Evidence-based migraine risk indicator construction system

Abstract

The present invention relates to the technical field related to risk indicator construction and management, and specifically includes an evidence-based migraine risk indicator construction system, comprising: a feature extraction module that acquires physiological data and coupled abnormal features, an error correction module that maps features and corrects errors, a dynamic adjustment module that adjusts probability confidence intervals, an update module that evaluates interventions and optimizes surfaces, and a synchronization module that constructs matrices and prepares risk reports for synchronization to a user end. This solves the technical problem that the generation of risk reports is fixed to preset migraine risk indicators, cannot adapt to individual differences, and has limited accuracy in risk assessment. The system extracts physiological feature data and analyzes coupled abnormal features, more comprehensively reflects physiological changes before a migraine attack, and improves the reliability of risk assessment. At the same time, historical intervention cases are introduced to dynamically adjust the confidence intervals of risk probability values, thereby making dynamic adjustments based on individual differences and intervention responses of patients, thereby improving the adaptability of migraine risk reports.

Description

Technical Field

[0001] The present invention relates to the technical field related to risk indicator construction and management, and in particular to an evidence-based migraine risk indicator construction system. Background Art

[0002] The pathogenesis of migraine is complex, involving multiple interactions involving neurovascular, neurotransmitter, genetic, and environmental factors. Due to the sudden and recurrent nature of migraine attacks, it is often difficult to predict them in advance, leading to a passive response during an attack and an inability to take effective preventive or mitigating measures. Existing prediction methods mostly rely on subjective symptom reporting, simple physiological indicator monitoring, or risk assessment based on conventional statistical models. Individual patient descriptions and perceptions of symptoms vary, making it difficult to ensure the accuracy and consistency of symptom reporting, thus impacting the reliability of risk prediction.

[0003] In summary, the generation of risk reports in the prior art is fixed to preset migraine risk indicators, cannot adapt to individual differences, and has technical problems such as limited accuracy of risk assessment. Summary of the Invention

[0004] This application provides an evidence-based migraine risk indicator construction system to solve the technical problems in the existing technology that the generation of risk reports is fixed to preset migraine risk indicators, cannot adapt to individual differences, and has limited accuracy in risk assessment.

[0005] In view of the above problems, the technical solution to implement this application is:

[0006] The present application provides an evidence-based migraine risk index construction system, wherein the system includes: a feature extraction module for acquiring physiological feature data including cerebral oxygen saturation fluctuation curve and carotid artery blood flow spectrum, extracting coupling abnormality features, wherein the coupling abnormality features include blood oxygen oscillation phase desynchronization and vascular wall shear stress variation coefficient; an error correction module for mapping the coupling abnormality features to the migraine risk level space, and formulating a risk probability surface, wherein the risk probability surface is corrected for periodic spectrum offset errors using ambient infrasound exposure intensity and blue light irradiation dose parameters; a dynamic adjustment module for configuring the risk probability surface to be associated with a standardized wind speed. The risk feature vector and the initial risk probability value are obtained by combining the risk feature vector and the initial risk probability value, and introducing the historical intervention cases of the target user to dynamically adjust the confidence interval of the initial risk probability value; an updating module is used to, at the same time, perform intervention response evaluation on the standardized risk feature vector and the initial risk probability value based on the historical migraine association network, and when several pre-response evaluation values ​​are lower than the intervention response threshold coordinated with the damage index, the risk probability surface is updated using iterative optimization instructions driven by Bayesian evidence theory; a synchronization module is used to construct a migraine risk feature matrix on the updated risk probability surface, and the migraine risk feature matrix is ​​used to formulate a migraine risk report and synchronize it to the user terminal.

[0007] In summary, one or more technical solutions provided in this application realize the extraction of physiological characteristic data and the analysis of coupled abnormal characteristics, more comprehensively reflect the physiological changes before the onset of migraine, and improve the reliability of risk assessment. At the same time, historical intervention cases are introduced to dynamically adjust the confidence interval of the risk probability value, thereby dynamically adjusting it according to the individual differences of patients and the intervention response, thereby improving the technical effect of the adaptability of migraine risk reporting. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of the structure of the system for building evidence-based migraine risk indicators is provided for this application;

[0009] Figure 2 A schematic diagram of the distributed iterative training process of the feature extraction module of the evidence-based migraine risk indicator construction system is provided for this application.

[0010] Description of the accompanying drawings: feature extraction module M100, error correction module M200, dynamic adjustment module M300, update module M400, synchronization module M500. DETAILED DESCRIPTION

[0011] Example

[0012] The present application will be described in detail below with reference to the accompanying drawings. Figure 1 As shown, the present application provides an evidence-based migraine risk indicator construction system, wherein the system includes:

[0013] The feature extraction module M100 is used to obtain physiological feature data including the cerebral oxygen saturation fluctuation curve and the carotid artery blood flow spectrum, and extract coupling abnormality features, wherein the coupling abnormality features include the blood oxygen oscillation phase desynchronization degree and the vascular wall shear stress variation coefficient.

[0014] The error correction module M200 is used to map the coupling abnormality characteristics to the migraine risk level space and formulate a risk probability surface. The risk probability surface is used to correct the periodic spectrum offset error based on the ambient infrasound exposure intensity and blue light irradiation dose parameters.

[0015] Specifically, the cerebral oxygen saturation fluctuation curve refers to the trajectory of changes in oxygen saturation in brain tissue over time, which is continuously monitored through near-infrared spectroscopy technology and other means, and is used to reflect the dynamic status of the balance of blood oxygen supply and demand in the brain; the carotid artery blood flow spectrum is the distribution curve of carotid artery blood flow velocity, flow and other parameters over time or cardiac cycle obtained by Doppler ultrasound technology, which reflects the hemodynamic characteristics.

[0016] The phase desynchronization of blood oxygen oscillation refers to the degree of phase difference of blood oxygen oscillation in different regions or at different times in the brain oxygen saturation fluctuation curve. Phase desynchronization suggests abnormalities in local blood circulation or oxygen metabolism regulation in the brain; the coefficient of variation of vascular wall shear stress is a relative indicator to measure the degree of shear stress fluctuation caused by blood flow on the vascular wall, reflecting the stability of the vascular wall under the impact of blood flow. The higher the coefficient of variation, the greater the shear stress fluctuation, and the more likely the vascular endothelial function may be damaged.

[0017] The migraine risk level space is a mathematical model space constructed based on multi-dimensional physiological characteristics and risk factors, which is used to quantify various characteristic parameters into migraine attack risk levels; periodic spectrum offset error correction refers to the use of signal processing technologies such as Fourier transform to analyze the periodic variation patterns of environmental infrasound exposure intensity and blue light irradiation dose parameters in the frequency domain, and adjust the risk probability surface to eliminate errors caused by periodic interference.

[0018] The brain oxygen saturation fluctuation curve and carotid artery blood flow spectrum data were obtained. Specifically, the brain oxygen saturation changes in the frontal lobe, parietal lobe and other areas of the brain were received from the near-infrared spectrometer. After analysis, it was found that within 24 hours before the onset of migraine, the fluctuation amplitude of brain oxygen saturation increased on average compared with the baseline level. At the same time, the carotid artery blood flow spectrum was analyzed, and the abnormal blood flow characteristic data was determined by combining the peak systolic flow velocity and end-diastolic flow velocity of the carotid artery in migraine patients.

[0019] Based on abnormal blood flow characteristic data, the phase desynchronization of blood oxygen oscillations was extracted. The phase information of different frequency bands was determined by wavelet transform decomposition of the cerebral oxygen saturation fluctuation curve, and the shear stress variation coefficient of the vascular wall was determined. According to the hemodynamic formula τ=4μQ / (πr³) (τ is shear stress, μ is blood viscosity, Q is blood flow, and r is blood vessel radius), combined with the carotid artery blood flow spectrum data, the proportion of the shear stress variation coefficient in migraine patients can be obtained. These coupled abnormal characteristics can more comprehensively reflect the physiological changes before a migraine attack.

[0020] When mapping the coupling abnormality characteristics to the migraine risk level space, the environmental infrasound exposure intensity (unit: dB) and blue light exposure dose (unit: J / cm²) parameters are used to correct the periodic spectrum offset error. Specifically, the environmental infrasound exposure intensity data (frequency range 0.1Hz-20Hz) and the blue light exposure dose are collected. By calculating the periodic spectral components of the environmental infrasound exposure intensity and blue light exposure dose parameters, the least squares method is used for error correction, and the risk probability surface is adjusted to ensure that the characteristic data input to the model are highly relevant and representative.

[0021] The dynamic adjustment module M300 is used to configure the risk probability surface to associate with the standardized risk feature vector and the initial risk probability value, and introduce historical intervention cases of the target user to dynamically adjust the confidence interval of the initial risk probability value.

[0022] The updating module M400 is used to, at the same time, perform an intervention response evaluation on the standardized risk feature vector and the initial risk probability value based on the historical migraine association network, and when a number of pre-response evaluation values ​​are lower than the intervention response threshold coordinated with the damage index, update the risk probability surface using iterative optimization instructions driven by Bayesian evidence theory.

[0023] The synchronization module M500 is used to construct a migraine risk feature matrix based on the updated risk probability surface. The migraine risk feature matrix is ​​used to prepare a migraine risk report and synchronize it to the user terminal.

[0024] Specifically, the standardized risk feature vector refers to a vector formed by normalizing multiple coupled abnormal features extracted from physiological feature data (such as blood oxygen oscillation phase desynchronization, vascular wall shear stress variation coefficient, etc.). The normalization process usually uses linear transformation or Z-score standardization to make its values ​​fall within a unified range, which facilitates comparison and comprehensive analysis between different features; the initial risk probability value is a basic probability value of the risk of migraine attacks set based on general population big data or prior knowledge, reflecting the possible probability of suffering a migraine in the absence of specific individual information; the confidence interval is a quantitative interval of the estimation accuracy of the initial risk probability value according to the statistical significance level, which is used to measure the reliability of the estimated value.

[0025] The historical migraine association network is a knowledge graph constructed based on a large amount of migraine patient data. It includes migraine-related physiological characteristics, environmental factors, intervention measures and the correlation between various physiological characteristics, which are mined through technologies such as graph neural networks; the intervention response evaluation value is a quantitative indicator to measure the user's response to previous intervention measures (such as drugs, lifestyle adjustments, etc.), which is calculated by analyzing data such as changes in physiological characteristics before and after the intervention, headache attack frequency, etc.

[0026] The impairment index is a comprehensive indicator that assesses the extent to which migraine attacks impair a patient's physical function and quality of life. It is calculated using specific weights for factors such as headache intensity, duration, and accompanying symptoms. Bayesian evidence theory-driven iterative optimization instructions utilize Bayesian theorem to continuously update prior knowledge and combine it with new evidence (such as new physiological characteristic data and intervention response results) to gradually optimize and adjust the risk probability surface. The migraine risk signature matrix is ​​a two-dimensional or high-dimensional matrix that integrates standardized risk signature vectors, dynamically adjusted initial risk probability values, and related correlation information. It is used to comprehensively and systematically describe migraine risk status.

[0027] When configuring the risk probability surface to associate the standardized risk feature vectors and the initial risk probability value, the physiological characteristic data of the target user for a continuous period of time (for example, one month) is collected to obtain the standardized blood oxygen oscillation phase desynchronization, vascular wall shear stress variation coefficient, etc., and these feature vectors are associated with the initial risk probability value to construct the risk probability surface; after introducing the historical intervention cases of the target user, the confidence interval of the initial risk probability value is dynamically adjusted accordingly to narrow its width, thereby improving the accuracy of the risk assessment and making the risk probability value more in line with the individual user's actual situation.

[0028] According to the historical migraine association network, when evaluating the intervention response of the standardized risk feature vector and the initial risk probability value, an intervention response threshold that is coordinated with the damage index is set. When the intervention response evaluation value is lower than the intervention response threshold that is coordinated with the damage index, the iterative optimization instruction driven by Bayesian evidence theory is triggered. With the newly collected physiological characteristic data as evidence, the Bayesian evidence theory is used to make the risk probability surface more accurately reflect the user's real-time risk status; when constructing the migraine risk feature matrix, the updated risk probability surface data, physiological characteristic change trends and other information are integrated. The migraine risk report based on this matrix can list in detail the user's migraine attack risk level, the contribution of major risk factors and other key content, and synchronize it to the user terminal in real time.

[0029] Furthermore, the migraine risk feature matrix is ​​used to prepare a migraine risk report and synchronize it to the user terminal. The synchronization module M500 is also used to execute the following method:

[0030] An integrated UV intensity sensor and air pressure change detection unit monitors light intensity and altitude changes during outdoor activities in real time. Based on these changes, the system evaluates the environmental induced index and makes a judgment based on the individual tolerance threshold. If the judgment result is yes, the system automatically plans navigation based on the user's location data.

[0031] Specifically, the UV intensity sensor is a device that can detect the intensity of ambient UV radiation in real time. Its measurement unit is usually microwatts per square centimeter (μW / cm²), which can be used to evaluate the impact of outdoor light on the human body; the air pressure change detection unit monitors changes in atmospheric pressure through an air pressure sensor, usually in hectopascals (hPa), which can be used to infer changes in altitude because the air pressure decreases with increasing altitude; the environmental induced index refers to a quantitative indicator that evaluates the possibility of these factors inducing migraines after comprehensively considering multiple environmental factors such as light intensity and altitude changes. This index is usually established based on a large amount of statistical data and the environmental exposure responses of migraine patients.

[0032] The individual tolerance threshold refers to the maximum intensity or range of variation of environmental inducing factors that each user can withstand based on their own physiological characteristics and historical migraine attacks. It is an important parameter for individualized risk assessment; automatic planning navigation refers to the use of map services and path planning based on the user's location data and migraine risk assessment results to generate a navigation route for the user that avoids high migraine risk areas.

[0033] The integrated UV intensity sensor and air pressure change detection unit monitors light intensity and altitude changes during outdoor activities in real time. The sensor measures UV intensity at fixed intervals. When the UV intensity exceeds the UV intensity threshold (for example, 300μW / cm²), it is recorded as high-intensity light. At the same time, the air pressure sensor detects that the air pressure is dropping below the lower limit, inferring that the altitude may be rising. Based on this data, the environmental induced index is evaluated. Statistical analysis found that when the environmental induced index exceeds the individual tolerance threshold, the risk of migraine attacks increases.

[0034] The system makes a judgment based on the individual tolerance threshold. If the judgment result is yes (that is, the environmental inducing factors exceed the individual tolerance threshold), it will combine the user's location data (through latitude and longitude coordinates) and use the map service API to automatically plan a navigation route that avoids high-intensity light areas and sections with sharp altitude changes; by real-time monitoring of environmental factors and evaluating their inducing risks, potential migraine-inducing environmental conditions are promptly discovered, and corresponding avoidance suggestions are provided to users, thereby enhancing the practicality and user experience of the system, and expanding migraine risk assessment from simple physiological monitoring to a comprehensive assessment of comprehensive environmental and physiological factors, providing users with more comprehensive migraine prevention support.

[0035] Furthermore, the synchronization module M500 is further configured to execute the following method:

[0036] Integrate a sound wave spectrum analysis unit in the noise reduction headphones to monitor the ambient noise in real time. The acoustic induced index is determined by the energy proportion of the noise in the wave frequency band; when the acoustic induced index exceeds the individualized tolerance threshold, the active noise reduction system is activated for dynamic attenuation, and the noise reduction intensity gradient is synchronously adjusted in combination with the user's heart rate variability data.

[0037] Specifically, the sound wave spectrum analysis unit is an electronic component integrated into the noise reduction headphones. Its function is to perform spectrum decomposition on the ambient noise, that is, to split the complex sound signal according to different frequency components and calculate the energy proportion of each frequency band. The acoustic induced index is based on the sound wave spectrum analysis results, combined with the migraine patients' A quantitative indicator derived from the sensitivity data of noise in the current frequency band is used to assess the risk of migraine induced by environmental noise.

[0038] Individualized tolerance threshold refers to the maximum acceptable value of the acoustic induced index set for each user based on the user's personal auditory sensitivity, history of migraines, and previous reaction to noise; noise is offset by generating sound waves with opposite phase to the external noise, and dynamic attenuation refers to the process of automatically adjusting the noise reduction depth according to real-time monitoring of noise intensity and frequency changes.

[0039] Heart rate variability data refers to the changes in the user's heart rate over a certain period of time, usually obtained through wearable heart rate monitoring devices. It reflects the activity state of the autonomic nervous system and is closely related to stress and pain perception; the noise reduction intensity gradient refers to the rate and amplitude of the active noise reduction system adjusting the noise reduction intensity under different noise conditions. Synchronous adjustment means changing the noise reduction intensity in real time according to the heart rate variability data to achieve optimal comfort and noise reduction effect.

[0040] Preferably, Frequency band noise will stimulate the auditory nerve, thereby affecting the balance of neurotransmitters in the brain. The sound wave spectrum analysis unit integrated in the noise reduction headphones monitors the environmental noise in real time. The sound wave spectrum analysis unit performs spectrum analysis on the environmental noise, divides the sound frequency range into multiple frequency bands, and determines the energy proportion of each frequency band. Migraine patients are particularly sensitive to noise in fixed frequency bands. The acoustic induced index is evaluated. When the acoustic induced index exceeds the individual tolerance threshold, the active noise reduction system is immediately activated. At the same time, the user's heart rate variability data is obtained in real time. According to the rate of change of heart rate variability, the gradient of the noise reduction intensity is adjusted synchronously to dynamically enhance and reduce The negative impact of frequency band noise on migraine patients is improved, thereby improving the effectiveness of the system in practical applications.

[0041] Furthermore, physiological characteristic data including the cerebral oxygen saturation fluctuation curve and the carotid artery blood flow spectrum are obtained to extract coupling abnormality features. The feature extraction module M100 is also used to perform the following method:

[0042] According to the physiological characteristic data, the time-varying causal relationship between cerebral oxygen saturation and carotid artery blood flow velocity is analyzed to determine the attenuation rate of prefrontal lobe-brainstem functional connectivity; based on the attenuation rate of prefrontal lobe-brainstem functional connectivity, a coupled differential equation of vascular wall shear stress and intracranial pressure conduction is constructed to determine the compensatory critical point, which is used to quantify the physiological function compensation state before the onset of migraine.

[0043] Specifically, time-varying causality refers to the dynamic causal relationship between cerebral oxygen saturation and carotid blood flow velocity at different time points, that is, the change in cerebral oxygen saturation at a certain moment may be caused by the fluctuation of carotid blood flow velocity in the previous period of time, and this causal relationship changes over time; the prefrontal-brainstem functional connectivity decay rate is an indicator of the rate at which the strength of the functional connection between the prefrontal lobe and the brainstem decreases over time. It is usually based on functional magnetic resonance imaging (fMRI) or near-infrared spectroscopy imaging (fNIRS) data and is determined by analyzing the synchronous changes in blood oxygen level fluctuations in the two brain regions. The higher the decay rate, the faster the decline in functional synergy between the two.

[0044] The coupled differential equation for the transmission of vascular wall shear stress and intracranial pressure is a mathematical model used to describe the dynamic transmission relationship between shear stress on the vascular wall and changes in intracranial pressure. The equation incorporates hemodynamic parameters (such as blood flow velocity and vessel diameter) and cerebrospinal fluid dynamic parameters (such as intracranial pressure and cerebrospinal fluid flow resistance). Solving this equation can reveal the laws governing their interaction. The compensatory critical point refers to the critical state before a migraine attack, where the body's compensatory mechanisms reach their limits. At this point, even small changes in physiological indicators trigger a headache. The compensatory critical point is determined by analyzing the changing trends of the solutions to the coupled differential equation under specific conditions. It is used to quantify the limiting state of the body's compensatory capacity before a migraine attack.

[0045] Based on physiological characteristic data, the time-varying causal relationship between cerebral oxygen saturation and carotid blood flow velocity was analyzed using time series analysis such as causal tests. Taking near-infrared spectral imaging data as an example, the time series of cerebral oxygen saturation and carotid blood flow velocity obtained by monitoring were analyzed. For example, it was found that when the carotid blood flow velocity increased by 10% at time t, the cerebral oxygen saturation increased by an average of 5% at time t+2 minutes, and this causal relationship significantly indicated the existence of a causal association. By calculating the changes in causal strength within multiple time windows, the attenuation rate of the prefrontal lobe-brainstem functional connectivity, that is, the functional connectivity between the two per minute, was determined, providing support for the subsequent construction of coupled differential equations.

[0046] Based on the determined attenuation rate of prefrontal lobe-brainstem functional connectivity, a coupled differential equation for vascular wall shear stress and intracranial pressure transmission was constructed; using coupled differential equation simulation analysis, the compensatory critical point was determined, and the risk of migraine attacks increased at the compensatory critical point; by deeply exploring the physiological mechanisms behind the physiological characteristic data, quantifying the changes in neural functional connectivity and constructing a coupling model, it provides a key basis for more accurate assessment of the risk of migraine attacks.

[0047] Furthermore, the compensation critical point is used to quantify the physiological function compensation state before the migraine attack, and the feature extraction module M100 is further used to perform the following method:

[0048] Monitor the pulsation propagation velocity of the middle meningeal artery and establish a nonlinear regression function between the pulsation propagation velocity and cerebrospinal fluid pressure fluctuations. If the standard deviation of the arterial pulsation propagation velocity exceeds the baseline value, combine the time window to deeply explore the associated physiological characteristics that change synergistically with the compensatory state of the physiological function, and configure a time series association mechanism.

[0049] Specifically, the middle meningeal artery pulsation propagation velocity refers to the rate at which the blood flow pulsation of the middle meningeal artery (the blood flow pulse generated by the heartbeat) propagates in the blood vessels. It is usually measured in meters per second (m / s) and can reflect the stability of brain hemodynamics. Spinal fluid pressure fluctuation refers to the change in cerebrospinal fluid pressure in the ventricular system and subarachnoid space over time. It is usually measured in millimeters of mercury (mmHg). Its fluctuation is closely related to cerebral blood flow regulation and intracranial pressure balance.

[0050] The nonlinear regression function is a mathematical model used to describe the nonlinear relationship between two variables, referring to the complex association between pulsation velocity and cerebrospinal fluid pressure fluctuations. This relationship is expressed by finding the optimal function form by fitting historical data. The standard deviation of arterial pulsation velocity is an indicator that measures the degree of dispersion of pulsation velocity around its mean value. A larger standard deviation indicates a more severe fluctuation in pulsation velocity.

[0051] The baseline value refers to the average level of the standard deviation of arterial pulse propagation velocity in a normal physiological state or when there is no risk of migraine attack, which serves as a reference value for judging whether it is abnormal; the time window refers to the length of the time period used to analyze the data, and is used to extract characteristic information within a specific time period from continuous data. Associated physiological characteristics of the coordinated changes in the compensatory state of physiological function refer to other related physiological indicators that change simultaneously with the compensatory state of physiological function, such as heart rate variability, blood oxygen saturation, and vascular wall shear stress. These characteristics may show specific change patterns before a migraine attack; the temporal association mechanism is used to explore the correlation between different physiological characteristics in the time series, determine the order, mutual influence, and common change rules between different physiological characteristics, and more comprehensively understand the physiological changes before a migraine attack.

[0052] Monitor the pulsation propagation velocity of the middle meningeal artery. If the monitored average pulsation propagation velocity is 0.5m / s and the standard deviation is 0.12m / s, while the standard deviation of the baseline value is only 0.05m / s, indicating that the standard deviation significantly exceeds the baseline value, the system, combined with the set time window, deeply mines the associated physiological characteristics that coordinate changes with the compensatory state of physiological function. Specifically, within the time window with abnormal pulsation propagation velocity standard deviation, the heart rate variability standard deviation decreases, the blood oxygen saturation fluctuation amplitude increases, and the coefficient of variation of vascular wall shear stress increases; based on these characteristics, a time series association mechanism is established, and through the Granger causality test, it is found that the change in pulsation propagation velocity precedes the change in heart rate variability, the blood oxygen saturation fluctuation and the pulsation propagation velocity change occur almost simultaneously, and the vascular wall shear stress change lags behind the pulsation propagation velocity change.

[0053] Through the above analysis, we have deepened our understanding of the compensatory state of physiological functions before a migraine attack. By exploring the temporal correlation of multiple physiological characteristics, we have provided strong support for the accurate identification of early warning signals of migraine, effectively enriched the early warning capabilities of the entire risk assessment system, and enabled the system to capture the complex physiological changes before a migraine attack in a more timely and comprehensive manner.

[0054] Furthermore, the feature extraction module M100 is further configured to perform the following method:

[0055] The physiological function compensation state includes an eye movement pattern; based on the timing association mechanism, a micro pressure sensor array embedded in the contact lens is activated to receive eyelid microtremor frequency and intraocular pressure fluctuation data; and an association mapping index item between the eye movement pattern and the prodromal stage of migraine is set through the eyelid microtremor frequency and intraocular pressure fluctuation data.

[0056] Specifically, the micro-pressure sensor array refers to a group of tiny pressure sensors embedded in contact lenses, which can monitor the frequency of eyelid micro-tremors and intraocular pressure fluctuations in real time; the frequency of eyelid micro-tremors refers to the frequency of involuntary eyelid tremors, measured in Hertz (Hz), reflecting the tension of the eyelid muscles and the state of neural regulation; intraocular pressure fluctuation data refers to the change of intraocular pressure over time, usually in millimeters of mercury (mmHg). Abnormal intraocular pressure fluctuations may be related to changes in cerebrospinal fluid pressure and migraine attacks.

[0057] Eye movement patterns refer to a series of characteristics of eye movements, including eyelid microtwitching frequency, intraocular pressure fluctuations, eye movement trajectories, etc. These characteristics may show specific change patterns during the prodromal period of migraine; the association mapping index item refers to the index that establishes an association between the eye movement pattern and the prodromal period of migraine. By analyzing the changing characteristics of the eye movement pattern, key parameters are extracted as indexes to quickly identify the arrival of the prodromal period of migraine.

[0058] Based on the temporal association mechanism, the micro pressure sensor array embedded in the contact lens is activated. Specifically, the micro pressure sensor array embedded in the contact lens is activated to synchronously receive eyelid micro-tremor frequency and intraocular pressure fluctuation data; by collecting these data and combining them with the temporal association mechanism, the association mapping index items between eye movement patterns and the prodromal period of migraine are set; by introducing the new physiological characteristic dimension of eye movement patterns, the data source for risk assessment is further enriched. Furthermore, changes in eye movement patterns can reflect early changes in the autonomic nervous system and brain hemodynamics, providing a more comprehensive basis for early warning of migraine attacks.

[0059] Furthermore, the feature extraction module M100 is further configured to perform the following method:

[0060] Exosome concentration is introduced. When the correlation coefficient between the exosome concentration and the compensation critical point meets the correlation coefficient threshold, the exosome concentration is incorporated into the physiological function compensation status assessment system. In the physiological function compensation status assessment system, a quantum key distribution protocol is used to generate a biofeedback training key, and the biofeedback training key is matched with the historical intervention case of the target user.

[0061] Specifically, exosome concentration refers to the number of exosomes per unit volume of body fluids (such as blood and cerebrospinal fluid). Exosomes are tiny vesicles secreted by cells that carry a variety of biomolecules (such as proteins and nucleic acids). Changes in their concentration can reflect cellular physiological states and pathological processes. The correlation coefficient threshold is a numerical standard used to determine whether the correlation between exosome concentration and the compensatory critical point is strong enough. It is usually between 0.3 and 0.5. When the correlation coefficient exceeds this threshold, the two are considered to be significantly correlated.

[0062] The physiological function compensation status assessment system is a systematic model that comprehensively evaluates the compensatory ability of various systems of the body when facing physiological dysfunction. It contains multiple physiological indicators and evaluation parameters, which are used to quantify the body's compensation status; the quantum key distribution protocol is an encryption communication protocol based on the principles of quantum mechanics. It establishes a secure key that cannot be stolen between the communicating parties through the transmission of quantum states, which is used to protect the transmission security of biofeedback training keys; the biofeedback training key is a set of coding parameters generated based on the user's physiological data and intervention history, and is used to guide users to conduct targeted biofeedback training to help them regulate their physiological functions and relieve migraine symptoms.

[0063] Exosome concentration was introduced as a new evaluation indicator, and the correlation coefficient between exosome concentration and the compensation critical point was determined. Assuming that the correlation coefficient threshold was set at 0.4, statistical analysis found that the correlation coefficient between the two was 0.45, which exceeded the threshold, indicating that exosome concentration can reflect changes in the body's compensatory state. Therefore, it was included in the physiological function compensation state evaluation system, which increased the indicator dimension of the evaluation system and enriched the source of evaluation data.

[0064] In the evaluation system, the quantum key distribution protocol is used to generate biofeedback training keys. Correspondingly, if the user responds well to the biofeedback training, the frequency of their headache attacks will decrease. The encrypted data is transmitted to the user's terminal device to guide the user to conduct effective biofeedback training. In the above steps, the introduction of exosome concentration expands the breadth and depth of the evaluation system, enabling it to more accurately capture changes in the body's compensatory state and improve the comprehensiveness and accuracy of risk assessment. The use of the quantum key distribution protocol ensures the security of the biofeedback training keys, ensuring that users can receive personalized, safe and reliable training guidance, thereby improving the effectiveness of intervention measures.

[0065] Furthermore, if Figure 2 As shown, the feature extraction module M100 is also used to perform the following method:

[0066] In the physiological function compensation status assessment system, a data drift unit is configured, and the data drift unit is used to analyze the distribution KL divergence changes corresponding to the historical intervention cases of the target user; a population subgroup difference analysis is performed on the target user, and if the difference threshold is exceeded, the federated learning framework of the central server is activated to perform distributed iterative training on each population subgroup.

[0067] Specifically, the data drift unit is a module used to monitor and analyze changes in data distribution. It can detect whether the distribution characteristics of data in different time periods or under different conditions have shifted, which is crucial for evaluating the stability and reliability of the model; the distribution KL divergence is an asymmetric measure of the difference between two probability distributions. It is used to quantify the degree of difference between the target user's historical intervention case data distribution and the current data distribution. The larger the value, the greater the distribution difference.

[0068] Population subgroup difference analysis involves dividing the population into different subgroups based on specific characteristics (such as age, gender, and medical history), and analyzing differences between subgroups in terms of physiological function compensation status, intervention response, and other aspects, in order to identify groups with different risk characteristics and intervention needs. The difference threshold refers to a pre-set standard value used to determine whether the differences between population subgroups are significant. When the KL divergence exceeds this threshold, the difference is considered large enough to require further model optimization measures. The federated learning framework is a distributed machine learning method that allows multiple devices or institutions to collaboratively train models without sharing raw data. It protects data privacy through encryption technology, while enabling knowledge sharing and model optimization, thereby improving the model's generalization capabilities for different population subgroups.

[0069] A data drift unit is configured in the physiological function compensation status assessment system to analyze the changes in the distribution KL divergence corresponding to the historical intervention cases of the target user. For example, the intervention case data of user A in the past 6 months are collected, including physiological indicators, intervention measures and effects before and after the intervention, and are divided into a training data set (data from the first 3 months) and a test data set (data from the last 3 months); the distribution KL divergence of the two data sets is determined. If the difference threshold is set to 0.15, if the calculated KL divergence is 0.20, which exceeds the difference threshold, it indicates that the data distribution has changed significantly, which may be due to changes in factors such as the user's physiological state, intervention response or external environment.

[0070] At this time, the target users are triggered to conduct a population subgroup difference analysis, and the population is divided into different subgroups according to characteristics such as age (such as less than 30 years old, 30-50 years old, and more than 50 years old), gender, and medical history (such as whether there is a family history of migraine). This shows that there are significant differences between different subgroups. At the same time, the federated learning framework of the central server is activated, and the data of each population subgroup is encrypted and assigned to different computing nodes for distributed iterative training, while protecting the user's privacy data. In the above steps, by monitoring data drift and analyzing population subgroup differences, the dynamic adaptability and accuracy of the evaluation system are ensured, and the changes in the applicability of the model in different populations and at different times are discovered in a timely manner. Targeted optimization is carried out through federated learning, so that the system can continue to provide reliable risk assessments and intervention recommendations, effectively improving the long-term effectiveness and wide applicability of the program.

[0071] In summary, the beneficial effects of the embodiments of the present application are:

[0072] Due to the use of a feature extraction module, it is used to obtain physiological feature data including cerebral oxygen saturation fluctuation curve and carotid artery blood flow spectrum, and extract coupling abnormality features; an error correction module is used to map the coupling abnormality features to the migraine risk level space, and to formulate a risk probability surface. The risk probability surface is used to perform periodic spectrum offset error correction based on the environmental infrasound exposure intensity and blue light irradiation dose parameters; a dynamic adjustment module is used to configure the risk probability surface to associate the standardized risk feature vector and the initial risk probability value, and introduce the historical intervention cases of the target user to dynamically adjust the confidence interval of the initial risk probability value; an update module is used to, at the same time, perform intervention response evaluation on the standardized risk feature vector and the initial risk probability value based on the historical migraine association network, and several pre-response When the assessment value is lower than the intervention response threshold coordinated with the damage index, the risk probability surface is updated using iterative optimization instructions driven by Bayesian evidence theory; a synchronization module is used to construct a migraine risk feature matrix on the updated risk probability surface. The migraine risk feature matrix is ​​used to formulate a migraine risk report and synchronize it to the user terminal. This application provides an evidence-based migraine risk indicator construction system to extract physiological feature data and analyze coupled abnormal features, more comprehensively reflect the physiological changes before a migraine attack, and improve the reliability of risk assessment. At the same time, historical intervention cases are introduced to dynamically adjust the confidence interval of the risk probability value, thereby making dynamic adjustments based on the individual differences of patients and the intervention response, thereby improving the technical effect of improving the adaptability of migraine risk reporting.

[0073] In summary, any step can be stored as a computer instruction or program in an unlimited computer memory and can be called and recognized by an unlimited computer processor, without any unnecessary restrictions.

[0074] Furthermore, the above technical solution only reflects the preferred technical solution of the technical solution of the embodiment of the present application. Some changes that may be made to certain parts thereof by technical personnel in this technical field all reflect the novel principles of the embodiment of the present application. Obviously, technical personnel in this field can make various changes and modifications to the present application without departing from the scope of the present application.

Claims

1. A system for constructing evidence-based migraine risk indicators, characterized by: include: A feature extraction module is used to obtain physiological feature data including cerebral oxygen saturation fluctuation curve and carotid artery blood flow spectrum, and extract coupling abnormality features, wherein the coupling abnormality features include blood oxygen oscillation phase desynchronization and vascular wall shear stress variation coefficient; an error correction module for mapping the coupling abnormality characteristics to a migraine risk level space and formulating a risk probability surface, wherein the risk probability surface is corrected for periodic spectrum offset errors using parameters of ambient infrasound exposure intensity and blue light irradiation dose; A dynamic adjustment module is used to configure the risk probability surface to associate with the standardized risk feature vector and the initial risk probability value, and introduce historical intervention cases of the target user to dynamically adjust the confidence interval of the initial risk probability value; an updating module, configured to simultaneously perform intervention response assessment on the standardized risk feature vector and the initial risk probability value based on a historical migraine association network, and update the risk probability surface using an iterative optimization instruction driven by Bayesian evidence theory when a number of pre-response assessment values ​​are lower than an intervention response threshold coordinated with the damage index; The synchronization module is used to construct a migraine risk feature matrix in the updated risk probability surface, and the migraine risk feature matrix is ​​used to prepare a migraine risk report and synchronize it to the user terminal.

2. The system for constructing an evidence-based migraine risk index according to claim 1, wherein: The migraine risk feature matrix is ​​used to prepare a migraine risk report and synchronize it to the user terminal, and also includes: Integrated UV intensity sensor and air pressure change detection unit to monitor light intensity and altitude changes during outdoor activities in real time; Based on the changes in light intensity and altitude, the environmental induction index is evaluated and determined in combination with the individual tolerance threshold; If the judgment result is yes, automatic planning and navigation will be performed in combination with the user's location data.

3. The system for constructing an evidence-based migraine risk index according to claim 2, wherein: Also includes: Integrate a sound wave spectrum analysis unit in the noise reduction headphones to monitor the ambient noise in real time. The energy proportion of the noise in the wave frequency band is used to determine the acoustic induced index; When the acoustic induced index exceeds the individualized tolerance threshold, the active noise reduction system is activated for dynamic attenuation, and the noise reduction intensity gradient is synchronously adjusted in combination with the user's heart rate variability data.

4. The system for constructing an evidence-based migraine risk index according to claim 1, wherein: Acquire physiological characteristic data including cerebral oxygen saturation fluctuation curve and carotid artery blood flow spectrum, extract coupling abnormality features, and also include: Based on the physiological characteristic data, analyzing the time-varying causal relationship between cerebral oxygen saturation and carotid artery blood flow velocity, and determining the attenuation rate of prefrontal lobe-brainstem functional connectivity; Based on the attenuation rate of the prefrontal lobe-brainstem functional connectivity, a coupled differential equation of vascular wall shear stress and intracranial pressure conduction is constructed to determine the compensatory critical point, which is used to quantify the physiological function compensation state before the onset of migraine.

5. The system for constructing an evidence-based migraine risk index according to claim 4, wherein: The compensation critical point is used to quantify the physiological function compensation state before the migraine attack, and also includes: Monitor the pulsation propagation velocity of the middle meningeal artery and establish a nonlinear regression function between the pulsation propagation velocity and cerebrospinal fluid pressure fluctuations; If the standard deviation of the arterial pulsation propagation velocity exceeds the baseline value, combined with the time window, the associated physiological characteristics that change synergistically with the compensatory state of the physiological function are deeply mined, and a time series association mechanism is configured.

6. The system for constructing an evidence-based migraine risk index according to claim 5, wherein: The physiological function compensation state includes eye movement patterns; Based on the timing association mechanism, a micro pressure sensor array embedded in the contact lens is activated to receive eyelid micro-tremor frequency and intraocular pressure fluctuation data; An association mapping index item between the eye movement pattern and the prodromal phase of migraine is set based on the eyelid microtwitching frequency and intraocular pressure fluctuation data.

7. The system for constructing an evidence-based migraine risk index according to claim 6, wherein: Introducing exosome concentration, when the correlation coefficient between the exosome concentration and the compensation critical point meets the correlation coefficient threshold, the exosome concentration is included in the physiological function compensation status evaluation system; In the physiological function compensation state assessment system, a quantum key distribution protocol is used to generate a biofeedback training key, and the biofeedback training key is matched with the historical intervention case of the target user.

8. The system for constructing an evidence-based migraine risk index according to claim 7, wherein: include: In the physiological function compensation state assessment system, a data drift unit is configured, and the data drift unit is used to analyze the distribution KL divergence changes corresponding to the historical intervention cases of the target user; Perform population subgroup difference analysis on the target users. If the difference threshold is exceeded, activate the federated learning framework of the central server to conduct distributed iterative training on each population subgroup.

Images