Assistant system and method for risk assessment and clinical decision of migraine patient

Abstract

The invention relates to the field of migraine auxiliary analysis, and discloses a migraine patient risk assessment and clinical decision auxiliary system and method, and the method comprises the steps: querying biomarker detection data of a migraine patient, carrying out the data quantification, obtaining the quantified biological data, and recognizing the brain blood vessel region of the migraine patient; analyzing brain features of the migraine patient, performing feature quantization to obtain quantified brain features, and constructing a nerve-pathological model of the migraine patient; performing brain abnormality analysis on the migraine patient to obtain a brain abnormality analysis result, and performing risk assessment on the migraine patient to obtain a migraine state of the patient; the method comprises the following steps: constructing an auxiliary scheme for the migraine patient, collecting pathology-related data and life data, classifying a first auxiliary effect and a second auxiliary effect for the migraine patient to analyze the auxiliary improvement level of the migraine patient, and constructing a risk assessment-clinical auxiliary report. According to the invention, the reliability of risk assessment and clinical decision assistance of migraine patients can be improved.

Description

Technical Field

[0001] The present invention relates to the field of migraine auxiliary analysis, and in particular to a migraine patient risk assessment and clinical decision-making assistance system and method. Background Art

[0002] Migraine is a common chronic neurological disease that has a serious impact on the quality of life of patients. During clinical diagnosis and treatment, it is particularly important to conduct accurate risk assessments for migraine patients and provide effective clinical decision-making assistance. Accurate risk assessments can help medical staff know in advance the various risks that migraine patients may face, such as worsening of the disease and the onset of other complications, and then formulate targeted prevention and response measures. Scientific and reasonable clinical decision-making assistance methods can help doctors quickly screen out the most suitable treatment options for individual patients from a variety of treatment options, improve the accuracy and effectiveness of treatment, enhance the patient's recovery effect, and optimize the rational allocation of medical resources.

[0003] Currently, in the field of risk assessment and clinical decision support for migraine patients, most rely on the doctor's clinical experience combined with some routine examination indicators to make a comprehensive judgment. Doctors rely on their past experience and analyze the patient's current symptoms, medical history and other basic information, and then refer to common examination results to roughly assess the risk and determine the treatment decision. However, this method has certain limitations. On the one hand, the experience levels of different doctors vary, which may lead to inaccurate and incomplete risk assessment results for the same patient, thereby affecting the scientific nature of subsequent clinical decisions; on the other hand, relying solely on conventional indicators makes it difficult to fully consider the individual differences of each patient, such as the patient's special physical condition, living habits and other factors, making it impossible to accurately fit the patient's actual situation when making clinical decisions, which ultimately affects the overall treatment effect and prognosis of migraine patients. Summary of the Invention

[0004] The present invention provides a migraine patient risk assessment and clinical decision support system, the main purpose of which is to improve the reliability of migraine patient risk assessment and clinical decision support.

[0005] To achieve the above-mentioned objectives, the present invention provides a migraine patient risk assessment and clinical decision support system, comprising: a brain region identification module, a model construction module, a state analysis module, and an auxiliary analysis module; The brain region identification module is configured to query biomarker detection data of a migraine patient, quantify the biomarker detection data to obtain quantified biological data, collect a brain scan image of the migraine patient, and identify the brain vascular region of the migraine patient using the brain scan image; The model building module is configured to analyze the morphology and blood perfusion of the cerebral blood vessels of the migraine patient using the cerebral vascular regions to obtain brain features of the migraine patient, quantify the brain features to obtain quantified brain features, and construct a neuropathological model of the migraine patient using the quantified biological data and the quantified brain features; The state analysis module is configured to collect an electroencephalogram (EEG) of the migraine patient, identify brain activity characteristics of the migraine patient using the EEG, analyze the visual-spatial ability of the migraine patient using the brain activity characteristics, identify a blood oxygen level-dependent signal of the migraine patient using the EEG, perform a brain abnormality analysis on the migraine patient using the blood oxygen level-dependent signal, obtain a brain abnormality analysis result, and perform a risk assessment on the migraine patient based on the visual-spatial ability and the brain abnormality analysis result to determine the patient's migraine state; The auxiliary analysis module is used to construct an auxiliary plan for the migraine patient using the patient's migraine status, collect pathology-related data and life data of the migraine patient under the auxiliary plan, analyze the first auxiliary effect of the migraine patient using the pathology-related data and the neuro-pathology model, analyze the second auxiliary effect of the migraine patient using the life data, analyze the auxiliary improvement level of the migraine patient based on the first auxiliary effect and the second auxiliary effect, and construct a risk assessment-clinical auxiliary report for the migraine patient based on the auxiliary improvement level.

[0006] A method for risk assessment and clinical decision support for migraine patients, characterized in that the method comprises: querying biomarker detection data of a migraine patient, quantifying the biomarker detection data to obtain quantified biological data, acquiring a brain scan image of the migraine patient, and identifying a brain vascular region of the migraine patient using the brain scan image; Analyzing the morphology and blood perfusion of the cerebral blood vessels of the migraine patient using the brain vascular regions to obtain brain features of the migraine patient, quantifying the brain features to obtain quantified brain features, and constructing a neuropathological model of the migraine patient using the quantified biological data and the quantified brain features; collecting an electroencephalogram (EEG) of the migraine patient, identifying brain activity characteristics of the migraine patient using the EEG, analyzing the visual-spatial ability of the migraine patient using the brain activity characteristics, identifying a blood oxygen level-dependent signal of the migraine patient using the EEG, performing a brain abnormality analysis on the migraine patient using the blood oxygen level-dependent signal, obtaining a brain abnormality analysis result, and performing a risk assessment on the migraine patient based on the visual-spatial ability and the brain abnormality analysis result to determine the patient's migraine status; Using the patient's migraine status, an auxiliary plan for the migraine patient is constructed, and pathology-related data and life data of the migraine patient under the auxiliary plan are collected. Using the pathology-related data and the neuro-pathology model, the first auxiliary effect of the migraine patient is analyzed. Using the life data, the second auxiliary effect of the migraine patient is analyzed. Based on the first auxiliary effect and the second auxiliary effect, the auxiliary improvement level of the migraine patient is analyzed. Based on the auxiliary improvement level, a risk assessment-clinical auxiliary report for the migraine patient is constructed.

[0007] Based on the application requirements, the present invention first queries biomarker test data from migraine patients to understand the patient's physiological and pathological conditions. Using technologies such as ELISA, PCR, and LC-MS, the test data can be quantified into more scientific and objective quantitative biological data for easier comparative analysis. Brain scan images (perhaps using MRI) are then collected from migraine patients to identify brain vascular regions and construct a brain vascular network. Finally, the quantitative biological data is combined to construct a neuropathological model for migraine patients, exploring the potential mechanisms by which biomarker changes affect migraine onset and disease progression. Furthermore, the present invention collects electroencephalograms (EEGs) from migraine patients (perhaps using brain CT scans), identifies brain activity characteristics from the EEGs, constructs spectrograms, and analyzes their spectral characteristics, waveform morphology, and topological distribution. This allows the EEG frequency, amplitude, and waveform characteristics to be derived, thereby analyzing the patient's visual-spatial ability, identifying key brain regions, extracting target features, and identifying specific bands associated with migraine. Visual-spatial ability is then determined by comparing the bands with those of a healthy population. The system also uses EEG to identify blood oxygenation-dependent signals (requiring simultaneous fMRI data acquisition), based on which brain abnormality analysis is performed. Finally, by integrating visual-spatial ability and brain abnormality analysis results, a risk assessment is performed on the migraine patient by constructing a comprehensive assessment index, identifying the number of abnormal brain regions, and using conditional probability calculations to determine the patient's migraine status (e.g., mild, moderate, or high risk). Furthermore, the present invention utilizes the determined patient's migraine status to construct an assistance plan. This assistance framework is constructed by stratifying attack frequency and classifying aura pain levels. This framework is optimized based on the queried physiological factors and refined based on continuous monitoring data. Pathology-related data and daily life data within the assistance plan are collected. The pathology-related data and neuropathology model are used to analyze the primary assistance effect. From the perspective of daily life data, an assistance improvement score is calculated by identifying the number of lifestyle factors and quantifying their values ​​to determine the secondary assistance effect. The two are combined to analyze the level of assistance improvement. Finally, a risk assessment-clinical assistance report (which can be generated by compiling data using a Java-generated script) is constructed, covering the current condition, improvement, risk prediction, and follow-up recommendations. This report provides a valuable reference for clinical decision-making and patient disease management. Therefore, the reliability of risk assessment and clinical decision assistance for migraine patients is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 This is a functional module diagram of a migraine patient risk assessment and clinical decision support system provided by one embodiment of the present invention; Figure 2 A flowchart of a method for risk assessment and clinical decision support for migraine patients provided by one embodiment of the present invention; The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0009] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0010] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0011] In practice, the server-side device deployed by the migraine patient risk assessment and clinical decision support system may be composed of one or more devices. The aforementioned migraine patient risk assessment and clinical decision support system can be implemented as a service instance, a virtual machine, or hardware devices. For example, the migraine patient risk assessment and clinical decision support system can be implemented as a service instance deployed on one or more devices in a cloud node. Simply put, the migraine patient risk assessment and clinical decision support system can be understood as software deployed on a cloud node, used to provide migraine patient risk assessment and clinical decision support services to various user terminals. Alternatively, the migraine patient risk assessment and clinical decision support system can be implemented as a virtual machine deployed on one or more devices in a cloud node. Application software for managing various user terminals is installed in the virtual machine. Alternatively, the migraine patient risk assessment and clinical decision support system can be implemented as a server-side device composed of multiple hardware devices of the same or different types, with one or more hardware devices configured to provide migraine patient risk assessment and clinical decision support services to various user terminals.

[0012] In terms of implementation, the migraine patient risk assessment and clinical decision support system and the user end are mutually compatible. Specifically, if the migraine patient risk assessment and clinical decision support system is an application installed on a cloud service platform, the user end serves as a client that establishes a communication connection with the application. Alternatively, if the migraine patient risk assessment and clinical decision support system is implemented as a website, the user end serves as a webpage. Alternatively, if the migraine patient risk assessment and clinical decision support system is implemented as a cloud service platform, the user end serves as a mini-program within an instant messaging application.

[0013] Reference Figure 1 , which is a functional module diagram of a migraine patient risk assessment and clinical decision support system provided by one embodiment of the present invention.

[0014] The migraine patient risk assessment and clinical decision support system 100 of the present invention can be installed in a cloud server. In terms of implementation, it can be implemented as one or more service devices, or as an application installed in the cloud (e.g., a migraine patient risk assessment and clinical decision support server, server cluster, etc.), or developed as a website. Depending on the functionality implemented, the migraine patient risk assessment and clinical decision support system 100 includes a brain region identification module 1010, a model construction module 102, a state analysis module 103, and an auxiliary analysis module 104.

[0015] In the embodiment of the present invention, each of the aforementioned modules can be independently implemented and called upon from other modules in the migraine patient risk assessment and clinical decision support tracking system. The term "call" here can be understood as a module being able to connect to multiple modules of a different type and provide corresponding services to the connected modules. In the migraine patient risk assessment and clinical decision support system provided by the embodiment of the present invention, the scope of application of the migraine patient risk assessment and clinical decision support architecture can be adjusted by adding modules and directly calling them, without modifying the program code. This allows for clustered horizontal expansion, thereby achieving the goal of rapidly and flexibly expanding the migraine patient risk assessment and clinical decision support system. In practical applications, the aforementioned modules can be deployed on the same device, on different devices, or even on virtual devices, such as service instances on a cloud server.

[0016] The following describes the various components and specific workflows of the migraine patient risk assessment and clinical decision support system in conjunction with specific embodiments.

[0017] The brain region identification module is used to query biomarker detection data of migraine patients, quantify the biomarker detection data to obtain quantified biological data, collect brain scan images of the migraine patients, and use the brain scan images to identify brain vascular regions of the migraine patients.

[0018] The embodiments of the present invention can provide a preliminary understanding of potential pathophysiological changes in patients by querying the biomarker detection data of migraine patients, providing a basis for comprehensively assessing the disease, exploring the root cause of the disease, and formulating precise treatment strategies.

[0019] Among them, the biomarker detection data refers to the result information obtained after detecting markers in biological samples (such as blood, cerebrospinal fluid, urine, tissues, etc.) that can reflect the physiological and pathological status of the body and related characteristics such as disease occurrence, development, and prognosis through specific detection technologies and means, such as protein, gene and metabolite markers.

[0020] Optionally, the biomarker detection data can be obtained by querying the medical monitoring data of the migraine patient.

[0021] In the embodiments of the present invention, by quantifying the biomarker detection data, quantitative biological data can be obtained, which can convert what may originally be described as qualitative descriptions (such as test results being positive or negative) or relatively vague semi-quantitative expressions (such as concentration ranges described as "higher" or "lower", etc.) into precise, specific numerical values ​​that can be used for calculation and comparison. The quantified data is more scientific and objective, and facilitates horizontal and vertical comparative analysis between different patients and between different stages of the same patient.

[0022] Optionally, the quantitative biological data can be obtained by converting the biomarker detection data using ELISA, PCR and LC-MS.

[0023] Furthermore, the embodiments of the present invention can help doctors intuitively understand whether there are vascular malformations or abnormal brain tissue structure (such as atrophy, lesions, etc.) in the patient's brain by collecting brain scan images of the migraine patient, which helps to explore the potential causes of migraine from an anatomical perspective.

[0024] Optionally, the brain scan image can be acquired using MRI technology.

[0025] Furthermore, the embodiments of the present invention can help users determine whether the morphology of brain blood vessels is normal and whether there are lesions such as stenosis or dilation by using the brain scan image to identify the brain blood vessel area of ​​the migraine patient. It also provides a basic positioning and quantification basis for subsequent research on the relationship between blood vessels and surrounding brain tissue and analysis of blood perfusion.

[0026] Optionally, the brain vascular region can be identified by using a machine learning model to identify features of the corresponding vascular region in the brain scan image.

[0027] The model construction module is used to use the brain vascular area to analyze the cerebral vascular morphology and blood perfusion of the migraine patient, obtain brain characteristics of the migraine patient, quantify the brain characteristics to obtain quantitative brain characteristics, and use the quantitative biological data and the quantitative brain characteristics to construct a neuropathological model of the migraine patient.

[0028] By analyzing the morphology and blood perfusion of the migraine patient's cerebral vessels using the brain vascular regions, the embodiments of the present invention can provide brain characteristics of the migraine patient, helping users explore the root causes of migraine from both anatomical and physiological perspectives. For example, if a patient's cerebral vessels are found to have congenital vascular malformations, this may result in chronically abnormal local hemodynamics, which may in turn predispose to migraine attacks. Alternatively, if a region of insufficient blood perfusion is detected, the corresponding brain tissue function may be affected, contributing to the neuropathological processes associated with migraine.

[0029] Among them, the cerebral vascular morphology refers to the appearance characteristics of the brain blood vessels in the anatomical structure, including the thickness, direction, curvature, branching, and presence of deformities of the blood vessels. The blood perfusion condition refers to the state of blood flowing in the cerebral blood vessels and delivering nutrients to the brain tissue, covering relevant indicators such as blood flow rate, blood flow velocity, blood volume, and whether the perfusion of different brain regions is uniform.

[0030] As one embodiment of the present invention, the use of the brain vascular region to analyze the cerebral vascular morphology and blood perfusion of the migraine patient to obtain brain characteristics of the migraine patient includes: constructing a brain vascular network of the migraine patient based on the brain vascular region; analyzing the vascular orientation and tortuosity of the migraine patient's cerebral vessels using the brain vascular network; determining the cerebral vascular morphology of the migraine patient based on the vascular orientation and tortuosity; calculating the vascular pixels in the brain vascular region; identifying the blood perfusion of the migraine patient based on the vascular pixels; and determining the brain characteristics of the migraine patient based on the cerebral vascular morphology and blood perfusion.

[0031] The brain vascular network refers to a complex and orderly systematic structure formed by the interconnected and interwoven vascular structures such as numerous arteries, veins and capillaries in the brain.

[0032] Optionally, the cerebral vascular network can utilize image analysis software or algorithms to organize and integrate individual vascular segments within the identified cerebral vascular regions according to their connectivity relationships, identifying vascular branches and junctions, and constructing a network structure that reflects vascular interconnectivity. For example, vascular orientation and network connectivity can be determined by tracking pixel connectivity. Analyzing the vascular orientation and tortuosity of migraine patients' cerebral vessels using the cerebral vascular network can be accomplished by determining the extension direction, i.e., the vascular orientation, along the continuous pixel path of the vessel within the constructed cerebral vascular network. This can be accomplished by calculating the degree to which the vessel deviates from a straight line at different locations, for example, by comparing the actual vascular trajectory with a fitted straight line. Determining the cerebral vascular morphology of migraine patients based on the vascular orientation and tortuosity can be accomplished by integrating the obtained vascular orientation information (e.g., the distribution of major vessels and the brain regions they flow to) with vascular tortuosity data (determining whether the vessels exhibit abnormal tortuosity or tortuosity) to comprehensively delineate whether the cerebral vessels exhibit normal morphology or abnormal morphological features, such as tortuosity or localized stenosis.

[0033] Furthermore, as yet another optional embodiment of the present invention, identifying the blood perfusion status of the migraine patient based on the vascular pixels includes: calculating the perivascular area of ​​the migraine patient's blood vessels using the vascular pixels, calculating the regional area of ​​the migraine patient's brain region based on the vascular pixels, and calculating the vascular perfusion index of the migraine patient based on the perivascular area and the regional area: ; ;

[0034] Where PI represents the vascular perfusion index, β represents the area around the blood vessel, γ represents the area of ​​the region, n represents the number of pixel statistics of the area around the blood vessel, m represents the number of pixel statistics of the region, and a×b represents the image resolution; The blood perfusion condition of the migraine patient is analyzed based on the vascular perfusion index.

[0035] Furthermore, the embodiments of the present invention quantify the brain features to obtain quantified brain features, which can summarize and organize the specific manifestations obtained from the above-mentioned analysis of cerebral vascular morphology and blood perfusion, thereby forming a set of features that can comprehensively describe the brain state of migraine patients.

[0036] Optionally, the quantification of the brain features can be achieved by measuring the thickness of cerebral blood vessels using image analysis software, recording their direction as coordinates or angles, and calculating the curvature using geometric algorithms to quantify the morphology of cerebral blood vessels. Imaging technology and analysis software can be used to obtain blood flow, and blood flow velocity can be measured based on relevant tests to quantify blood perfusion. The blood perfusion condition can be determined by first defining the reference range of the vascular perfusion index for normal people. Then, the vascular perfusion index of migraine patients can be compared with the reference range. If the index is lower than the reference range, it may indicate insufficient blood perfusion; if it is higher than the reference range, it may mean excessive perfusion. At the same time, the actual blood perfusion situation can be comprehensively judged based on the patient's symptoms, attack frequency, etc.

[0037] The embodiments of the present invention utilize the quantitative biological data and the quantitative brain features to construct a neuropathological model for migraine patients, thereby exploring the potential mechanisms of how changes in biomarkers affect brain structure and function, thereby leading to migraine attacks and disease progression.

[0038] As an embodiment of the present invention, the use of the quantified biological data and the quantified brain features to construct the neuropathological model of the migraine patient includes: constructing a pathological analysis regression model for the migraine patient, using the quantified biological data as input data of the pathological analysis regression model, using the quantified brain features as output data of the pathological analysis regression model, using the input data and the output data to train the pathological analysis regression model to obtain a training model, evaluating the model accuracy of the training model, and constructing a linear function of the training model when the model accuracy meets a preset accuracy to obtain a neuropathological model for the migraine patient.

[0039] Among them, the pathological analysis regression model refers to a mathematical model constructed based on statistical principles, which aims to explore and quantify the relationship between independent variables (usually quantitative biological data in migraine-related situations, such as the content and concentration of various biomarkers) and dependent variables (here refers to quantitative brain characteristics, such as cerebral vascular morphology-related parameters, blood perfusion indicators, brain tissue density values, etc.), and then analyze and predict disease-related pathological changes.

[0040] Optionally, the pathology analysis regression model can be constructed by selecting an appropriate regression model type (e.g., linear regression, multivariate regression, etc.) based on migraine disease-related expertise and data analysis requirements, and by using statistical analysis software or programming tools to construct an initial pathology analysis regression model framework. Training the pathology analysis regression model using the input and output data can involve dividing the input and output data into a training set, a validation set, and a test set. Using an appropriate optimization algorithm (e.g., gradient descent), the model continuously adjusts internal parameters based on the training set data. The effectiveness of the adjustments is then evaluated using the validation set, and optimization is iterated multiple times until a predetermined number of training cycles or performance indicators are achieved. The accuracy of the trained model can be evaluated using accuracy evaluation metrics such as mean squared error (MSE) and coefficient of determination (CDR). Model accuracy meeting a predetermined accuracy requirement means that, when evaluated using MSE, the MSE is no greater than 0.2 (specific settings will depend on the actual application).

[0041] The state analysis module is configured to collect an electroencephalogram (EEG) of the migraine patient, identify brain activity characteristics of the migraine patient using the EEG, analyze the visual-spatial ability of the migraine patient using the brain activity characteristics, identify a blood oxygen level-dependent signal of the migraine patient using the EEG, perform a brain abnormality analysis on the migraine patient using the blood oxygen level-dependent signal, obtain a brain abnormality analysis result, and perform a risk assessment on the migraine patient based on the visual-spatial ability and the brain abnormality analysis result to determine the patient's migraine state.

[0042] The embodiment of the present invention can understand the potential changes caused by the electrical activity of neurons in the brain of migraine patients by collecting the electroencephalogram of the migraine patients, obtain a series of data signals of potential changes over time, and provide data support for subsequent analysis of brain characteristics, functions, and abnormalities.

[0043] Optionally, the EEG can be acquired using brain CT.

[0044] The embodiment of the present invention can mine valuable key information that can represent the essence of brain activity from the original EEG data by using the EEG to identify the brain activity characteristics of the migraine patient.

[0045] As an embodiment of the present invention, the use of the electroencephalogram to identify the brain activity characteristics of the migraine patient includes: constructing a spectrum graph corresponding to the electroencephalogram, analyzing the spectral characteristics, waveform morphology and topological distribution of the spectrum graph, analyzing the brain wave frequency, brain wave amplitude and brain wave waveform characteristics of the migraine patient based on the spectral characteristics, the waveform morphology and the topological distribution, and identifying the brain activity characteristics of the migraine patient based on the brain wave frequency, the brain wave amplitude and the brain wave waveform characteristics.

[0046] Among them, the spectral characteristics refer to the relevant characteristics of different frequency components presented on the EEG spectrum, such as the δ frequency band usually corresponds to 0.5-4Hz, the θ frequency band is 4-8Hz, the α frequency band is 8-13Hz, the β frequency band covers 13-30Hz, and the γ frequency band is above 30Hz. The waveform morphology refers to the specific shape characteristics of the brain waves in the EEG, including the sharpness of the peak, the depth of the trough, the width of the waveform, the overall smoothness, and the presence of special morphologies such as notches, spikes, and sharp waves. The topological distribution refers to the distribution pattern of the waveforms corresponding to each frequency band of the EEG in different areas of the brain (such as the frontal lobe, parietal lobe, temporal lobe, occipital lobe, and other different brain regions).

[0047] Optionally, the spectrogram can be generated by performing spectral analysis such as fast Fourier transform on the collected raw EEG signal, converting the time-domain signal into a frequency-domain signal to visually display the distribution of different frequency components. Analysis of the spectrogram's spectral characteristics, waveform morphology, and topological distribution can be performed on the generated spectrogram, observing spectral characteristics such as the energy distribution of different frequency bands (e.g., the δ, θ, α, β, and γ bands), examining morphological characteristics such as the overall shape and smoothness of the waveform, and the distribution of each frequency band in different brain regions, i.e., the topological distribution. Analysis of the EEG frequency, EEG amplitude, and EEG waveform characteristics of the migraine patient based on the spectral characteristics, waveform morphology, and topological distribution can be achieved by determining the dominant frequency range based on the distribution of each frequency band in the spectrogram, thereby determining the EEG frequency; measuring the EEG amplitude by the amplitude of the waveform on the vertical axis; and analyzing and summarizing the EEG waveform characteristics based on the overall waveform morphology and the waveforms corresponding to different frequency bands. The brain activity characteristics can be integrated with the obtained brain wave frequency, amplitude, and waveform characteristics, and compared with the corresponding standards of normal healthy people to determine whether the brain neuron activity is in an excited, inhibited or abnormal state, etc., thereby identifying the brain activity characteristics unique to migraine patients.

[0048] The embodiments of the present invention utilize the brain activity characteristics to analyze the visual-spatial ability of the migraine patient to understand the scope and extent of the impact of migraine on the patient's cognitive function, providing a basis for comprehensively evaluating the patient's condition, quality of life, and subsequent formulation of targeted intervention measures.

[0049] As an embodiment of the present invention, the use of the brain activity characteristics to analyze the visual-spatial ability of the migraine patient includes: determining a key brain area for visual-spatial ability, extracting activity characteristics of the key brain area corresponding to the brain activity characteristics to obtain a target feature, extracting a migraine-specific band from the target feature, constructing a normal population band library corresponding to the specific band, using the migraine-specific band and the normal population band to analyze changes in resting-state characteristics and task-state characteristics of the migraine patient, and determining the visual-spatial ability of the migraine patient based on the degree of transformation corresponding to the resting-state characteristic changes and the task-state characteristic changes.

[0050] Optionally, the key brain regions can be identified based on existing neuroscience research results and brain function maps, such as the parietal lobe and occipital lobe, which are closely related to visual-spatial abilities, and used as key areas of focus. The target features can filter out the activity feature information such as brain wave frequency, amplitude, waveform, etc. corresponding to the above-mentioned key brain regions from the overall brain activity feature data, and summarize them to form target features. The migraine-specific band can be obtained by performing frequency band analysis on the target feature data to find out the specific frequency band brain waves that are significantly different from the normal state in migraine patients and are closely related to visual-spatial abilities, as the migraine-specific band. The normal population band library can be formed by collecting a large number of normal population EEG data of the corresponding frequency bands of the same key brain regions, and organizing them into a normal population band library that can be used for comparison, covering the normal range, mean value and other characteristics of the bands of different individuals. Analyzing changes in resting-state and task-state characteristics of migraine patients using the migraine-specific waveband and the normal population waveband can be accomplished by comparing differences in frequency, amplitude, waveform, and other aspects between the migraine-specific waveband and the normal population waveband while the patient is in a resting state (without external task stimulation) and while performing a specific visual-spatial task, and observing corresponding characteristic changes. The visual-spatial ability of the migraine patient can be determined based on the amplitude and direction of characteristic changes in the two states, thereby comprehensively determining whether the migraine patient's visual-spatial ability is enhanced, weakened, or abnormal compared to the normal population.

[0051] Furthermore, embodiments of the present invention utilize the electroencephalogram (EEG) to identify the blood oxygen level-dependent signal of a migraine patient, thereby understanding the functional activation and metabolic changes in the patient's brain, providing a deeper understanding of the condition of local brain regions during or at the onset of a migraine. The blood oxygen level-dependent signal is a signal detected using functional magnetic resonance imaging (fMRI) technology that reflects changes in blood oxygen content in brain tissue.

[0052] Optionally, the blood oxygen level dependent signal can be identified using electroencephalogram (EEG) in migraine patients. This requires simultaneous data acquisition with fMRI, signal extraction and preprocessing, and identification through analysis of the correlation between EEG and fMRI blood oxygen level dependent signals using a specific algorithm.

[0053] The embodiment of the present invention utilizes the blood oxygen level dependent signal to perform brain abnormality analysis on the migraine patient. The obtained brain abnormality analysis results can help users clarify key information such as the possible lesion site, abnormality nature and severity in the brain, which plays a vital role in exploring the cause of migraine, formulating accurate treatment plans, and predicting the development trend of the disease.

[0054] In the embodiment of the present invention, a risk assessment is performed on the migraine patient based on the visual-spatial ability and the brain abnormality analysis results. The patient's migraine status can be obtained to systematically quantitatively or qualitatively assess the patient's future migraine attack frequency, severity, possible complication risks, and the possibility of further damage to life and cognitive functions, ultimately determining the patient's current migraine status (e.g., mild risk, moderate risk, high risk, etc.).

[0055] As one embodiment of the present invention, the risk assessment of the migraine patient based on the visual-spatial ability and the brain abnormality analysis results to obtain the patient's migraine status includes: constructing a comprehensive assessment index of the visual-spatial ability, identifying the number of abnormal brain regions in the migraine patient based on the brain abnormality analysis results, and calculating the conditional probability of the migraine patient's risk assessment corresponding to the risk assessment level based on the comprehensive assessment index and the number of abnormal brain regions using the following method:

[0056] in, represents conditional probability, A represents comprehensive evaluation index, B represents the number of abnormal brain regions, R represents risk assessment level, represents the probability value of the comprehensive evaluation index, It indicates the probability that the number of abnormal brain regions is B when the comprehensive evaluation index is A. It indicates the probability of r occurring when the comprehensive evaluation index is A and the number of abnormal brain regions is B. Indicates the first level in the risk assessment hierarchy. Indicates the second level in the risk assessment hierarchy, Indicates the nth level in the risk assessment hierarchy; Based on the conditional probability, a migraine state of the migraine patient is determined.

[0057] Optionally, constructing the comprehensive assessment index of visual-spatial ability can be achieved by constructing an assessment table using a Bayesian network for probabilistic assessment. Determining the migraine status of the migraine patient based on the conditional probability can include comparing the conditional probabilities of each risk assessment level, and determining the risk assessment level to which the patient belongs based on the probability, thereby defining the migraine status, such as low risk, medium risk, and high risk.

[0058] The auxiliary analysis module is used to construct an auxiliary plan for the migraine patient using the patient's migraine status, collect pathology-related data and life data of the migraine patient under the auxiliary plan, analyze the first auxiliary effect of the migraine patient using the pathology-related data and the neuro-pathology model, analyze the second auxiliary effect of the migraine patient using the life data, analyze the auxiliary improvement level of the migraine patient based on the first auxiliary effect and the second auxiliary effect, and construct a risk assessment-clinical auxiliary report for the migraine patient based on the auxiliary improvement level.

[0059] The embodiment of the present invention utilizes the patient's migraine state to construct an auxiliary program for the migraine patient, which can accurately provide assistance based on the patient's actual needs and disease characteristics, thereby improving the effectiveness of treatment.

[0060] As an embodiment of the present invention, constructing an auxiliary plan for the migraine patient using the patient's migraine state includes: stratifying the patient's migraine state by attack frequency to obtain stratified attack frequency, classifying the patient's migraine state by aura pain level to obtain graded aura pain, constructing an auxiliary framework for the migraine patient based on the stratified attack frequency and the graded aura pain, querying the migraine patient's physiological factors, optimizing the auxiliary framework based on the physiological factors to obtain an optimized auxiliary framework, performing auxiliary continuous monitoring on the migraine patient to obtain continuous detection data, and refining the optimized auxiliary framework based on the continuous detection data to obtain an auxiliary plan.

[0061] Optionally, stratified attack frequency can be determined by counting the number of migraine attacks per month or year and categorizing them according to established criteria, such as 1-3 attacks per month as low frequency, 4-6 attacks per month as medium frequency, and 7 or more attacks per month as high frequency. The stratified aura pain can be categorized into different levels, such as mild (no or mild aura, mild pain), moderate (some aura, moderate pain), and severe (clear and complex aura, severe pain), based on whether the patient experiences aura symptoms (such as visual or sensory auras) before the migraine attack and the severity of the pain during the attack (measured using a rating scale). The auxiliary framework can be used to preliminarily determine a general plan for medication treatment (e.g., medications to use during an attack, preventive medication selection), lifestyle adjustments (sleep, diet, and exercise recommendations), and other aspects based on different attack frequency stratifications and aura pain grading combinations, forming a basic auxiliary approach. Physiological factors can be obtained by collecting physiological information such as the patient's age, gender, comorbidities (such as hypertension and diabetes), and liver and kidney function. The optimization assistance framework can be combined with the physiological factors queried to adjust the previous assistance framework. For example, elderly patients can adjust drug dosages, and patients with other diseases can avoid using drugs that may affect each other. This makes the assistance framework more suitable for the individual patient's physical condition and forms an optimized solution framework. The assistance plan can be based on the implementation effect of the plan reflected by continuous monitoring data. For example, if the frequency of seizures does not decrease, the type of drug or dosage can be adjusted, and if the lifestyle does not improve, the specific requirements can be further refined. The assistance framework is continuously improved and optimized, and ultimately a specific and actionable assistance plan is formed.

[0062] The embodiment of the present invention can intuitively present the changes in the inherent physiological and pathological states of the disease from a medical professional perspective by collecting the pathological-related data and life data of migraine patients under the auxiliary scheme, and help determine whether the treatment measures have a positive impact on the root cause of migraine.

[0063] This can be achieved by continuously recording various data of the migraine patient under the auxiliary program.

[0064] The embodiment of the present invention utilizes the pathology-related data and the neuropathology model to analyze the auxiliary first effect of the migraine patient, and can quantitatively evaluate the effect of the auxiliary program in improving the patient's migraine condition from the perspective of disease-neuropathology, such as determining whether the disease-related abnormal brain activity is reduced, and whether some pathologically changed brain tissue is repaired, thereby obtaining an effect evaluation index based on the medical professional pathology level.

[0065] Optionally, the use of the pathology-related data and the neuro-pathology model to analyze the auxiliary first effect of the migraine patient can be achieved by comprehensively collecting and organizing the pathology-related data of the migraine patient after receiving the auxiliary program, such as biomarkers, brain images, etc.; then, the data is pre-processed and input into the neuro-pathology model to start the operation; finally, based on the output results of the model, the auxiliary first effect at the pathological level is interpreted to evaluate the effectiveness of the program.

[0066] The embodiment of the present invention can understand which changes in the patient's daily life are beneficial to controlling migraine by analyzing the auxiliary second effect of the migraine patient using the life data.

[0067] As one embodiment of the present invention, analyzing the auxiliary second effect of the migraine patient using the life data includes: identifying the number of lifestyle factors of the migraine patient using the life data, numerically quantifying the lifestyle factors to obtain quantified factor values, and calculating the auxiliary improvement score of the migraine patient based on the quantified factor values ​​using the following formula:

[0068] in, represents the auxiliary improvement score, p represents the number of lifestyle factors, represents the quantitative value of the k-th lifestyle factor, represents the average value of all quantitative values ​​of lifestyle factors, A quantitative indicator of migraine attacks, represents the average value of migraine attack index, represents the weight matrix of the association between lifestyle factors and migraine attacks; An auxiliary secondary effect for the migraine patient is determined based on the auxiliary improvement score.

[0069] Optionally, the auxiliary second effect of the migraine patient determined based on the auxiliary improvement score can be determined according to a specific score of the auxiliary improvement score, such as 1-2 points for poor, 2-4 for ordinary, 4-7 for medium, and 7-9 for excellent.

[0070] Furthermore, the embodiment of the present invention can determine the auxiliary improvement level of the migraine patient by comprehensively analyzing the auxiliary first effect and the auxiliary second effect through analyzing the auxiliary improvement level of the migraine patient based on the auxiliary first effect and the auxiliary second effect, and can grasp the changes of the patient in multiple dimensions as a whole, and more accurately know the degree to which the auxiliary program helps the patient, and provide a comprehensive and reliable reference basis for subsequent decision-making (such as whether to continue to use the current program, whether to make local adjustments to the program, etc.), to ensure that the treatment and intervention of the patient is always carried out in a direction that is conducive to improvement of the condition.

[0071] Optionally, the analysis of the auxiliary improvement level of the migraine patient based on the auxiliary first effect and the auxiliary second effect can first be based on the auxiliary first effect of the migraine patient (derived based on analysis of pathological-related data and neuropathological model) and the auxiliary second effect (corresponding to relevant evaluation indicators, etc.), and the two can be comprehensively considered to compare the changes in the patient's pathology, symptoms, etc. before and after the implementation of the auxiliary program, so as to analyze the auxiliary improvement level and judge the effectiveness of the program in improving the overall condition of migraine patients.

[0072] By constructing a risk assessment-clinical assistance report for a migraine patient based on the assistance improvement level, embodiments of the present invention can produce a detailed risk assessment-clinical assistance report. The report covers the patient's current migraine condition, improvement after implementation of the assistance program, predicted risk of future attacks (e.g., classification into low-risk, medium-risk, and high-risk levels, with explanation of the corresponding basis), and specific recommendations for follow-up treatment and lifestyle adjustments. Furthermore, for physicians, this report serves as a valuable reference for summarizing the treatment process, analyzing treatment effects, and formulating further treatment plans. This helps physicians make informed clinical decisions based on comprehensive and intuitive information. For patients, the report provides a clear understanding of their condition, treatment effectiveness, and subsequent precautions, enhancing their understanding and management of their disease.

[0073] Optionally, the risk assessment-clinical auxiliary report can be obtained by collating the data records generated by the entire analysis auxiliary process using a script generated by Java.

[0074] like Figure 2 FIG. 1 is a flow chart of a method for risk assessment and clinical decision support for migraine patients according to an embodiment of the present invention. In this embodiment, the method for risk assessment and clinical decision support for migraine patients includes: querying biomarker detection data of a migraine patient, quantifying the biomarker detection data to obtain quantified biological data, acquiring a brain scan image of the migraine patient, and identifying a brain vascular region of the migraine patient using the brain scan image; Analyzing the morphology and blood perfusion of the cerebral blood vessels of the migraine patient using the brain vascular regions to obtain brain features of the migraine patient, quantifying the brain features to obtain quantified brain features, and constructing a neuropathological model of the migraine patient using the quantified biological data and the quantified brain features; collecting an electroencephalogram (EEG) of the migraine patient, identifying brain activity characteristics of the migraine patient using the EEG, analyzing the visual-spatial ability of the migraine patient using the brain activity characteristics, identifying a blood oxygen level-dependent signal of the migraine patient using the EEG, performing a brain abnormality analysis on the migraine patient using the blood oxygen level-dependent signal, obtaining a brain abnormality analysis result, and performing a risk assessment on the migraine patient based on the visual-spatial ability and the brain abnormality analysis result to determine the patient's migraine status; Using the patient's migraine status, an auxiliary plan for the migraine patient is constructed, and pathology-related data and life data of the migraine patient under the auxiliary plan are collected. Using the pathology-related data and the neuro-pathology model, the first auxiliary effect of the migraine patient is analyzed. Using the life data, the second auxiliary effect of the migraine patient is analyzed. Based on the first auxiliary effect and the second auxiliary effect, the auxiliary improvement level of the migraine patient is analyzed. Based on the auxiliary improvement level, a risk assessment-clinical auxiliary report for the migraine patient is constructed.

[0075] In the several embodiments provided by the present invention, it should be understood that the provided systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and actual implementation may employ other division methods.

[0076] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A migraine patient risk assessment and clinical decision support system, characterized in that: The system for risk assessment and clinical decision support for migraine patients includes: a brain region identification module, a model building module, a state analysis module, and an auxiliary analysis module; The brain region identification module is configured to query biomarker detection data of a migraine patient, quantify the biomarker detection data to obtain quantified biological data, collect a brain scan image of the migraine patient, and identify the brain vascular region of the migraine patient using the brain scan image; The model building module is configured to analyze the morphology and blood perfusion of the cerebral blood vessels of the migraine patient using the cerebral vascular regions to obtain brain features of the migraine patient, quantify the brain features to obtain quantified brain features, and construct a neuropathological model of the migraine patient using the quantified biological data and the quantified brain features; The state analysis module is configured to collect an electroencephalogram (EEG) of the migraine patient, identify brain activity characteristics of the migraine patient using the EEG, analyze the visual-spatial ability of the migraine patient using the brain activity characteristics, identify a blood oxygen level-dependent signal of the migraine patient using the EEG, perform a brain abnormality analysis on the migraine patient using the blood oxygen level-dependent signal, obtain a brain abnormality analysis result, and perform a risk assessment on the migraine patient based on the visual-spatial ability and the brain abnormality analysis result to determine the patient's migraine state; The auxiliary analysis module is used to construct an auxiliary plan for the migraine patient using the patient's migraine status, collect pathology-related data and life data of the migraine patient under the auxiliary plan, analyze the first auxiliary effect of the migraine patient using the pathology-related data and the neuro-pathology model, analyze the second auxiliary effect of the migraine patient using the life data, analyze the auxiliary improvement level of the migraine patient based on the first auxiliary effect and the second auxiliary effect, and construct a risk assessment-clinical auxiliary report for the migraine patient based on the auxiliary improvement level.

2. The migraine patient risk assessment and clinical decision support system according to claim 1, wherein: The method of analyzing the cerebral vascular morphology and blood perfusion of the migraine patient using the brain vascular region to obtain brain characteristics of the migraine patient includes: constructing a brain vascular network of the migraine patient based on the brain vascular region; Analyzing the vascular orientation and tortuosity of the cerebral blood vessels of the migraine patient using the cerebral vascular network; determining the morphology of the cerebral blood vessels of the migraine patient based on the direction of the blood vessels and the tortuosity of the blood vessels; Calculating blood vessel pixels in the brain blood vessel area; identifying the blood perfusion status of the migraine patient according to the blood vessel pixels; The brain characteristics of the migraine patient are determined based on the cerebral vascular morphology and the blood perfusion condition.

3. The migraine patient risk assessment and clinical decision support system according to claim 2, wherein: The identifying the blood perfusion condition of the migraine patient based on the blood vessel pixels includes: calculating the peripheral area of ​​the blood vessels of the migraine patient using the blood vessel pixels; calculating the area of ​​the brain region of the migraine patient based on the blood vessel pixels; calculating a vascular perfusion index of the migraine patient based on the blood vessel perimeter area and the regional area; The blood perfusion condition of the migraine patient is analyzed based on the vascular perfusion index.

4. The migraine patient risk assessment and clinical decision support system according to claim 1, wherein: The method of constructing a neuropathological model of the migraine patient using the quantitative biological data and the quantitative brain features comprises: Constructing a pathological analysis regression model for the migraine patients; using the quantified biological data as input data for the pathology analysis regression model; using the quantified brain features as output data of the pathology analysis regression model; Using the input data and the output data, the pathology analysis regression model is trained to obtain a training model; evaluating the model accuracy of the trained model; When the model accuracy meets the preset accuracy, a linear function of the training model is constructed to obtain a neuropathological model of the migraine patient.

5. The migraine patient risk assessment and clinical decision support system according to claim 1, wherein: The identifying brain activity characteristics of the migraine patient using the electroencephalogram includes: Constructing a spectrum graph corresponding to the electroencephalogram; Analyzing the spectrum characteristics, waveform shape and topological distribution of the spectrum graph; Analyzing the EEG frequency, EEG amplitude, and EEG waveform characteristics of the migraine patient based on the spectral characteristics, the waveform morphology, and the topological distribution; Based on the brain wave frequency, the brain wave amplitude and the brain wave waveform characteristics, the brain activity characteristics of the migraine patient are identified.

6. The migraine patient risk assessment and clinical decision support system according to claim 1, wherein: The analyzing the visual-spatial ability of the migraine patient using the brain activity characteristics includes: Identify key brain regions for visual-spatial abilities; Extracting the activity features of the key brain regions corresponding to the brain activity features to obtain target features; extracting a migraine-specific band from the target feature; Constructing a normal population band library corresponding to the specific band; Utilizing the migraine-specific waveband and the normal population waveband, analyzing the changes in resting-state characteristics and task-state characteristics of the migraine patient; The visual-spatial ability of the migraine patient is determined based on the degree of change corresponding to the resting-state feature change and the task-state feature change.

7. The migraine patient risk assessment and clinical decision support system according to claim 1, wherein: The risk assessment of the migraine patient based on the visual-spatial ability and the brain abnormality analysis results to obtain the patient's migraine status includes: Constructing a comprehensive assessment index of the visual-spatial ability; identifying the number of abnormal brain regions in the migraine patient based on the brain abnormality analysis results; Calculating the conditional probability of the risk assessment level corresponding to the risk assessment of the migraine patient based on the comprehensive assessment index and the number of abnormal brain regions; Based on the conditional probability, a migraine state of the migraine patient is determined.

8. The migraine patient risk assessment and clinical decision support system according to claim 1, wherein: The method of utilizing the patient's migraine condition to construct an auxiliary program for the migraine patient includes: stratifying the attack frequency of the patient's migraine state to obtain the stratified attack frequency; Classifying the aura pain level of the patient's migraine state to obtain graded aura pain; constructing an auxiliary framework for the migraine patient based on the stratified attack frequency and the graded aura pain; inquiring about physiological factors of the migraine patient; Based on the physiological factors, the auxiliary framework is optimized to obtain an optimized auxiliary framework; Performing auxiliary continuous monitoring on the migraine patient to obtain continuous detection data; Based on the continuous detection data, the optimization auxiliary framework is refined to obtain an auxiliary solution.

9. The migraine patient risk assessment and clinical decision support system according to claim 1, wherein: The analyzing the auxiliary second effect of the migraine patient using the life data includes: identifying a number of lifestyle factors of the migraine patient using the life data; Numerically quantifying the lifestyle factors to obtain quantitative factor values; calculating an auxiliary improvement score for the migraine patient based on the quantitative factor value; An auxiliary secondary effect for the migraine patient is determined based on the auxiliary improvement score.

10. A method for risk assessment and clinical decision support for migraine patients, characterized in that: The method comprises: querying biomarker detection data of a migraine patient, quantifying the biomarker detection data to obtain quantified biological data, acquiring a brain scan image of the migraine patient, and identifying a brain vascular region of the migraine patient using the brain scan image; Analyzing the morphology and blood perfusion of the cerebral blood vessels of the migraine patient using the brain vascular regions to obtain brain features of the migraine patient, quantifying the brain features to obtain quantified brain features, and constructing a neuropathological model of the migraine patient using the quantified biological data and the quantified brain features; collecting an electroencephalogram (EEG) of the migraine patient, identifying brain activity characteristics of the migraine patient using the EEG, analyzing the visual-spatial ability of the migraine patient using the brain activity characteristics, identifying a blood oxygen level-dependent signal of the migraine patient using the EEG, performing a brain abnormality analysis on the migraine patient using the blood oxygen level-dependent signal, obtaining a brain abnormality analysis result, and performing a risk assessment on the migraine patient based on the visual-spatial ability and the brain abnormality analysis result to determine the patient's migraine status; Using the patient's migraine status, an auxiliary plan for the migraine patient is constructed, and pathology-related data and life data of the migraine patient under the auxiliary plan are collected. Using the pathology-related data and the neuro-pathology model, the first auxiliary effect of the migraine patient is analyzed. Using the life data, the second auxiliary effect of the migraine patient is analyzed. Based on the first auxiliary effect and the second auxiliary effect, the auxiliary improvement level of the migraine patient is analyzed. Based on the auxiliary improvement level, a risk assessment-clinical auxiliary report for the migraine patient is constructed.

Images