Epilepsy determination method, device, electronic device and computer readable storage medium

Abstract

The embodiments of the present application provide an epilepsy determination method, device, electronic device and computer-readable storage medium, which relate to the field of computer technology. The method includes: obtaining EEG feature data of the subject, performing EEG feature analysis on the EEG feature data to obtain EEG feature analysis results; inputting the EEG feature data into a trained epilepsy analysis model to obtain epilepsy analysis results through the epilepsy analysis model; combining the EEG feature analysis results and the epilepsy analysis results to determine the epilepsy state of the subject. It can be seen that combining the EEG feature analysis results and the epilepsy analysis results to determine the epilepsy state of the subject avoids human bias and improves the accuracy of the determined epilepsy state.

Description

Background Art

[0002] This section is intended to provide a background or context to embodiments of the invention that are recited in the claims. No description herein is admitted to be prior art by inclusion in this section.

[0003] In recent years, with the improvement of people's quality of life and the improvement of medical level, the awareness and attention of brain diseases such as epilepsy have gradually increased, and the number of EEG monitoring has also increased. EEG analysis is an important detection method for early prevention of EEG diseases. However, at present, EEG analysis mostly relies on doctors, which makes the doctors' work subjective and heavy, and easily causes human bias, thereby reducing the accuracy of the determined EEG disease status of patients.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] Based on the above problems, the inventors have conducted corresponding thinking and made targeted improvements, providing an epilepsy determination method, an epilepsy determination device, an electronic device and a computer-readable storage medium, which can perform EEG feature analysis on EEG feature data to obtain EEG feature analysis results, and input the EEG feature data into a trained epilepsy analysis model to obtain epilepsy analysis results through the epilepsy analysis model; combine the EEG feature analysis results and the epilepsy analysis results to determine the epilepsy state of the subject, avoid human bias, and improve the accuracy of the determined epilepsy state of the subject.

[0006] According to a first aspect of an embodiment of the present application, a method for determining epilepsy is disclosed, comprising:

[0007] Acquiring EEG characteristic data of the subject, and performing EEG characteristic analysis on the EEG characteristic data to obtain an EEG characteristic analysis result;

[0008] Inputting the EEG feature data into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model;

[0009] The epileptic state of the subject is determined by combining the EEG feature analysis result and the epilepsy analysis result.

[0010] In one embodiment, based on the above scheme, the EEG characteristic data includes EEG characteristic data corresponding to a plurality of monitoring channels respectively; the EEG characteristic analysis result includes a rhythm analysis result;

[0011] The performing EEG feature analysis on the EEG feature data to obtain an EEG feature analysis result includes:

[0012] Determining target EEG characteristic data of a target monitoring channel from the EEG characteristic data;

[0013] Performing rhythm analysis on the target EEG characteristic data to obtain the rhythm analysis result.

[0014] In one embodiment, based on the above scheme, the rhythm analysis result includes the occipital rhythm analysis result; the target monitoring channel includes a first monitoring channel and a second monitoring channel corresponding to the occipital region;

[0015] The step of performing rhythm analysis on the target EEG characteristic data to obtain the rhythm analysis result includes:

[0016] Determining first alpha wave electroencephalogram characteristic data and second alpha wave electroencephalogram characteristic data belonging to alpha waves from the first electroencephalogram characteristic data and the second electroencephalogram characteristic data; wherein the first electroencephalogram characteristic data corresponds to the first monitoring channel, and the second electroencephalogram characteristic data corresponds to the second monitoring channel;

[0017] The occipital region rhythm analysis result is obtained by analyzing the EEG variation rules represented by the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data.

[0018] In one embodiment, based on the aforementioned solution, the EEG feature analysis results include EEG functional connectivity analysis results;

[0019] The performing EEG feature analysis on the EEG feature data to obtain an EEG feature analysis result includes:

[0020] Performing correlation analysis on the EEG characteristic data corresponding to the multiple monitoring channels to obtain a correlation matrix;

[0021] Determine a preset threshold for measuring the EEG functional connection state, and compare the value in the correlation matrix with the preset threshold to obtain a numerical comparison result;

[0022] The EEG functional connection analysis results corresponding to the multiple monitoring channels are obtained according to the numerical comparison results.

[0023] In one embodiment, based on the aforementioned solution, the EEG feature analysis result includes an eye-opening inhibition analysis result;

[0024] The performing EEG feature analysis on the EEG feature data to obtain an EEG feature analysis result includes:

[0025] Determining, from the first EEG characteristic data, third EEG characteristic data of the subject in a first eye change state and fourth EEG characteristic data of the subject in a second eye change state;

[0026] Analyze the EEG change rules represented by the third EEG characteristic data and the fourth EEG characteristic data to obtain a first occipital region rhythm analysis result and a second occipital region rhythm analysis result;

[0027] A difference comparison is performed on the first occipital region rhythm analysis result and the second occipital region rhythm analysis result to obtain the eye opening inhibition analysis result according to the difference comparison result.

[0028] In one embodiment, based on the above solution, the method further includes:

[0029] Taking a preset time point as a starting time, dividing the EEG feature data based on a preset time interval to obtain a plurality of divided segments;

[0030] The multiple segmented segments are input into the trained epilepsy analysis model.

[0031] In one embodiment, based on the aforementioned scheme, the epilepsy analysis model includes an epileptic seizure analysis model;

[0032] The step of inputting the EEG feature data into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model includes:

[0033] The multiple segmented segments are input into the trained epilepsy analysis model to determine whether the subject is in an epileptic seizure period.

[0034] In one embodiment, based on the aforementioned scheme, the epilepsy analysis model includes a sleep phase analysis model;

[0035] The step of inputting the EEG feature data into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model includes:

[0036] The multiple divided segments are input into the trained sleep stage analysis model to determine the sleep stage of the subject.

[0037] In one embodiment, based on the above scheme, inputting the EEG feature data into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model includes:

[0038] Acquire a monitoring video of the subject, and obtain human body feature information and motion feature information of the subject from the monitoring video;

[0039] The EEG feature data, the human body feature information and the motion feature information are input into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model.

[0040] In one embodiment, based on the above solution, obtaining the human body feature information and motion feature information of the subject from the monitoring video includes:

[0041] Extracting a plurality of frame images corresponding to the monitoring video respectively;

[0042] Detecting object key points corresponding to the detected object and key point spatial coordinates corresponding to the object key points from the multiple frame images respectively; the object key points include object facial key points and body key points;

[0043] Constructing human body feature information according to the spatial coordinates of all key points of the tested object for the key points of the target object;

[0044] The human body feature information is subjected to human body motion analysis to obtain the motion feature information of the subject.

[0045] In one embodiment, based on the above solution, the step of inputting the EEG feature data, the human body feature information and the motion feature information into a trained epilepsy analysis model includes:

[0046] Taking a preset time point as a starting time, and based on a preset time interval, dividing the EEG feature data, the human body feature information, and the motion feature information respectively to obtain a plurality of divided segments;

[0047] The multiple segmented segments are input into the trained epilepsy analysis model.

[0048] In one embodiment, based on the aforementioned scheme, the epilepsy analysis model includes an interictal epilepsy analysis model;

[0049] The step of inputting the EEG feature data into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model includes:

[0050] The multiple segmented segments are input into the trained interictal epilepsy analysis model to determine whether the subject is currently in an abnormal discharge state.

[0051] According to a second aspect of an embodiment of the present application, a device for determining epilepsy is disclosed, the device comprising:

[0052] An EEG characteristic analysis unit is used to obtain EEG characteristic data of the subject, and perform EEG characteristic analysis on the EEG characteristic data to obtain an EEG characteristic analysis result;

[0053] An epilepsy analysis unit, used for inputting the EEG feature data into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model;

[0054] An epilepsy state determination unit is used to determine the epilepsy state of the subject in combination with the EEG feature analysis result and the epilepsy analysis result.

[0055] According to a third aspect of an embodiment of the present application, an electronic device is disclosed, including: a processor; and a memory, wherein computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the epilepsy determination method disclosed in the first aspect is implemented.

[0056] According to a fourth aspect of an embodiment of the present application, a computer program medium is disclosed, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer executes the epilepsy determination method disclosed according to the first aspect of the present application.

[0057] The embodiment of the present application can perform EEG feature analysis on EEG feature data to obtain EEG feature analysis results, input the EEG feature data into a trained epilepsy analysis model, obtain EEG analysis results through the epilepsy analysis model, and determine the epilepsy state of the subject by combining the EEG feature analysis results and the epilepsy analysis results. On the one hand, it avoids analyzing the EEG feature data through manual judgment by doctors, avoids human bias, and obtains EEG feature analysis results with higher accuracy; on the other hand, it also inputs the EEG feature data into a trained epilepsy analysis model, which improves the accuracy and efficiency of the epilepsy analysis results obtained by the epilepsy analysis model, thereby improving the accuracy and efficiency of the epilepsy state of the subject determined subsequently.

[0058] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0059] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become readily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, wherein:

[0061] Figure 1 Shown is a flow chart of an epilepsy determination method according to an exemplary embodiment of the present application;

[0062] Figure 2 What is shown is a multi-channel EEG signal diagram of a test subject collected in an embodiment of the present disclosure;

[0063] Figure 3 It shows a flow chart of obtaining the occipital rhythm analysis result in the embodiment of the present disclosure;

[0064] Figure 4 What is shown is a schematic diagram of a process for obtaining EEG functional connection analysis results in an embodiment of the present disclosure;

[0065] Figure 5 What is shown is a schematic diagram of a process for obtaining an eye-opening inhibition analysis result in an embodiment of the present disclosure;

[0066] Figure 6 Shown is a schematic diagram of a process for determining whether a subject is in an epileptic seizure period;

[0067] Figure 7 What is shown is a schematic diagram of a process of determining the current sleep period of the subject under test;

[0068] Figure 8 What is shown is a flow chart of inputting EEG feature data, human body feature data and motion feature data into a trained interictal epilepsy analysis model in an embodiment of the present disclosure;

[0069] Fig. 9 What is shown is a flow chart of determining the epileptic state of the subject in accordance with the embodiment of the present disclosure by combining the EEG feature analysis results and the epilepsy analysis results;

[0070] Fig.10 Shown is a structural block diagram of an epilepsy determination device according to an exemplary embodiment of the present application;

[0071] Fig.11 Shown is an electronic device according to another alternative exemplary embodiment of the present application.

[0072] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0073] The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present application, and are not intended to limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0074] Those skilled in the art know that the embodiments of the present application can be implemented as a device, apparatus, method or computer program product. Therefore, the present application can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0075] According to the embodiments of the present application, an epilepsy determination method, an epilepsy determination device, an electronic device, and a computer-readable storage medium are proposed.

[0076] Any number of elements in the drawings is for illustration and not limitation, and any naming is for distinction only and does not have any limiting meaning.

[0077] The principles and spirit of the present application are explained in detail below with reference to several representative implementations of the present application. SUMMARY OF THE INVENTION

[0079] At present, the existing technology for epilepsy determination is usually: relying on experienced specialists to analyze EEG feature data to obtain EEG feature analysis results and epilepsy analysis results. However, human bias is prone to occur during the manual analysis process. Therefore, the determination of epilepsy status using the above method will reduce the accuracy and efficiency of the determined epilepsy status.

[0080] Based on the above problems, the applicant has come up with the idea of ​​avoiding the need for multiple doctors to analyze EEG feature data during the process of determining epilepsy, using a machine to directly analyze the EEG feature data, and inputting the EEG feature data into a trained epilepsy analysis model to determine the epileptic state of the subject. It can be seen that the phenomenon of multiple doctors analyzing EEG feature data in the prior art is avoided, and the accuracy and efficiency of determining the epileptic state of the subject is improved.

[0081] Application Scenario Overview

[0082] It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the implementation of the present application is not limited in this respect. On the contrary, the implementation of the present application can be applied to any applicable scenario.

[0083] When applied to the scenario of determining the epileptic state of the subject, it can avoid the phenomenon of multiple doctors analyzing the EEG characteristic data of the subject, thereby improving the accuracy and efficiency of determining the epileptic state of the subject.

[0084] Exemplary Methods

[0085] In combination with the above application scenarios, refer to Figure 1 and Fig.11 A method for determining epilepsy according to an exemplary embodiment of the present application will be described.

[0086] See also Figure 1 , Figure 1 FIG. 2 is a flow chart of an epilepsy determination method according to an exemplary embodiment of the present application. Figure 1 As shown, the epilepsy determination method may include:

[0087] Step S110: Acquire the EEG characteristic data of the subject, and perform EEG characteristic analysis on the EEG characteristic data to obtain EEG characteristic analysis results.

[0088] Step S120: inputting the EEG feature data into the trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model.

[0089] Step S130: Determine the epileptic state of the subject by combining the EEG feature analysis results and the epilepsy analysis results.

[0090] Implementation Figure 1 The epilepsy determination method shown in the figure performs an EEG feature analysis on the EEG feature data to obtain an EEG feature analysis result, inputs the EEG feature data into a trained epilepsy analysis model, obtains an EEG analysis result through the epilepsy analysis model, and combines the EEG feature analysis result and the epilepsy analysis result to determine the epilepsy state of the subject. On the one hand, it avoids analyzing the EEG feature data by manual judgment of doctors, avoids human bias, and obtains an EEG feature analysis result with higher accuracy; on the other hand, the EEG feature data is also input into the trained epilepsy analysis model, which improves the accuracy and efficiency of the epilepsy analysis result obtained by the epilepsy analysis model, thereby improving the accuracy and efficiency of the epilepsy state of the subject determined subsequently.

[0091] These steps are described in detail below.

[0092] In step S110, the EEG characteristic data of the subject is obtained, and an EEG characteristic analysis is performed on the EEG characteristic data to obtain an EEG characteristic analysis result.

[0093] Specifically, the test subject refers to a patient whose epileptic state needs to be determined at this time, for example, a patient suspected of being in an epileptic seizure, or a patient suspected of being in the interictal period of an epileptic seizure.

[0094] EEG feature data refers to data that can reflect the EEG features of the subject, for example, it can be the collected EEG signal of the subject. One or more EEG feature analysis results can be obtained by performing EEG feature analysis of different dimensions on the EEG feature data. For example, the EEG feature analysis result can be a rhythm analysis result, an EEG functional connectivity analysis result, or an eye-opening inhibition analysis result.

[0095] As an optional embodiment, the EEG feature data includes EEG feature data corresponding to multiple monitoring channels respectively; the EEG feature analysis results include rhythm analysis results; the EEG feature analysis is performed on the EEG feature data to obtain the EEG feature analysis results, including: determining target EEG feature data of the target monitoring channel from the EEG feature data; and performing rhythm analysis on the target EEG feature data to obtain the rhythm analysis results.

[0096] Specifically, the EEG feature data includes EEG feature data corresponding to multiple channels. Figure 2 FIG. 4 shows a multi-channel EEG signal diagram of a subject collected in an embodiment of the present disclosure, such as Figure 2 As described above, each row in the figure corresponds to the real-time EEG signal of the subject in one channel.

[0097] The EEG characteristic analysis result may be a rhythm analysis result, for example, the rhythm analysis result of the occipital region (i.e., the back of the head of the subject), which is used to reflect the real-time change pattern of EEG waves of different frequencies in the occipital region of the subject.

[0098] The target monitoring channel refers to the EEG channel corresponding to the analysis site (e.g., occipital region) corresponding to the rhythm analysis result. For example, for the occipital region rhythm analysis result, the target EEG feature data of the two target monitoring channels O1 and O2 need to be determined from the EEG feature data.

[0099] Based on this, the rhythm range, amplitude, and regulation difference of the target EEG characteristic data are analyzed to obtain the corresponding rhythm analysis results by performing rhythm analysis on the target EEG characteristic data. The rhythm analysis results can be used to determine whether the current EEG characteristics of the subject are normal.

[0100] It can be seen that implementing this optional embodiment to determine the target EEG characteristic data of the target monitoring channel from the EEG characteristic data is helpful for subsequently obtaining targeted target EEG characteristic data.

[0101] As an optional embodiment, the rhythm analysis result includes the rhythm analysis result of the occipital region; the target monitoring channel includes the first monitoring channel and the second monitoring channel corresponding to the occipital region; the rhythm analysis is performed on the target EEG characteristic data to obtain the rhythm analysis result, including: determining the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data belonging to the alpha wave from the first EEG characteristic data and the second EEG characteristic data; wherein the first EEG characteristic data corresponds to the first monitoring channel, and the second EEG characteristic data corresponds to the second monitoring channel; the occipital region rhythm analysis result is obtained by analyzing the EEG change law represented by the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data.

[0102] Specifically, the rhythm analysis result may be an occipital rhythm analysis result. When the rhythm analysis result is an occipital rhythm analysis result, the first monitoring channel is the O1 channel, and the second monitoring channel is the O2 channel.

[0103] The first EEG characteristic data is the EEG signal corresponding to the O1 channel, and the second EEG characteristic data is the EEG signal corresponding to the O2 channel. Alpha wave refers to a basic brain wave, and its frequency range is mainly 8-13Hz. The frequency range of the first EEG characteristic data and the frequency range of the second EEG characteristic data are judged to determine the first alpha wave EEG characteristic data at 8-13Hz in the first EEG characteristic data and the second alpha wave EEG characteristic data at 8-13Hz in the second EEG characteristic data.

[0104] Based on this, the rhythm range, amplitude, amplitude modulation, whether it is rhythmic and regulation of the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data are analyzed to obtain the occipital rhythm analysis results. Among them, when there are at least three consecutive waves that fluctuate within the range of 9-11Hz in the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data, it is considered to be rhythmic; then the amplitude of the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data needs to be calculated; when the EEG signals in the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data show a shuttle shape that gradually increases and then gradually decreases, it is considered that the amplitude modulation is good, otherwise it is poor; judge whether the frequency difference of each alpha wave in the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data exceeds 2Hz. If it does not exceed 2Hz, it is considered that it is well regulated, otherwise it is poorly regulated. The rhythm analysis of the target EEG characteristic data is completed through the above dimensions.

[0105] Figure 3 Shown is a flow chart of obtaining occipital rhythm analysis results in an embodiment of the present disclosure.

[0106] It can be seen that by implementing this optional embodiment, the EEG variation patterns represented by the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data are analyzed, human bias is avoided, and a highly accurate occipital rhythm analysis result can be obtained.

[0107] As an optional embodiment, the EEG feature analysis results include EEG functional connection analysis results; performing EEG feature analysis on EEG feature data to obtain EEG feature analysis results, including: performing correlation analysis on EEG feature data corresponding to multiple monitoring channels to obtain a correlation matrix; determining a preset threshold for measuring the state of EEG functional connection, comparing the value in the correlation matrix with the preset threshold to obtain a numerical comparison result; and obtaining EEG functional connection analysis results corresponding to multiple monitoring channels according to the numerical comparison results.

[0108] Specifically, the EEG feature analysis results also include EEG functional connectivity analysis results. The EEG functional connectivity analysis results can be used to analyze whether the subject currently has cognitive impairment.

[0109] The Pearson product difference algorithm is used to perform correlation analysis on the EEG feature data corresponding to multiple monitoring channels to obtain the calculation result, that is, the correlation matrix. The correlation matrix is ​​normalized to limit the values ​​in the correlation matrix to the range of 0 to 1.

[0110] The preset threshold refers to a value used to measure the functional connection state of EEG. Compare each normalized value in the correlation matrix with the preset threshold. If a value is greater than the preset threshold, it is considered that the EEGs between the monitoring channels corresponding to the value can be connected to each other; if a value is less than or equal to the preset threshold, it is considered that the EEGs between the monitoring channels corresponding to the value cannot be connected to each other. If the EEGs are more interconnected, it is considered that the subject is more likely to be in a normal state; if the EEGs are less interconnected, the subject is more likely to be in a cognitive impairment state, thereby obtaining the EEG functional connection analysis results of the subject.

[0111] Figure 4 What is shown is a schematic diagram of a process for obtaining EEG functional connection analysis results in an embodiment of the present disclosure.

[0112] It can be seen that by implementing this optional embodiment, through the correlation analysis of the EEG feature data corresponding to multiple monitoring channels, the EEG connection analysis results representing whether the subject is in cognitive impairment can be obtained.

[0113] As an optional embodiment, the EEG feature analysis result includes an eye-opening inhibition analysis result; performing EEG feature analysis on the EEG feature data to obtain the EEG feature analysis result includes:

[0114] The third EEG characteristic data of the subject being in the first eye change state and the fourth EEG characteristic data of the subject being in the second eye change state are determined in the first EEG characteristic data, and the fifth EEG characteristic data of the subject being in the first eye change state and the sixth EEG characteristic data of the subject being in the second eye change state are determined in the second EEG characteristic data; the EEG change rules represented by the third EEG characteristic data and the fourth EEG characteristic data are analyzed to obtain the first occipital area rhythm analysis result and the second occipital area rhythm analysis result, and the EEG change rules represented by the fifth EEG characteristic data and the sixth EEG characteristic data are analyzed to obtain the third occipital area rhythm analysis result and the fourth occipital area rhythm analysis result; the first occipital area rhythm analysis result and the second occipital area rhythm analysis result are compared for difference, and the third occipital area rhythm analysis result and the fourth occipital area rhythm analysis result are compared for difference, so as to obtain the eye opening inhibition analysis result according to the difference comparison result.

[0115] Specifically, the first eye change state refers to the eye change state of the subject from opening eyes to closing eyes, and the second eye change state refers to the eye change state of the subject from closing eyes to opening eyes.

[0116] Based on this, the third EEG characteristic data represents the EEG characteristic data of the subject in the first EEG characteristic data in the first eye change state, and similarly, the fifth EEG characteristic data represents the EEG characteristic data of the subject in the first eye change state in the second EEG characteristic data. The fourth EEG characteristic data represents the EEG characteristic data of the subject in the second eye change state in the first EEG characteristic data, and similarly, the sixth EEG characteristic data represents the EEG characteristic data of the subject in the second eye change state in the second EEG characteristic data.

[0117] The rhythm analysis results of the first occipital area and the rhythm analysis results of the second occipital area correspond to the third EEG characteristic data and the fourth EEG characteristic data respectively, and the rhythm analysis results of the third occipital area and the rhythm analysis results of the fourth occipital area correspond to the fifth EEG characteristic data and the sixth EEG characteristic data respectively.

[0118] Through difference comparison, if the rhythm exists in the rhythm analysis results of the first occipital area and disappears in the rhythm analysis results of the second occipital area, or the rhythm exists in the rhythm analysis results of the third occipital area and disappears in the rhythm analysis results of the fourth occipital area, then the eyes opening inhibition analysis result is complete eyes opening inhibition; if the rhythm exists in the rhythm analysis results of the first occipital area and is partially weakened in the rhythm analysis results of the second occipital area, or the rhythm exists in the rhythm analysis results of the third occipital area and is partially weakened in the rhythm analysis results of the fourth occipital area, then the eyes opening inhibition analysis result is incomplete eyes opening inhibition.

[0119] Figure 5What is shown is a schematic diagram of a process for obtaining the eye-opening inhibition analysis result in an embodiment of the present disclosure.

[0120] It can be seen that by implementing this optional embodiment, the current eye opening inhibition state of the subject can be obtained by differentially comparing the different results of occipital rhythm analysis under the first eye change state and the second eye change state, which provides theoretical support for the subsequent determination of the epileptic state of the subject.

[0121] In step S120, the EEG feature data is input into the trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model.

[0122] Specifically, the epilepsy analysis model refers to a trained neural network model. By inputting EEG feature data into the trained epilepsy analysis model, the corresponding prediction result (ie, epilepsy analysis result) can be obtained.

[0123] As an optional embodiment, the method further includes: taking a preset time point as a starting time, dividing the EEG feature data based on a preset time interval to obtain a plurality of divided segments; and inputting the plurality of divided segments into a trained epilepsy analysis model.

[0124] Specifically, after obtaining the EEG feature data, the EEG feature data is not directly input into the trained epilepsy analysis model, but the EEG feature data is divided and processed.

[0125] Specifically, the EEG feature data is divided and processed according to a preset time interval (e.g., 2 seconds) with a preset time point as the starting time (e.g., the starting time of collecting the EEG feature data of the subject), and a corresponding plurality of divided segments can be obtained. After obtaining the plurality of divided segments, the plurality of divided segments are input into the trained epilepsy analysis model.

[0126] It can be seen that by implementing this optional embodiment, multiple divided segments are input into the epilepsy analysis model, and the obtained epilepsy analysis results correspond to the EEG feature data of a specific segment, which can better understand the characteristic changes caused by the EEG feature data on the subject.

[0127] As an optional embodiment, the epilepsy analysis model includes an epilepsy analysis model during the ictal period;

[0128] The EEG feature data is input into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model, including: inputting the multiple divided segments into a trained seizure epilepsy analysis model to determine whether the subject is in an epileptic seizure period.

[0129] Specifically, the epilepsy analysis model can be an epilepsy analysis model during the seizure period, that is, a neural network model for predicting whether the subject is in an epileptic seizure period at this time. The multiple segmented segments obtained after the EEG feature data is segmented are input into the trained epilepsy analysis model during the seizure period to obtain a prediction result, through which it can be known whether the subject is in an epileptic seizure period at this time.

[0130] Figure 6 Shown is a schematic diagram of a flow chart for determining whether a subject is in an epileptic seizure period.

[0131] It can be seen that by implementing this optional embodiment, it is possible to predict whether the subject is in an epileptic seizure period based on the EEG feature data and the seizure period telecommunication analysis model.

[0132] As an optional embodiment, the epilepsy analysis model includes a sleep period analysis model; the EEG feature data is input into the trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model, including: inputting multiple divided segments into the trained sleep period analysis model to determine the sleep period of the subject.

[0133] Specifically, the epilepsy analysis model also includes a sleep stage analysis model. By inputting multiple divided segments of EEG feature data into the trained sleep stage analysis model, corresponding prediction results can be obtained. Through the prediction results, it can be known whether the current subject is in the wakefulness stage, sleep stage I, sleep stage II, sleep stage III, or rapid eye movement stage of sleep.

[0134] Figure 7 The figure shows a flow chart of determining the current sleep period of the subject.

[0135] It can be seen that by implementing this optional embodiment, the sleep period of the subject can be predicted based on the EEG feature data and the sleep period analysis model.

[0136] As an optional embodiment, the EEG feature data is input into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model, including: obtaining a monitoring video of the subject, and obtaining the human body feature information and motion feature information of the subject from the monitoring video; the EEG feature data, the human body feature information and the motion feature information are input into the trained epilepsy analysis model to obtain the epilepsy analysis result through the epilepsy analysis model.

[0137] Specifically, the monitoring video refers to the video collected during the process of monitoring the object under test. For example, a monitoring device can be carried on the head of the object under test, and there is a camera in the device to collect dynamic video of the object under test in real time.

[0138] Human body features refer to features that describe a certain part of the human body of the subject. Human body feature information may be feature information of the eyes of the subject, feature information of the nose of the subject, feature information of the hands of the subject, feature information of the neck of the subject, or feature information of the feet of the subject, and this exemplary embodiment does not specifically limit this.

[0139] The motion characteristic information may be the motion characteristic information corresponding to the action of raising the arm when the subject is testing, or the motion characteristic information corresponding to the action of twitching the leg when the subject is testing, and this exemplary embodiment does not specifically limit this.

[0140] Figure 8 FIG. 1 is a flow chart showing how to input EEG feature data, human body feature data, and motion feature data into a trained interictal epilepsy analysis model in an embodiment of the present disclosure. Figure 8 As shown, the EEG feature data, the human feature information obtained by monitoring the video, and the motion feature information are input into the trained interictal epilepsy analysis model, and the epilepsy analysis result of the subject at this time can be obtained. For example, it is determined whether the subject is in an epileptic seizure period at this time.

[0141] It can be seen that by implementing this optional embodiment, the data input into the trained epilepsy analysis model includes, in addition to the EEG feature data, also human body feature information and motion feature information, which increases the accuracy of the final epilepsy analysis result.

[0142] As an optional embodiment, obtaining the human body feature information and the motion feature information of the subject from the monitoring video includes: extracting a plurality of frame images corresponding to the monitoring video respectively;

[0143] The object key points corresponding to the tested object and the key point spatial coordinates corresponding to the object key points are detected from multiple frame images respectively; the object key points include the object's facial key points and body key points; human body feature information is constructed based on the spatial coordinates of all key points of the tested object for the target object key points; human body feature information is subjected to human motion analysis to obtain the motion feature information of the tested object.

[0144] The monitoring video is actually composed of multiple frames of images. According to the characteristics of the human body, it is possible to detect which part of the multi-frame graphics is the key point of the object under test, and also detect the position of the key point in the multi-frame graphics (i.e. the spatial coordinates of the key point).

[0145] It is worth noting that the object key points include the object facial key points of the subject's face and the body key points of the subject's body. For example, the object key points may be the object key points corresponding to the outside of the right eye, and the object key points may also be the object key points corresponding to the left hip.

[0146] The human feature information used to characterize the human features of the subject can be obtained through the key point spatial coordinates corresponding to the key points of the same target object in multiple frame graphics. For example, the human feature information of the left hip can be obtained through the key point spatial coordinates of the key points of the target object corresponding to the left hip, and then the human motion analysis of the human feature information can be performed to determine that the left hip of the subject is shaking at this time (the shaking of the left hip is a motion feature information).

[0147] It can be seen that by implementing this optional embodiment, human feature information reflecting key points of human objects and motion feature information reflecting human motions can be obtained by monitoring the video, and then the human feature information and motion feature information can be input into the trained epilepsy analysis model to improve the accuracy of the epilepsy analysis results.

[0148] As an optional embodiment, the EEG feature data, human body feature information and motion feature information are input into a trained epilepsy analysis model, including: taking a preset time point as the starting time, and based on a preset time interval, dividing the EEG feature data, human body feature information and motion feature information respectively to obtain multiple divided segments; and inputting the multiple divided segments into the trained epilepsy analysis model.

[0149] Specifically, after obtaining the EEG feature data, human body feature information and motion feature information, the EEG feature data, human body feature information and motion feature information are not directly input into the trained epilepsy analysis model, but the EEG feature data, human body feature information and motion feature information are divided and processed.

[0150] Specifically, a preset time point is used as the starting time (for example, the starting time of collecting the EEG feature data and monitoring video of the subject), and the EEG feature data, human feature information, and motion feature information are divided and processed according to a preset time interval (for example, 2 seconds), so as to obtain a plurality of corresponding divided segments. After obtaining the plurality of divided segments, the plurality of divided segments are input into the trained epilepsy analysis model.

[0151] It can be seen that by implementing this optional embodiment, multiple divided segments are input into the epilepsy analysis model, and the obtained epilepsy analysis results correspond to a specific EEG feature data, a segment of human feature information, and a segment of motion feature information, which can better understand the feature changes produced by the subject when obtaining the epilepsy analysis results.

[0152] As an optional embodiment, the epilepsy analysis model includes an interictal epilepsy analysis model; the EEG feature data is input into the trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model, including: inputting multiple divided segments into the trained interictal epilepsy analysis model to determine whether the subject is currently in an abnormal discharge state.

[0153] Specifically, the epilepsy analysis model also includes an interictal epilepsy analysis model. Inputting a plurality of segmented segments into the interictal epilepsy analysis model can determine whether the subject is currently in an abnormal discharge state.

[0154] It can be seen that by implementing this optional embodiment, the abnormal EEG discharge state of the subject can be predicted based on the EEG characteristic data and the interictal epilepsy analysis model.

[0155] In step S130, the epileptic state of the subject is determined by combining the EEG feature analysis result and the epilepsy analysis result.

[0156] Specifically, the EEG feature analysis results include rhythm analysis results, EEG functional connection analysis results and eye opening inhibition analysis results. The epilepsy analysis results include determining whether the subject is in an epileptic seizure period, determining the subject's sleep period and determining whether the subject is in an abnormal discharge state at this time. By combining the above contents, the epileptic state of the subject can be determined more accurately.

[0157] Fig. 9 FIG. 1 is a flow chart showing how to determine the epileptic state of a subject by combining the EEG feature analysis results and the epilepsy analysis results in the embodiment of the present disclosure. Fig. 9 As shown, EEG feature analysis specifically includes rhythm analysis, brain function connection analysis and eye-opening inhibition analysis. The EEG feature analysis results (i.e., occipital rhythm analysis results, EEG function connection analysis results and eye-opening inhibition analysis results) are obtained through the above three analysis processes. Model analysis includes ictal EEG analysis using the ictal epilepsy analysis model, sleep period analysis using the sleep period analysis model and interictal analysis using the interictal epilepsy analysis model. The corresponding epilepsy analysis results can be obtained through the above three models. Based on this, combined with the EEG feature analysis results and the epilepsy analysis results, the epileptic state of the subject is finally determined.

[0158] In the implementation of the embodiment of the present application, the EEG feature data is subjected to EEG feature analysis to obtain EEG feature analysis results, the EEG feature data is input into a trained epilepsy analysis model, the EEG analysis results are obtained through the epilepsy analysis model, and the epilepsy state of the subject is determined by combining the EEG feature analysis results and the epilepsy analysis results. On the one hand, it avoids analyzing the EEG feature data by manual judgment by doctors, avoids human bias, and obtains EEG feature analysis results with higher accuracy; on the other hand, the EEG feature data is also input into a trained epilepsy analysis model, which improves the accuracy and efficiency of the epilepsy analysis results obtained by the epilepsy analysis model, thereby improving the accuracy and efficiency of the epilepsy state of the subject determined subsequently.

[0159] Exemplary Media

[0160] After introducing the method according to the exemplary embodiment of the present application, next, the medium according to the exemplary embodiment of the present application will be described.

[0161] In some possible implementations, various aspects of the present application may also be implemented as a medium on which program code is stored, and when the program code is executed by a processor of a device, it is used to implement the steps of the epilepsy determination method according to various exemplary implementations of the present application described in the above “Exemplary Method” section of this specification.

[0162] Specifically, when the processor of the device executes the program code, it is used to implement the following steps: obtaining the EEG feature data of the subject, performing EEG feature analysis on the EEG feature data to obtain EEG feature analysis results; inputting the EEG feature data into a trained epilepsy analysis model to obtain epilepsy analysis results through the epilepsy analysis model; and determining the epileptic state of the subject by combining the EEG feature analysis results and the epilepsy analysis results.

[0163] In some embodiments of the present application, the processor of the device is also used to implement the following steps when executing the program code: determining target EEG characteristic data of the target monitoring channel from the EEG characteristic data; performing rhythm analysis on the target EEG characteristic data to obtain a rhythm analysis result.

[0164] In some embodiments of the present application, the processor of the device is also used to implement the following steps when executing the program code: determining the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data belonging to the alpha wave from the first EEG characteristic data and the second EEG characteristic data; wherein the first EEG characteristic data corresponds to the first monitoring channel, and the second EEG characteristic data corresponds to the second monitoring channel; and obtaining the occipital rhythm analysis result by analyzing the EEG change law represented by the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data.

[0165] In some embodiments of the present application, the processor of the device is also used to implement the following steps when executing the program code: performing correlation analysis on the EEG feature data corresponding to multiple monitoring channels to obtain a correlation matrix; determining a preset threshold for measuring the state of EEG functional connection, and comparing the numerical value in the correlation matrix with the preset threshold to obtain a numerical comparison result; and obtaining the EEG functional connection analysis results corresponding to multiple monitoring channels according to the numerical comparison results.

[0166] In some embodiments of the present application, the processor of the device is also used to implement the following steps when executing the program code: determining the third EEG feature data of the subject in the first eye change state and the fourth EEG feature data in the second eye change state in the first EEG feature data, and determining the fifth EEG feature data of the subject in the first eye change state and the sixth EEG feature data in the second eye change state in the second EEG feature data; analyzing the EEG change rules represented by the third EEG feature data and the fourth EEG feature data, respectively, to obtain the first occipital area rhythm analysis result and the second occipital area rhythm analysis result, analyzing the EEG change rules represented by the fifth EEG feature data and the sixth EEG feature data, respectively, to obtain the third occipital area rhythm analysis result and the fourth occipital area rhythm analysis result; performing a difference comparison between the first occipital area rhythm analysis result and the second occipital area rhythm analysis result, and performing a difference comparison between the third occipital area rhythm analysis result and the fourth occipital area rhythm analysis result, so as to obtain the eye opening inhibition analysis result according to the difference comparison result.

[0167] In some embodiments of the present application, the processor of the device is further used to implement the following steps when executing the program code: taking a preset time point as the starting time, dividing the EEG feature data based on a preset time interval to obtain a plurality of divided segments; and inputting the plurality of divided segments into a trained epilepsy analysis model.

[0168] In some embodiments of the present application, when the processor of the device executes the program code, it is also used to implement the following steps: inputting the multiple segmented segments into a trained epilepsy analysis model during seizure to determine whether the subject is in an epileptic seizure period.

[0169] In some embodiments of the present application, when the processor of the device executes the program code, it is also used to implement the following steps: inputting multiple segmented segments into a trained sleep period analysis model to determine the sleep period of the subject.

[0170] In some embodiments of the present application, the processor of the device is also used to implement the following steps when executing the program code: obtaining a monitoring video of the subject, and obtaining the human feature information and motion feature information of the subject from the monitoring video; inputting the EEG feature data, the human feature information, and the motion feature information into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model.

[0171] In some embodiments of the present application, the processor of the device is also used to implement the following steps when executing the program code: respectively extracting multiple frame images corresponding to the monitoring video; respectively detecting object key points corresponding to the test object and key point spatial coordinates corresponding to the object key points from the multiple frame images; the object key points include object facial key points and body key points; constructing human body feature information based on all key point spatial coordinates of the test object for the target object key points; performing human motion analysis on the human body feature information to obtain motion feature information of the test object.

[0172] In some embodiments of the present application, the processor of the device is also used to implement the following steps when executing the program code: taking a preset time point as the starting time, based on a preset time interval, dividing the EEG feature data, human body feature information, and motion feature information respectively to obtain multiple divided segments; and inputting the multiple divided segments into a trained epilepsy analysis model.

[0173] In some embodiments of the present application, the processor of the device is further used to implement the following steps when executing the program code: inputting multiple segmented segments into a trained interictal epilepsy analysis model to determine whether the subject is currently in an abnormal discharge state.

[0174] It should be noted that the above-mentioned medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0175] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, wherein readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to: electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0176] The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0177] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user computing device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0178] Exemplary Devices

[0179] After introducing the medium of the exemplary embodiment of the present application, next, reference is made to Fig.10 An epilepsy determination device according to an exemplary embodiment of the present application is described.

[0180] See also Fig.10 , Fig.10 FIG. 2 is a block diagram of a device for determining epilepsy according to an exemplary embodiment of the present application. Fig.10 As shown, an epilepsy determination device 1000 according to an exemplary embodiment of the present application includes: an EEG feature analysis unit 1010, an epilepsy analysis unit 1020, and an epilepsy state determination unit 1030, wherein:

[0181] The EEG characteristic analysis unit 1010 is used to obtain EEG characteristic data of the subject, and perform EEG characteristic analysis on the EEG characteristic data to obtain EEG characteristic analysis results;

[0182] An epilepsy analysis unit 1020, used for inputting the EEG feature data into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model;

[0183] The epilepsy state determination unit 1030 is used to determine the epilepsy state of the subject by combining the EEG feature analysis result and the epilepsy analysis result.

[0184] It can be seen that the implementation Fig.10 The device shown performs EEG feature analysis on EEG feature data to obtain EEG feature analysis results, inputs the EEG feature data into a trained epilepsy analysis model, obtains EEG analysis results through the epilepsy analysis model, and determines the epilepsy state of the subject by combining the EEG feature analysis results and the epilepsy analysis results. On the one hand, it avoids analyzing the EEG feature data by manual judgment by doctors, avoids human bias, and obtains EEG feature analysis results with higher accuracy; on the other hand, the EEG feature data is also input into a trained epilepsy analysis model, which improves the accuracy and efficiency of the epilepsy analysis results obtained by the epilepsy analysis model, thereby improving the accuracy and efficiency of the epilepsy state of the subject determined subsequently.

[0185] In one embodiment, based on the above scheme, the EEG feature analysis unit 1010 performs EEG feature analysis on the EEG feature data to obtain an EEG feature analysis result, including:

[0186] The target EEG characteristic data of the target monitoring channel are determined from the EEG characteristic data; the rhythm analysis is performed on the target EEG characteristic data to obtain the rhythm analysis result.

[0187] It can be seen that implementing this optional embodiment to determine the target EEG characteristic data of the target monitoring channel from the EEG characteristic data is helpful for subsequently obtaining targeted target EEG characteristic data.

[0188] In one embodiment, based on the above scheme, rhythm analysis is performed on the target EEG characteristic data, and the rhythm analysis results obtained include:

[0189] The first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data belonging to the alpha wave are determined from the first EEG characteristic data and the second EEG characteristic data; wherein the first EEG characteristic data corresponds to the first monitoring channel, and the second EEG characteristic data corresponds to the second monitoring channel; by analyzing the EEG change rules represented by the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data, the occipital area rhythm analysis result is obtained.

[0190] It can be seen that by implementing this optional embodiment, the EEG variation patterns represented by the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data are analyzed, human bias is avoided, and a highly accurate occipital rhythm analysis result can be obtained.

[0191] In one embodiment, based on the aforementioned scheme, the EEG feature analysis results include EEG functional connection analysis results; performing EEG feature analysis on the EEG feature data to obtain the EEG feature analysis results, including: performing correlation analysis on the EEG feature data corresponding to multiple monitoring channels to obtain a correlation matrix; determining a preset threshold for measuring the state of EEG functional connection, and comparing the numerical value in the correlation matrix with the preset threshold to obtain a numerical comparison result; and obtaining the EEG functional connection analysis results corresponding to multiple monitoring channels according to the numerical comparison results.

[0192] It can be seen that by implementing this optional embodiment, through the correlation analysis of the EEG feature data corresponding to multiple monitoring channels, the EEG connection analysis results representing whether the subject is in cognitive impairment can be obtained.

[0193] In one embodiment, based on the above scheme, the EEG feature analysis result includes an eye-opening inhibition analysis result; performing EEG feature analysis on the EEG feature data to obtain the EEG feature analysis result includes: determining the third EEG feature data of the subject being in a first eye change state and the fourth EEG feature data of the subject being in a second eye change state in the first EEG feature data, and determining the fifth EEG feature data of the subject being in the first eye change state and the sixth EEG feature data of the subject being in the second eye change state in the second EEG feature data; analyzing the EEG change rules represented by the third EEG feature data and the fourth EEG feature data, respectively, to obtain the first occipital region rhythm analysis result and the second occipital region rhythm analysis result, analyzing the EEG change rules represented by the fifth EEG feature data and the sixth EEG feature data, respectively, to obtain the third occipital region rhythm analysis result and the fourth occipital region rhythm analysis result; performing a difference comparison between the first occipital region rhythm analysis result and the second occipital region rhythm analysis result, and performing a difference comparison between the third occipital region rhythm analysis result and the fourth occipital region rhythm analysis result, so as to obtain the eye-opening inhibition analysis result according to the difference comparison result.

[0194] It can be seen that by implementing this optional embodiment, the current eye opening inhibition state of the subject can be obtained by differentially comparing the different results of occipital rhythm analysis under the first eye change state and the second eye change state, which provides theoretical support for the subsequent determination of the epileptic state of the subject.

[0195] In one embodiment, based on the above scheme, the epilepsy analysis unit 1020 further includes: taking a preset time point as a starting time, dividing the EEG feature data based on a preset time interval to obtain a plurality of divided segments; and inputting the plurality of divided segments into a trained epilepsy analysis model.

[0196] It can be seen that by implementing this optional embodiment, multiple divided segments are input into the epilepsy analysis model, and the obtained epilepsy analysis results correspond to the EEG feature data of a specific segment, which can better understand the characteristic changes caused by the EEG feature data on the subject.

[0197] In one embodiment, based on the aforementioned scheme, the epilepsy analysis unit 1020 inputs the EEG feature data into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model, including: inputting the multiple divided segments into a trained seizure epilepsy analysis model to determine whether the subject is in an epileptic seizure period.

[0198] It can be seen that by implementing this optional embodiment, it is possible to predict whether the subject is in an epileptic seizure period based on the EEG feature data and the seizure period telecommunication analysis model.

[0199] In one embodiment, based on the aforementioned scheme, the epilepsy analysis unit 1020 inputs the EEG feature data into a trained epilepsy analysis model to obtain epilepsy analysis results through the epilepsy analysis model, including: inputting multiple divided segments into a trained sleep period analysis model to determine the sleep period of the subject.

[0200] It can be seen that by implementing this optional embodiment, the sleep period of the subject can be predicted based on the EEG feature data and the sleep period analysis model.

[0201] In one embodiment, based on the aforementioned scheme, EEG feature data is input into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model, including: obtaining a monitoring video of the subject, and obtaining the human body feature information and motion feature information of the subject from the monitoring video; and inputting the EEG feature data, the human body feature information, and the motion feature information into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model.

[0202] It can be seen that by implementing this optional embodiment, the data input into the trained epilepsy analysis model includes, in addition to the EEG feature data, also human body feature information and motion feature information, which increases the accuracy of the final epilepsy analysis result.

[0203] In one embodiment, based on the aforementioned scheme, human feature information and motion feature information of the subject are obtained from the monitoring video, including: extracting multiple frame images corresponding to the monitoring video respectively; detecting object key points corresponding to the subject and key point spatial coordinates corresponding to the object key points from the multiple frame images; the object key points include object facial key points and body key points; constructing human feature information based on all key point spatial coordinates of the subject for the target object key points; performing human motion analysis on the human feature information to obtain the motion feature information of the subject.

[0204] It can be seen that by implementing this optional embodiment, human feature information reflecting key points of human objects and motion feature information reflecting human motions can be obtained by monitoring the video, and then the human feature information and motion feature information can be input into the trained epilepsy analysis model to improve the accuracy of the epilepsy analysis results.

[0205] In one embodiment, based on the aforementioned scheme, EEG feature data, human body feature information and motion feature information are input into a trained epilepsy analysis model, including: taking a preset time point as the starting time, and based on a preset time interval, dividing the EEG feature data, human body feature information and motion feature information respectively to obtain multiple divided segments; and inputting the multiple divided segments into the trained epilepsy analysis model.

[0206] It can be seen that by implementing this optional embodiment, multiple divided segments are input into the epilepsy analysis model, and the obtained epilepsy analysis results correspond to a specific EEG feature data, a segment of human feature information, and a segment of motion feature information, which can better understand the feature changes produced by the subject when obtaining the epilepsy analysis results.

[0207] In one embodiment, based on the aforementioned scheme, the epilepsy analysis model includes an interictal epilepsy analysis model; the EEG feature data is input into the trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model, including: inputting multiple divided segments into the trained interictal epilepsy analysis model to determine whether the subject is currently in an abnormal discharge state.

[0208] It can be seen that by implementing this optional embodiment, the abnormal EEG discharge state of the subject can be predicted based on the EEG characteristic data and the interictal epilepsy analysis model.

[0209] It should be noted that although several modules or units of the epilepsy determination device are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units.

[0210] Exemplary Electronic Devices

[0211] After introducing the method, medium, and apparatus according to the exemplary embodiment of the present application, next, an electronic device according to another exemplary embodiment of the present application is introduced.

[0212] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0213] Refer to the following Fig.11 1100 according to this embodiment of the present invention will be described. Fig.11 The electronic device 1100 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0214] like Fig.11 As shown, the electronic device 1100 is in the form of a general computing device. The components of the electronic device 1100 may include but are not limited to: the at least one processing unit 1110, the at least one storage unit 1120, a bus 1130 connecting different system components (including the storage unit 1120 and the processing unit 1110), and a display unit 1140.

[0215] The storage unit stores program codes, which can be executed by the processing unit 1110, so that the processing unit 1110 executes the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0216] The storage unit 1120 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 1121 and / or a cache memory unit 1122 , and may further include a read-only memory unit (ROM) 1123 .

[0217] The storage unit 1120 may also include a program / utility 1124 having a set (at least one) of program modules 1125, such program modules 1125 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include the reality of a network environment.

[0218] The bus 1130 may include a data bus, an address bus, and a control bus.

[0219] The electronic device 1100 may also communicate with one or more external devices 1170 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), and such communication may be performed via an input / output (I / O) interface 1150. In addition, the electronic device 1100 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 1160. As shown, the network adapter 1160 communicates with other modules of the electronic device 1100 via a bus 1130. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0220] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0221] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible embodiments, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0222] Although the spirit and principle of the present application have been described with reference to several specific embodiments, it should be understood that the present application is not limited to the specific embodiments of the invention, and the division of various aspects does not mean that the features in these aspects cannot be combined to benefit, and such division is only for the convenience of expression. The present application is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the attached claims.

Claims

1. A method for determining epilepsy, characterized in that: The method comprises: Acquire EEG characteristic data of the subject, and perform EEG characteristic analysis on the EEG characteristic data to obtain EEG characteristic analysis results; the EEG characteristic data includes EEG characteristic data corresponding to multiple monitoring channels respectively; the EEG characteristic analysis results include occipital rhythm analysis results, eye opening inhibition analysis results, and EEG functional connection analysis results; Acquire a monitoring video of the subject, and obtain human body feature information and motion feature information of the subject from the monitoring video; Inputting the EEG feature data, the human body feature information and the motion feature information into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model; the epilepsy analysis model includes an epilepsy analysis model during the attack period, an analysis model during the sleep period and an epilepsy analysis model during the interictal period; Determine the epileptic state of the subject by combining the EEG feature analysis result and the epilepsy analysis result; The performing of EEG feature analysis on the EEG feature data to obtain an EEG feature analysis result includes: Determine the target EEG characteristic data of the target monitoring channel from the EEG characteristic data; the target monitoring channel includes a first monitoring channel and a second monitoring channel corresponding to the occipital area; the first EEG characteristic data corresponds to the first monitoring channel, and the second EEG characteristic data corresponds to the second monitoring channel; determine the third EEG characteristic data of the subject being in a first eye change state and the fourth EEG characteristic data of the subject being in a second eye change state from the first EEG characteristic data, and determine the fifth EEG characteristic data of the subject being in the first eye change state and the sixth EEG characteristic data of the subject being in the second eye change state from the second EEG characteristic data. characteristic data; analyzing the EEG change rules represented by the third EEG characteristic data and the fourth EEG characteristic data, respectively, to obtain the first occipital area rhythm analysis result and the second occipital area rhythm analysis result, analyzing the EEG change rules represented by the fifth EEG characteristic data and the sixth EEG characteristic data, respectively, to obtain the third occipital area rhythm analysis result and the fourth occipital area rhythm analysis result; performing a difference comparison on the first occipital area rhythm analysis result and the second occipital area rhythm analysis result, and performing a difference comparison on the third occipital area rhythm analysis result and the fourth occipital area rhythm analysis result, so as to obtain the eye opening inhibition analysis result according to the difference comparison result; Perform correlation analysis on the EEG feature data corresponding to multiple monitoring channels to obtain a correlation matrix; determine a preset threshold for measuring the EEG functional connection state, compare the numerical value in the correlation matrix with the preset threshold to obtain a numerical comparison result; and obtain the EEG functional connection analysis results corresponding to the multiple monitoring channels according to the numerical comparison result.

2. The method according to claim 1, characterized in that The performing EEG feature analysis on the EEG feature data to obtain an EEG feature analysis result also includes: Determining first alpha wave electroencephalogram characteristic data and second alpha wave electroencephalogram characteristic data belonging to alpha waves from the first electroencephalogram characteristic data and the second electroencephalogram characteristic data; wherein the first electroencephalogram characteristic data corresponds to the first monitoring channel, and the second electroencephalogram characteristic data corresponds to the second monitoring channel; The occipital region rhythm analysis result is obtained by analyzing the EEG variation rules represented by the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data.

3. The method according to claim 1, characterized in that The method further comprises: Taking a preset time point as a starting time, dividing the EEG feature data based on a preset time interval to obtain a plurality of divided segments; The multiple segmented segments are input into the trained epilepsy analysis model.

4. The method according to claim 3, characterized in that The step of inputting the EEG feature data, the human body feature information, and the motion feature information into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model includes: The multiple segmented segments are input into the trained epilepsy analysis model to determine whether the subject is in an epileptic seizure period.

5. The method according to claim 3, characterized in that: The step of inputting the EEG feature data, the human body feature information, and the motion feature information into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model includes: The multiple divided segments are input into the trained sleep stage analysis model to determine the sleep stage of the subject.

6. The method according to claim 1, characterized in that The obtaining of the human body feature information and the motion feature information of the subject from the monitoring video includes: Extracting a plurality of frame images corresponding to the monitoring video respectively; Detecting object key points corresponding to the detected object and key point spatial coordinates corresponding to the object key points from the multiple frame images respectively; the object key points include object facial key points and body key points; Constructing human body feature information according to the spatial coordinates of all key points of the tested object for the key points of the target object; The human body feature information is subjected to human body motion analysis to obtain the motion feature information of the subject.

7. The method according to claim 1, characterized in that The step of inputting the EEG feature data, the human body feature information, and the motion feature information into a trained epilepsy analysis model includes: Taking a preset time point as a starting time, and based on a preset time interval, dividing the EEG feature data, the human body feature information, and the motion feature information respectively to obtain a plurality of divided segments; The multiple segmented segments are input into the trained epilepsy analysis model.

8. The method according to claim 7, characterized in that The step of inputting the EEG feature data, the human body feature information, and the motion feature information into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model includes: The multiple segmented segments are input into the trained interictal epilepsy analysis model to determine whether the subject is currently in an abnormal discharge state.

9. An epilepsy determination device, characterized in that: The device comprises: An EEG characteristic analysis unit is used to obtain EEG characteristic data of the subject, and perform EEG characteristic analysis on the EEG characteristic data to obtain EEG characteristic analysis results; the EEG characteristic data includes EEG characteristic data corresponding to multiple monitoring channels respectively; the EEG characteristic analysis results include occipital rhythm analysis results, eye opening inhibition analysis results, and EEG functional connection analysis results; An epilepsy analysis unit is used to obtain a monitoring video of the subject, and obtain human characteristic information and motion characteristic information of the subject from the monitoring video; input the EEG characteristic data, the human characteristic information and the motion characteristic information into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model; the epilepsy analysis model includes an epilepsy analysis model during the attack period, an analysis model during the sleep period, and an epilepsy analysis model during the interictal period; An epilepsy state determination unit, configured to determine the epilepsy state of the subject in combination with the EEG feature analysis result and the epilepsy analysis result; The performing of EEG feature analysis on the EEG feature data to obtain an EEG feature analysis result includes: Determine the target EEG characteristic data of the target monitoring channel from the EEG characteristic data; the target monitoring channel includes a first monitoring channel and a second monitoring channel corresponding to the occipital area; the first EEG characteristic data corresponds to the first monitoring channel, and the second EEG characteristic data corresponds to the second monitoring channel; determine the third EEG characteristic data of the subject being in a first eye change state and the fourth EEG characteristic data of the subject being in a second eye change state from the first EEG characteristic data, and determine the fifth EEG characteristic data of the subject being in the first eye change state and the sixth EEG characteristic data of the subject being in the second eye change state from the second EEG characteristic data. characteristic data; analyzing the EEG change rules represented by the third EEG characteristic data and the fourth EEG characteristic data, respectively, to obtain the first occipital area rhythm analysis result and the second occipital area rhythm analysis result, analyzing the EEG change rules represented by the fifth EEG characteristic data and the sixth EEG characteristic data, respectively, to obtain the third occipital area rhythm analysis result and the fourth occipital area rhythm analysis result; performing a difference comparison on the first occipital area rhythm analysis result and the second occipital area rhythm analysis result, and performing a difference comparison on the third occipital area rhythm analysis result and the fourth occipital area rhythm analysis result, so as to obtain the eye opening inhibition analysis result according to the difference comparison result; Perform correlation analysis on the EEG feature data corresponding to multiple monitoring channels to obtain a correlation matrix; determine a preset threshold for measuring the EEG functional connection state, compare the numerical value in the correlation matrix with the preset threshold to obtain a numerical comparison result; and obtain the EEG functional connection analysis results corresponding to the multiple monitoring channels according to the numerical comparison result.

10. The device according to claim 9, characterized in that The performing EEG feature analysis on the EEG feature data to obtain an EEG feature analysis result also includes: Determining first alpha wave electroencephalogram characteristic data and second alpha wave electroencephalogram characteristic data belonging to alpha waves from the first electroencephalogram characteristic data and the second electroencephalogram characteristic data; wherein the first electroencephalogram characteristic data corresponds to the first monitoring channel, and the second electroencephalogram characteristic data corresponds to the second monitoring channel; The occipital region rhythm analysis result is obtained by analyzing the EEG variation rules represented by the first alpha wave EEG characteristic data and the second alpha wave EEG characteristic data.

11. The device according to claim 9, characterized in that The device also includes: Taking a preset time point as a starting time, dividing the EEG feature data based on a preset time interval to obtain a plurality of divided segments; The multiple segmented segments are input into the trained epilepsy analysis model.

12. The device according to claim 11, characterized in that The step of inputting the EEG feature data, the human body feature information, and the motion feature information into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model includes: The multiple segmented segments are input into the trained epilepsy analysis model to determine whether the subject is in an epileptic seizure period.

13. The device according to claim 11, characterized in that The step of inputting the EEG feature data, the human body feature information, and the motion feature information into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model includes: The multiple divided segments are input into the trained sleep stage analysis model to determine the sleep stage of the subject.

14. The device according to claim 9, characterized in that The obtaining of the human body feature information and the motion feature information of the subject from the monitoring video includes: Extracting a plurality of frame images corresponding to the monitoring video respectively; Detecting object key points corresponding to the detected object and key point spatial coordinates corresponding to the object key points from the multiple frame images respectively; the object key points include object facial key points and body key points; Constructing human body feature information according to the spatial coordinates of all key points of the tested object for the key points of the target object; The human body feature information is subjected to human body motion analysis to obtain the motion feature information of the subject.

15. The device according to claim 9, characterized in that The step of inputting the EEG feature data, the human body feature information, and the motion feature information into a trained epilepsy analysis model includes: Taking a preset time point as a starting time, and based on a preset time interval, dividing the EEG feature data, the human body feature information, and the motion feature information respectively to obtain a plurality of divided segments; The multiple segmented segments are input into the trained epilepsy analysis model.

16. The device according to claim 15, characterized in that The step of inputting the EEG feature data, the human body feature information, and the motion feature information into a trained epilepsy analysis model to obtain an epilepsy analysis result through the epilepsy analysis model includes: The multiple segmented segments are input into the trained interictal epilepsy analysis model to determine whether the subject is currently in an abnormal discharge state.

17. An electronic device, characterized in that: include: processor; A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 8 by executing the executable instructions.

18. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images