Consciousness level evaluation method and device based on TEP data

Abstract

The invention discloses a TEP data-based consciousness level evaluation method and apparatus. The method comprises the steps of obtaining a target state of a target object and a target duration corresponding to the target state; determining a target stimulation parameter according to the target state and the target duration; in a first preset time period, periodically stimulating the target object through the transcranial magnetic stimulation equipment according to the target stimulation parameters to obtain n pieces of first TEP data; performing interference removal on the n pieces of first TEP data to obtain n pieces of second TEP data; determining second TEP data meeting a first preset condition in the n pieces of second TEP data to obtain m pieces of second TEP data; determining m consciousness index values according to the m pieces of second TEP data; and determining the target consciousness state of the target object according to the m consciousness index values. By adopting the embodiment of the invention, the consciousness level of the target object can be evaluated under the condition that the target object cannot interact with the environment.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a method and device for assessing the level of consciousness based on TEP data. Background Art

[0002] In clinical practice, there has been a lack of objective and reliable methods for assessing the level of consciousness. For subjects who can interact with their surroundings (for example, people in a coma), the level of consciousness can be assessed by observing their activity status; however, for subjects under anesthesia or special brain injury, they may be conscious but unable to interact with the environment, and their level of consciousness cannot be assessed at this time. Therefore, how to assess the subject's level of consciousness when the subject cannot interact with the environment has become an urgent problem to be solved. Summary of the invention

[0003] The embodiments of the present application provide a method and device for evaluating the level of consciousness based on TEP data, which can evaluate the level of consciousness of a target object when the target object cannot interact with the environment.

[0004] In a first aspect, an embodiment of the present application provides a method for assessing the level of consciousness based on TEP data, which is applied to an electronic device connected to a transcranial magnetic stimulation device, and the method includes: Acquire a target state of a target object and a target duration corresponding to the target state; the target state includes any one of the following: anesthesia state, brain injury state; Determining target stimulation parameters according to the target state and the target duration; In a first preset time period, the target object is periodically stimulated by the transcranial magnetic stimulation device with the target stimulation parameters to obtain n first TEP data; each stimulation corresponds to one first TEP data; n is an integer greater than 1; De-interference is performed on the n first TEP data to obtain n second TEP data; Determine the second TEP data that meets the first preset condition among the n second TEP data to obtain m second TEP data; m is a positive integer less than or equal to n; Determine m consciousness index values ​​according to the m second TEP data; The target consciousness state of the target object is determined according to the m consciousness index values; the target consciousness state includes any one of the following: awake, drowsy, confused, lethargic, and coma.

[0005] In a second aspect, an embodiment of the present application provides a consciousness level assessment device based on TEP data, which is applied to an electronic device, wherein the electronic device is connected to a transcranial magnetic stimulation device, and the device includes: an acquisition unit, a control unit, and an assessment unit, wherein: The acquisition unit is used to acquire a target state of the target object and a target duration corresponding to the target state; the target state includes any one of the following: an anesthesia state and a brain injury state; The control unit is used to determine the target stimulation parameters according to the target state and the target duration; within a first preset time period, the target object is periodically stimulated by the transcranial magnetic stimulation device with the target stimulation parameters to obtain n first TEP data; each stimulation corresponds to one first TEP data; n is an integer greater than 1; the n first TEP data are de-interfered to obtain n second TEP data; the second TEP data that meets the first preset condition among the n second TEP data is determined to obtain m second TEP data; m is a positive integer less than or equal to n; The evaluation unit is used to determine m consciousness index values ​​according to the m second TEP data; determine the target consciousness state of the target object according to the m consciousness index values; the target consciousness state includes any one of the following: wakefulness, drowsiness, confusion, lethargy, and coma.

[0006] In a third aspect, the present application provides an electronic device comprising: a processor and a memory, wherein the memory is used to store one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the present application.

[0007] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the present application.

[0008] In a fifth aspect, the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the present application. The computer program product may be a software installation package.

[0009] The implementation of this application has the following beneficial effects: It can be seen that the method for evaluating the level of consciousness based on TEP data described in the embodiment of the present application includes: obtaining a target state of a target object and a target duration corresponding to the target state; determining target stimulation parameters according to the target state and the target duration; within a first preset time period, periodically stimulating the target object with the target stimulation parameters through a transcranial magnetic stimulation device to obtain n first TEP data; de-interfering the n first TEP data to obtain n second TEP data; determining the second TEP data that meets the first preset condition among the n second TEP data to obtain m second TEP data; determining m consciousness index values ​​according to the m second TEP data; determining the target consciousness state of the target object according to the m consciousness index values; by collecting the TEP data of the target object, the TEP data is the direct electrophysiological response of the brain to stimulation and can more truly reflect the state of consciousness of a person, analyzing the TEP data to obtain the consciousness index value, and determining the level of consciousness of the target object according to the consciousness index value, thereby achieving the evaluation of the level of consciousness of the target object when the target object cannot interact with the environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0011] Figure 1 is a structural schematic diagram of a consciousness level assessment device provided in an embodiment of the present application; Figure 2 This is a scenario application diagram of a consciousness level assessment device provided in an embodiment of the present application; Figure 3 is a flow chart of a method for assessing level of consciousness based on TEP data provided in an embodiment of the present application; Figure 4 is a schematic diagram of a TMS control page provided in an embodiment of the present application; Figure 5 is a waveform diagram of a TEP waveform provided in an embodiment of the present application; Figure 6 is a schematic diagram of a first straight line provided in an embodiment of the present application; Figure 7 It is a block diagram of the functional units of a consciousness level assessment device based on TEP data provided in an embodiment of the present application; Figure 8 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0013] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0014] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0015] The electronic devices described in the embodiments of the present application may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptops, video matrices, monitoring platforms, mobile Internet devices (mobile internet devices, MID) or wearable devices, etc. The above are only examples and not exhaustive, including but not limited to the above devices. Of course, the above electronic devices can also be servers, for example, cloud servers.

[0016] The following is an explanation of some professional terms involved in this application: Transcranial Magnetic Stimulation (TMS) technology is a magnetic stimulation technology that uses pulsed magnetic fields to act on the central nervous system, change the membrane potential of cortical nerve cells, generate induced currents, affect brain metabolism and neural electrical activity, and thus cause a series of physiological and biochemical reactions.

[0017] TMS stimulation parameters: refers to the various operating indicators of the TMS device during work, such as stimulation intensity, stimulation frequency, number of stimulation pulses, etc.

[0018] TMS-evoked potential (TEP): refers to the potential changes caused by the electrical activity of brain neurons recorded on the surface of the scalp after TMS acts on a specific area of ​​the cerebral cortex. It reflects the brain's response to TMS stimulation and is an important electrophysiological signal used to study brain function and neurophysiological activities. TEP waveforms usually contain multiple components, which may correspond to different brain neural activity processes. By analyzing the complexity and components of the waveform, we can understand the neural mechanisms of the brain in different cognitive, motor or sensory functions, and thus evaluate the brain's level of consciousness.

[0019] Depth of anesthesia: refers to the degree to which the human central nervous system is suppressed by anesthetic drugs during general anesthesia. It is a comprehensive concept used to measure the degree to which a patient goes from a conscious state to a complete loss of consciousness and no response to noxious stimuli. The depth of anesthesia is not a simple linear measurement, but a complex state description involving the interaction of multiple physiological and pharmacological factors.

[0020] Perturbational Complexity Index (PCI): is an indicator used to measure the complexity of a system (especially the brain system in the field of neuroscience). It is mainly used to evaluate the complexity of the brain's neural activity pattern when it is subjected to external stimulation (such as TMS) or internal state changes (such as transitions between different states of consciousness). The calculation of this index is usually based on the analysis of brain electrophysiological signals (for example, EEG, transcranial magnetic stimulation evoked potential TEP). Its calculation process is complex and time-consuming, making it unsuitable for clinical use as an algorithm indicator for real-time online detection, which limits the promotion and application of this indicator.

[0021] Perturbational Complexity Index of TEP data in the short-term (PCIst): is an index used to quantify the complexity of TEP data in a short period of time (usually within a short time window after transcranial magnetic stimulation). It is obtained by performing a series of complex mathematical processing on TEP data. It is generally used to evaluate the differences in the complexity of neural activity in the brain under different states of consciousness, degree of brain damage, etc. Compared with PCI, PCIst is accurate, reliable, and time-saving, making it suitable as an algorithm indicator for online detection.

[0022] See also Figure 1 , Figure 1 is a schematic diagram of the structure of a consciousness level assessment device provided in an embodiment of the present application, such as Figure 1As shown, the consciousness level assessment device may include an electronic device and a transcranial magnetic stimulation device (hereinafter referred to as TMS device), wherein: The specific components of TMS equipment may include a stimulation coil and a pulse generator. The pulse generator is used to generate high-intensity current pulses, which are converted into magnetic field pulses through the stimulation coil to stimulate the cerebral cortex, induce the brain to generate TEP data, collect TEP data, and transmit these TEP data to electronic devices. The pulse generator can adjust the intensity, frequency, duration and other parameters of the pulse to meet different stimulation needs. These TEP data reflect the neural activity of the brain under stimulation and are an important basis for evaluating the level of consciousness. Different stimulation parameters (such as intensity, frequency, etc.) can trigger different brain reactions, so the excitability and consciousness state of the brain can be judged based on these reactions.

[0023] Electronic equipment is the core equipment for processing and analyzing data. It can run special signal processing software and perform operations such as filtering, feature extraction, and data analysis on the raw data (TEP data) collected by the TMS device. For example, the software can remove noise such as power frequency interference and electromyographic artifacts in the TEP data to improve data quality and extract effective information related to the level of consciousness. For example, the level of consciousness can be judged by calculating various characteristic parameters such as the latency and amplitude of the TEP data. At the same time, electronic equipment can also be used to control the parameter settings and stimulation process of the TMS device to achieve synchronous operation of the two.

[0024] See also Figure 2 , Figure 2 This is a scene application diagram of a consciousness level assessment device provided by an embodiment of the present application. When TMS stimulation is required for the target object, the stimulation coil can be placed above the head of the target object. The TMS device can receive the control instructions issued by the electronic device. The pulse generator generates a corresponding electric pulse signal according to the control instruction. The electric pulse signal is transmitted to the stimulation coil, and the stimulation coil converts the electric pulse into a magnetic field pulse. This magnetic field pulse can penetrate the scalp and skull and act on the cerebral cortex, thereby inducing neural electrical activity in the brain and generating TEP data; then, the electronic device can use the consciousness level assessment method based on TEP data provided by the embodiment of the present application to analyze these TEP data to assess the level of consciousness of the target object.

[0025] See also Figure 3 , Figure 3 : is a flowchart of a method for assessing the level of consciousness based on TEP data provided in an embodiment of the present application. The method is applied to an electronic device connected to a transcranial magnetic stimulation device. The method may include the following steps: S301. Obtain a target state of a target object and a target duration corresponding to the target state; the target state includes any one of the following: an anesthesia state and a brain injury state.

[0026] In the embodiment of the present application, detailed communication can be conducted with the target object (if conscious and able to communicate), family members, nursing staff or other relevant personnel to inquire about the target object's recent physical condition, whether it has undergone surgery or trauma, etc. At the same time, the target object's medical record data in the target hospital can also be obtained, including admission records, medical records, surgical records, diagnosis reports, etc. Through medical history inquiries, it can be learned whether the target object has received anesthesia and related conditions of anesthesia, such as anesthesia methods, anesthesia time, etc. If the target object has received anesthesia at the current moment or before the current moment, it can be determined that the target state is an anesthesia state, and then the injection time of the anesthetic drug can be obtained. By subtracting the injection time from the current moment, the target duration can be obtained; conversely, if the medical record data records that the target object has suffered brain damage, it can be determined that the target state is a brain damage state, and the starting time when the target object is diagnosed with brain damage can be obtained. By subtracting the injection time from the starting time of brain damage, the target duration can be obtained. Among them, the target hospital is the hospital where the target object is treated.

[0027] S302: Determine target stimulation parameters according to the target state and the target duration.

[0028] In the embodiment of the present application, the target stimulation parameters may include at least one of the following: stimulation intensity, stimulation frequency, number of stimulation pulses, stimulation site, etc., which are not limited here.

[0029] In a specific embodiment, analysis may be performed based on the target state and the target duration to obtain stimulation parameters that meet the actual situation of the target object, that is, target stimulation parameters.

[0030] Optionally, in step S302, when the target state includes the anesthesia state, determining the target stimulation parameter according to the target state and the target duration may include the following steps: A1. obtaining a target drug type and a target anesthetic drug amount to be injected into the target subject; A2. estimating the onset time of the first drug required for the target subject to reach a preset anesthesia depth according to the target drug type and the target anesthetic dose; A3, estimating the target anesthesia depth of the target subject at the current moment according to the first drug onset time, the target duration and the preset anesthesia depth; the target duration is the time between the injection time of the anesthetic drug and the current moment; A4, determining a first stimulation parameter corresponding to the target anesthesia depth; A5. Obtaining target physical health parameters of the target object; A6. Determine a first influencing factor corresponding to the target physical health parameter; A7. adjusting the first stimulation parameter according to the first influencing factor to obtain a second stimulation parameter; A8. Within a second preset time period, the target object is periodically stimulated by the transcranial magnetic stimulation device with the second stimulation parameters to obtain a reference TEP data; a is a positive integer less than n; each stimulation corresponds to a reference TEP data; the end time of the second preset time period is earlier than the start time of the first preset time period; A9. Remove interference from the a reference TEP data to obtain a TEP data; A10. When the a TEP data satisfy a second preset condition, determine the target stimulation parameter according to the second stimulation parameter.

[0031] In an embodiment of the present application, the target drug type may include one of the following: intravenous anesthetics, inhalation anesthetics, opioid analgesics, muscle relaxants, etc., which are not limited here; the preset anesthesia depth and the second preset condition can be preset or defaulted in advance, and the second preset condition is used to determine whether the data quality of the acquired a TEP data is qualified; the target physical health parameters may include one of the following: blood oxygen concentration, blood pressure, blood routine indicators, cardiopulmonary function indicators (for example, maximum oxygen uptake), immune function indicators (for example, immunoglobulin levels), etc., which are not limited here.

[0032] In a specific embodiment, the target drug type and target anesthetic amount of the anesthetic drug injected into the target object can be first obtained. Specifically, the anesthesia record sheet of the target object can be obtained, which will record in detail the type of anesthetic drug used, the route of administration (such as intravenous injection, inhalation, etc.), the injection amount, and the time node of medication, thereby obtaining the target drug type and target anesthetic amount. Alternatively, the electronic device can be connected to the anesthesia information management system of the target hospital to query the anesthesia information of the target object from the anesthesia information management system, thereby obtaining the target drug type and target anesthetic amount.

[0033] Next, the onset time of the first drug required for the target object to reach the preset anesthetic depth can be estimated based on the target drug type and the target anesthetic dose. Specifically, the onset time range of the anesthetic drug of the target drug type from the injection time to the target object reaching the preset anesthetic depth can be obtained from a preset database (for example, an anesthesia sharing database). For example, assuming that the onset time range of the intravenous anesthetic from the injection time to the target object reaching the preset anesthetic depth is 2 minutes to 5 minutes, and because the onset time of the anesthetic drug will be affected by the dose, the onset time of the first drug can be determined from the onset time range based on the target anesthetic dose. Generally speaking, within the safe dose range, the larger the anesthetic dose, the shorter the onset time. For example, a mapping relationship between a preset anesthetic dose and an onset factor can be pre-stored, and a target onset factor corresponding to the target anesthetic dose is determined based on the mapping relationship. The value range of the target onset factor is -0.3~0, and it can be calculated based on the target onset factor and the onset time range. The calculation formula is as follows: The first drug’s onset time = the lower limit of the onset time range + (the upper limit of the onset time range - the lower limit of the onset time range) × (1 + target onset factor); According to the above formula, the onset time of the first drug can be obtained. Then, the target anesthesia depth of the target object at the current moment can be estimated according to the onset time of the first drug, the target duration and the preset anesthesia depth. Specifically, the target duration can be subtracted from the onset time of the first drug to obtain the target duration difference. Then, the target duration difference and the preset anesthesia depth can be calculated. The calculation formula is as follows: Target anesthesia depth = preset anesthesia depth + preset anesthesia depth × (1 + target duration difference / first drug onset duration) × 100%; According to the above formula, the target anesthesia depth can be obtained. Then, the first stimulation parameter corresponding to the target anesthesia depth can be determined. For example, a mapping relationship between a preset anesthesia depth and a stimulation parameter can be pre-stored, and the first stimulation parameter corresponding to the target anesthesia depth can be determined based on the mapping relationship. Then, the target physical health parameter of the target object can be obtained. Specifically, the target physical health parameter can be blood pressure, and the blood pressure of the target object can be measured by a blood pressure measuring instrument, that is, the target physical health parameter. Further, the first influencing factor corresponding to the target physical health parameter can be determined. For example, a mapping relationship between a preset physical health parameter and an influencing factor can be pre-stored, and the first influencing factor corresponding to the target physical health parameter can be determined based on the mapping relationship. The value range of the first influencing factor can be -0.5~0.5, and the first stimulation parameter can be adjusted according to the first influencing factor. The specific calculation formula is as follows: The second stimulation parameter = the first stimulation parameter × (1 + the first influencing factor); According to the above formula, the second stimulation parameter can be obtained; within the second preset time period, the target object can be periodically stimulated with the second stimulation parameter through the TMS device to obtain a reference TEP data; it should be explained that the stimulation cycle can be preset or defaulted in advance, for example, the stimulation cycle can be 2.5 seconds.

[0034] Next, the a reference TEP data may be de-interfered to obtain a TEP data. The specific de-interference step may be the same as the step of S304, which will be described in detail below and will not be repeated here. When the a TEP data meets the second preset condition, the second stimulation parameter may be directly used as the target stimulation parameter, and then the stimulation parameter of the transcranial magnetic stimulation device may be adjusted to the target stimulation parameter through the electronic device. For an example, please refer to Figure 4 , Figure 4 is a schematic diagram of a TMS control page provided in an embodiment of the present application. The TMS control page is an operation page of an electronic device, such as Figure 4 As shown, the TMS control page includes: serial port number, transcranial magnetic stimulator, disconnect, current intensity 50%, "+", "-", ready button, start stimulation button, fast stimulation button, port number 9230, whether to receive external commands (in Figure 4 In the figure, if the left side of receiving external commands is “√”, it means that the electronic device can receive external commands; if the left side of receiving external commands is “×”, it means that the electronic device does not receive external commands) and other information.

[0035] Among them, transcranial magnetic stimulator indicates the device type; "+" and "-" are used to increase or decrease the stimulation intensity; click the ready button to start preparation; click the start stimulation button to start stimulating the target object; click the quick stimulation button to directly stimulate the target object without preparation. When the target stimulation parameter is the stimulation intensity, the stimulation parameter of the transcranial magnetic stimulation device can be adjusted to the target stimulation parameter through the "+" and "-" buttons; of course, if the target stimulation parameter is not the stimulation intensity, it can also be controlled and adjusted through other operation pages of the electronic device.

[0036] When a TEP data does not meet the second preset condition, the second stimulation intensity can be adjusted according to the preset ratio. The specific calculation formula is as follows: The updated second stimulation intensity = the second stimulation intensity × (1 + preset ratio); Among them, the preset ratio can be preset in advance or defaulted; the updated second stimulation intensity is obtained according to the above formula; the target object is periodically stimulated again with the updated second stimulation intensity through the transcranial magnetic stimulation device to obtain updated a TEP data, and it is determined whether the updated a TEP data meet the second preset condition; if the updated a TEP data still does not meet the above second preset condition, the updated second stimulation intensity is continued to be adjusted according to the preset ratio until the latest a TEP data meet the above second preset condition, and the latest second stimulation parameters are used as the target stimulation parameters.

[0037] In this way, by obtaining the target drug type and target anesthetic dosage, the onset time of the first drug required for the target object to reach the preset anesthesia depth is estimated, and then the target anesthesia depth at the current moment is estimated to determine the corresponding first stimulation parameters, taking into account the effect of anesthetic drugs on the brain state. Because the excitability of the brain is different at different anesthesia depths, the response to TMS stimulation is also different. For example, at a shallower anesthesia depth, the brain may react relatively strongly to TMS, and parameters such as the stimulation intensity need to be appropriately reduced; at a deeper anesthesia depth, stronger stimulation may be required to cause an effective response. Therefore, the stimulation parameters determined in this way are more in line with the brain state of the target object at that time, and provide suitable stimulation conditions for the subsequent acquisition of valuable TEP data, thereby improving the accuracy of consciousness level assessment.

[0038] Optionally, the method may further include the following steps: B1. Obtain the signal-to-noise ratio of each TEP data in the a TEP data to obtain a signal-to-noise ratio; B2. Determine a signal-to-noise ratio that is not less than a first preset signal-to-noise ratio among the a signal-to-noise ratios, and obtain b signal-to-noise ratios; b is a natural number less than a; B3, determining a first pass rate according to the b signal-to-noise ratios and the a signal-to-noise ratios; B4. When the first qualified rate is less than a preset qualified rate, determining that the a TEP data do not meet the second preset condition; B5. When the first qualified rate is not less than the preset qualified rate, determine the waveform corresponding to each TEP data in the a TEP data to obtain a TEP waveforms; B6. Determine the latency and amplitude corresponding to each of the a TEP waveforms to obtain a latency and a amplitude; B7, determining the target incubation period duration range corresponding to the a incubation periods; B8, determining the target overlap between the target incubation period duration range and the preset incubation period duration range; B9. When the target overlap is less than the preset overlap, determining that the a TEP data do not meet the second preset condition; B10. When the target overlap is not less than the preset overlap, fitting is performed based on the a incubation periods and the starting time corresponding to each incubation period to obtain a first straight line; the horizontal axis is time, and the vertical axis is the duration of the incubation period; B11. Obtaining a first slope corresponding to the first straight line; B12, determining the amplitudes within the preset amplitude range among the a amplitudes, and obtaining c amplitudes; c is a natural number less than a; B13, determining a second pass rate according to the c amplitudes and the a amplitudes; B14. When the first slope is not less than a preset slope, and / or the second pass rate is less than the preset pass rate, determining that the a TEP data do not meet the second preset condition; B15. When the first slope is less than the preset slope and the second pass rate is not less than the preset pass rate, determine that the a TEP data meet the second preset condition.

[0039] In the embodiment of the present application, the first preset signal-to-noise ratio, the preset pass rate, the preset latency period range, the preset overlap degree, the preset amplitude range, and the preset slope can all be preset or defaulted in advance.

[0040] In a specific embodiment, the signal-to-noise ratio of each TEP data among a TEP data can be obtained to obtain a signal-to-noise ratios. Specifically, the signal-to-noise ratios of a TEP data can be calculated using a preset signal-to-noise ratio calculation method to obtain a signal-to-noise ratios, wherein the preset signal-to-noise ratio calculation method can be any one of the following: power spectrum estimation method, root mean square method, peak signal-to-noise ratio method; then, a signal-to-noise ratio that is not less than a first preset signal-to-noise ratio (for example, 3 decibels) can be found out among the a signal-to-noise ratios to obtain b signal-to-noise ratios; a first qualified rate is determined according to the b signal-to-noise ratios and the a signal-to-noise ratios, and the specific calculation formula is as follows: The first pass rate = b / a × 100%; According to the above formula, a first pass rate can be obtained; when the first pass rate is less than the preset pass rate, it can be determined that a TEP data does not meet the second preset condition; When the first qualified rate is not less than the preset qualified rate, a TEP data can be converted into corresponding waveforms to obtain a TEP waveforms. Specifically, each TEP data includes a series of electrophysiological signal intensity values, reflecting the potential changes of the brain after TMS stimulation. Professional drawing software (for example, MATLAB software) can be used to draw according to the a TEP data to obtain a TEP waveform.

[0041] For an example, see Figure 5 , Figure 5 is a waveform diagram of a TEP waveform provided in an embodiment of the present application, such as Figure 5 As shown, the horizontal axis x of the waveform graph is time, the unit is milliseconds (ms), and the vertical axis y is the potential size, the unit can be microvolts (μV).

[0042] Among them, the coordinate origin (0, 0) is the starting moment when the TMS device just starts stimulating, and the latency is the time interval from the starting moment (the coordinate origin) to the appearance of a specific peak or trough in the TEP waveform. It reflects the time required for the nerve impulse to be transmitted from the stimulation point to the brain area where the recording electrode is located, and can be used to evaluate the functional state of the nerve conduction pathway. The peak is the point in the TEP waveform where the potential deviates positively from the baseline (the zero potential line where the horizontal axis is located) to reach the maximum value, representing the positive potential change of the brain's electrical activity. The trough is the point in the TEP waveform where the potential deviates negatively from the baseline to reach the maximum value, representing the negative potential change of the brain's electrical activity. The amplitude is the potential difference from the baseline (i.e., the coordinate axis x) to the peak (or trough), which is used to measure the intensity of a waveform component in the TEP signal. It reflects information such as the number of activated neurons and the synchronization of neuronal activity. The peak-to-peak value is the potential difference between the peak and the trough, which comprehensively considers the maximum positive and negative changes of the TEP waveform and can more comprehensively reflect the dynamic range of potential changes.

[0043] Next, the latency and amplitude corresponding to each TEP waveform in a TEP waveforms can be determined to obtain a latency and a amplitude. Specifically, the a TEP waveforms can be analyzed by professional drawing software to obtain characteristic data of each TEP waveform, and a latency and a amplitude can be extracted from the characteristic data. Then, the target latency duration range corresponding to the a latency can be determined. Specifically, the maximum value and the minimum value in the a latency can be found, and the target latency duration range can be obtained by subtracting the maximum value from the minimum value. Then, the target overlap between the target latency duration range and the preset latency duration range can be determined. Specifically, the overlap duration range between the target latency duration range and the preset latency duration range can be found first. For example, assuming that the target latency duration range is 5 milliseconds to 20 milliseconds and the preset latency duration range is 5 milliseconds to 15 milliseconds, the overlap duration range is 5 milliseconds to 15 milliseconds. The calculation is performed based on the overlap duration range and the preset latency duration range. The specific calculation formula is as follows: Target overlap = overlap duration range / preset latency duration range × 100%; According to the above formula, the target overlap can be obtained; when the target overlap is less than the preset overlap, it can be determined that a TEP data does not meet the second preset condition; When the target overlap is not less than the preset overlap, fitting can be performed based on the a latent periods and the starting moment corresponding to each latent period to obtain a first straight line. Specifically, the starting moment corresponding to each of the a latent periods can be obtained first to obtain a starting moments, and the a starting moments can be combined with the corresponding latent periods in the a latent periods to obtain a coordinate points. The least squares method can be used to fit the a coordinate points, thereby obtaining the first straight line.

[0044] For an example, see Figure 6 , Figure 6 is a schematic diagram of a first straight line L1 provided in an embodiment of the present application, Figure 6 Each black dot in represents one of the a coordinate points mentioned above, and the first straight line L1 can be obtained by fitting based on these black dots.

[0045] Next, the first slope corresponding to the first straight line can be obtained; further, the amplitudes in the preset amplitude range can be found out among the a amplitudes to obtain c amplitudes; then, the second qualified rate can be determined according to the c amplitudes and the a amplitudes, and the specific calculation formula is as follows: The second pass rate = c / a × 100%; The second pass rate can be obtained according to the above formula; when the first slope is not less than the preset slope, and / or the second pass rate is less than the preset pass rate, it is determined that a TEP data does not meet the second preset condition; When the first slope is smaller than the preset slope and the second pass rate is not smaller than the preset pass rate, it is determined that the a TEP data satisfy the second preset condition.

[0046] In this way, by obtaining the signal-to-noise ratio of each TEP data and screening out data with a signal-to-noise ratio not less than a first preset signal-to-noise ratio, data with greater noise interference can be removed, ensuring that the retained data has higher reliability and reducing the impact of noise on subsequent analysis, thereby improving the credibility of TEP data analysis.

[0047] Optionally, in step S302, when the target state includes the brain injury state, determining the target stimulation parameters according to the target state and the target duration may include the following steps: C1. determining a target injury cause corresponding to the brain injury state; C2. determining a third stimulation parameter corresponding to the target injury cause; C3. determining a first stimulation tolerance parameter of the target object according to the target physical health parameter; C4. determining a parameter difference between the first stimulation tolerance parameter and a preset stimulation tolerance parameter to obtain a first parameter difference; C5. estimating the parameter difference corresponding to the target object after the target duration based on the target injury cause, and obtaining a second parameter difference; the target duration is the time from the start time when the target object is determined to be in the brain injury state to the current time; C6. determining a target deviation between the first parameter difference and the second parameter difference; C7. Determine a second influencing factor corresponding to the target deviation; C8. adjusting the third stimulation parameter according to the second influencing factor to obtain a fourth stimulation parameter; C9. When the fourth stimulation parameter is within a preset stimulation parameter range, determining the target stimulation parameter according to the fourth stimulation parameter.

[0048] In the embodiment of the present application, the preset stimulation tolerance parameter can be preset in advance or defaulted. The stimulation tolerance parameter is used to indicate the human body's tolerance to TMS stimulation. The larger the preset stimulation tolerance parameter is, the higher the human body's tolerance to TMS stimulation is.

[0049] In a specific embodiment, a target injury cause corresponding to a brain injury state can be determined. Specifically, the medical record data of the target object can be obtained, and the target injury cause can be determined based on the medical record data. For example, if the medical record data records that the target object "suffered from cardiac arrest, impaired consciousness and limb convulsions after resuscitation", combined with clinical manifestations and related examinations, it can be determined that the brain injury was caused by hypoxia. For another example, if the medical record records that "the patient (i.e., the target object) was involved in a rear-end collision while riding in a car, and his head hit the windshield violently", then the target injury cause of the brain injury can be determined to be head trauma caused by a traffic accident; then, the third stimulation parameter corresponding to the target injury cause can be determined. Specifically, a mapping relationship between a preset injury cause and a stimulation parameter can be pre-stored, and the third stimulation parameter corresponding to the target injury cause can be determined based on the mapping relationship.

[0050] Next, the first stimulation tolerance parameter of the target object can be determined according to the target physical health parameter. Specifically, a mapping relationship between preset physical health parameters and stimulation tolerance parameters can be pre-stored, and the first stimulation tolerance parameter corresponding to the target physical health parameter can be determined based on the mapping relationship; then, the preset stimulation tolerance parameter can be subtracted from the first stimulation tolerance parameter to obtain a first parameter difference; then, based on the target injury cause, the change value of the stimulation tolerance parameter of the target object after the target duration, that is, the second parameter difference, can be estimated. Specifically, clinical research papers, case reports, treatment guidelines, etc. related to the target injury cause can be found. These documents may It contains the data of the brain receiving TMS stimulation after a certain period of time (for example, the target duration) in similar brain injury situations. The second parameter difference is determined based on these data. For example, in the literature on neurorehabilitation after craniocerebral trauma, it is mentioned that one week after the injury (assuming the target duration is one week), the patient's brain's maximum tolerance threshold (stimulation parameter) to TMS stimulation increased by an average of about 15%, so 15% can be used as the second parameter difference; it should be explained that both the first parameter difference and the second parameter difference can be percentages; further, the target deviation between the first parameter difference and the second parameter difference can be calculated, and the specific calculation formula is as follows: Target deviation = |first parameter difference - second parameter difference| / second parameter difference × 100%; According to the above formula, the target deviation can be obtained. Then, the second influencing factor corresponding to the target deviation can be determined. Specifically, a mapping relationship between a preset deviation and an influencing factor can be pre-stored, and the second influencing factor corresponding to the target deviation can be determined based on the mapping relationship. The value range of the second influencing factor can be -0.25~0.25; then, the third stimulation parameter can be adjusted according to the second influencing factor. The specific calculation formula is as follows: The fourth stimulation parameter = the third stimulation parameter × (1 + the second influencing factor); The fourth stimulation parameter can be obtained according to the above formula; when the fourth stimulation parameter is within the preset stimulation parameter range, the fourth stimulation parameter can be directly used as the target stimulation parameter.

[0051] When the fourth stimulation parameter is not within the preset stimulation parameter range, the preset stimulation parameter upper limit and the preset stimulation parameter lower limit of the preset stimulation parameter range can be obtained to determine whether the fourth stimulation parameter is close to the preset stimulation parameter upper limit or the preset stimulation parameter lower limit. If the fourth stimulation parameter is close to the preset stimulation parameter upper limit, the preset stimulation parameter upper limit is used as the target stimulation parameter. If the fourth stimulation parameter is close to the preset stimulation parameter lower limit, the preset stimulation parameter lower limit is used as the target stimulation parameter.

[0052] In this way, by determining the target cause of injury corresponding to the brain injury state, and then finding the corresponding third stimulation parameters, this is a personalized treatment idea based on etiology. Different causes of injury will cause the brain to be in different pathophysiological states, and the response to TMS stimulation will also be different. For example, brain injury caused by trauma may be accompanied by physical damage and local inflammation of brain tissue, which is very different from brain injury caused by cerebrovascular disease (such as hematoma compression and local ischemia after cerebral hemorrhage) in terms of brain microenvironment and neurological function changes. Formulating the initial third stimulation parameters for these different causes of injury can make TMS stimulation more targeted and improve the stimulation effect.

[0053] S303. Within a first preset time period, periodically stimulate the target object with the target stimulation parameters through the transcranial magnetic stimulation device to obtain n first TEP data; each stimulation corresponds to one first TEP data; n is an integer greater than 1.

[0054] In the embodiment of the present application, the first preset time period can be preset in advance or defaulted.

[0055] In a specific embodiment, within a first preset time period, the target object is periodically stimulated with target stimulation parameters by a transcranial magnetic stimulation device, and the TEP data generated by the brain after each stimulation is synchronously recorded by a data recording device (e.g., an electroencephalograph), thereby obtaining n first TEP data.

[0056] S304: De-interference the n first TEP data to obtain n second TEP data.

[0057] In the embodiment of the present application, each of the n first TEP data may be subjected to interference removal (eg, artifact removal, filtering, etc.) to obtain n second TEP data.

[0058] Optionally, step S304, performing interference removal on the n first TEP data to obtain n second TEP data, may include the following steps: S41, obtaining target first TEP data; the target first TEP data is any first TEP data among the n first TEP data; S42, collecting third TEP data of the target object within a third preset time period; the start time of the third preset time period is later than the end time of the second preset time period, and the end time of the third preset time period is earlier than the start time of the first preset time period; S43, removing the maximum value and the minimum value of the third TEP data to obtain fourth TEP data; S44, determining a target mean value corresponding to the fourth TEP data; S45, performing baseline correction on the target first TEP data based on the target mean value to obtain fifth TEP data; S46. Filter the fifth TEP data using a preset filtering algorithm to obtain second TEP data corresponding to the target first TEP data.

[0059] In an embodiment of the present application, the third preset time period and the preset filtering algorithm can be preset or defaulted in advance, wherein the preset filtering algorithm can include at least one of the following: wavelet filtering algorithm, Butterworth filtering algorithm, Chebyshev filtering algorithm, etc., which are not limited here.

[0060] In a specific embodiment, the target first TEP data can be obtained first; then, the third TEP data of the target object can be collected by the TMS device within a third preset time period, and then the maximum and minimum values ​​of the third TEP data can be found, and the maximum and minimum values ​​can be deleted from the third TEP data to obtain fourth TEP data; then, the average value of the fourth TEP data, that is, the target mean value, can be calculated; then, the target first TEP data can be baseline-corrected based on the target mean value to obtain fifth TEP data. Specifically, the potential value at each time point in the target first TEP data can be subtracted from the target mean value to obtain the fifth TEP data, which can eliminate the baseline offset caused by factors such as electrode polarization and slow potential drift, so that the potential change of the fifth TEP data can more truly reflect the brain's response to TMS stimulation; finally, the fifth TEP data can be filtered by a preset filtering algorithm, thereby obtaining second TEP data corresponding to the target first TEP data.

[0061] It should be explained that the third preset time period is a short period of time before TMS stimulation is performed on the target object (such as 100-200 milliseconds before stimulation). During this period of time, the brain's electrical activity is relatively stable, and the potential during this period can be used as a baseline for baseline correction.

[0062] In this way, the target first TEP data is baseline corrected by the target mean, which can eliminate the baseline drift in the data. Baseline drift may be caused by electrode polarization, slow physiological changes (such as changes in body temperature, blood circulation fluctuations, etc.), or external environmental factors (such as electromagnetic interference). The corrected fifth TEP data uses a more stable baseline as a reference, so that the potential changes of the TEP data can more accurately reflect the brain's response to TMS stimulation, rather than being masked or distorted by changes in the baseline, thereby improving the accuracy of the TEP data.

[0063] S305 , determining the second TEP data satisfying the first preset condition among the n second TEP data, and obtaining m second TEP data; m is a positive integer less than or equal to n.

[0064] In the embodiment of the present application, the first preset condition may be preset in advance or defaulted, and the first preset condition is used to determine whether the TEP data is normal data.

[0065] In a specific embodiment, the n second TEP data may be matched with the first preset condition in sequence, and the second TEP data that do not meet the first preset condition may be removed, thereby obtaining m second TEP data.

[0066] S306. Determine m consciousness index values ​​according to the m second TEP data.

[0067] In the embodiment of the present application, an index value calculation may be performed on each of the m second TEP data to obtain m consciousness index values, and each second TEP data corresponds to one consciousness index value.

[0068] Optionally, step S306, determining m consciousness index values ​​according to the m second TEP data, may include the following steps: D1. Acquire target second TEP data; the target second TEP data is any second TEP data among the m second TEP data; D2. Perform singular value decomposition on the target second TEP data to obtain i eigenvalues ​​and i eigenvectors; each eigenvalue corresponds to one eigenvector; i is a positive integer; D3, determining the proportion of the energy of each of the i eigenvalues ​​to the sum of the energies of the i eigenvalues, and obtaining i proportions; Determine the signal-to-noise ratio corresponding to each of the i eigenvectors to obtain i signal-to-noise ratios; D4, sorting the i weights from large to small to obtain a first weight sequence; D5. Selecting feature vectors from the i feature vectors based on the i signal-to-noise ratios and the first weight sequence to obtain j feature vectors; j is a positive integer less than or equal to i; D6. Determine the normalized space-time complexity corresponding to each of the j feature vectors to obtain j normalized space-time complexities; D7. Determine the consciousness index value corresponding to the target second TEP data based on the j normalized spatiotemporal complexities.

[0069] In the embodiment of the present application, the awareness indicator value may be PCIst.

[0070] In a specific embodiment, the target second TEP data may be first obtained, which is recorded as A(P, t), wherein P is the number of data channels, that is, the number of electrode channels used when recording TEP data, reflecting the spatial dimension of data acquisition; t is the number of time samples, representing the number of points for sampling TEP signals in the time dimension, reflecting the time resolution of data acquisition; then, the target second TEP data may be subjected to singular value decomposition, and the specific calculation formula is as follows: ; Wherein, A represents the TEP data matrix corresponding to the target second TEP data; Represents the projection of the TEP data matrix onto the eigenvector The data component obtained in the direction represented; is the i-th eigenvalue, which measures the variance of the data in different principal component directions and reflects the importance of the data in this direction; for The corresponding eigenvectors represent the distribution patterns of the data in different principal component directions. Since singular value decomposition is a conventional technique, the specific singular value decomposition process will not be described here. According to the above formula, i eigenvalues ​​and i eigenvectors can be obtained. Then, the proportion of the energy of each of the i eigenvalues ​​to the sum of the energies of the i eigenvalues ​​can be calculated. The specific calculation formula is as follows: ; in, represents the i-th weight among i weights, is the i-th eigenvalue. According to the above formula, i proportions can be obtained by calculating i times. Further, the signal-to-noise ratio corresponding to each eigenvector of i eigenvectors can be determined. The specific calculation formula is as follows: ; Where t represents time, is the signal-to-noise ratio of the ith eigenvector, represents the time before TMS stimulation, Represents the time after TMS stimulation; calculate i times according to the above formula to obtain i signal-to-noise ratios; then, the i weights can be sorted from large to small to obtain the first weight sequence; then, feature vectors can be selected from the i feature vectors based on the i signal-to-noise ratios and the first weight sequence to obtain j feature vectors; then, the normalized spatiotemporal complexity corresponding to each feature vector in the j feature vectors can be determined to obtain j normalized spatiotemporal complexities. Specifically, the target feature vector can be obtained. The target feature vector is any feature vector in the j feature vectors. The amplitude variation complexity of the target feature vector in the time domain can be quantified by recursive analysis, and the absolute value of the amplitude difference between the two time points can be calculated to obtain the distance matrix. and , corresponding to the situation before and after TMS stimulation, respectively. The specific calculation formula is as follows: ; ; Among them, "||·||" in the above formula means finding the norm, which refers to the norm of the vector here. j and k represent different time points respectively. The two distance matrices are used to measure the difference in the amplitude of the principal component at different time points. Then, the distance matrix can be adjusted according to the preset threshold. and Binarize and get the binary matrix and , calculate the normalized result of the difference between the two binary matrices, the specific calculation formula is as follows: ; in, Represents the binary matrix Sum all the elements in ; Represents the binary matrix Sum all the elements in , Represents the normalized space-time complexity of the target feature vector. According to the above formula, j normalized space-time complexities can be calculated j times to obtain j normalized space-time complexities. Finally, these j normalized space-time complexities can be added up to obtain the consciousness index value corresponding to the target second TEP data.

[0071] In this way, by comprehensively considering multiple parameters such as eigenvalues ​​and signal-to-noise ratios to select eigenvectors, we can adapt to TEP data with different characteristics. For example, for TEP data with different noise levels and different brain electrical activity patterns, we can extract the most relevant information by adjusting the criteria for selecting eigenvectors (based on signal-to-noise ratios and weight sequences), thereby ensuring the accuracy and reliability of the calculation of consciousness index values ​​and making it play a role in different application scenarios.

[0072] Optionally, step D5, selecting feature vectors from the i feature vectors based on the i signal-to-noise ratios and the first weight sequence to obtain j feature vectors, may include the following steps: E1. Determine a signal-to-noise ratio greater than a second preset signal-to-noise ratio among the i signal-to-noise ratios, and obtain k signal-to-noise ratios; k is a positive integer not greater than i and not less than j; E2. Selecting k weights from the first weight sequence based on the k signal-to-noise ratios, and sorting the k weights from large to small to obtain a second weight sequence; E3, selecting weights from the second weight sequence in order until the sum of the selected weights is greater than the preset weight, to obtain j weights; E4. Determine the eigenvector corresponding to each of the j eigenweights to obtain the j eigenvectors.

[0073] In the embodiment of the present application, the second preset signal-to-noise ratio and the preset weight may be preset or defaulted in advance.

[0074] In a specific embodiment, each of the i signal-to-noise ratios may be compared with a second preset signal-to-noise ratio (e.g., 1.2 decibels) to obtain k signal-to-noise ratios greater than the second preset signal-to-noise ratio; then, a weight corresponding to each of the k signal-to-noise ratios may be found from the first weight sequence to obtain k weights, and the k weights may be sorted from large to small to obtain a second weight sequence; further, weights may be selected from the second weight sequence in order until the sum of the selected weights is greater than a preset weight (e.g., 0.99) to obtain j weights. Specifically, the sum of the first weights may be initialized to 0, and the sum of the first weights may be sorted from the second weight sequence in order. Select weights from the weight sequence, and each time a weight is selected, add the weight to the first weight sum, then compare the first weight sum with the preset weights to obtain the size relationship between the two. If the first weight sum is greater than the preset weight, all the selected weights can be used as j weights. Otherwise, if the first weight sum is not greater than the preset weight, continue to select weights from the second weight sequence, and add the selected weights to the first weight sum until the first weight sum is greater than the preset weight, and obtain j weights. Finally, the eigenvector corresponding to each of the j weights in the i eigenvectors can be determined to obtain j eigenvectors.

[0075] In this way, by setting the second preset signal-to-noise ratio for screening, those feature vectors with higher signal quality can be retained preferentially, so that subsequent analysis can focus more on real and reliable brain electrical activity information, thereby improving the accuracy of consciousness level assessment.

[0076] S307. Determine the target consciousness state of the target object according to the m consciousness index values; the target consciousness state includes any one of the following: awake, drowsy, confused, lethargic, and coma.

[0077] In an embodiment of the present application, the average value of m consciousness index values ​​can be calculated to obtain the target consciousness index mean, and then the target consciousness state can be determined based on the target consciousness index mean. For example, a mapping relationship between a preset consciousness index mean and a consciousness state can be pre-stored, and the target consciousness state corresponding to the target consciousness index mean can be determined based on the mapping relationship.

[0078] The implementation of this application has the following beneficial effects: It can be seen that the method for evaluating the level of consciousness based on TEP data described in the embodiment of the present application includes: obtaining a target state of a target object and a target duration corresponding to the target state; determining target stimulation parameters according to the target state and the target duration; within a first preset time period, periodically stimulating the target object with the target stimulation parameters through a transcranial magnetic stimulation device to obtain n first TEP data; de-interfering the n first TEP data to obtain n second TEP data; determining the second TEP data that meets the first preset condition among the n second TEP data to obtain m second TEP data; determining m consciousness index values ​​according to the m second TEP data; determining the target consciousness state of the target object according to the m consciousness index values; by collecting the TEP data of the target object, the TEP data is the direct electrophysiological response of the brain to stimulation and can more truly reflect the state of consciousness of a person, analyzing the TEP data to obtain the consciousness index value, and determining the level of consciousness of the target object according to the consciousness index value, thereby achieving the evaluation of the level of consciousness of the target object when the target object cannot interact with the environment.

[0079] See also Figure 7 , Figure 7 : is a functional unit composition block diagram of a consciousness level assessment device 700 based on TEP data provided in an embodiment of the present application, which is applied to an electronic device, wherein the electronic device is connected to a transcranial magnetic stimulation device, and the consciousness level assessment device 700 based on TEP data includes: an acquisition unit 701, a control unit 702, and an assessment unit 703, wherein: The acquisition unit 701 is used to acquire a target state of a target object and a target duration corresponding to the target state; the target state includes any one of the following: anesthesia state, brain injury state; The control unit 702 is used to determine the target stimulation parameters according to the target state and the target duration; within a first preset time period, the target object is periodically stimulated by the transcranial magnetic stimulation device with the target stimulation parameters to obtain n first TEP data; each stimulation corresponds to one first TEP data; n is an integer greater than 1; the n first TEP data are de-interfered to obtain n second TEP data; the second TEP data satisfying the first preset condition among the n second TEP data is determined to obtain m second TEP data; m is a positive integer less than or equal to n; The evaluation unit 703 is used to determine m consciousness index values ​​according to the m second TEP data; determine the target consciousness state of the target object according to the m consciousness index values; the target consciousness state includes any one of the following: wakefulness, drowsiness, confusion, lethargy, and coma.

[0080] Optionally, when the target state includes the anesthesia state, in determining the target stimulation parameter according to the target state and the target duration, the control unit 702 is specifically configured to: obtaining a target drug type and a target anesthetic drug amount of the anesthetic drug to be injected into the target subject; estimating the onset time of the first drug required for the target subject to reach a preset anesthesia depth according to the target drug type and the target anesthetic amount; estimating the target anesthesia depth of the target subject at the current moment according to the first drug onset time, the target duration and the preset anesthesia depth; the target duration is the time between the injection time of the anesthetic drug and the current moment; determining a first stimulation parameter corresponding to the target anesthesia depth; Acquire target physical health parameters of the target object; Determining a first influencing factor corresponding to the target physical health parameter; Adjusting the first stimulation parameter according to the first influencing factor to obtain a second stimulation parameter; In a second preset time period, the target object is periodically stimulated by the transcranial magnetic stimulation device with the second stimulation parameter to obtain a reference TEP data; a is a positive integer less than n; each stimulation corresponds to a reference TEP data; the end time of the second preset time period is earlier than the start time of the first preset time period; De-interference is performed on the a reference TEP data to obtain a TEP data; When the a TEP data meet a second preset condition, the target stimulation parameter is determined according to the second stimulation parameter.

[0081] Optionally, the consciousness level assessment device 700 based on TEP data is further specifically used for: Obtaining a signal-to-noise ratio of each TEP data in the a TEP data to obtain a signal-to-noise ratios; Determine a signal-to-noise ratio that is not less than a first preset signal-to-noise ratio among the a signal-to-noise ratios, and obtain b signal-to-noise ratios; b is a natural number less than a; Determine a first pass rate according to the b signal-to-noise ratios and the a signal-to-noise ratios; When the first pass rate is less than a preset pass rate, determining that the a TEP data do not meet the second preset condition; When the first qualified rate is not less than the preset qualified rate, determining a waveform corresponding to each TEP data in the a TEP data to obtain a TEP waveforms; Determine the latency and amplitude corresponding to each of the a TEP waveforms to obtain a latency and a amplitude; Determine the target incubation period duration range corresponding to the a incubation periods; Determining a target overlap between the target incubation period duration range and a preset incubation period duration range; When the target overlap is less than the preset overlap, determining that the a TEP data do not meet the second preset condition; When the target overlap is not less than the preset overlap, fitting is performed based on the a latent periods and the starting time corresponding to each latent period to obtain a first straight line; the horizontal axis is time, and the vertical axis is the duration of the latent period; Obtaining a first slope corresponding to the first straight line; Determine the amplitudes within the preset amplitude range among the a amplitudes to obtain c amplitudes; c is a natural number less than a; Determining a second pass rate according to the c amplitudes and the a amplitudes; When the first slope is not less than a preset slope, and / or the second pass rate is less than the preset pass rate, determining that the a TEP data do not meet the second preset condition; When the first slope is smaller than the preset slope and the second pass rate is not smaller than the preset pass rate, it is determined that the a TEP data meet the second preset condition.

[0082] Optionally, when the target state includes the brain injury state, in determining the target stimulation parameters according to the target state and the target duration, the control unit 702 is specifically configured to: determining a target injury cause corresponding to the brain injury state; Determining a third stimulation parameter corresponding to the target injury cause; determining a first stimulation tolerance parameter of the target object according to the target physical health parameter; determining a parameter difference between the first stimulation tolerance parameter and a preset stimulation tolerance parameter to obtain a first parameter difference; estimating a parameter difference corresponding to the target object after the target duration based on the target injury cause, and obtaining a second parameter difference; the target duration is the time between the start time when the target object is determined to be in the brain injury state and the current time; determining a target deviation between the first parameter difference and the second parameter difference; Determining a second influencing factor corresponding to the target deviation; adjusting the third stimulation parameter according to the second influencing factor to obtain a fourth stimulation parameter; When the fourth stimulation parameter is within a preset stimulation parameter range, the target stimulation parameter is determined according to the fourth stimulation parameter.

[0083] Optionally, in the aspect of removing interference from the n first TEP data to obtain n second TEP data, the control unit 702 is specifically configured to: Acquire target first TEP data; the target first TEP data is any first TEP data among the n first TEP data; collecting third TEP data of the target object within a third preset time period; the start time of the third preset time period is later than the end time of the second preset time period, and the end time of the third preset time period is earlier than the start time of the first preset time period; Removing the maximum value and the minimum value of the third TEP data to obtain fourth TEP data; Determining a target mean value corresponding to the fourth TEP data; Baseline-correct the target first TEP data based on the target mean value to obtain fifth TEP data; The fifth TEP data is filtered by a preset filtering algorithm to obtain second TEP data corresponding to the target first TEP data.

[0084] Optionally, in determining the m consciousness index values ​​according to the m second TEP data, the evaluation unit 703 is specifically configured to: Acquire target second TEP data; the target second TEP data is any second TEP data among the m second TEP data; Perform singular value decomposition on the target second TEP data to obtain i eigenvalues ​​and i eigenvectors; each eigenvalue corresponds to an eigenvector; i is a positive integer; Determine the proportion of the energy of each of the i eigenvalues ​​to the sum of the energies of the i eigenvalues ​​to obtain i proportions; Determine the signal-to-noise ratio corresponding to each of the i eigenvectors to obtain i signal-to-noise ratios; Sort the i weights from large to small to obtain a first weight sequence; Selecting feature vectors from the i feature vectors based on the i signal-to-noise ratios and the first weight sequence to obtain j feature vectors; j is a positive integer less than or equal to i; Determine the normalized space-time complexity corresponding to each of the j feature vectors to obtain j normalized space-time complexities; Determine the consciousness index value corresponding to the target second TEP data according to the j normalized spatiotemporal complexities.

[0085] Optionally, the selecting feature vectors from the i feature vectors based on the i signal-to-noise ratios and the first weight sequence to obtain j feature vectors, the evaluating unit 703 is specifically configured to: Determine a signal-to-noise ratio greater than a second preset signal-to-noise ratio among the i signal-to-noise ratios, and obtain k signal-to-noise ratios; k is a positive integer not greater than i and not less than j; Selecting k weights from the first weight sequence based on the k signal-to-noise ratios, and sorting the k weights from large to small to obtain a second weight sequence; Selecting weights from the second weight sequence in order until the sum of the selected weights is greater than the preset weight, to obtain j weights; Determine a feature vector corresponding to each of the j features to obtain the j feature vectors.

[0086] It can be understood that the functions of each unit module of the consciousness level assessment device 700 based on TEP data provided in this embodiment can be specifically implemented according to the method in the above method embodiment, and its specific implementation process can refer to the relevant description of the above method embodiment, which will not be repeated here.

[0087] See also Figure 8 , Figure 8 It is a structural diagram of an electronic device provided in an embodiment of the present application, and the electronic device includes a processor, a memory, a communication interface and one or more programs. The processor, the memory and the communication interface are interconnected through a bus. The one or more programs are stored in the memory and are configured to be executed by the processor. The one or more programs include instructions for executing other implementations described in the method for assessing the level of consciousness based on TEP data provided in the above embodiment of the present invention, which will not be repeated here.

[0088] An embodiment of the present invention also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments, and the above computer includes an electronic device.

[0089] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0090] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0091] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0093] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0094] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0095] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the above-mentioned methods in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0096] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for assessing the level of consciousness based on TEP data, characterized in that: Applied to an electronic device, the electronic device is connected to a transcranial magnetic stimulation device, and the method comprises: Acquire a target state of a target object and a target duration corresponding to the target state; the target state includes any one of the following: anesthesia state, brain injury state; Determining target stimulation parameters according to the target state and the target duration; In a first preset time period, the target object is periodically stimulated by the transcranial magnetic stimulation device with the target stimulation parameters to obtain n first TEP data; each stimulation corresponds to one first TEP data; n is an integer greater than 1; De-interference is performed on the n first TEP data to obtain n second TEP data; Determine the second TEP data that meets the first preset condition among the n second TEP data to obtain m second TEP data; m is a positive integer less than or equal to n; Determine m consciousness index values ​​according to the m second TEP data; The target consciousness state of the target object is determined according to the m consciousness index values; the target consciousness state includes any one of the following: awake, drowsy, confused, lethargic, and coma.

2. The method according to claim 1, characterized in that When the target state includes the anesthesia state, determining the target stimulation parameter according to the target state and the target duration includes: obtaining a target drug type and a target anesthetic drug amount of the anesthetic drug to be injected into the target subject; estimating the onset time of the first drug required for the target subject to reach a preset anesthesia depth according to the target drug type and the target anesthetic amount; estimating the target anesthesia depth of the target subject at the current moment according to the first drug onset time, the target duration and the preset anesthesia depth; the target duration is the time between the injection time of the anesthetic drug and the current moment; determining a first stimulation parameter corresponding to the target anesthesia depth; Acquire target physical health parameters of the target object; Determining a first influencing factor corresponding to the target physical health parameter; Adjusting the first stimulation parameter according to the first influencing factor to obtain a second stimulation parameter; In a second preset time period, the target object is periodically stimulated by the transcranial magnetic stimulation device with the second stimulation parameter to obtain a reference TEP data; a is a positive integer less than n; each stimulation corresponds to a reference TEP data; the end time of the second preset time period is earlier than the start time of the first preset time period; De-interference is performed on the a reference TEP data to obtain a TEP data; When the a TEP data meet a second preset condition, the target stimulation parameter is determined according to the second stimulation parameter.

3. The method according to claim 2, characterized in that The method further comprises: Obtaining a signal-to-noise ratio of each TEP data in the a TEP data to obtain a signal-to-noise ratios; Determine a signal-to-noise ratio that is not less than a first preset signal-to-noise ratio among the a signal-to-noise ratios, and obtain b signal-to-noise ratios; b is a natural number less than a; Determine a first pass rate according to the b signal-to-noise ratios and the a signal-to-noise ratios; When the first pass rate is less than a preset pass rate, determining that the a TEP data do not meet the second preset condition; When the first qualified rate is not less than the preset qualified rate, determining a waveform corresponding to each TEP data in the a TEP data to obtain a TEP waveforms; Determine the latency and amplitude corresponding to each of the a TEP waveforms to obtain a latency and a amplitude; Determine the target incubation period duration range corresponding to the a incubation periods; Determining a target overlap between the target incubation period duration range and a preset incubation period duration range; When the target overlap is less than the preset overlap, determining that the a TEP data do not meet the second preset condition; When the target overlap is not less than the preset overlap, fitting is performed based on the a latent periods and the starting time corresponding to each latent period to obtain a first straight line; the horizontal axis is time, and the vertical axis is the duration of the latent period; Obtaining a first slope corresponding to the first straight line; Determine the amplitudes within the preset amplitude range among the a amplitudes to obtain c amplitudes; c is a natural number less than a; Determining a second pass rate according to the c amplitudes and the a amplitudes; When the first slope is not less than a preset slope, and / or the second pass rate is less than the preset pass rate, determining that the a TEP data do not meet the second preset condition; When the first slope is smaller than the preset slope and the second pass rate is not smaller than the preset pass rate, it is determined that the a TEP data meet the second preset condition.

4. The method according to claim 2, characterized in that When the target state includes the brain injury state, determining the target stimulation parameter according to the target state and the target duration includes: determining a target injury cause corresponding to the brain injury state; Determining a third stimulation parameter corresponding to the target injury cause; determining a first stimulation tolerance parameter of the target object according to the target physical health parameter; determining a parameter difference between the first stimulation tolerance parameter and a preset stimulation tolerance parameter to obtain a first parameter difference; estimating a parameter difference corresponding to the target object after the target duration based on the target injury cause, and obtaining a second parameter difference; the target duration is the time between the start time when the target object is determined to be in the brain injury state and the current time; determining a target deviation between the first parameter difference and the second parameter difference; Determining a second influencing factor corresponding to the target deviation; adjusting the third stimulation parameter according to the second influencing factor to obtain a fourth stimulation parameter; When the fourth stimulation parameter is within a preset stimulation parameter range, the target stimulation parameter is determined according to the fourth stimulation parameter.

5. The method according to any one of claims 2 to 4, characterized in that: The step of removing interference from the n first TEP data to obtain n second TEP data includes: Acquire target first TEP data; the target first TEP data is any first TEP data among the n first TEP data; collecting third TEP data of the target object within a third preset time period; the start time of the third preset time period is later than the end time of the second preset time period, and the end time of the third preset time period is earlier than the start time of the first preset time period; Removing the maximum value and the minimum value of the third TEP data to obtain fourth TEP data; Determining a target mean value corresponding to the fourth TEP data; Baseline-correct the target first TEP data based on the target mean value to obtain fifth TEP data; The fifth TEP data is filtered by a preset filtering algorithm to obtain second TEP data corresponding to the target first TEP data.

6. The method according to any one of claims 1 to 4, characterized in that: The determining m consciousness index values ​​according to the m second TEP data comprises: Acquire target second TEP data; the target second TEP data is any second TEP data among the m second TEP data; Perform singular value decomposition on the target second TEP data to obtain i eigenvalues ​​and i eigenvectors; each eigenvalue corresponds to an eigenvector; i is a positive integer; Determine the proportion of the energy of each of the i eigenvalues ​​to the sum of the energies of the i eigenvalues ​​to obtain i proportions; Determine the signal-to-noise ratio corresponding to each of the i eigenvectors to obtain i signal-to-noise ratios; Sort the i weights from large to small to obtain a first weight sequence; Selecting feature vectors from the i feature vectors based on the i signal-to-noise ratios and the first weight sequence to obtain j feature vectors; j is a positive integer less than or equal to i; Determine the normalized space-time complexity corresponding to each of the j feature vectors to obtain j normalized space-time complexities; Determine the consciousness index value corresponding to the target second TEP data according to the j normalized spatiotemporal complexities.

7. The method according to claim 6, characterized in that The step of selecting feature vectors from the i feature vectors based on the i signal-to-noise ratios and the first weight sequence to obtain j feature vectors includes: Determine a signal-to-noise ratio greater than a second preset signal-to-noise ratio among the i signal-to-noise ratios, and obtain k signal-to-noise ratios; k is a positive integer not greater than i and not less than j; Selecting k weights from the first weight sequence based on the k signal-to-noise ratios, and sorting the k weights from large to small to obtain a second weight sequence; Selecting weights from the second weight sequence in order until the sum of the selected weights is greater than the preset weight, to obtain j weights; Determine a feature vector corresponding to each of the j features to obtain the j feature vectors.

8. A consciousness level assessment device based on TEP data, characterized in that: Applied to an electronic device, the electronic device is connected to a transcranial magnetic stimulation device, the device comprises: an acquisition unit, a control unit, and an evaluation unit, wherein: The acquisition unit is used to acquire a target state of the target object and a target duration corresponding to the target state; the target state includes any one of the following: an anesthesia state and a brain injury state; The control unit is used to determine the target stimulation parameters according to the target state and the target duration; within a first preset time period, the target object is periodically stimulated by the transcranial magnetic stimulation device with the target stimulation parameters to obtain n first TEP data; each stimulation corresponds to one first TEP data; n is an integer greater than 1; the n first TEP data are de-interfered to obtain n second TEP data; the second TEP data that meets the first preset condition among the n second TEP data is determined to obtain m second TEP data; m is a positive integer less than or equal to n; The evaluation unit is used to determine m consciousness index values ​​according to the m second TEP data; determine the target consciousness state of the target object according to the m consciousness index values; the target consciousness state includes any one of the following: wakefulness, drowsiness, confusion, lethargy, and coma.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store one or more programs and is configured to be executed by the processor, wherein the program includes instructions for executing the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 7.

Images