Epilepsy prediction system based on synchronously acquired electroencephalogram-electrogastrogram signals

Abstract

The invention relates to the field of disease prediction, in particular to an epilepsy prediction system based on synchronously acquired electroencephalogram-gastric electrical signals, comprising: a data acquisition module for acquiring data including electroencephalogram data and gastrointestinal electrical data; the first analysis module is used for obtaining an average electrode inconsistency index of the first channel and the second channel based on a first model according to the time sequence data; and the prediction module is used for comparing the average electrode inconsistency index of the subject with a preset evaluation threshold value so as to predict an epileptic. The system provided by the invention can more accurately and efficiently distinguish epilepsy patients from healthy people, and can be used as an auxiliary diagnosis tool to be applied to primary screening of epilepsy of relatively large people (such as communities and physical examination centers).

Description

Technical Field

[0001] The present invention relates to the field of disease prediction, and in particular to an epilepsy prediction system based on synchronously collected electroencephalogram (EEG) and electrogastric signal. Background Art

[0002] Epilepsy is a chronic neurological disease that affects approximately 70 million people worldwide. It is listed by the World Health Organization as one of the five major neuropsychiatric diseases that require global prevention and treatment, and is also a key public relations area of ​​the Global Brain Science Program. Epileptic seizures are caused by abnormal discharges of a group of brain cells. Different parts of the brain may become the site of abnormal discharges. They are characterized by repeated attacks, sudden onset and cessation, and difficult to capture EEG during the attack. During an epileptic seizure, a part of the body or the entire body often experiences brief involuntary convulsions, sometimes accompanied by loss of consciousness and urinary and fecal incontinence. Seizures range from very brief loss of consciousness or muscle reflexes to severe and persistent convulsions. The frequency of seizures can also vary, ranging from less than once a year to several times a day.

[0003] The current basis for the diagnosis of epilepsy includes clinical seizures and epileptiform discharges on the electroencephalogram. On the one hand, the assessment of EEG abnormalities may be subjective and not very sensitive. For example, in conventional EEG recordings, only 29%-55% of patients have epileptiform discharges (such as spikes, sharp waves, spike-slow complexes, and sharp-slow complexes, etc.). On the other hand, a large proportion of epilepsy patients have epileptic seizures that last for a very short time, and even if they are subjected to an EEG examination, it is difficult to capture their abnormal discharges. Therefore, the current existing technology based on EEG can only detect epileptiform discharges in subjects, which is suitable for the diagnosis of epileptic seizures, but difficult to use for screening of epilepsy.

[0004] It is reported that up to 70% of epilepsy patients can achieve zero seizures through the proper use of anti-epileptic drugs. It can be seen that the "early detection and early treatment" of epilepsy has great practical significance. However, there are at least 10 million epilepsy patients in my country, but only about one-third of them receive correct and adequate treatment. The Global Burden of Disease Study estimates that the burden of epilepsy in my country is 1.6 million disability-adjusted life years (DALYs), accounting for 12% of the world and 95% of East Asia. The reasons for the above results may be the long-term misunderstanding, fear and prejudice of epilepsy patients about epilepsy, which has led to a considerable number of people in my country being unwilling to go to medical institutions for further examination even if they have epileptic seizures; and the existing diagnosis of epilepsy is based on the detection of epileptiform discharges of subjects, which leads to the omission of epilepsy patients who do not have epileptiform discharges during EEG testing by existing technologies. Another part of patients may suffer from non-epileptic paroxysmal diseases (such as neurotic seizures, transient ischemic attacks), but they often worry that they have epilepsy, which is difficult to distinguish from epilepsy only through clinical manifestations. Correct diagnosis is a prerequisite for effective treatment, but existing technology makes it difficult to distinguish between non-epileptic patients and epileptic patients based solely on the patient's oral description and electroencephalogram (EEG) in which no abnormal discharges are observed, especially in larger populations such as communities and physical examination centers.

[0005] Chinese patent application CN117481666A discloses a method for coupling gastric EEG signals in a resting state, which reflects the degree of bidirectional influence between the original gastric EEG signals and the original EEG signals by extracting the phase-amplitude coupling, phase-phase coupling and amplitude-amplitude coupling indicators in different frequency bands, as well as the transfer entropy. However, its application scenario is limited to regulating gastric function, and it is difficult to diagnose diseases. Summary of the invention

[0006] The present invention provides an epilepsy prediction system based on synchronously collected EEG-Gastrointestinal electrical signals, which is characterized by comprising:

[0007] A data acquisition module, used to acquire data, the data including EEG data and gastrointestinal electrical data, the EEG data being acquired from the first channel, and the gastrointestinal electrical data being acquired from the second channel; the data including sample data from a sample population and subject data from a subject;

[0008] A data preprocessing module, used for preprocessing the data to obtain corresponding time series data;

[0009] A first analysis module is used to obtain an average electrode inconsistency index of the first channel and the second channel based on the time series data and a first model; the first model includes: Among them, JSD represents the JS divergence scoring function, t represents time, ait represents the time series data of the corresponding channels of the first channel and the second channel recorded at the time point t seconds of the subject, m represents the total number of channels, n represents the total duration of the time series data of the corresponding channels; ICI represents the inconsistency index of the corresponding channel;

[0010] A prediction module, used for comparing the average electrode inconsistency index of the subject with a preset evaluation threshold, and when the average electrode inconsistency index of the subject is not lower than the preset evaluation threshold, the subject is predicted to be an epileptic patient;

[0011] Among them, the first channel includes F3, C4, P4, O2, T7, FC1, CP1, CP6, TP9, TP10, F2, C1, C2, P2, FC3, FC4, CP3, CP4, PO4, P6, PO8, CPz and POz; the second channel includes the gastric body, lesser curvature of the stomach, gastric antrum, ascending colon, transverse colon, descending colon and rectal passage.

[0012] In some embodiments, the system further includes a second analysis module for converting the time series data into probability density distribution data.

[0013] In some embodiments, the second analysis module is further used to obtain an inconsistency index of a corresponding channel based on a second model according to the probability density distribution data, and the second model includes: ; Where ICI represents the inconsistency index function, D KL represents the KL divergence function, t represents time, a it represents the time series data of the corresponding channel recorded at time point t seconds of the subject, b it represents the time series data of the corresponding channel recorded at time point t seconds for healthy people, n is the total duration of the time series data of the corresponding channel, P(a it ) represents the sample distribution, Q(b it ) represents the reference distribution.

[0014] In some embodiments, the system further includes a database for storing data obtained by the data acquisition module, the data preprocessing module, the first analysis module, the second analysis module and the prediction module, and for generating a corresponding sample data set.

[0015] In some embodiments, the system also includes an evaluation threshold setting module, which randomly obtains the average electrode inconsistency index of 50-70% of the epilepsy patient samples in the sample data set and calculates the critical value of epilepsy occurrence, and sets the average electrode inconsistency index corresponding to the minimum critical value as the evaluation threshold.

[0016] In some embodiments, the EEG data and the gastrointestinal electrical data are collected synchronously.

[0017] In some embodiments, the collection time of the EEG data and the gastrointestinal electrical data is at least 5 minutes.

[0018] In some embodiments, the preprocessing includes filtering the EEG data to filter out EEG signals below 1 Hz and above 30 Hz, and normalizing the gastrointestinal electrical data and the filtered EEG data to obtain the time series data.

[0019] In some embodiments, the data is collected before or after a meal.

[0020] In some embodiments, the data is collected from a subject in a normal state. As used herein, "normal state" refers to normal brain electrical activity of the subject, i.e., no detectable epileptiform discharges in the subject's electroencephalogram. In some embodiments, when the subject is a healthy population (i.e., a non-epileptic patient), the normal state is any state of the subject. In some embodiments, when the subject is an epileptic patient, the normal state is during a non-epileptic seizure (or between epileptic seizures) of the subject.

[0021] In some embodiments, the subject is an epileptic patient.

[0022] In some embodiments, the epilepsy patient has focal or generalized epilepsy.

[0023] Compared with the prior art, the beneficial effects of the present invention include at least the following aspects:

[0024] The present invention provides an epilepsy prediction system based on synchronously collected EEG-Gastrointestinal electrical signals. The prior art method for processing EEG signals and Gastrointestinal electrical signals is to perform phase-amplitude coupling, phase-phase coupling and amplitude-amplitude coupling on EEG signals and Gastrointestinal electrical signals in different frequency bands. There is no report on the use of EEG signals and Gastrointestinal electrical signals for epilepsy prediction and diagnosis in the prior art.

[0025] Different from the conventional idea of ​​extracting frequency bands from EEG signals, the present invention achieves accurate prediction of epilepsy by collecting EEG data and gastrointestinal electrical data corresponding to streamlined EEG channels and gastrointestinal electrical channels (i.e., the first channel and the second channel of the present invention) and combining them with processing methods such as inconsistency index. It should be emphasized that, on the one hand, the present invention breaks through the general idea of ​​simultaneously selecting channels with higher correlation in EEG channels and gastrointestinal electrical channels. By streamlining the channels with higher correlation with gastrointestinal electrical channels in EEG channels and replacing them with specific gastrointestinal electrical channels, the channels are streamlined, which reduces the actual operation difficulty while improving the accuracy and sensitivity of diagnosing epilepsy. On the other hand, the present invention does not detect epileptic seizures in epileptic patients by detecting whether abnormal discharges appear in the electroencephalogram, but diagnoses whether the subject is an epileptic patient based on the EEG (and gastric electricity) of the subject in a normal state.

[0026] In large-scale screening, even experienced clinicians can hardly judge whether a subject is an epilepsy patient based on the subject's verbal description of the "epileptic" seizure symptoms in a time-constrained and lacking diagnostic basis. The accuracy and sensitivity of the prediction model obtained based on the streamlined channels and specific algorithms of the present invention are both at a high level, and can capture and amplify the differences between epilepsy patients and healthy people who have almost the same EEG activities under conventional methods (such as naked eye observation), and then distinguish them. It is suitable for assisting the diagnosis of subjects who may not have abnormal discharges in the EEG in large-scale screening (such as healthy people who have symptoms similar to epilepsy but are not epilepsy patients, and epilepsy patients with infrequent epileptic seizures).

[0027] Based on this, the system provided by the present invention not only requires a short data collection time, but also can more accurately and efficiently distinguish between epilepsy patients and healthy people. It can be used as an auxiliary diagnostic tool to conduct initial screening of epilepsy patients in a larger population (such as communities, physical examination centers). BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale. Obviously, the drawings described below are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without paying creative labor.

[0029] Figure 1 It is a simplified schematic diagram of the positions of the first channel and the second channel of the present invention;

[0030] Figure 2 Result graphs showing the performance of different prediction models obtained for the present invention;

[0031] Figure 3 A flow chart of a method for analyzing synchronously collected EEG-Gastrointestinal electrical signals provided by the present invention;

[0032] Figure 4 A schematic diagram of an epilepsy prediction system based on synchronously collected EEG-gastrointestinal electrical signals provided by the present invention.

[0033] 100 is a prediction system, 102 is a data acquisition module, 104 is a data preprocessing module, 106 is a first analysis module, 108 is a second analysis module, 110 is a prediction module, 112 is a database, and 114 is an evaluation threshold setting module. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0035] Herein, suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present invention, and have no specific meanings by themselves. Therefore, "module", "component" or "unit" can be used mixedly.

[0036] In this document, the directions or positional relationships indicated by the terms "upper", "lower", "inner", "outer", "front", "rear", "one end", "the other end", etc. are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific direction, be constructed and operate in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0037] In this document, unless otherwise clearly specified and limited, the terms "installed", "provided with", "connected", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0038] Herein "and / or" includes any and all combinations of one or more of the associated listed items.

[0039] Herein, "plurality" means two or more than two, ie, it includes two, three, four, five, etc.

[0040] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0041] As used in this specification, the term "about" typically means + / - 5% of the stated value, more typically + / - 4% of the stated value, more typically + / - 3% of the stated value, more typically + / - 2% of the stated value, even more typically + / - 1% of the stated value, and even more typically + / - 0.5% of the stated value.

[0042] In this specification, some embodiments may be disclosed in a format of being in a range. It should be understood that this description of "being in a range" is only for convenience and brevity, and should not be interpreted as a rigid limitation on the disclosed range. Therefore, the description of the range should be considered to have specifically disclosed all possible sub-ranges and independent numerical values ​​within this range. For example, the description of the range 1-6 should be considered to have specifically disclosed sub-ranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6, etc., as well as individual numbers within this range, such as 1, 2, 3, 4, 5 and 6. Regardless of the breadth of the range, the above rules apply.

[0043] Embodiment 1

[0044] 1.1 Dataset

[0045] Subjects: This example included 102 patients with epilepsy of focal or generalized origin (57 males, aged 33.82±12.65 years) and 46 healthy controls (26 males, aged 31.00±8.45 years).

[0046] 1.1.1 EEG recording

[0047] Subjects were seated in a quiet room and prepared for the test. Five-minute resting-state EEG data were obtained from all subjects using 64 Ag / AgCl electrodes (Brain Products, Munich, Germany) placed behind a 10 / 20 system with an impedance <10 kΩ. EEG data were amplified and collected using an actiCAmp amplifier (BrainVision System Amplifier; Brain Products, Munich, Germany) at a sampling rate of 1000 Hz. Subjects were instructed to fix their gaze at the center of the screen and to avoid body movements as much as possible during the EEG recording.

[0048] 1.1.2 Gastrointestinal electrical signal (EGG) recording

[0049] Gastrointestinal electromyographic activity was measured using an 8-channel gastrointestinal electromyograph (XDJ-S8, Hefei Kaili Co., Hefei, China). Subjects were told to avoid alcohol and spicy or irritating foods for at least three days and to fast for more than 6 hours before the examination. Measurements were performed in the supine position. Four gastric electrodes (reflecting the gastric body, gastric antrum, lesser curvature of the stomach, and greater curvature of the stomach) and four intestinal electrodes (reflecting the ascending colon, transverse colon, descending colon, and rectum) were placed on the abdominal skin (Hanjie Co., Shanghai, China). The placement sites of the above electrodes are as follows: gastric body: three to five centimeters to the left and one centimeter above the midpoint of the line connecting the xiphoid process and the umbilicus; gastric antrum: two to four centimeters to the right of the midpoint of the line connecting the xiphoid process and the umbilicus; lesser curvature of the stomach: 1 / 2 of the midpoint of the line connecting the xiphoid process and the umbilicus upward; greater curvature of the stomach: 1 / 2 of the midpoint of the line connecting the xiphoid process and the umbilicus downward. Ascending colon: 2 to 4 cm to the right at the level of the navel; transverse colon: one centimeter below the navel; descending colon: 2 to 4 cm to the left at the level of the navel; rectum: under the coccyx at the back. The ground electrode was placed on the inner ankle of the right calf, and the reference electrode was placed on the inner wrist of the right hand. The subjects were told to remain quiet during the test and not to move or talk. In addition, after 6 minutes of EGG recording before the meal, a mealtime functional stress test was performed with a meal of about 200 kcal.

[0050] 1.2 Prediction algorithm based on Jensen–Shannon divergence (JSD)

[0051] 1.2.1 Data Preprocessing

[0052] The dataset was divided into training and testing sets in a ratio of 7:3. For independent training, only EEG or EGG signals were used. For EEG-EGG multimodal fusion training, both EEG and EGG signals were used.

[0053] First, the raw EEG signal was filtered using EEGLAB in MATLAB to maintain data integrity by removing signals below 1 Hz and above 30 Hz. Second, the filtered EEG data and the raw EGG signal were normalized. The preprocessed EEG time series or the feature matrix of the preprocessed EGG time series is shown below.

[0054]

[0055] Where m and n represent the dimensions of the feature matrix of the EEG signal or EGG signal respectively. m is the total number of electrodes, so the i-th row represents the number of electrodes e i The records are recorded at each second. n is the total duration of the EEG time series signal or EGG time series signal, that is, the entire EEG data or EGG data contains n seconds, so the tth column represents the EEG data or EGG data measured at each electrode at the time point t seconds. Therefore, a it is the electrode e recorded at time t seconds i EEG signal or EGG signal.

[0056] 1.2.2 Convert the preprocessed EEG time series or preprocessed EGG time series into probability density distribution data

[0057] The data of each electrode is converted into probability density distribution data. In the training set, the time series data of each electrode is used. it To fit the sample distribution P(a it ), where the mean value u1 i and standard deviation σ1 i In addition, for the healthy control data in the training set, the time series data b of each electrode is it Fitting to the reference distribution Q(b it ), where the mean value u2 i and standard deviation σ2 i As a reference feature for differentiation.

[0058]

[0059] Among them, P(a it ) represents the sample distribution, a it Represents the time series data of each electrode of the sample, u1 i represents the mean of the sample, σ1 i Represents the standard deviation of the sample.

[0060]

[0061] Among them, Q(b it ) represents the reference distribution, b itRepresents the time series data of each electrode of the reference, u2 i represents the mean of the reference, σ2 i represents the standard deviation of the reference.

[0062] When the difference between the sample feature and the reference feature is small, it means that there is no substantial difference between the sample distribution and the reference distribution, indicating the absence of epilepsy. Conversely, when the difference is quite large, it means that there is a significant difference between the sample distribution and the reference distribution, indicating the presence of epilepsy.

[0063] 1.2.3 Constructing inconsistency indicators based on JSD

[0064] The JS divergence was used to quantify the deviation of the sample distribution from the reference distribution to measure the difference between different states (i.e., epilepsy and healthy controls); the inconsistency index (ICI) was calculated for each electrode to represent the difference between time points.

[0065]

[0066] Among them, D KL represents the KL divergence function, P(a it ) represents the sample distribution, Q(b it ) represents the reference distribution, a it represents the time series data of the corresponding channel of the sample recorded at time point t seconds, b it Represents the time series data of the corresponding channel of the reference recorded at time point t seconds, t represents time, and T represents total time.

[0067]

[0068] ICI represents the inconsistency index function, P(a it ) represents the sample distribution, Q(b it ) represents the reference distribution, a it represents the time series data of the corresponding channel of the sample recorded at time point t seconds, b it represents the time series data of the corresponding channel of the reference recorded at the time point t seconds, t represents the time, and n is the total duration of the time series data of the corresponding channel.

[0069] By calculating the ICI, the fluctuations caused by the reference distribution at all time points are quantified. The average ICI score for each electrode can be used as a quantitative measure to assess the degree of distribution difference over time. When the average ICI score is small, it indicates that there is no substantial difference between the sample distribution of the electrode and the reference distribution of the electrode. Conversely, when the average ICI score is large, it indicates that there is a significant difference between the sample distribution of the electrode and the reference distribution of the electrode.

[0070] 1.2.4 Identification of DNB Electrode

[0071] Based on the DNB (Dynamic Network Biomarker) theory, the average ICI score for each electrode is calculated by assuming that a set of known molecules signals the pre-disease state of complex diseases before a significant transition. Subsequently, the above scores are ranked according to the relative importance of key moments. The fluctuations caused by the reference distribution between each electrode at all time points are obtained according to the above equation, and then the ICI score of each electrode is ranked.

[0072] In this embodiment, the selection of DNB electrodes is divided into two different strategies. For EEG training alone, the electrodes ranked in the top 50% according to the highest average score are classified as DNB electrodes.

[0073] For EEG-EGG multimodal fusion training, a total of 78 channels (62 EEG channels and 16 EGG channels) were included. First, the top 30 channels with the highest average scores for each individual were selected. Then, if a channel appeared in more than half of the individuals in the training set, it was used as a DNB electrode. Because different electrodes may be associated with different areas of the brain or stomach, a higher score for a specific electrode in the entire array indicates that it is significantly related to epileptic activity.

[0074] 1.2.5 Calculating JSD of Global Time Series

[0075] The average electrode inconsistency index of the global time series is defined as follows:

[0076]

[0077] Among them, JSD represents the JS divergence scoring function, t represents time, a it represents the time series data of the corresponding channel recorded at the time point t seconds, m represents the total number of channels, n represents the total duration of the time series data of the corresponding channel; ICI represents the inconsistency index of the corresponding channel.

[0078] The JSD score is used to quantify the distribution differences between all electrodes, which helps to identify any significant deviations between the distributions. Higher scores indicate significant differences between the distributions, and when this difference is exceeded, it indicates that the difference has escalated to a critical level, thereby predicting epilepsy. In order to find the appropriate threshold level for each patient, the following training scenario can be used: 70% of the epilepsy data is used as training data to obtain the threshold. For each epilepsy case in the training dataset, based on the JSD score, the critical value in the DNB theory for each attack can be obtained, and the minimum of these critical values ​​is used as the threshold. When the score at a certain time point exceeds the threshold, the subject is diagnosed with epilepsy.

[0079] 1.3 Correlation analysis between EEG channels and EGG channels

[0080] The probability distribution of each channel was estimated by analyzing the 62-channel EEG data and 16-channel EGG data of each individual according to the following equation:

[0081]

[0082] The density function P(a) obtained using EEG and EGG channels it ) and P(a it ) to calculate the P value. The correlation between EEG and EGG channels was determined by comparing the size of their P values. A P value less than 0.05 indicates that there is no significant difference between the two, thus supporting the hypothesis that there is a relationship between them. To identify the EEG channels with the strongest correlation with the EGG channels, the first three EEG channels with the least statistical deviation from the distribution of the 16 EGG channels in each sample were selected.

[0083] Embodiment 2

[0084] It should be noted that, in the present invention, the selection of DNB electrodes is performed in two different ways. For individual EEG training, the top 50% of electrodes with the highest average ICI scores are selected as DNB electrodes based on the total number of electrodes used. For EEG-EGG multimodal fusion training, the top 30 channels with the highest average ICI scores for each individual in the training set are selected. If a channel appears in more than half of the training sets, it is designated as a common DNB electrode for predicting epilepsy. The results are shown in Figure 2. Figure 1 As shown, the 30 channels obtained by the present invention include: 23 EEG channels (first channel): F3, C4, P4, O2, T7, FC1, CP1, CP6, TP9, TP10, F2, C1, C2, P2, FC3, FC4, CP3, CP4, PO4, P6, PO8, CPz and POz; 7 gastrointestinal channels (second channel): gastric body channel (i.e., electrode 1), lesser curvature of stomach channel (i.e., electrode 2), gastric antrum (i.e., electrode 4), ascending colon channel (i.e., electrode 5), transverse colon channel (i.e., electrode 6), descending colon channel (i.e., electrode 7) and rectal channel (i.e., electrode 8).

[0085] Figure 2 In the above, EEG represents a prediction model obtained by training with data collected from 62 EEG channels using the method of the present invention; EEG *represents a prediction model trained by using the method of the present invention and data collected from the top 50% of electrodes with the highest average ICI scores in 62 EEG channels; EEG+EGG represents a prediction model trained by using the method of the present invention and data collected from 78 channels (i.e., 62 EEG channels and 16 EGG channels); EEG+EGG * It represents a prediction model obtained by training with the data collected from the first channel and the second channel using the method of the present invention.

[0086] like Figure 2 As shown, the prediction model obtained by processing EEG or EEG+EGG data using the method of the present invention has shown good prediction ability, but it needs to collect and calculate more data, and the accuracy is difficult to reach 95%. The prediction model constructed based on the electrodes obtained by the present invention not only requires a reduced number of electrodes to be placed, but also improves the performance of predicting epilepsy, and 98.92% accuracy and 98.82% sensitivity are observed.

[0087] Correlation analysis between EEG channels and EGG channels.

[0088] This example further explores whether there is a certain correlation between different EEG channels and EGG channels in predicting epilepsy through probability distribution. Specifically, this example analyzes the probability distribution of 62 EEG channels and 16 EGG channels for each subject. In 148 samples, the frequency of occurrence of 62 EEG channels is statistically similar to that of 16 EGG channels, and then this example extracts the top three EEG channels related to each EGG channel in the subject, which are defined as key related factors for specific EGG channels.

[0089] The distribution of all gastrointestinal electricity and EEG channels was compared for similarity, and the number of occurrences of eight gastrointestinal electricity leads that had no significant difference in distribution with the EEG channels in 148 subjects was calculated. The greater the number of occurrences, the higher the correlation between the EEG leads and gastrointestinal electricity. This embodiment determined that the top 20% of the EEG channels did not show statistically significant distribution differences compared with the 16 EGG channels, and designated them as highly correlated EEG channels, as shown in Table 1.

[0090] Table 1: Statistical analysis of the frequency of occurrence of the top 20% EEG channels related to gastrointestinal electricity in 148 sample results

[0091] The results show that most of the EEG channels shown in Table 1 are not included in the first channel. Based on this, the present invention believes that the predictive effect of most of the EEG channels shown in Table 1 on epilepsy can be replaced by related gastrointestinal electrical channels (i.e., the above-mentioned second channel).

[0092] Embodiment 3

[0093] See also Figure 3 The present invention provides a method for analyzing synchronously collected EEG-Gastrointestinal electrical signals, comprising the following steps:

[0094] S101 inputs the synchronously collected EEG data and gastrointestinal electrical data of the subject;

[0095] In some embodiments, the EEG data is collected from a first channel, and the gastrointestinal electrical data is collected from a second channel.

[0096] In the present invention, "channel", "electrode" and "lead" have the same meaning unless otherwise specified.

[0097] In some embodiments, the first channel includes F3, C4, P4, O2, T7, FC1, CP1, CP6, TP9, TP10, F2, C1, C2, P2, FC3, FC4, CP3, CP4, PO4, P6, PO8, CPz and POz; the second channel includes the body, lesser curvature, antrum, ascending colon, transverse colon, descending colon and rectal passage.

[0098] It should be noted that the first channel and the second channel are respectively the simplified EEG channel and gastrointestinal EEG channel of the present invention, and the first channel and the second channel have a low correlation in epilepsy.

[0099] Unlike the prior art of coupling gastrointestinal electrical signals and EEG signals, after obtaining the EEG channels with strong gastrointestinal electrical correlation in epileptic patients, the present invention excludes these EEG channels from the EEG channels actually to be collected, thereby obtaining the above-mentioned first channel. The present invention finds that the predictive effect of this part of the EEG channels can be replaced by related gastrointestinal electrical channels (i.e., the above-mentioned second channel). After using the above-mentioned first channel and second channel with low correlation in predicting epilepsy, not only the difficulty of the acquisition operation is reduced, but also the accuracy of the prediction of epilepsy patients is improved, which is more convenient for practical application. However, the use of a lower number of EEG channels (such as conventional 16 leads, 32 leads, etc.) is not enough to cover the entire brain, and it is difficult to predict epilepsy.

[0100] In some embodiments, the collection time of the EEG data and the gastrointestinal electrical data is at least 5 minutes.

[0101] In some embodiments, the data is collected before or after a meal.

[0102] In some embodiments, the data is collected from subjects in a normal state.

[0103] In some embodiments, the subject is an epileptic patient.

[0104] In some embodiments, the epilepsy patient has focal or generalized epilepsy.

[0105] S102 preprocesses the synchronously collected EEG data and gastrointestinal electrical data to obtain corresponding time series data;

[0106] In some embodiments, the preprocessing includes filtering the EEG data to filter out EEG signals below 1 Hz and above 30 Hz, and normalizing the gastrointestinal electrical data and the filtered EEG data to obtain the time series data.

[0107] S103, based on the first model, obtaining an average electrode inconsistency index of the first channel and the second channel;

[0108] In some embodiments, the first model comprises: Among them, JSD represents the JS divergence scoring function, t represents time, a it represents the time series data of the corresponding channels of the first channel and the second channel recorded at the time point t seconds of the subject, m represents the total number of channels, n represents the total duration of the time series data of the corresponding channels; ICI represents the inconsistency index of the corresponding channel.

[0109] In some embodiments, the corresponding channels refer to F3, C4, P4, O2, T7, FC1, CP1, CP6, TP9, TP10, F2, C1, C2, P2, FC3, FC4, CP3, CP4, PO4, P6, PO8, CPz, POz, gastric body channel, gastric lesser curvature channel, gastric antrum channel, ascending colon channel, transverse colon channel, descending colon and rectal channel. In some embodiments, the total duration refers to the total duration of the entire synchronously collected EEG data and gastrointestinal electrical data, for example, when the acquisition time is 5 minutes, the total duration is 5 minutes.

[0110] Based on the above-mentioned first channel and second channel, the present invention not only reduces the difficulty of acquisition operation, but also reduces the amount of data that needs to be analyzed and calculated, improves the efficiency of calculation, and maintains accuracy and sensitivity at a high level.

[0111] In some embodiments, the method further includes S201 converting the time series data into probability density distribution data.

[0112] In some embodiments, the method further includes S202 obtaining an inconsistency index of a corresponding channel based on a second model according to the probability density distribution data, wherein the second model includes: ; Where ICI represents the inconsistency index function, D KL represents the KL divergence function, t represents time, a it represents the time series data of the corresponding channel recorded at time point t seconds of the subject, b it represents the time series data of the corresponding channel recorded at time point t seconds for healthy people, n is the total duration of the time series data of the corresponding channel, P(a it ) represents the sample distribution, Q(b it ) represents the reference distribution.

[0113] S104 compares the average electrode inconsistency index of the subject with a preset evaluation threshold; when the average electrode inconsistency index of the subject is not lower than the preset evaluation threshold, the subject is predicted to be an epileptic patient.

[0114] In some embodiments, the method for obtaining the preset evaluation threshold includes S203 randomly obtaining the average electrode inconsistency index of 50-70% of the cognitive impairment patient samples in the sample data set and calculating the critical value of epilepsy occurrence (based on DNB theory), and setting the average electrode inconsistency index corresponding to the minimum critical value as the evaluation threshold.

[0115] Embodiment 4

[0116] See also Figure 4 The present invention provides an epilepsy prediction system 100 based on synchronously collected EEG-Gastrointestinal electrical signals, characterized in that it includes:

[0117] A data acquisition module 102, used to acquire data, wherein the data includes EEG data and gastrointestinal electrical data;

[0118] In some embodiments, the EEG data and the gastrointestinal electrical data are collected synchronously.

[0119] In some embodiments, the collection time of the EEG data and the gastrointestinal electrical data is at least 5 minutes.

[0120] In some embodiments, the data is collected before or after a meal.

[0121] In some embodiments, the EEG data is collected from a first channel, and the gastrointestinal electrical data is collected from a second channel.

[0122] In some embodiments, the data includes sample data from a sample population and subject data from a subject.

[0123] In some embodiments, the sample population includes healthy people and epilepsy patients.

[0124] In some embodiments, the data is collected from subjects in a normal state.

[0125] In some embodiments, the subject is an epileptic patient.

[0126] In some embodiments, the epilepsy patient has focal or generalized epilepsy.

[0127] In some embodiments, the first channel includes F3, C4, P4, O2, T7, FC1, CP1, CP6, TP9, TP10, F2, C1, C2, P2, FC3, FC4, CP3, CP4, PO4, P6, PO8, CPz and POz; the second channel includes the body, lesser curvature, antrum, ascending colon, transverse colon, descending colon and rectal passage.

[0128] A data preprocessing module 104, used for preprocessing the data to obtain corresponding time series data;

[0129] In some embodiments, the preprocessing includes filtering the EEG data to filter out EEG signals below 1 Hz and above 30 Hz, and normalizing the gastrointestinal electrical data and the filtered EEG data to obtain the time series data.

[0130] A first analysis module 106, configured to obtain, according to the time series data and based on a first model, an average electrode inconsistency index of the first channel and the second channel;

[0131] In some embodiments, the first model comprises: Among them, JSD represents the JS divergence scoring function, t represents time, a it represents the time series data of the corresponding channels of the first channel and the second channel recorded at the time point t seconds of the subject, m represents the total number of channels, n represents the total duration of the time series data of the corresponding channels; ICI represents the inconsistency index of the corresponding channel.

[0132] The second analysis module 108 is used to convert the time series data into probability density distribution data.

[0133] In some embodiments, the second analysis module 108 is further configured to obtain an inconsistency index of each sub-channel based on a second model according to the probability density distribution data.

[0134] In some embodiments, the second model comprises: ; Where ICI represents the inconsistency index function, D KLrepresents the KL divergence function, t represents time, a it represents the time series data of the corresponding channel recorded at time point t seconds of the subject, b it represents the time series data of the corresponding channel recorded at time point t seconds for healthy people, n is the total duration of the time series data of the corresponding channel, P(a it ) represents the sample distribution, Q(b it ) represents the reference distribution.

[0135] In some embodiments, the first analysis module 106 and the second analysis module 108 may be combined into an analysis module.

[0136] A prediction module 110, configured to compare the average electrode inconsistency index of the subject with a preset evaluation threshold, and when the average electrode inconsistency index of the subject is not lower than the preset evaluation threshold, the subject is predicted to be an epileptic patient;

[0137] The database 112 is used to store the data obtained by the data acquisition module 102, the data preprocessing module 104, the first analysis module 106, the second analysis module 108 and the prediction module 110, and to generate a corresponding sample data set.

[0138] In some embodiments, the sample dataset includes a healthy population dataset and an epilepsy patient dataset.

[0139] The evaluation threshold setting module 114 randomly obtains the average electrode inconsistency index of 50-70% of the epilepsy patient samples in the epilepsy sample data set and calculates the critical value of their epilepsy occurrence, and sets the average electrode inconsistency index corresponding to the minimum critical value as the evaluation threshold.

[0140] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a computer terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0141] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. An epilepsy prediction system based on synchronously collected EEG-gastrointestinal electrical signals, characterized in that: include: A data acquisition module, used to acquire data, the data including EEG data and gastrointestinal electrical data, the EEG data being acquired from the first channel, and the gastrointestinal electrical data being acquired from the second channel; the data including sample data from a sample population and subject data from a subject; A data preprocessing module, used for preprocessing the data to obtain corresponding time series data; A first analysis module is used to obtain an average electrode inconsistency index of the first channel and the second channel based on the time series data and a first model; the first model includes: Among them, JSD represents the JS divergence scoring function, t represents time, a it represents the time series data of the corresponding channels of the first channel and the second channel recorded at the time point t seconds of the subject, m represents the total number of channels, n represents the total duration of the time series data of the corresponding channels; ICI represents the inconsistency index of the corresponding channel; A prediction module, used for comparing the average electrode inconsistency index of the subject with a preset evaluation threshold, and when the average electrode inconsistency index of the subject is not lower than the preset evaluation threshold, the subject is predicted to be an epileptic patient; Among them, the first channel includes F3, C4, P4, O2, T7, FC1, CP1, CP6, TP9, TP10, F2, C1, C2, P2, FC3, FC4, CP3, CP4, PO4, P6, PO8, CPz and POz; the second channel includes the gastric body, lesser curvature of the stomach, gastric antrum, ascending colon, transverse colon, descending colon and rectal passage.

2. The system according to claim 1, characterized in that The system also includes a second analysis module for converting the time series data into probability density distribution data.

3. The system according to claim 2, characterized in that The second analysis module is further used to obtain an inconsistency index of a corresponding channel based on a second model according to the probability density distribution data, and the second model includes: Where ICI represents the inconsistency index function, D KL represents the KL divergence function, t represents time, a it represents the time series data of the corresponding channel recorded at time point t seconds of the subject, b it represents the time series data of the corresponding channel recorded at time point t seconds for healthy people, n is the total duration of the time series data of the corresponding channel, P(a it ) represents the sample distribution, Q(b it ) represents the reference distribution.

4. The system according to claim 2, characterized in that The system also includes a database for storing the data obtained by the data acquisition module, the data preprocessing module, the first analysis module, the second analysis module and the prediction module, and for generating a corresponding sample data set.

5. The system according to claim 4, characterized in that The system also includes an evaluation threshold setting module, which randomly obtains the average electrode inconsistency index of 50-70% of the epilepsy patient samples in the sample data set and calculates the critical value of their epilepsy occurrence, and sets the average electrode inconsistency index corresponding to the minimum critical value as the evaluation threshold.

6. The system according to claim 1, wherein: The EEG data and the gastrointestinal electrical data are collected synchronously.

7. The system according to claim 1, characterized in that The acquisition time of the EEG data and the gastrointestinal electrical data is at least 5 minutes.

8. The system of claim 1, wherein: The preprocessing includes filtering the EEG data to filter out EEG signals below 1 Hz and above 30 Hz, and normalizing the gastrointestinal electrical data and the filtered EEG data to obtain the time series data.

9. The system according to claim 1, characterized in that The data are collected before or after a meal.

10. The system according to claim 1, wherein: The data were collected from subjects in normal condition.

Images