Postoperative consciousness monitoring system based on multi-modal data analysis
By collecting EEG signals and pupillary status images from the midthalamus and prefrontal cortex, analyzing theta and gamma signal waves, and constructing a correlation between consciousness transmission and pupillary response, the limitations of single-modality monitoring were overcome, and the accuracy of postoperative consciousness monitoring was improved.
Patent Information
- Application Number
- CN202511714505.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-21
- Publication Date
- 2026-01-27
AI Technical Summary
Existing technologies fail to fully reflect the postoperative state of consciousness in patients. Single-modal monitoring cannot combine brain neural transmission and pupillary response, and lacks quantitative indicators to assess the risk of abnormal consciousness, thus affecting the accuracy of postoperative consciousness monitoring.
By collecting EEG signals from the midthalamus and prefrontal cortex, combined with pupil state images, analyzing theta and gamma signal waves, constructing the correspondence between the duration of consciousness transmission representation and the duration of pupil response representation, and using the Pearson correlation coefficient to determine early warning prompts.
Multimodal monitoring was achieved, accurately reflecting the postoperative patient's state of consciousness, improving the accuracy and timeliness of consciousness monitoring, and reducing misjudgments.
Smart Images

Figure CN121400847A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of consciousness behavior feature recognition technology, and in particular to a postoperative consciousness monitoring system based on multimodal data analysis. Background Technology
[0002] In modern medicine, postoperative monitoring of patient consciousness is crucial. Anesthetic drugs used during surgery can suppress the central nervous system, leading to a decline in the patient's level of consciousness and impairing cognitive function. Postoperative consciousness recovery is closely linked to patient prognosis. Delayed recovery may stem from factors such as nerve damage, metabolic disorders, or drug toxicity. Early detection and timely intervention can significantly improve patient outcomes. Currently, traditional methods of postoperative consciousness monitoring have many limitations, relying primarily on the subjective observation and experience of medical staff, which suffers from high subjectivity and limited accuracy. Furthermore, single-modal physiological monitoring techniques, such as monitoring only EEG signals or focusing solely on pupil status, have low information utilization rates and cannot comprehensively reflect the patient's level of consciousness. Therefore, a system capable of integrating multi-source information and accurately and in real-time monitoring of postoperative patient consciousness is urgently needed in clinical practice.
[0003] For example, Chinese Patent Publication No. CN119073917A discloses a system for monitoring the course of consciousness disorders. A multi-dimensional data acquisition module uses multiple sensors installed on the patient's body to collect real-time physiological signal data such as electroencephalogram (EEG), heart rate variability (HRV), and electrical conductance of the skin (EDA). The collected data is preprocessed using edge computing devices. An adaptive course prediction model, based on the physiological signal data collected by the multi-dimensional data acquisition module and combined with the patient's historical course data, uses an adaptive algorithm to train a personalized course prediction model. During the progression of the patient's condition, the model parameters are adaptively updated using machine learning algorithms to achieve dynamic prediction of the progression of consciousness disorders. A continuous course monitoring module continuously acquires the patient's physiological signals using high-frequency sampling technology and identifies key events in the course of the disease in real time using an anomaly detection algorithm, including sudden decline in consciousness and epileptic seizures, generating warning signals and triggering an emergency response mechanism.
[0004] The following problems still exist in the existing technology: Existing technologies do not consider the problem that single-modal monitoring cannot fully reflect consciousness-related neural activity and peripheral responses. Existing technologies have not established the correlation between brain neural transmission and pupillary response, and lack quantitative indicators to assess the risk of consciousness abnormalities, which affects the accuracy of postoperative consciousness monitoring. Summary of the Invention
[0005] To address this, the present invention provides a postoperative consciousness monitoring system based on multimodal data analysis, which overcomes the problems of existing technologies that fail to establish the correlation between brain neural transmission and pupillary response, lack quantitative indicators to assess the risk of abnormal consciousness, and thus affect the accuracy of postoperative consciousness monitoring.
[0006] To achieve the above objectives, the present invention provides a postoperative consciousness monitoring system based on multimodal data analysis, comprising: The acquisition module includes a first acquisition unit for acquiring electroencephalogram (EEG) signals from the medial thalamus and prefrontal cortex of the target object, and a second acquisition unit for acquiring images of the pupil state of the target object. The brain signal analysis module, which is connected to the acquisition module, includes a waveform extraction unit and a data analysis unit. The waveform extraction unit is used to acquire theta signal waves based on the electroencephalogram (EEG) signals from the medial thalamus and gamma signal waves based on the EEG signals from the prefrontal cortex. The data analysis unit is used to determine the signal acquisition window based on the waveform information of the θ signal wave, and to extract a sub-band of the γ signal wave within the signal acquisition window, and to determine whether to determine the signal acquisition window as a consciousness feature explicit window based on the waveform information of the sub-band. The activation module is connected to the acquisition module and the brain signal analysis module respectively, and is used to control the second acquisition unit to stimulate the pupil of the target object with light and acquire the pupil state image during the activation cycle. The activation cycle is determined according to the consciousness feature explicit window. An information matching module, which is connected to the activation module and the brain signal analysis module respectively, is used to draw a pupil state change curve based on pupil state images at continuous time intervals, so as to determine the duration of consciousness response representation and construct the correspondence between the duration of consciousness response representation and the duration of consciousness transmission representation. The duration of the consciousness transmission representation is determined based on the waveform characteristics of the θ signal wave and the γ signal wave. The early warning module, which is connected to the information matching module, is used to calculate the follow-up coefficient between the consciousness transmission representation duration and the consciousness response representation duration, and to determine whether to issue an early warning prompt based on the follow-up coefficient.
[0007] Furthermore, the data analysis unit is used to determine the start time of signal acquisition and the middle time of the window, wherein, The data analysis unit is used to obtain the slope of several points on the θ signal wave, and the points with a slope greater than the preset slope reference value are determined as the signal acquisition start time. The data analysis unit uses the signal acquisition start point as the time starting point and determines the time corresponding to the first point with a slope of zero as the middle time of the window according to the time sequence.
[0008] Furthermore, the data analysis unit is used to determine the signal acquisition window based on the signal acquisition start time and the midpoint of the window; The duration of the signal acquisition window is twice the duration between the start time of signal acquisition and the middle time of the window.
[0009] Furthermore, the data analysis unit is used to acquire waveform information of the sub-bands of the γ signal wave within the signal acquisition window, wherein, The data analysis unit is used to acquire sub-bands of the γ signal wave within the signal acquisition window, and to calculate the average peak amplitude based on the amplitude of several peaks within the sub-band.
[0010] Furthermore, the data analysis unit is used to determine whether to identify the signal acquisition window as a window with explicit consciousness characteristics, wherein, The data analysis unit is used to compare the average value of the peak amplitude with the reference value of the peak amplitude; If the average value of the peak amplitude is greater than the reference value of the peak amplitude, the data analysis unit determines that the signal acquisition window is a window for the explicit characteristics of consciousness. The reference value for peak amplitude is determined based on the peak amplitude in the previous time window, which has the same duration as the signal acquisition window.
[0011] Furthermore, the activation module is used to determine the activation cycle based on the explicit window of the consciousness feature, wherein, The start time of the activation cycle is the end time of the explicit window of consciousness features, and the duration of the activation cycle is greater than or equal to the duration of the explicit window of consciousness features.
[0012] Furthermore, the information matching module is used to plot the pupil state change curve, wherein, The information matching module is used to determine the pupil diameter in the pupil state image at consecutive time points, and plots the state change curve of the pupil diameter over time with the pupil diameter as the vertical axis and time as the horizontal axis.
[0013] Furthermore, the information matching module is used to determine the duration of the consciousness response representation and the duration of the consciousness transmission representation, wherein, The information matching module determines the duration from the start of the activation cycle to the moment corresponding to the maximum value of the vertical axis of the state change curve as the duration of the consciousness response representation. The information matching module determines the duration from the start time of the signal acquisition window to the time corresponding to the maximum peak value of the γ signal wave within the signal acquisition window as the duration of the consciousness transmission representation.
[0014] Furthermore, the information matching module is used to establish a correspondence between the duration of consciousness response representation and the duration of consciousness transmission representation in the same activation cycle.
[0015] Furthermore, the early warning module is used to determine whether to issue an early warning notification, wherein, The early warning module is used to compare the follow-up coefficient with a preset follow-up coefficient threshold. If the follow-up coefficient is less than the follow-up coefficient threshold, the early warning module determines to issue an early warning prompt; If the follow-up coefficient is greater than or equal to the follow-up coefficient threshold, the early warning module determines that no early warning will be issued. The follow-up coefficient is the Pearson correlation coefficient between the duration of consciousness response representation and the corresponding duration of consciousness transmission representation of the same target object over several consecutive activation cycles.
[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention acquires EEG signals from the thalamus and prefrontal cortex through a first acquisition unit, acquires pupil state images of the target object through a second acquisition unit, determines the signal acquisition window using the waveform information of theta signal waves through a brain signal analysis module, determines the dominant window of consciousness characteristics by analyzing the gamma signal waves of the EEG signals of the prefrontal cortex within the signal acquisition window, controls the second acquisition unit to illuminate and acquire pupil state images of the target object through an excitation module, plots pupil state change curves through an information matching module, and constructs a correspondence between the duration of consciousness response representation and the duration of consciousness transmission representation, and calculates the follow-up coefficients of the duration of consciousness transmission representation and the duration of consciousness response representation through an early warning module to determine whether to issue an early warning prompt. Thus, the present invention achieves multimodal monitoring of consciousness-related neural activities and peripheral responses, establishes the correlation between brain neural transmission and pupil response, and improves the accuracy of postoperative consciousness monitoring.
[0017] Furthermore, this invention locates key time points of consciousness-related neural activity by capturing significant changes in the slope of the theta wave. The slope of the theta wave reflects its rate of change. When the slope is greater than a preset reference value, it indicates a significant and rapid upward trend in the theta wave, suggesting that consciousness-related neural activity may have been triggered in the corresponding midthalamic region. Therefore, this point is determined as the starting moment of signal acquisition, serving as the starting marker for key neural activity. This time point determination method based on slope characteristics essentially captures consciousness-related neural activity precisely by quantifying the dynamic changes in waveform.
[0018] Furthermore, this invention utilizes the principle that gamma signal waves in the prefrontal cortex are closely related to higher neural activity. By extracting gamma wave sub-bands within the signal acquisition window, high-frequency neural activity characteristics that may be related to the triggering of theta waves in the midthalamus can be specifically captured. By calculating the average amplitude of several peaks within the sub-band, the overall activity intensity of gamma waves during that period can be effectively quantified, reflecting the level of neural activity more stably.
[0019] Furthermore, the activation cycle determined in this invention is based on the temporal correlation between neural activity and peripheral physiological response. The explicit window of consciousness characteristics indicates that the transmission of neural activity from the midthalamus to the prefrontal cortex has formed significant consciousness-related characteristics. At this time, the activation of pupillary illumination activation can accurately capture the peripheral physiological response after the brain's consciousness-related neural activity. This forms a temporal match with the previous neural activity window, providing a reasonable temporal correlation basis for the correlation analysis of the temporal relationship between consciousness transmission and pupillary response, and improving the scientific nature of multimodal data fusion.
[0020] Furthermore, this invention, based on the temporal correspondence between neural activity transmission and peripheral physiological response, constructs a multimodal index correlation by precisely anchoring key time nodes: the duration from the start of the excitation cycle to the maximum point of the pupil state change curve is defined as the duration of consciousness response representation, quantifying the response time of the peripheral physiological system to light stimulation; the duration from the start of the signal acquisition window to the maximum peak of the gamma wave is defined as the duration of consciousness transmission representation, quantifying the neural transmission time of the thalamic theta wave triggering the prefrontal gamma wave within the brain. By constructing a correspondence between the two under the same excitation cycle, a direct temporal correlation is established between central neural activity transmission and peripheral physiological response, providing a quantitative basis for analyzing their synergy and realizing the complete chain monitoring of consciousness from neural activity to physiological manifestation.
[0021] Furthermore, this invention uses a quantitative analysis of the synergy between central nervous system activity transmission and peripheral physiological response to determine the stability of postoperative consciousness. The linear correlation between the duration of consciousness transmission from the theta wave in the thalamus to the gamma wave in the prefrontal cortex and the duration of consciousness response to pupillary light is calculated using the Pearson correlation coefficient. The follow-up coefficient objectively reflects the degree of synergy between the two in the time dimension. Under normal consciousness, central nervous system transmission and peripheral physiological response have high synergy, corresponding to a high follow-up coefficient. When the follow-up coefficient is below a preset threshold, it indicates a low level of synergy, suggesting that central nervous system activity and peripheral physiological response may be asynchronous, and there is a risk of abnormal consciousness activity. In this situation, the warning module issues a warning, thus achieving multimodal monitoring of consciousness-related neural activity and peripheral responses, establishing a correlation between brain neural transmission and pupillary response, and improving the accuracy of postoperative consciousness monitoring. Attached Figure Description
[0022] Figure 1 This is a system block diagram of a postoperative consciousness monitoring system based on multimodal data analysis, according to an embodiment of the present invention. Figure 2 This is a schematic diagram illustrating the determination of the signal acquisition window in an embodiment of the present invention; Figure 3 This is a flowchart illustrating the logic of the data analysis unit in this embodiment of the invention in determining whether to identify the signal acquisition window as a window for the explicit manifestation of consciousness features. Figure 4 This is a flowchart illustrating the logic of the warning module in this embodiment of the invention for determining whether to issue a warning notification. In the figure, 1 represents the θ signal wave, 2 represents the γ signal wave, and 3 represents the signal acquisition window. Detailed Implementation
[0023] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.
[0024] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.
[0025] It should be noted that in the description of this invention, the terms "upper," "lower," "inner," "outer," etc., which indicate the direction or positional relationship, are based on the direction or positional relationship shown in the drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.
[0026] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation" and "connection" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.
[0027] Please see Figure 1 The diagram shown is a system block diagram of a postoperative consciousness monitoring system based on multimodal data analysis according to an embodiment of the present invention. The postoperative consciousness monitoring system based on multimodal data analysis of the present invention includes: The acquisition module includes a first acquisition unit for acquiring electroencephalogram (EEG) signals from the medial thalamus and prefrontal cortex of the target object, and a second acquisition unit for acquiring images of the pupil state of the target object. Specifically, the first acquisition unit in this invention can be an EEG electrode cap and a memory. The acquisition of EEG signals from the midthalamus and prefrontal cortex through the EEG electrode cap and the storage of the acquired signal intensity through the memory are existing clinical techniques, which will not be elaborated here.
[0028] Specifically, the second acquisition unit in this invention can be a camera with a support component and a camera that captures high-definition pupil state images. The support component is used to open the eyes of the target object so that the camera can capture pupil state images. The cooperation between the support component and the camera to acquire pupil state images is a common technical means of existing pupil monitoring, which will not be elaborated here.
[0029] The brain signal analysis module, which is connected to the acquisition module, includes a waveform extraction unit and a data analysis unit. The waveform extraction unit is used to acquire theta signal waves based on the electroencephalogram (EEG) signals from the medial thalamus and gamma signal waves based on the EEG signals from the prefrontal cortex. Those skilled in the art will understand that when consciousness arises, the theta wave phase in the central thalamus will synchronize first, driving gamma wave oscillatory signal activity in the lateral prefrontal cortex. This driving has a clear directionality, namely from the central thalamus to the prefrontal cortex. The theta signal wave in the central thalamus refers to the neural oscillatory activity in the central thalamus.
[0030] In this invention, the waveform extraction unit of the brain signal analysis module obtains the theta signal wave based on the electroencephalogram (EEG) signal of the midthalamus in the following way: First, the EEG signals collected by all electrodes in the midthalamus region are subjected to mean filtering; then, the midthalamus region is determined according to the standard brain atlas, and the real-time power value of the EEG signal collected by each electrode in the midthalamus region in the theta frequency band is calculated. The average power value of these power values is obtained, and the average power value signal is filtered by a 4-7Hz bandpass filter to obtain the required theta signal wave. In this invention, the gamma signal wave is separated from the EEG signal of the prefrontal cortex region by Fourier transform. In this invention, the frequency band of the theta signal wave is 4-8Hz, and the frequency band of the gamma signal wave is 28-93Hz.
[0031] The brain signal analysis module in this invention can be a signal processor with integrated signal amplification circuit. The processing of brain wave signals is a current medical technology and will not be described in detail here.
[0032] The data analysis unit is used to determine the signal acquisition window based on the waveform information of the θ signal wave, and to extract a sub-band of the γ signal wave within the signal acquisition window, and to determine whether to determine the signal acquisition window as a consciousness feature explicit window based on the waveform information of the sub-band. The activation module is connected to the acquisition module and the brain signal analysis module respectively, and is used to control the second acquisition unit to stimulate the pupil of the target object with light and acquire the pupil state image during the activation cycle. The activation cycle is determined according to the consciousness feature explicit window. Specifically, the excitation module in this invention includes a logic controller and an excitation light source. The logic controller is used to receive and send signals, and the excitation light source is used to receive signals from the logic controller to illuminate the pupil. This is the existing pupil monitoring method in clinical practice, and will not be described in detail here.
[0033] An information matching module, which is connected to the activation module and the brain signal analysis module respectively, is used to draw a pupil state change curve based on pupil state images at continuous time intervals, so as to determine the duration of consciousness response representation and construct the correspondence between the duration of consciousness response representation and the duration of consciousness transmission representation. The duration of the consciousness transmission representation is determined based on the waveform characteristics of the θ signal wave and the γ signal wave. The early warning module, which is connected to the information matching module, is used to calculate the follow-up coefficient between the consciousness transmission representation duration and the consciousness response representation duration, and to determine whether to issue an early warning prompt based on the follow-up coefficient.
[0034] Specifically, the early warning module in this invention can be a display and a buzzer, used to emit a buzzer and display information about the bed and target object where consciousness monitoring shows abnormalities.
[0035] Specifically, the data analysis unit is used to determine the start time of signal acquisition and the middle time of the window, wherein, The data analysis unit is used to obtain the slope of several points on the θ signal wave, and the points with a slope greater than the preset slope reference value are determined as the signal acquisition start time. The data analysis unit uses the signal acquisition start point as the time starting point and determines the time corresponding to the first point with a slope of zero as the middle time of the window according to the time sequence.
[0036] Please see Figure 2 As shown, this is a schematic diagram of determining the signal acquisition window in an embodiment of the present invention. A point a with a slope greater than a preset slope reference value is determined on the θ signal wave 1, and the first point b with a slope equal to zero in the subsequent time corresponding to point a is determined. That is, the time corresponding to point a is the signal acquisition start time, and the time corresponding to point b is the middle time of the window.
[0037] In this invention, the preset slope reference value can be set in advance by those skilled in the art. In order to avoid the omission of wave neural activity capture of the θ signal due to the slope reference value being too large and the misidentification of wave neural activity of the θ signal due to the slope reference value being too small, the range of the slope reference value can be [0.15, 0.2]. Preferably, in this invention, the slope reference value is 0.18.
[0038] Understandably, this invention locates key time points of consciousness-related neural activity by capturing significant changes in the slope of the theta wave. The slope of the theta wave reflects its rate of change; when the slope exceeds a preset reference value, it indicates a significant and rapid upward trend in the theta wave, suggesting that consciousness-related neural activity may have been triggered in the corresponding midthalamic region. Therefore, this point is determined as the starting moment of signal acquisition, serving as the initial marker for key neural activity. This slope-based time point determination method essentially uses the quantification of dynamic waveform changes to accurately capture consciousness-related neural activity.
[0039] Specifically, the data analysis unit is used to determine the signal acquisition window based on the signal acquisition start time and the midpoint of the window; The duration of the signal acquisition window is twice the duration between the start time of signal acquisition and the middle time of the window.
[0040] Please continue reading. Figure 2 As shown, twice the duration between the time corresponding to point a and the time corresponding to point b is defined as the signal acquisition window 3, and the local band of the γ signal wave 2 within the signal acquisition window 3 is defined as the sub-band of the γ signal wave 2.
[0041] Understandably, this invention constructs a symmetrical time window using key time points of the theta signal wave as anchor points to ensure the integrity of neural activity within a complete time period. The signal acquisition start time corresponds to the trigger point of the rapid rise of the theta wave, and the middle time of the window corresponds to the peak point of the theta wave. The duration between the two reflects the performance of the rising phase of neural activity from initiation to peak. Setting the window duration to twice the duration of this rising phase means that, with the peak point as the center, the rising process from trigger to peak is covered forward, and the falling process from peak to activity decay is covered backward for an equal duration, forming a symmetrical time window. This conforms to the periodic characteristics of the rise to peak and then decay that are usually exhibited by bioelectrical signal waveforms, and can completely capture the full-time waveform information of a single neural activity trigger, ensuring the comprehensiveness and effectiveness of data features.
[0042] Specifically, the data analysis unit is used to obtain waveform information of the sub-bands of the γ signal wave within the signal acquisition window, wherein, The data analysis unit is used to acquire sub-bands of the γ signal wave within the signal acquisition window, and to calculate the average peak amplitude based on the amplitude of several peaks within the sub-band.
[0043] Those skilled in the art will understand that gamma wave signals in the prefrontal cortex are closely related to higher neural activity. By extracting gamma wave sub-bands within the signal acquisition window, high-frequency neural activity characteristics that may be related to the triggering of theta waves in the midthalamus can be specifically captured. By calculating the average amplitude of several peaks within the sub-band, the overall activity intensity of gamma waves during that period can be effectively quantified, reflecting the level of neural activity more stably.
[0044] Specifically, please refer to Figure 3 The diagram shown is a flowchart illustrating the logic of a data analysis unit in an embodiment of the present invention determining whether to identify a signal acquisition window as a window displaying conscious characteristics. The data analysis unit is used to determine whether to identify the signal acquisition window as a window displaying conscious characteristics. The data analysis unit is used to compare the average value of the peak amplitude with the reference value of the peak amplitude; If the average value of the peak amplitude is less than or equal to the reference value of the peak amplitude, the data analysis unit determines that the signal acquisition window is not a visible window of consciousness features. If the average value of the peak amplitude is greater than the reference value of the peak amplitude, the data analysis unit determines that the signal acquisition window is a window for the explicit characteristics of consciousness. The reference value for peak amplitude is determined based on the peak amplitude in the previous time window, which has the same duration as the signal acquisition window.
[0045] In this invention, the reference value for peak amplitude is the average value of peak amplitude in the previous time window of the current signal acquisition window, and the duration of the previous time window of the signal acquisition window is the same as the duration of the signal acquisition window.
[0046] Specifically, this invention compares the average peak amplitude of the current window with the reference value of the peak amplitude of the previous time window, and uses the temporal correlation of neural activity to determine the significance of the change. When the current average value is greater than the reference value, it indicates that the intensity of gamma wave activity is significantly enhanced, which is affected by the triggering effect of the theta wave in the midthalamus. Therefore, this window can be identified as a window with explicit consciousness characteristics.
[0047] Specifically, the activation module is used to determine the activation cycle based on the explicit window of the consciousness characteristics, wherein, The start time of the activation cycle is the end time of the explicit window of consciousness features, and the duration of the activation cycle is greater than or equal to the duration of the explicit window of consciousness features.
[0048] In this invention, the duration of the explicit window of consciousness features can be twice the duration of the activation cycle, so as to monitor consciousness of pupil information during the period when the neural activity transmission characteristics from the midthalamus to the prefrontal cortex are obvious, thereby improving the representativeness of the data and avoiding ineffective monitoring during the period when the neural activity transmission characteristics from the midthalamus to the prefrontal cortex are not obvious.
[0049] It is understood that the determination of the excitation cycle in this invention is based on the temporal correlation between neural activity and peripheral physiological response. The explicit window of consciousness characteristics indicates that the transmission of neural activity from the midthalamus to the prefrontal cortex has formed significant consciousness-related characteristics. At this time, the pupillary light excitation can accurately capture the peripheral physiological response after the brain's consciousness-related neural activity. This forms a temporal match with the previous neural activity window, providing a reasonable temporal correlation basis for the correlation analysis of the temporal relationship between consciousness transmission and pupillary response, and improving the scientific nature of multimodal data fusion.
[0050] Specifically, the information matching module is used to draw the pupil state change curve, wherein, The information matching module is used to determine the pupil diameter in the pupil state image at consecutive time points, and plots the state change curve of the pupil diameter over time with the pupil diameter as the vertical axis and time as the horizontal axis.
[0051] In this invention, the pupil diameter can be obtained by image processing and analysis of pupil state images acquired at continuous intervals. First, the images are processed with noise reduction and contrast enhancement to locate the pupil region using pupil edge features. Then, a geometric feature extraction algorithm is used to calculate the geometric dimensions of the pupil, with the pupil diameter being the longest distance passing through the center of the pupil. The unit of pupil diameter is mm.
[0052] Specifically, the information matching module is used to determine the duration of consciousness response representation and the duration of consciousness transmission representation, wherein, The information matching module determines the duration from the start of the activation cycle to the moment corresponding to the maximum value of the vertical axis of the state change curve as the duration of the consciousness response representation. The information matching module determines the duration from the start time of the signal acquisition window to the time corresponding to the maximum peak value of the γ signal wave within the signal acquisition window as the duration of the consciousness transmission representation.
[0053] Specifically, the information matching module is used to establish a correspondence between the duration of consciousness response representation and the duration of consciousness transmission representation in the same activation cycle.
[0054] Understandably, this invention is based on the temporal correspondence between neural activity transmission and peripheral physiological response. It constructs a multimodal index correlation by precisely anchoring key time nodes: the duration from the start of the excitation cycle to the maximum value of the pupillary state change curve is defined as the duration of consciousness response representation, quantifying the response time of the peripheral physiological system to light stimulation; the duration from the start of the signal acquisition window to the maximum peak value of the gamma wave is defined as the duration of consciousness transmission representation, quantifying the neural transmission time of the thalamic theta wave triggering the prefrontal gamma wave within the brain. By establishing a correspondence between the two under the same excitation cycle, a direct temporal correlation is established between central neural activity transmission and peripheral physiological response, providing a quantitative basis for analyzing their synergy and enabling the complete chain monitoring of consciousness from neural activity to physiological manifestation.
[0055] Specifically, please refer to Figure 4 The diagram shown is a flowchart illustrating the logic of the warning module in an embodiment of the present invention for determining whether to issue a warning alert. The warning module is used to determine whether to issue a warning alert. The early warning module is used to compare the follow-up coefficient with a preset follow-up coefficient threshold. If the follow-up coefficient is less than the follow-up coefficient threshold, the early warning module determines to issue an early warning prompt; If the follow-up coefficient is greater than or equal to the follow-up coefficient threshold, the early warning module determines that no early warning will be issued. The follow-up coefficient is the Pearson correlation coefficient between the duration of consciousness response representation and the corresponding duration of consciousness transmission representation of the same target object over several consecutive activation cycles.
[0056] Specifically, this invention is based on the neurophysiological law of central and peripheral coordination. Those skilled in the art will understand that, under normal physiological conditions, the process of neural activity in the midthalamus being transmitted to the prefrontal cortex is related to the regulatory pathway of pupillary light reflex, and the temporal changes of the two should be correlated. If the follow-up coefficient is lower than the theoretical follow-up coefficient threshold, it indicates that the coordination of the neural pathway deviates from the normal physiological range. Based on this and the experimental average value of clinical historical data, the range of the follow-up coefficient threshold is set to [0.8, 0.85]. Those skilled in the art can set the follow-up coefficient threshold according to the monitoring sensitivity. Preferably, the follow-up coefficient threshold can be set to 0.82.
[0057] Understandably, this invention is based on a quantitative analysis of the synergy between central nervous system activity transmission and peripheral physiological response to determine the stability of postoperative consciousness. The linear correlation between the duration of consciousness transmission from the theta wave in the thalamus to the gamma wave in the prefrontal cortex and the duration of consciousness response to pupillary light is calculated using the Pearson correlation coefficient. The follow-up coefficient objectively reflects the degree of synergy between the two in the time dimension. Under normal consciousness, central nervous system transmission and peripheral physiological response have high synergy, corresponding to a high follow-up coefficient. When the follow-up coefficient is below a preset threshold, it indicates a low level of synergy, suggesting that central nervous system activity and peripheral physiological response may be asynchronous, and there is a risk of abnormal consciousness activity. In this situation, the warning module issues a warning, thus achieving multimodal monitoring reflecting consciousness-related neural activity and peripheral responses, establishing a correlation between brain neural transmission and pupillary response, and improving the accuracy of postoperative consciousness monitoring.
[0058] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.
[0059] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A postoperative consciousness monitoring system based on multimodal data analysis, characterized in that, include: The acquisition module includes a first acquisition unit for acquiring electroencephalogram (EEG) signals from the medial thalamus and prefrontal cortex of the target object, and a second acquisition unit for acquiring images of the pupil state of the target object. The brain signal analysis module, which is connected to the acquisition module, includes a waveform extraction unit and a data analysis unit. The waveform extraction unit is used to acquire theta signal waves based on the electroencephalogram (EEG) signals from the medial thalamus and gamma signal waves based on the EEG signals from the prefrontal cortex. The data analysis unit is used to determine the signal acquisition window based on the waveform information of the θ signal wave, and to extract a sub-band of the γ signal wave within the signal acquisition window, and to determine whether to determine the signal acquisition window as a consciousness feature explicit window based on the waveform information of the sub-band. The activation module is connected to the acquisition module and the brain signal analysis module respectively, and is used to control the second acquisition unit to stimulate the pupil of the target object with light and acquire the pupil state image during the activation cycle. The activation cycle is determined according to the consciousness feature explicit window. An information matching module, which is connected to the activation module and the brain signal analysis module respectively, is used to draw a pupil state change curve based on pupil state images at continuous time intervals, so as to determine the duration of consciousness response representation and construct the correspondence between the duration of consciousness response representation and the duration of consciousness transmission representation. The duration of the consciousness transmission representation is determined based on the waveform characteristics of the θ signal wave and the γ signal wave. The early warning module, which is connected to the information matching module, is used to calculate the follow-up coefficient between the consciousness transmission representation duration and the consciousness response representation duration, and to determine whether to issue an early warning prompt based on the follow-up coefficient.
2. The postoperative consciousness monitoring system based on multimodal data analysis according to claim 1, characterized in that, The data analysis unit is used to determine the start time of signal acquisition and the middle time of the window, wherein, The data analysis unit is used to obtain the slope of several points on the θ signal wave, and the points with a slope greater than the preset slope reference value are determined as the signal acquisition start time. The data analysis unit uses the signal acquisition start point as the time starting point and determines the time corresponding to the first point with a slope of zero as the middle time of the window according to the time sequence.
3. The postoperative consciousness monitoring system based on multimodal data analysis according to claim 2, characterized in that, The data analysis unit is used to determine the signal acquisition window based on the signal acquisition start time and the midpoint of the window. The duration of the signal acquisition window is twice the duration between the start time of signal acquisition and the middle time of the window.
4. The postoperative consciousness monitoring system based on multimodal data analysis according to claim 3, characterized in that, The data analysis unit is used to obtain waveform information of the sub-bands of the γ signal wave within the signal acquisition window, wherein, The data analysis unit is used to acquire sub-bands of the γ signal wave within the signal acquisition window, and to calculate the average peak amplitude based on the amplitude of several peaks within the sub-band.
5. The postoperative consciousness monitoring system based on multimodal data analysis according to claim 4, characterized in that, The data analysis unit is used to determine whether to identify the signal acquisition window as a window with explicit consciousness characteristics, wherein, The data analysis unit is used to compare the average value of the peak amplitude with the reference value of the peak amplitude; If the average value of the peak amplitude is greater than the reference value of the peak amplitude, the data analysis unit determines that the signal acquisition window is a window for the explicit characteristics of consciousness. The reference value for peak amplitude is determined based on the peak amplitude in the previous time window, which has the same duration as the signal acquisition window.
6. The postoperative consciousness monitoring system based on multimodal data analysis according to claim 5, characterized in that, The activation module is used to determine the activation cycle based on the explicit window of the consciousness characteristics, wherein... The start time of the activation cycle is the end time of the explicit window of consciousness features, and the duration of the activation cycle is greater than or equal to the duration of the explicit window of consciousness features.
7. The postoperative consciousness monitoring system based on multimodal data analysis according to claim 6, characterized in that, The information matching module is used to draw the pupil state change curve, wherein, The information matching module is used to determine the pupil diameter in the pupil state image at consecutive time points, and plots the state change curve of the pupil diameter over time with the pupil diameter as the vertical axis and time as the horizontal axis.
8. The postoperative consciousness monitoring system based on multimodal data analysis according to claim 7, characterized in that, The information matching module is used to determine the duration of consciousness response representation and the duration of consciousness transmission representation, wherein, The information matching module determines the duration from the start of the activation cycle to the moment corresponding to the maximum value of the vertical axis of the state change curve as the duration of the consciousness response representation. The information matching module determines the duration from the start time of the signal acquisition window to the time corresponding to the maximum peak value of the γ signal wave within the signal acquisition window as the duration of the consciousness transmission representation.
9. The postoperative consciousness monitoring system based on multimodal data analysis according to claim 8, characterized in that, The information matching module is used to establish a correspondence between the duration of consciousness response representation and the duration of consciousness transmission representation in the same activation cycle.
10. The postoperative consciousness monitoring system based on multimodal data analysis according to claim 9, characterized in that, The early warning module is used to determine whether to issue an early warning notification, wherein, The early warning module is used to compare the follow-up coefficient with a preset follow-up coefficient threshold. If the follow-up coefficient is less than the follow-up coefficient threshold, the early warning module determines to issue an early warning prompt; If the follow-up coefficient is greater than or equal to the follow-up coefficient threshold, the early warning module determines that no early warning will be issued. The follow-up coefficient is the Pearson correlation coefficient between the duration of consciousness response representation and the corresponding duration of consciousness transmission representation of the same target object over several consecutive activation cycles.
Citation Information
Patent Citations
Disorder of consciousness disease course monitoring system
CN119073917A
