-assisted awakening device, an EEG acquisition device, and other physiological parameter acquisition devices in advance, which establish a communication connection with the control center.

[0053] Figure 1 Schematic diagram of the main steps of Embodiment 1 of the anesthesia assisted awakening method based on EEG data analysis of the present invention. Figure 1 As shown, the method of this embodiment is applicable to the control center, and the method of this embodiment includes steps A10-A40:

[0054] Step A10, obtaining the patient's EEG data and other physiological data.

[0055] Among them, EEG data includes: all whole-brain EEGs from the time of anesthetic administration to the current time point and the corresponding acquisition time points; other physiological data include: all blood pressure data, heart rate data and / or eye movement data from the time of anesthetic administration to the current time point. These data can come from EEG acquisition equipment and other physiological parameter acquisition equipment.

[0056] Step A20, determining the patient's current consciousness category based on the EEG data and other physiological data.

[0057] Step A30, determining the current control strategy according to the mapping relationship between the preset time node, consciousness category and control strategy.

[0058] Specifically, if the current time node is an anesthesia time node and the patient's current consciousness category is awake, the current control strategy is determined to be an anesthesia control strategy; if the current time node is an awakening time node and the patient's current consciousness category is to be awakened, the current control strategy is determined to be an awakening control strategy.

[0059] Step A40, controlling the anesthesia auxiliary awakening device to perform corresponding operations according to the current control strategy.

[0060] Specifically, if the current control strategy is the anesthesia control strategy, the anesthesia assisted awakening device is controlled to play the specified audio for calming and soothing according to the anesthesia control strategy; if the current control strategy is the awakening control strategy, the anesthesia assisted awakening device is controlled to play the specified awakening audio and / or trigger the specified physical stimulation according to the awakening control strategy.

[0061] In an optional embodiment, step A20 may specifically include steps A21-A29:

[0062] Step A21, using a spatiotemporal feature extraction network to extract EEG spatiotemporal features from EEG data.

[0063] Specifically, a trained graph convolutional network is used to extract the spatiotemporal features of EEG data.

[0064] Step A22, input the EEG spatiotemporal features into the consciousness classification model and output the first category.

[0065] Step A23, determining the corresponding consciousness category according to other physiological data to obtain the second category. This step specifically includes steps A231-A232:

[0066] Step A231, determining the consciousness category corresponding to each current physiological data of the patient according to other physiological data and the mapping relationship between the preset numerical range of each physiological data and the consciousness category.

[0067] Specifically, when other physiological data include blood pressure data, heart rate data and eye movement data, because the mapping relationship between the numerical ranges of these three types of data and the consciousness categories is pre-set, the consciousness categories corresponding to these three types of physiological data can be determined respectively according to the ranges of the three types of data currently obtained.

[0068] Step A232, determining the second category according to the consciousness category corresponding to each current physiological data of the patient.

[0069] Specifically, when other physiological data include blood pressure data, heart rate data and eye movement data, if at least two of the consciousness categories corresponding to the current three data are consistent, the second category is determined based on the consciousness categories corresponding to these two data; otherwise, the three data can be re-collected for a period of time and steps A231-A232 are executed.

[0070] Step A24, determine whether the first category and the second category are the same; if they are the same, go to step A24; otherwise, go to step A26.

[0071] Step A25, determining the first category as the patient's current consciousness category.

[0072] Step A26, calculating the credibility of the EEG data. This step may specifically include steps A261-A262:

[0073] Step A261, evaluating the integrity of the EEG data based on the continuity of the acquisition time points in the EEG data.

[0074] Step A262, determining the credibility of the EEG data based on the integrity assessment result.

[0075] Step A27, determine whether the credibility is higher than a preset threshold; if so, go to step A28; otherwise, go to step A29.

[0076] Step A28, determining the first category as the patient's current consciousness category.

[0077] Step A29, re-determine the second category and determine the second category as the patient's current consciousness category. This step may specifically include steps A291-A294:

[0078] Step A291, screening other physiological data based on data integrity.

[0079] Specifically, the physiological data may be screened according to their temporal continuity, and the physiological data with poor continuity may be excluded.

[0080] Step A292, determining the consciousness category corresponding to each current physiological data of the patient based on the filtered other physiological data and the preset mapping relationship between the numerical range of each physiological data and the consciousness category.

[0081] Step A293, re-determine the second category based on the consciousness category corresponding to each current physiological data of the patient.

[0082] Specifically, when other physiological data include blood pressure data, heart rate data and eye movement data, if at least two of the consciousness categories corresponding to the current three physiological data are consistent, the second category is determined based on the consciousness categories corresponding to these two physiological data; otherwise, the three physiological data can be re-collected for a period of time and steps A291-A293 are executed.

[0083] Step A294, the re-determined second category is used as the patient's current consciousness category.

[0084] Figure 2 Schematic diagram of the main steps of Embodiment 2 of the anesthesia assisted awakening method based on EEG data analysis of the present invention. Figure 2 As shown, the method of this embodiment is applicable to the control center, and the method of this embodiment includes steps B10-B50:

[0085] Step B10, obtaining the patient's EEG data and other physiological data.

[0086] Among them, the EEG data includes: all whole-brain EEGs from the time of anesthetic administration to the current time point and the corresponding collection time points; other physiological data include: all blood pressure data, heart rate data and / or eye movement data from the time of anesthetic administration to the current time point.

[0087] Step B20, the EEG data and various other physiological data are associated with each other according to time and displayed visually in real time.

[0088] Step B30, determining the patient's current consciousness category based on the EEG data and other physiological data.

[0089] Step B40, determining the current control strategy according to the mapping relationship between the preset time node, consciousness category and control strategy.

[0090] Specifically, if the current time node is an anesthesia time node and the patient's current consciousness category is awake, the current control strategy is determined to be an anesthesia control strategy; if the current time node is an awakening time node and the patient's current consciousness category is to be awakened, the current control strategy is determined to be an awakening control strategy.

[0091] Step B50, controlling the anesthesia auxiliary awakening device to perform corresponding operations according to the current control strategy. Afterwards, the process can go to step B10 to obtain and display relevant data again, so as to understand the patient's condition in real time.

[0092] Although the various steps in the above embodiment are described in the above-mentioned order, those skilled in the art can understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple changes are within the scope of protection of the present invention.

[0093] Based on the above method embodiment, the present invention further provides an embodiment of a control center. The control center of this embodiment includes a memory and a processor. The memory stores a computer program that can be loaded by the processor and execute the method as described above.

[0094] Based on the above method embodiment, the present invention further provides an embodiment of a storage device. The storage device of this embodiment stores a computer program that can be loaded by a processor and execute the above method.

[0095] The storage device may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0096] Those skilled in the art should be able to appreciate that the method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0097] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An anesthesia-assisted awakening control center based on EEG data analysis, characterized in that: The control center includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the following method: Obtain the patient's EEG data and other physiological data; Determining the patient's current consciousness category based on the EEG data and the other physiological data; Determine the current control strategy based on the mapping relationship between the preset time node, awareness category and control strategy; Controlling the anesthesia auxiliary awakening device to perform corresponding operations according to the current control strategy; in, The EEG data includes: all whole-brain EEGs from the time point of anesthetic administration to the current time point and the corresponding acquisition time points; The other physiological data include: all blood pressure data, heart rate data and / or eye movement data from the time point of anesthetic administration to the current time point; Determining the patient's current consciousness category according to the EEG data and the other physiological data includes: Using a spatiotemporal feature extraction network to extract the spatiotemporal features of the EEG data; Inputting the EEG spatiotemporal features into a consciousness classification model and outputting a first category; Determine a corresponding consciousness category according to the other physiological data to obtain a second category; Determine whether the first category is the same as the second category; if they are the same, determine the first category as the patient's current consciousness category; otherwise, Calculating the credibility of the EEG data; Determine whether the credibility is higher than a preset threshold; if so, determine the first category as the patient's current consciousness category; otherwise, re-determine the second category and determine the second category as the patient's current consciousness category.

2. The anesthesia-assisted awakening control center based on EEG data analysis according to claim 1, characterized in that: Determining the corresponding consciousness category according to the other physiological data to obtain the second category includes: Determine the consciousness category corresponding to each current physiological data of the patient according to the mapping relationship between the other physiological data and the preset numerical range of each physiological data and the consciousness category; The second category is determined according to the consciousness category corresponding to each current physiological data of the patient.

3. The anesthesia-assisted awakening control center based on EEG data analysis according to claim 1, characterized in that: The calculating the credibility of the EEG data comprises: Assessing the integrity of the EEG data based on the continuity of the acquisition time points in the EEG data; The credibility of the EEG data is determined based on the integrity assessment result.

4. The anesthesia-assisted awakening control center based on EEG data analysis according to claim 2, characterized in that: The re-determining the second category and determining the second category as the patient's current consciousness category comprises: Screening the other physiological data based on the completeness of the data; Determine the consciousness category corresponding to each current physiological data of the patient according to the filtered other physiological data and the mapping relationship between the preset numerical range of each physiological data and the consciousness category; re-determining the second category according to the consciousness category corresponding to each current physiological data of the patient; The re-determined second category is used as the patient's current consciousness category.

5. The anesthesia-assisted awakening control center based on EEG data analysis according to claim 1, characterized in that: Determining the current control strategy according to the mapping relationship between the preset time node, consciousness category and control strategy includes: If the current time node is an anesthesia time node, and the patient's current consciousness category is awake, then determining that the current control strategy is an anesthesia control strategy; The controlling the anesthesia auxiliary awakening device to perform corresponding operations according to the current control strategy includes: The anesthesia auxiliary awakening device is controlled to play designated audio for calming and soothing according to the anesthesia control strategy.

6. The anesthesia-assisted awakening control center based on EEG data analysis according to claim 1, characterized in that: Determining the current control strategy according to the mapping relationship between the preset time node, consciousness category and control strategy includes: If the current time node is a wake-up time node, and the patient's current consciousness category is to be awakened, then determining that the current control strategy is a wake-up control strategy; The controlling the anesthesia auxiliary awakening device to perform corresponding operations according to the current control strategy includes: The anesthesia auxiliary awakening device is controlled to play a specified awakening audio and / or trigger a specified physical stimulation according to the awakening control strategy.

7. The anesthesia-assisted awakening control center based on EEG data analysis according to any one of claims 1 to 6, characterized in that: Before the operation, the patient wears the anesthesia auxiliary awakening device, the EEG acquisition device and other physiological parameter acquisition devices in advance; wherein the anesthesia auxiliary awakening device, the EEG acquisition device and the other physiological parameter acquisition devices are connected to the control center; The method further comprises: The EEG data and various other physiological data are associated with each other according to time and displayed visually in real time.

Images