A brain state transition prediction method and apparatus

Abstract

This invention discloses a method and device for predicting brain state transitions. The method includes: acquiring real-time electroencephalogram (EEG) signals of a target subject; calculating an energy index characterizing the level of local energy mobilization in the brain based on the EEG signals, the energy index reflecting the brain's control intention to change its current state; calculating a dynamic index characterizing the dynamic flexibility of the brain network based on the EEG signals, the dynamic index reflecting the brain network's ability to switch between different modes; calculating a control conflict index based on the nonlinear coupling relationship between the energy index and the dynamic index; and generating an early warning signal indicating that a critical state transition is imminent when the control conflict index exceeds a preset critical threshold. This invention achieves early warning of brain state transitions, realizing a leap from "reactive monitoring" to "predictive intervention," and can be widely applied in multiple fields such as anesthesia recovery prediction, epileptic seizure warning, and fatigue driving monitoring.

Description

Technical Field

[0001] This invention relates to the field of neural computing and biological signal processing technology, and in particular to a method and device for predicting brain state transitions. Background Technology

[0002] The brain, as the most complex dynamic system in the universe, has a state of operation (such as wakefulness, sleep, and anesthesia) that is far more complex than a simple on / off switch.

[0003] Existing technologies, such as clinical anesthesia monitors or epilepsy monitoring devices, are mostly based on "post-hoc" analysis of electroencephalogram (EEG) signals. This is similar to judging a car's speed by looking at the readings on the dashboard, rather than predicting what the driver is "about to" do. This "reactive" monitoring has inherent delays, missing valuable intervention windows in many high-risk scenarios (such as post-operative recovery, epileptic seizures, and pilot fatigue).

[0004] Therefore, there is an urgent need for a method that can predict changes in brain state in advance. Summary of the Invention

[0005] In view of the above problems, the present invention is proposed to provide a method and apparatus for predicting brain state transitions that overcomes or at least partially solves the above problems.

[0006] One embodiment of the present invention provides a method for predicting brain state transitions, the method comprising: Acquire real-time EEG signals of the target subject; Based on the electroencephalogram (EEG) signals, an energy index is calculated to characterize the level of local energy mobilization in the brain. The energy index reflects the brain's control intention to try to change the current state. Based on the electroencephalogram (EEG) signals, dynamic indicators characterizing the dynamic flexibility of the brain network are calculated, and these dynamic indicators reflect the brain network's ability to switch between different modes. Based on the nonlinear coupling relationship between the energy index and the kinetic index, a control conflict index is calculated; wherein the control conflict index increases nonlinearly when the energy index increases and the kinetic index decreases. The system monitors the changing trend of the control conflict index in real time, and generates an early warning signal that the brain is about to undergo a critical state transition when the control conflict index exceeds a preset critical threshold.

[0007] Optionally, the energy index is calculated based on the power of the high-frequency Gamma band of the EEG signal.

[0008] Optionally, the kinetic index is calculated based on the instantaneous frequency fluctuation rate of the EEG signal, which is obtained by applying empirical mode decomposition and Hilbert-Huang transform to the EEG signal.

[0009] Optionally, before calculating the volatility of the instantaneous frequency, a state adaptive selection step is further included: Based on the macroscopic brain state of the target object, the key modal component carrying the deadlock signal is automatically selected from the multiple intrinsic modal function components; The fluctuation rate of the instantaneous frequency is calculated for the key modal components.

[0010] Optionally, calculating the control conflict index based on the nonlinear coupling relationship between the energy index and the kinetic index includes calculating the control conflict index using the following formula: in, To control the conflict index, As a scale factor, As an energy indicator, For dynamic indicators, and It is a nonlinear enhancement index. and , To prevent extremely small constants with a denominator of zero.

[0011] Optionally, calculating the control conflict index based on the nonlinear coupling relationship between the energy index and the kinetic index includes calculating the control conflict index using the following formula: in, To control the conflict index, As a scale factor, As an energy indicator, For dynamic indicators, and It is a nonlinear enhancement index. and .

[0012] Optionally, the impending critical state transition of the brain includes at least one of the following: transition from anesthesia to wakefulness, onset of an epileptic seizure, or transition from wakefulness to sleep or microsleep.

[0013] Another embodiment of the present invention provides a brain state transition prediction device, the device comprising: The EEG signal acquisition unit is used to acquire real-time EEG signals of the target object; An energy index calculation unit is used to calculate an energy index that characterizes the level of local energy mobilization in the brain based on the electroencephalogram (EEG) signal. The energy index reflects the brain’s control intention to try to change the current state. The dynamic index calculation unit is used to calculate dynamic indices characterizing the dynamic flexibility of the brain network based on the electroencephalogram (EEG) signals. These dynamic indices reflect the brain network's ability to switch between different modes. A control conflict index calculation unit is used to calculate a control conflict index based on the nonlinear coupling relationship between the energy index and the kinetic index; wherein the control conflict index increases nonlinearly when the energy index increases and the kinetic index decreases. The early warning unit is used to monitor the changing trend of the control conflict index in real time. When the control conflict index exceeds a preset critical threshold, it generates an early warning signal that the brain is about to undergo a critical state transition.

[0014] Optionally, the energy index is calculated based on the power of the high-frequency Gamma band of the EEG signal.

[0015] Optionally, the kinetic index is calculated based on the instantaneous frequency fluctuation rate of the EEG signal, which is obtained by applying empirical mode decomposition and Hilbert-Huang transform to the EEG signal.

[0016] Optionally, it also includes a state adaptation unit, which is used to automatically select key mode components carrying deadlock signals from the plurality of intrinsic mode function components based on the macroscopic brain state of the target object before calculating the volatility of the instantaneous frequency; The fluctuation rate of the instantaneous frequency is calculated for the key modal components.

[0017] Optionally, the control conflict index calculation unit is further configured to calculate the control conflict index using the following formula: in, To control the conflict index, As a scale factor, As an energy indicator, For dynamic indicators, and It is a nonlinear enhancement index. and , To prevent extremely small constants with a denominator of zero.

[0018] Optionally, the control conflict index calculation unit is further configured to calculate the control conflict index using the following formula: in, To control the conflict index, As a scale factor, As an energy indicator, For dynamic indicators, and It is a nonlinear enhancement index. and .

[0019] Optionally, the impending critical state transition of the brain includes at least one of the following: transition from anesthesia to wakefulness, onset of an epileptic seizure, or transition from wakefulness to sleep or microsleep.

[0020] Another embodiment of the present invention provides an electronic device, wherein the electronic device includes: Processor; and, A memory is configured to store computer-executable instructions, which, when executed, cause the processor to perform the brain state transition prediction method described above.

[0021] Another embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, which, when executed by a processor, implement the above-described brain state transition prediction method.

[0022] The beneficial effects of this invention are as follows: This invention achieves a leap from "reactive monitoring" to "predictive early warning." By capturing the intrinsic driving force of state transitions—control conflict—it can issue early warning signals seconds to minutes before brain state changes occur, providing valuable time for clinical intervention or safety measures. This invention constructs a detection mechanism based on the nonlinear coupling of two-dimensional indicators, possessing extremely high signal-to-noise ratio and specificity. The control conflict index only produces a significant peak when two opposing phenomena—an abnormally high energy index and an abnormally low kinetic index—occur simultaneously, effectively avoiding false alarms caused by fluctuations in a single indicator. This invention has the potential for platform-based applications. The neural inertia principle and control conflict model upon which it is based are universal and adaptable to various scenarios such as anesthesia recovery prediction, epileptic seizure early warning, driver fatigue and microsleep monitoring, with a wide range of applications.

[0023] In addition, this invention introduces a state adaptive selection mechanism, which can dynamically adjust the selection of key modal components according to the macroscopic brain state, thereby improving the accuracy of index calculation. Attached Figure Description

[0024] Figure 1 This is a flowchart of a brain state transition prediction method according to an embodiment of the present invention; Figure 2This is a schematic diagram illustrating the principle of the control conflict index time evolution and early warning mechanism according to an embodiment of the present invention; Figure 3A This is a user interface diagram of an anesthesia monitoring scenario according to an embodiment of the present invention; Figure 3B This is a user interface diagram of an epilepsy early warning scenario according to an embodiment of the present invention; Figure 3C This is a user interface diagram of a fatigue driving monitoring scenario according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of a brain state transition prediction device according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of a computer-readable storage medium according to an embodiment of the present invention. Detailed Implementation

[0025] The theoretical foundation of this invention stems from a profound insight that transcends neuroscience and physics: "Neural Inertia." Similar to the physical inertia described by Newton's First Law, once the brain network stabilizes in a certain state (such as deep anesthesia or focused driving), it generates a powerful "inertia" that resists changes in that state.

[0026] To break through this "neural inertia" and complete the state transition, the brain must perform a drastic, non-linear "forced reboot." Analogous to the working principle of a thermodynamic engine, the brain can be viewed as a "cognitive engine." In this model, the "forced reboot" process inevitably triggers a violent internal conflict, which we define as a "cognitive engine control conflict," the core of which is: "Energetic Surge": In an attempt to break free from the constraints of "neural inertia," local control modules in the brain explosively mobilize energy, manifesting as a surge in the power of high-frequency neural oscillations (such as Gamma waves). This is the system's "control intention" to forcibly change its state.

[0027] "Dynamic Stalemate": However, due to the enormous resistance of "neural inertia," the dynamic flexibility of the entire brain network—that is, the ability of neural pathways to switch between different modes—cannot keep up and is instead temporarily "locked up" or "rigidified," manifested as a sudden collapse of nonlinear dynamic indicators of signals (such as instantaneous frequency fluctuation rate IFV). This is a "dynamic stalemate" in which the system is trapped in its current state.

[0028] This sharp contradiction between "control intention" and "dynamic deadlock" is the earliest and most reliable internal signal that the "cognitive engine" is about to become unstable and undergo a critical phase transition (state transition). It's like an aircraft stalling before its engine is roaring wildly while its wings have already lost lift.

[0029] However, to date, no technology has been able to directly quantify this cross-dimensional "control conflict" and transform it into a universal, predictable biomarker.

[0030] This invention aims to provide a novel and universal method and device for predicting brain state transitions. Instead of relying on descriptions of single states, it directly quantifies the "control conflict" generated by the "cognitive engine" in counteracting "neural inertia," thereby predicting critical state transitions that will occur in the brain before any observable external behavior or macroscopic state change takes place.

[0031] Figure 1 This is a flowchart illustrating a brain state transition prediction method according to an embodiment of the present invention. Figure 1 As shown, the method includes: S101: Acquire real-time EEG signals of the target object; In practical applications, multi-channel EEG signals of the target subject are acquired in real time using EEG acquisition equipment at a preset sampling frequency (e.g., 250-1024Hz). During the acquisition process, the signals can be preprocessed, such as bandpass filtering (e.g., 0.5-90Hz) and power frequency notch filtering.

[0032] S102: Calculate an energy index characterizing the level of local energy mobilization in the brain based on the electroencephalogram (EEG) signal, wherein the energy index reflects the brain’s control intention to change the current state. S103: Calculate a dynamic index based on the EEG signal to characterize the dynamic flexibility of the brain network, the dynamic index reflecting the brain network’s ability to switch between different modes; S104: Calculate the control conflict index based on the nonlinear coupling relationship between the energy index and the kinetic index; wherein the control conflict index increases nonlinearly when the energy index increases and the kinetic index decreases; In practical applications, the energy index, dynamic index, and control conflict index can be calculated based on a real-time sliding time window.

[0033] The embodiments of the present invention nonlinearly couple "increased energy" and "decreased flexibility" based on the control conflict index. When both occur simultaneously, the control conflict index will show explosive growth, thereby issuing an early warning several seconds to several minutes before the brain state changes.

[0034] S105: Monitor the changing trend of the control conflict index in real time, and generate an early warning signal that the brain is about to undergo a critical state transition when the control conflict index exceeds a preset critical threshold.

[0035] In practical applications, when the control conflict index exceeds a threshold and persists for a certain period of time (e.g., 2-10 seconds), a warning signal is generated indicating that the brain is about to undergo a critical state transition. This warning signal can trigger sound, light, vibration, or system intervention commands.

[0036] This invention represents a leap from "reactive monitoring" to "predictive early warning." By capturing the intrinsic driving force behind state transitions—control conflict—it can issue early warning signals seconds to minutes before brain state changes occur, providing valuable time for clinical intervention or safety measures. This invention constructs a detection mechanism based on the nonlinear coupling of two-dimensional indicators, exhibiting extremely high signal-to-noise ratio and specificity. The control conflict index only produces a significant peak when two opposing phenomena—an abnormally high energy index and an abnormally low kinetic index—occur simultaneously, effectively avoiding false alarms caused by fluctuations in a single indicator. This invention has platform application potential; the underlying neural inertia principle and control conflict model are universal and adaptable to various scenarios such as anesthesia recovery prediction, epileptic seizure early warning, driver fatigue and microsleep monitoring, with a wide range of applications.

[0037] In an optional embodiment of the present invention, the energy index is calculated based on the power of the high-frequency Gamma band of the electroencephalogram signal.

[0038] Understandably, the energy bursts in the Gamma band (such as 30-80Hz) directly reflect the highly synchronized activity of local neuronal clusters, corresponding to the brain's "accelerator-slamming" energy mobilization in order to break through inertia.

[0039] In this embodiment of the invention, the energy index is calculated based on the power of the high-frequency Gamma band (30-80Hz) of the EEG signal. Specifically, time-frequency analysis (such as short-time Fourier transform or wavelet transform) is performed on the EEG signal within each sliding time window to calculate the power spectral density of each channel in the Gamma band, and the median or mean of each channel is taken to obtain the global Gamma power P_γ at that moment.

[0040] To improve the comparability of the indicators, P_γ is normalized by quantiles to obtain the normalized energy index γ_norm∈[0,1]. The closer γ_norm is to 1, the stronger the energy mobilization.

[0041] Furthermore, the dynamic index is calculated based on the instantaneous frequency fluctuation rate of the EEG signal, which is obtained by applying empirical mode decomposition and Hilbert-Huang transform to the EEG signal.

[0042] Understandably, the lower the instantaneous frequency fluctuation rate, the weaker the brain network's ability to switch between different modes.

[0043] This invention likens the brain to a "cognitive engine." When the brain attempts to change its state, a phenomenon occurs simultaneously where "accelerator pedal is floored" (energy indicators rise, manifested as a burst of Gamma waves) and "gearbox jams" (dynamic indicators decrease, manifested as a collapse of network flexibility). This "control conflict" is a precursor to a change in the brain's state.

[0044] Preferably, to improve the sensitivity of the dynamic indicators to state transitions, a state adaptive selection step is included before calculating the fluctuation rate of the instantaneous frequency: Based on the macroscopic brain state of the target object, the key modal component carrying the deadlock signal is automatically selected from the multiple intrinsic modal function components (for example, in the anesthetized state, the lower frequency band IMF component is preferentially selected, while in the awake state, the higher frequency band IMF component can be selected, or the key component is automatically determined based on the relative change of the baseline volatility). The fluctuation rate of the instantaneous frequency is calculated for the key modal components.

[0045] In this embodiment, instantaneous frequency fluctuation rate is used as a dynamic indicator, and its calculation process is as follows: First, empirical mode decomposition (EMD) is applied to the preprocessed EEG signal to obtain multiple intrinsic mode function components (IMFs). A Hilbert transform is then performed on each IMF to obtain the instantaneous phase φ(t), and the instantaneous frequency f(t) = (1 / 2π)·dφ(t) / dt is calculated.

[0046] Next, state adaptive selection is performed. Based on the target subject's macroscopic brain state (e.g., determining whether they are under anesthesia or awake through background EEG characteristics), the key IMF component most sensitive to state rigidity is automatically selected. For example, dynamic rigidity in anesthesia is often reflected in the lower frequency IMF2, while in wakefulness it may be reflected in IMF1. Alternatively, a data-driven approach can be used, selecting the IMF component with the largest decrease in instantaneous frequency fluctuation relative to the baseline as the key component.

[0047] Then, for the key IMF components, the coefficient of variation of their instantaneous frequency within the sliding window is calculated as the original value of the dynamic index at that moment. The median of each channel is taken to obtain the global IFV, and quantile normalization is performed to obtain IFV_norm∈[0,1]. The lower the IFV_norm, the worse the network's dynamic flexibility, i.e., the higher the degree of rigidity.

[0048] Specifically, the calculation of the control conflict index based on the nonlinear coupling relationship between the energy index and the kinetic index includes calculating the control conflict index using the following formula: in, To control the conflict index, As a scale factor, As an energy indicator, For dynamic indicators, and It is a nonlinear enhancement index. and (By introducing an exponent greater than 1, the magnitude of CCI change when the energy index increases and the kinetic index decreases simultaneously can be significantly amplified, forming an easily detectable explosive peak.) To prevent extremely small constants with a denominator of zero.

[0049] Furthermore, the calculation of the control conflict index based on the nonlinear coupling relationship between the energy index and the kinetic index also includes calculating the control conflict index using the following formula: in, To control the conflict index, As a scale factor, As an energy indicator, For dynamic indicators, and It is a nonlinear enhancement index. and .

[0050] Specifically, the critical state transition that is about to occur in the brain includes at least one of the following: the transition from anesthesia to wakefulness, the onset of an epileptic seizure, and the transition from wakefulness to sleep or microsleep.

[0051] like Figure 2 As shown, when "slamming on the accelerator" (energy index rises) and "transmission jamming" (dynamic index drops) occur simultaneously at the conflict point 201, the CCI will generate an extremely sharp explosive peak 202. The real-time CCI value is compared with a preset critical threshold. When the CCI value exceeds the threshold line 203, a warning command is immediately generated.

[0052] The embodiments of this invention have the potential for platform-based applications. The neural inertia principle and control conflict model on which it is based are universal and can be adapted to various scenarios such as anesthesia recovery prediction, epileptic seizure early warning, driver fatigue and microsleep monitoring, with a wide range of applications.

[0053] Figure 3A This is a schematic diagram of a user interface for an anesthesia monitoring scenario according to an embodiment of the present invention. Figure 3A As shown, the system is connected to the operating room monitor. The application layer interface 130 translates the warning command into a clear visual and auditory alarm, prompting "Awakening Warning: Consciousness expected to return in 30 seconds," providing the anesthesiologist with a precise lead time to adjust medication and prepare for extubation.

[0054] Figure 3B This is a schematic diagram of a user interface for an epilepsy early warning scenario according to an embodiment of the present invention. Figure 3B As shown, the system can be integrated into a portable device for daily wear by epilepsy patients. When the system detects a "control conflict" signal preceding a seizure, it immediately sends a warning message via vibration or a mobile app: "Epileptic premonitory state! Please take immediate safety measures." This can occur earlier than any clinical sign, giving the patient crucial time to find a safe environment or administer intervention medication.

[0055] Figure 3C This is a schematic diagram of the user interface for a fatigue driving monitoring scenario according to an embodiment of the present invention. Figure 3C As shown, the system is integrated into smart cars or pilot helmets. When the driver's brain is fighting drowsiness, brief "control conflicts" (energy bursts trying to stay awake vs. network rigidity about to fall asleep) repeatedly occur. Upon detecting a CCI peak, instead of simply issuing an alarm, interventions can be proactively triggered, such as by vibrating the seat, emitting stimulating sounds, or even suggesting the vehicle take over or navigating to the nearest rest area in autonomous driving mode.

[0056] Figure 4 This is a schematic diagram illustrating the structure of brain state transition prediction according to an embodiment of the present invention. Figure 4 As shown, the brain state transition prediction device of this invention includes: The EEG signal acquisition unit 401 is used to acquire the real-time EEG signal of the target object; The energy index calculation unit 402 is used to calculate an energy index that characterizes the level of local energy mobilization in the brain based on the electroencephalogram signal. The energy index reflects the brain’s control intention to try to change the current state. The dynamic index calculation unit 403 is used to calculate dynamic indices characterizing the dynamic flexibility of the brain network based on the electroencephalogram (EEG) signals. The dynamic indices reflect the brain network's ability to switch between different modes. The control conflict index calculation unit 404 is used to calculate the control conflict index based on the nonlinear coupling relationship between the energy index and the kinetic index; wherein the control conflict index increases nonlinearly when the energy index increases and the kinetic index decreases. The early warning unit 405 is used to monitor the changing trend of the control conflict index in real time. When the control conflict index exceeds a preset critical threshold, it generates an early warning signal that the brain is about to undergo a critical state transition.

[0057] The brain state transition prediction device of this invention can be integrated into a monitor, portable EEG device or wearable device.

[0058] In an optional embodiment of the present invention, the energy index is calculated based on the power of the high-frequency Gamma band of the electroencephalogram signal.

[0059] Furthermore, the dynamic index is calculated based on the instantaneous frequency fluctuation rate of the EEG signal, which is obtained by applying empirical mode decomposition and Hilbert-Huang transform to the EEG signal.

[0060] Preferably, it further includes a state adaptive unit, used to automatically select key mode components carrying deadlock signals from the plurality of intrinsic mode function components based on the macroscopic brain state of the target object before calculating the fluctuation rate of the instantaneous frequency; The fluctuation rate of the instantaneous frequency is calculated for the key modal components.

[0061] Specifically, the control conflict index calculation unit 404 is further used to calculate the control conflict index using the following formula: in, To control the conflict index, As a scale factor, As an energy indicator, For dynamic indicators, and It is a nonlinear enhancement index. and , To prevent extremely small constants with a denominator of zero.

[0062] Specifically, the control conflict index calculation unit 404 is further used to calculate the control conflict index using the following formula: in, To control the conflict index, As a scale factor, As an energy indicator, For dynamic indicators, and It is a nonlinear enhancement index. and .

[0063] Specifically, the critical state transition that is about to occur in the brain includes at least one of the following: the transition from anesthesia to wakefulness, the onset of an epileptic seizure, and the transition from wakefulness to sleep or microsleep.

[0064] It should be noted that the brain state transition prediction devices in the above embodiments can be used to execute the methods in the foregoing embodiments, and therefore will not be described in detail one by one.

[0065] It should be noted that: Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0066] Similarly, it should be understood that, in order to simplify the invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this disclosure should not be construed as reflecting an intention that the claimed invention requires more features than expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of the single embodiment disclosed above. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0067] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention and form different embodiments.

[0068] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the device for detecting the wearing status of an electronic device according to embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can take the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0069] For example, Figure 5 A schematic diagram of an electronic device according to an embodiment of the present invention is shown. The electronic device conventionally includes a processor 51 and a memory 52 arranged to store computer-executable instructions (program code). The memory 52 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Figure 1 Storage space 53 for program code 54 of any method steps shown and in any of the embodiments. For example, storage space 53 for storing program code may include various program codes 54 for implementing the various steps in the methods above. This program code can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, CDs, memory cards, or floppy disks. Such computer program products are typically, for example, Figure 6 The aforementioned computer-readable storage medium. This computer-readable storage medium may have the same characteristics as... Figure 5 The memory 52 in the electronic device is similarly arranged as a storage segment, storage space, etc. The program code can be compressed, for example, in a suitable form. Typically, the storage space stores program code 61 for performing the steps of the method according to the invention, that is, program code that can be read by a processor 51, which, when run by the electronic device, causes the electronic device to perform the various steps of the method described above.

[0070] The above description is merely a specific embodiment of the present invention. Under the teachings of the present invention, those skilled in the art can make other improvements or modifications based on the above embodiments. Those skilled in the art should understand that the above specific description is only to better explain the purpose of the present invention, and the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for predicting brain state transitions, characterized in that, Acquire real-time EEG signals of the target subject; Based on the electroencephalogram (EEG) signals, an energy index is calculated to characterize the level of local energy mobilization in the brain. The energy index reflects the brain's control intention to try to change the current state. Based on the electroencephalogram (EEG) signals, dynamic indicators characterizing the dynamic flexibility of the brain network are calculated, and these dynamic indicators reflect the brain network's ability to switch between different modes. Based on the nonlinear coupling relationship between the energy index and the kinetic index, a control conflict index is calculated; wherein the control conflict index increases nonlinearly when the energy index increases and the kinetic index decreases. The system monitors the changing trend of the control conflict index in real time, and generates an early warning signal that the brain is about to undergo a critical state transition when the control conflict index exceeds a preset critical threshold.

2. The brain state transition prediction method according to claim 1, characterized in that, The energy index is calculated based on the power of the high-frequency Gamma band of the EEG signal.

3. The brain state transition prediction method according to claim 1, characterized in that, The dynamic index is calculated based on the instantaneous frequency fluctuation rate of the EEG signal, which is obtained by applying empirical mode decomposition and Hilbert-Huang transform to the EEG signal.

4. The brain state transition prediction method according to claim 3, characterized in that, Before calculating the fluctuation rate of the instantaneous frequency, a state adaptive selection step is also included: Based on the macroscopic brain state of the target object, the key modal component carrying the deadlock signal is automatically selected from the multiple intrinsic modal function components; The fluctuation rate of the instantaneous frequency is calculated for the key modal components.

5. The brain state transition prediction method according to claim 1, characterized in that, The calculation of the control conflict index based on the nonlinear coupling relationship between the energy index and the dynamic index includes calculating the control conflict index using the following formula: in, To control the conflict index, As a scale factor, As an energy indicator, For dynamic indicators, and It is a nonlinear enhancement index. and , To prevent extremely small constants with a denominator of zero.

6. The brain state transition prediction method according to claim 1, characterized in that, The calculation of the control conflict index based on the nonlinear coupling relationship between the energy index and the dynamic index includes calculating the control conflict index using the following formula: in, To control the conflict index, As a scale factor, As an energy indicator, For dynamic indicators, and It is a nonlinear enhancement index. and .

7. The brain state transition prediction method according to claim 1, characterized in that, The impending critical state transition in the brain includes at least one of the following: transition from anesthesia to wakefulness, onset of an epileptic seizure, or transition from wakefulness to sleep or microsleep.

8. A brain state transition prediction device, characterized in that, include: The EEG signal acquisition unit is used to acquire real-time EEG signals of the target object; An energy index calculation unit is used to calculate an energy index that characterizes the level of local energy mobilization in the brain based on the electroencephalogram (EEG) signal. The energy index reflects the brain’s control intention to try to change the current state. The dynamic index calculation unit is used to calculate dynamic indices characterizing the dynamic flexibility of the brain network based on the electroencephalogram (EEG) signals. These dynamic indices reflect the brain network's ability to switch between different modes. A control conflict index calculation unit is used to calculate a control conflict index based on the nonlinear coupling relationship between the energy index and the kinetic index; wherein the control conflict index increases nonlinearly when the energy index increases and the kinetic index decreases. The early warning unit is used to monitor the changing trend of the control conflict index in real time. When the control conflict index exceeds a preset critical threshold, it generates an early warning signal that the brain is about to undergo a critical state transition.

9. An electronic device, characterized in that, The electronic device includes: Processor; and, A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the brain state transition prediction method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs that, when executed by a processor, implement the brain state transition prediction method according to any one of claims 1-7.

Images