Big data model-based epilepsy auxiliary diagnosis and treatment system

Abstract

The invention discloses an epilepsy auxiliary diagnosis and treatment system based on a big data model, and relates to the field of epilepsy auxiliary diagnosis and treatment, the epilepsy auxiliary diagnosis and treatment system comprises a management center, the management center is in communication connection with a data acquisition module, a data analysis module, a model construction module and an auxiliary diagnosis and treatment module; the data acquisition module acquires clinical information, personal medical history information and a patient medical atlas of a patient; the data analysis module analyzes the clinical information to obtain epilepsy incidence data, epilepsy source data and epilepsy analysis data; the model construction module constructs a patient disease data model according to the epilepsy analysis data and the personal medical history information, processes the patient disease data model through the personal medical history information, and obtains a patient epilepsy research model, an abnormal active value and a disease prompt value; the auxiliary diagnosis and treatment module obtains an auxiliary coefficient and an auxiliary diagnosis and treatment scheme according to the patient epilepsy research model, the abnormal active value and the disease prompt value; the treatment effect and the medical resource utilization efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of epilepsy assisted diagnosis and treatment, and specifically to an epilepsy assisted diagnosis and treatment system based on a big data model. Background Art

[0002] Epilepsy is a chronic neurological disease caused by abnormal electrical discharges of brain neurons, manifested as repeated and sudden motor, sensory, consciousness or behavioral disorders. It is one of the most common neurological diseases worldwide; In recent years, with the rapid development of technologies such as big data, artificial intelligence (AI), cloud computing, and the Internet of Things (IoT), along with the accumulation of medical data and the development of computing technologies, using big data analysis to assist in diagnosis and treatment has become a trend. By collecting patients' physiological data and using big data analysis techniques, it can help improve the diagnostic accuracy, optimize treatment plans, and predict the development trend of diseases; In the prior art, epilepsy lesions are usually small, and it is not easy to accurately mark the lesion locations, which affects the diagnosis and treatment effects; there are different degrees of differences in the prevalence of various patient groups, and it is difficult to conduct targeted analysis of the diagnosis and treatment of patient groups; these are the problems we need to solve. For this reason, an epilepsy assisted diagnosis and treatment system based on a big data model is provided herein. Summary of the Invention

[0003] In order to solve the above technical problems, the purpose of the present invention is to provide an epilepsy assisted diagnosis and treatment system based on a big data model, including a management center, which is communicatively connected to a data acquisition module, a data analysis module, a model construction module, and an assisted diagnosis and treatment module; The data acquisition module is used to obtain the clinical information and personal medical history information of patients, and obtain the patient's medical treatment map based on the clinical information and personal medical history information; The data analysis module is used to analyze the clinical information to obtain epilepsy attack data and epilepsy source data, and obtain epilepsy analysis data based on the epilepsy attack data and epilepsy source data; The model construction module is used to construct a patient disease data model based on the epilepsy analysis data and personal medical history information, process the patient disease data model through the personal medical history information to obtain a patient epilepsy research model, and obtain an abnormal activity value and a disease prompt value based on the patient epilepsy research model; The assisted diagnosis and treatment module is used to obtain an assistance coefficient and an assisted diagnosis and treatment plan based on the patient epilepsy research model, abnormal activity value, and disease prompt value, and perform epilepsy assisted diagnosis and treatment on the patient through the assisted diagnosis and treatment plan and the assistance coefficient.

[0004] Further, the process of obtaining the clinical information and personal medical history information of patients and obtaining the patient's medical treatment map based on the clinical information and personal medical history information includes: The clinical information refers to the brain examination record information of the patient, including electroencephalogram waveforms, brain images, and recording time; The personal medical history information refers to the patient's historical illness course and current physical condition, including historical medical history, current medical history, and genetic history. The historical medical history includes the historical time of the medical history, other historical diseases, historical treatment plans, and historical medication plans; the current medical history refers to the latest seizure situation of epilepsy, the current seizure time, and patient information; Based on the historical time of the personal medical history information and the current seizure time, generate seizure nodes and seizure labels; based on the seizure nodes, clinical information, and personal medical history information, generate medical history nodes and examination nodes; based on the seizure nodes, medical history nodes, and examination nodes, generate the patient's medical treatment graph.

[0005] Further, the process of analyzing the clinical information to obtain epilepsy seizure data includes: Conduct an analysis of the disease characteristics of the clinical information. The analysis of the disease characteristics refers to analyzing the epilepsy-related seizure information for the electroencephalogram waveforms and brain images respectively; set a seizure window, and based on the electroencephalogram waveforms of the clinical information, obtain the normal waveform characteristics; based on each normal waveform characteristic, seizure window, and electroencephalogram waveforms, set the number of normal waveform characteristics; based on the number of normal waveform characteristics, obtain the normal electroencephalogram picture segments, and based on the electroencephalogram waveforms and normal electroencephalogram picture segments, obtain the abnormal electroencephalogram picture segments; based on each abnormal electroencephalogram picture segment, obtain the abnormal time period characteristics; based on the abnormal electroencephalogram picture segments and the corresponding abnormal time period characteristics, obtain the epilepsy seizure data.

[0006] Further, the process of analyzing the clinical information to obtain epilepsy source data and obtaining epilepsy analysis data based on the epilepsy seizure data and epilepsy source data includes: Based on the brain images of the clinical information, obtain the single epilepsy lesion area and the single area range, set the lesion association range, based on the lesion association range, obtain the epilepsy lesion group area, and obtain the area range of the epilepsy lesion group area, denoted as the group area range. Based on the recording time of each single epilepsy lesion area within the epilepsy lesion group area, obtain the recording time period of each single epilepsy lesion area. Based on the single area range and recording time period of each single epilepsy lesion area, obtain the recording axis time period of the epilepsy lesion group area. Statistically calculate the total number of single epilepsy lesion areas within the epilepsy lesion group area, denoted as the epilepsy group quantity, and based on the recording axis time period and epilepsy group quantity of the epilepsy lesion group area, obtain the epilepsy source data; Based on the epilepsy seizure data and epilepsy source data, obtain the epilepsy analysis data; Analyze the abnormal time period characteristics of epilepsy attack data and the recording axis time period of epileptic source data. When the time period corresponding to the abnormal time period characteristics completely belongs to the recording axis time period, obtain the attack correlation relationship; according to the attack correlation relationship, epilepsy attack data, and epileptic source data, obtain epilepsy analysis data.

[0007] Furthermore, the process of constructing a patient disease data model based on epilepsy analysis data and personal medical history information and processing the patient disease data model through personal medical history information to obtain a patient epilepsy research model includes: Establish a brain physical model based on the brain image corresponding to the personal medical history information, establish a brain analysis model based on the epilepsy analysis data corresponding to the personal medical history information, and obtain a patient disease data sub-model according to the personal medical history information, brain analysis model, and brain physical model corresponding to the brain analysis model. Obtain the patient disease data model according to each patient disease data sub-model; Obtain a patient center model and a patient sample model according to the personal medical history information of the diagnosed patient, and obtain a patient epilepsy research model according to the patient center model and the patient sample model.

[0008] Furthermore, the process of obtaining the abnormal activity value based on the patient epilepsy research model includes: Analyze the patient center model of the patient epilepsy research model to obtain the abnormal activity value and the disease prompt value; According to the epilepsy analysis data and attack correlation relationship of the patient center model, obtain the epilepsy attack data and epileptic source data with an attack correlation relationship, count the number of epilepsy attack data with an attack correlation relationship with the epileptic source data to obtain the epilepsy correlation quantity; obtain the abnormal sub-fragment according to the attack window and the abnormal EEG picture segment, and obtain the abnormal sub-time period according to the abnormal sub-fragment; compare the abnormal sub-time period with each recording time period of the recording axis time period. When the abnormal sub-time period belongs to the recording time period of the recording axis time period, respectively obtain the time span corresponding to the abnormal sub-time period and the recording time period, and obtain the abnormal activity degree according to the time span corresponding to the abnormal sub-time period and the recording time period. Count the number of abnormal sub-time periods belonging to the recording time period to obtain the activity coefficient, and obtain the abnormal activity value YH of the epileptic focus group area according to the single area range, abnormal activity degree, activity coefficient, and group area range;

[0009] Among them, refers to the abnormal activity degree corresponding to each recording time period, refers to the activity coefficient corresponding to each recording time period, refers to the single area range corresponding to each recording time period, refers to the group area range, Refers to the total number of single regions of epileptic foci within the epileptic focus group regions.

[0010] Further, according to the patient's epilepsy research model, the process of obtaining the disease indication value includes: Obtain the connection distances between the epileptic focus group regions, denoted as the group influence coefficient. Based on the group influence coefficient and the abnormal activity value, obtain the patient's disease indication value TB;

[0011] Among them, Refers to the group influence coefficient of each epileptic focus group region, Refers to the abnormal activity value of each epileptic focus group region, Refers to the total number of epileptic focus group regions.

[0012] Further, according to the patient's epilepsy research model, the abnormal activity value, and the disease indication value, obtain the auxiliary coefficient and the auxiliary diagnosis and treatment plan. The process of performing epilepsy auxiliary diagnosis and treatment on the patient through the auxiliary diagnosis and treatment plan and the auxiliary coefficient includes: Based on the abnormal activity value and the disease indication value, obtain the auxiliary coefficient ω;

[0013] Among them, Refers to the maximum value among the abnormal activity values of each epileptic focus group region, Refers to the minimum value among the abnormal activity values of each epileptic focus group region; Based on the patient sample model and the patient center model of the patient's epilepsy research model, obtain the sample status value and the patient status value. Based on the sample status value and the patient status value, obtain the guiding coefficient; When the guiding coefficient of the patient sample model is greater than or equal to the auxiliary coefficient, extract the corresponding patient sample model, and summarize the historical treatment plan and the historical medication plan of the extracted patient sample model to obtain the auxiliary diagnosis and treatment plan, and perform epilepsy auxiliary diagnosis and treatment on the patient through the auxiliary diagnosis and treatment plan and the auxiliary coefficient.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: Through the patient medical treatment map, historical epilepsy medical history management is carried out, which is conducive to providing data reference for the subsequent auxiliary diagnosis and treatment of patients; Through epilepsy attack data and epilepsy source data, the diagnosis accuracy and precision of epilepsy-related conditions are improved, and misdiagnosis and missed diagnosis are reduced; According to epilepsy attack data and epilepsy source data, epilepsy analysis data is obtained, and through the epilepsy analysis data, various data of the patient are integrated to help doctors track the development of the condition and improve the condition monitoring level; Through the patient epilepsy research model, it is beneficial to further accurately analyze the epilepsy condition of the patient, and through the abnormal activity value and disease prompt value, the abnormal conditions of the patient's brain are judged in real time, improving the auxiliary diagnosis and treatment efficiency of epilepsy patients; Through the auxiliary coefficient and the auxiliary diagnosis and treatment plan, it helps doctors make more accurate and efficient treatment decisions in complex situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 FIG. is a schematic structural diagram of an epilepsy auxiliary diagnosis and treatment system based on a big data model according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] As Figure 1 shown, an epilepsy auxiliary diagnosis and treatment system based on a big data model includes a management center, and the management center is communicatively connected to a data acquisition module, a data analysis module, a model construction module, and an auxiliary diagnosis and treatment module; The data acquisition module is used to obtain the clinical information and personal medical history information of the patient, and according to the clinical information and personal medical history information, obtain the patient medical treatment map; The data analysis module is used to analyze the clinical information to obtain epilepsy attack data and epilepsy source data, and according to the epilepsy attack data and epilepsy source data, obtain epilepsy analysis data; The model construction module is used to construct a patient disease data model according to the epilepsy analysis data and personal medical history information, process the patient disease data model through the personal medical history information, obtain a patient epilepsy research model, and according to the patient epilepsy research model, obtain an abnormal activity value and a disease prompt value; The auxiliary diagnosis and treatment module is used to obtain an auxiliary coefficient and an auxiliary diagnosis and treatment plan according to the patient epilepsy research model, the abnormal activity value, and the disease prompt value, and perform epilepsy auxiliary diagnosis and treatment on the patient through the auxiliary diagnosis and treatment plan and the auxiliary coefficient.

[0017] It should be further noted that in the specific implementation process, the process of obtaining the clinical information and personal medical history information of the patient and obtaining the patient medical treatment map according to the clinical information and personal medical history information is as follows: The clinical information refers to the brain examination record information of the patient, including electroencephalogram waveforms, brain images, and recording time. The electroencephalogram waveforms refer to the waveform information of brain waves, which are recorded by EEG; the brain images refer to the images of various regions of the brain, which are recorded by PET-MRI; The personal medical history information refers to the patient's historical disease history and current physical condition, including historical medical history, current medical history, and genetic history. The historical medical history includes the historical time of the medical history, other historical diseases, historical treatment plans, and historical medication plans; the current medical history refers to the latest seizure situation of epilepsy, the current seizure time, and patient information; the patient information includes name, gender, age, etc.; the current physical condition includes eating habits, exercise conditions, sleep conditions, etc.; Based on the historical time of the personal medical history information and the current seizure time, a disease onset node and a disease onset label are generated. The disease onset label represents the historical time of the patient's medical history and the current seizure time, and the disease onset label is marked within the disease onset node. The disease onset nodes are connected unidirectionally. The unidirectional connection means connecting the disease onset nodes in chronological order, marking the direction, and reflecting the patient's disease history; based on the disease onset nodes, clinical information, and personal medical history information, a medical history node and a disease examination node are generated. Through the disease onset node, the personal medical history information corresponding to the disease onset node is marked into the medical history node. Through the disease onset node and the recording time, the clinical information with the same recording time as the disease onset node is marked into the disease examination node. Through the disease onset node, medical history node, and disease examination node, and connecting the medical history node and disease examination node with the corresponding disease onset node, a patient medical treatment graph is generated.

[0018] It should be further noted that in the specific implementation process, the data analysis module is used to analyze the clinical information to obtain epilepsy onset data and epilepsy source data. The process of obtaining epilepsy analysis data based on the epilepsy onset data and epilepsy source data is as follows: Perform disease characteristics analysis on the clinical information. The disease characteristics analysis refers to analyzing the epilepsy-related onset information of the electroencephalogram waveforms and brain images respectively; It should be further noted that in the specific implementation process, the specific process of analyzing the disease characteristics of clinical information includes: setting a disease onset window, performing deep learning on the electroencephalogram waveform diagram of clinical information to obtain normal waveform characteristics; inputting each normal waveform characteristic into the disease onset window, and analyzing the electroencephalogram waveform diagram through the obtained disease onset window, setting the number of normal waveform characteristics, where the number of normal waveform characteristics refers to the number of specified continuous normal waveform characteristics; obtaining normal electroencephalogram picture segments through the number of normal waveform characteristics, screening the normal electroencephalogram picture segments in the electroencephalogram waveform diagram to obtain abnormal electroencephalogram picture segments; continuously identifying the time in each abnormal electroencephalogram picture segment to obtain abnormal period characteristics; recording the abnormal electroencephalogram picture segments and the corresponding abnormal period characteristics as epilepsy onset data; Performing deep learning on the brain image of clinical information through 3D U-Net technology to extract a single epileptic focus region and the single region range, setting the lesion association range, where the lesion association range includes the lesion spatial range and the lesion time range. Through the lesion time range, each single epileptic focus region within the lesion time range is boxed, and then through the lesion spatial range, the range of each boxed single epileptic focus region is boxed, recorded as the epileptic focus group region, and the regional range of the epileptic focus group region is obtained, recorded as the group region range. Through the recording time of each single epileptic focus region in the epileptic focus group region, the recording time period of each single epileptic focus region is obtained, associating the single region range of each single epileptic focus region with the corresponding recording time period, and performing a summary record to obtain the recorded axis time period of the epileptic focus group region. Counting the total number of single epileptic focus regions in the epileptic focus group region, recorded as the epilepsy group quantity, and marking the recorded axis time period and the epilepsy group quantity of the epileptic focus group region to the epileptic focus group region to obtain epilepsy source data; Obtaining epilepsy analysis data based on the epilepsy onset data and the epilepsy source data; It should be further noted that in the specific implementation process, the specific process of obtaining epilepsy analysis data based on the epilepsy onset data and the epilepsy source data is as follows: analyzing the epilepsy source data through the abnormal period characteristics of the epilepsy onset data, comparing the abnormal period characteristics with the recorded axis time period. When the time period corresponding to the abnormal period characteristics completely belongs to the recorded axis time period, associating the abnormal period characteristics with the recorded axis time period to obtain an onset association relationship. When the time period corresponding to the abnormal period characteristics does not completely belong to the recorded axis time period, the abnormal period characteristics and the recorded axis time period are not associated; recording the onset association relationship, the epilepsy onset data, and the epilepsy source data as epilepsy analysis data.

[0019] It should be further noted that in the specific implementation process, the process of constructing a patient disease data model based on epilepsy analysis data and personal medical history information, processing the patient disease data model through personal medical history information to obtain a patient epilepsy research model, and obtaining an abnormal activity value and a disease prompt value based on the patient epilepsy research model is as follows: Establish a brain physical model through the brain images corresponding to the personal medical history information, establish a brain analysis model through the epilepsy analysis data corresponding to the personal medical history information, input the personal medical history information corresponding to the brain analysis model into the brain analysis model, combine the brain physical model and the brain analysis model to obtain a patient disease data sub-model, and combine each patient disease data sub-model to obtain a patient disease data model; Through the personal medical history information of the diagnosed patient, record the corresponding patient disease data sub-model as the patient center model, record the remaining patient disease data sub-models as the patient sample model, and obtain the patient epilepsy research model based on the patient center model and the patient sample model; Analyze the patient center model of the patient epilepsy research model to obtain an abnormal activity value and a disease prompt value; It should be further noted that in the specific implementation process, the specific process of analyzing the patient center model is as follows: Analyze the epilepsy analysis data in the patient center model, obtain the epileptic seizure data and epileptic focus data with seizure correlation relationships through the seizure correlation relationship, count the number of epileptic seizure data with seizure correlation relationships with the epileptic focus data, and record it as the epilepsy correlation quantity; Identify the normal waveform characteristics of the electroencephalogram abnormal picture segments through the seizure window, screen out the sub-segments corresponding to the continuous abnormal waveform characteristics, and record them as abnormal sub-segments. Obtain the time period corresponding to the abnormal sub-segment characteristics of the abnormal sub-segments, and record it as the abnormal sub-time period; Compare the abnormal sub-time period with each recording time period of the recording axis period. When the abnormal sub-time period belongs to the recording time period of the recording axis period, respectively obtain the time span corresponding to the abnormal sub-time period and the recording time period, and perform a ratio calculation to obtain the abnormal activity degree. Count the number of abnormal sub-time periods belonging to the recording time period, and record it as the activity coefficient. Based on the single-region range, abnormal activity degree, activity coefficient, and group-region range, obtain the abnormal activity value YH of the epileptic focus group region;

[0020] Among them, refers to the abnormal activity degree corresponding to each recording time period, refers to the activity coefficient corresponding to each recording time period, refers to the single-region range corresponding to each recording time period, refers to the group-region range, refers to the total number of epileptic focus single regions within the epileptic focus group region; Obtain the connection distances between the regions of each epilepsy focus group, denoted as the group influence coefficient, and based on the group influence coefficient and the abnormal activity value, obtain the disease indication value TB of the patient;

[0021] Among them, refers to the group influence coefficient of the regions of each epilepsy focus group, refers to the abnormal activity value of the regions of each epilepsy focus group, refers to the total number of epilepsy focus group regions.

[0022] It should be further noted that in the specific implementation process, the process of obtaining the auxiliary coefficient and the auxiliary diagnosis and treatment plan according to the patient's epilepsy research model, the abnormal activity value, and the disease indication value, and performing epilepsy auxiliary diagnosis and treatment on the patient through the auxiliary diagnosis and treatment plan and the auxiliary coefficient is as follows: Obtain the auxiliary coefficient ω according to the abnormal activity value and the disease indication value;

[0023] Among them, refers to the maximum value among the abnormal activity values of the regions of each epilepsy focus group, refers to the minimum value among the abnormal activity values of the regions of each epilepsy focus group; Through deep learning, compare and analyze the patient sample model and the patient center model of the patient's epilepsy research model, screen out the patient sample models that are consistent with the patient information and genetic history of the patient center model, extract the latest epilepsy attack situation of the obtained patient sample models, and compare it with the latest epilepsy attack situation of the patient center model. Respectively extract the physical health status values corresponding to the latest epilepsy attack situations of the patient sample model and the patient center model, denoted as the sample status value and the patient status value, and perform a ratio calculation on the result of the difference calculation between the sample status value and the patient status value and the sample status value to obtain the guiding coefficient; Through the auxiliary coefficient and the guiding coefficient, screen the patient sample models. When the guiding coefficient of the patient sample model is greater than or equal to the auxiliary coefficient, extract the corresponding patient sample models, and summarize the historical treatment plans and historical medication plans of the extracted patient sample models for medical staff to refer to.

[0024] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An epilepsy auxiliary diagnosis and treatment system based on a big data model, comprising a management center, characterized in that: The management center is communicatively connected to a data acquisition module, a data analysis module, a model building module and an auxiliary diagnosis and treatment module; The data acquisition module is used to obtain the patient's clinical information and personal medical history information, and obtain the patient's medical map based on the clinical information and personal medical history information; The data analysis module is used to analyze clinical information, obtain epilepsy onset data and epilepsy source data, and obtain epilepsy analysis data based on the epilepsy onset data and epilepsy source data; The model building module is used to build a patient disease data model based on epilepsy analysis data and personal medical history information, process the patient disease data model through personal medical history information to obtain a patient epilepsy research model, and obtain an abnormal activity value and a disease indication value based on the patient epilepsy research model; The auxiliary diagnosis and treatment module is used to obtain auxiliary coefficients and auxiliary diagnosis and treatment plans according to the patient's epilepsy research model, abnormal activity value and disease indication value, and perform auxiliary diagnosis and treatment of epilepsy on the patient through the auxiliary diagnosis and treatment plan and auxiliary coefficients.

2. The epilepsy auxiliary diagnosis and treatment system based on big data model according to claim 1 is characterized in that: The process of obtaining the patient's clinical information and personal medical history information and obtaining the patient's medical map based on the clinical information and personal medical history information includes: The clinical information refers to the patient's brain examination record information, including EEG waveforms, brain images and recording time; The personal medical history information refers to the patient's historical medical history and current physical condition, including historical medical history, current medical history, and genetic history. The historical medical history includes the historical time of medical history, other historical diseases, historical treatment plans, and historical medication plans; the current medical history refers to the latest epileptic seizure, current seizure time, and patient information; Generate onset nodes and onset labels based on the historical time of personal medical history information and the current onset time; generate medical history nodes and disease investigation nodes based on onset nodes, clinical information and personal medical history information; generate patient medical treatment maps based on onset nodes, medical history nodes and disease investigation nodes.

3. The epilepsy auxiliary diagnosis and treatment system based on big data model according to claim 2 is characterized in that: The process of analyzing clinical information and obtaining epilepsy data includes: Perform disease feature analysis on clinical information, wherein the disease feature analysis refers to analyzing epilepsy-related disease information on EEG waveform graphs and brain images respectively; setting an onset window, and obtaining normal waveform features based on the EEG waveform graph of clinical information; setting a normal waveform feature number based on each normal waveform feature, the onset window and the EEG waveform graph; obtaining normal EEG image segments based on the normal waveform feature number, and obtaining abnormal EEG image segments based on the EEG waveform graph and the normal EEG image segments; obtaining abnormal time period features based on each abnormal EEG image segment; obtaining epilepsy onset data based on the abnormal EEG image segments and the corresponding abnormal time period features.

4. The epilepsy auxiliary diagnosis and treatment system based on big data model according to claim 3 is characterized in that: Analyze clinical information to obtain epilepsy source data. The process of obtaining epilepsy analysis data based on epilepsy onset data and epilepsy source data includes: According to the brain image of clinical information, the single epileptic focus area and the single area range are obtained, the focus association range is set, the epileptic focus group area is obtained according to the focus association range, and the regional range of the epileptic focus group area is obtained, which is recorded as the group area range, according to the recording time of each epileptic focus single area in the epileptic focus group area, the recording time period of each epileptic focus single area is obtained, according to the single area range and the recording time period of each epileptic focus single area, the recording time period of the epileptic focus group area is obtained, the total number of epileptic focus single areas in the epileptic focus group area is counted, which is recorded as the epileptic group quantity, and the epilepsy source data is obtained according to the recording time period and the epileptic group quantity of the epileptic focus group area; Obtain epilepsy analysis data based on epilepsy onset data and epilepsy source data; The abnormal time period characteristics of epilepsy attack data and the recorded time period of epilepsy source data are analyzed. When the time period corresponding to the abnormal time period characteristics completely belongs to the recorded time period, the disease association relationship is obtained; based on the disease association relationship, epilepsy attack data and epilepsy source data, epilepsy analysis data is obtained.

5. The epilepsy auxiliary diagnosis and treatment system based on big data model according to claim 4 is characterized in that: According to the epilepsy analysis data and personal medical history information, a patient disease data model is constructed. The patient disease data model is processed by personal medical history information. The process of obtaining the patient epilepsy research model includes: Establishing a brain physical model according to the brain image corresponding to the personal medical history information, establishing a brain analysis model according to the epilepsy analysis data corresponding to the personal medical history information, and obtaining a patient disease data sub-model according to the personal medical history information, the brain analysis model and the brain physical model corresponding to the brain analysis model, and obtaining a patient disease data model according to each patient disease data sub-model; According to the personal medical history information of the diagnosed patients, a patient-centered model and a patient sample model are obtained, and according to the patient-centered model and the patient sample model, a patient epilepsy research model is obtained.

6. The epilepsy auxiliary diagnosis and treatment system based on big data model according to claim 5, characterized in that: According to the patient epilepsy research model, the process of obtaining abnormal activity values ​​includes: Analyze the patient-centered model of the patient epilepsy research model to obtain abnormal activity values ​​and disease indication values; According to the epilepsy analysis data and the onset correlation of the patient-centered model, the epilepsy onset data and epilepsy source data with onset correlation are obtained, and the number of onset correlations with the epilepsy source data is counted to obtain the epilepsy correlation quantity; according to the onset window and the abnormal EEG image segment, the abnormal sub-segment is obtained, and according to the abnormal sub-segment, the abnormal sub-time period is obtained; the abnormal sub-time period is compared with each recording time period of the recording time period, and when the abnormal sub-time period belongs to the recording time period of the recording time period, the time span corresponding to the abnormal sub-time period and the recording time period is obtained respectively, and the abnormal activity is obtained according to the time span corresponding to the abnormal sub-time period and the recording time period, and the number of abnormal sub-time periods belonging to the recording time period is counted to obtain the activity coefficient, and according to the single area range, the abnormal activity, the activity coefficient and the group area range, the abnormal activity value YH of the epileptic focus group area is obtained; in, Refers to the abnormal activity corresponding to each recording time period. Refers to the activity coefficient corresponding to each recording time period, Refers to the single area range corresponding to each recording time period. Refers to the group area range, It refers to the total number of single epileptic focus areas within the epileptic focus group area.

7. The epilepsy auxiliary diagnosis and treatment system based on big data model according to claim 6, characterized in that: According to the patient epilepsy research model, the process of obtaining the disease indication value includes: The connection distance between each epileptic focus group area is obtained, recorded as the group influence coefficient, and the patient's disease indication value TB is obtained according to the group influence coefficient and the abnormal activity value; in, Refers to the group influence coefficient of each epileptic focus group area, Refers to the abnormal activity value of each epileptic focus group area, Refers to the total number of epileptic focus groups.

8. The epilepsy auxiliary diagnosis and treatment system based on big data model according to claim 7, characterized in that: According to the patient's epilepsy research model, abnormal activity value and disease indication value, the auxiliary coefficient and auxiliary diagnosis and treatment plan are obtained. The process of auxiliary diagnosis and treatment of epilepsy for patients through the auxiliary diagnosis and treatment plan and auxiliary coefficient includes: According to the abnormal activity value and the disease prompt value, the auxiliary coefficient ω is obtained; in, It refers to the maximum value of abnormal activity in each epileptic focus group area. It refers to the minimum value of abnormal activity in each epileptic focus group area; According to the patient sample model and the patient center model of the patient epilepsy research model, a sample state value and a patient state value are obtained, and a bootstrap coefficient is obtained according to the sample state value and the patient state value; When the bootstrap coefficient of the patient sample model is greater than or equal to the auxiliary coefficient, the corresponding patient sample model is extracted, and the historical treatment plan and historical medication plan of the extracted patient sample model are summarized to obtain an auxiliary diagnosis and treatment plan, and the patient is given auxiliary diagnosis and treatment of epilepsy through the auxiliary diagnosis and treatment plan and the auxiliary coefficient.

Images