CN115770050B - Epilepsy detection method and system - Google Patents

Abstract

The utility model discloses an epileptic detection method and system, wherein the epileptic detection system comprises a signal acquisition module, a detection module and a detection module, wherein the signal acquisition module is used for acquiring various physiological signals of a monitored user, such as brain wave signals and electrocardiosignals; the preprocessing module is used for preprocessing the acquired signals; the data analysis module is used for carrying out data analysis on the preprocessed physiological signals through the neural network model so as to identify whether the monitored user suffers from epilepsy or not; the early warning module is used for carrying out early warning when the epileptic seizure of the monitored user is identified; wherein, the preprocessing module includes: the four filters are used for preprocessing the collected physiological signals in sequence, so that the preprocessed physiological signals are directly input into the data analysis module, and the accuracy rate of epileptic identification is improved.

Description

Epilepsy detection method and system

priority application

This application will serve as the priority basis for subsequent patent applications (including, but not limited to, Chinese invention patent applications, Chinese utility model applications, PCT applications, and foreign applications based on the Paris Convention).

Technical field

The invention relates to the technical field of medical devices, and specifically designs a portable epilepsy detection method and system.

Background technique

Epilepsy is a chronic neurological disease caused by sudden abnormal discharges of brain neurons, which can lead to temporary brain dysfunction, resulting in symptoms such as stiffness of the limbs, abnormal twitching of the limbs, and loss of consciousness. Epileptic seizures often cause patients to suffer accidental injuries due to reasons such as loss of consciousness, loss of body control, and respiratory arrest. If the seizure is not treated in time, the brain inflammatory reaction may aggravate the damage to the nervous system, resulting in more serious consequences. Epileptic seizures are sudden and random, affecting patients' normal work and life, and causing patients to feel anxious. Epileptic seizures are accompanied by almost imperceptible brief absences or long-lasting severe clonus. The conditions are complex and diverse, and there is no obvious pattern. If the patient is not in public or unattended when the attack occurs, it will be difficult to detect it, and it will also be difficult to recall his or her attack history afterwards. Convulsive seizures are a major contributor to epilepsy-related injuries and fatalities from epilepsy. In addition, epileptic seizures are associated with stigma, headaches, and psychiatric conditions such as attention-deficit and hyperactivity disorder. When the abnormal neural activity is restricted to one specific area of the brain, it is called a focal seizure; when it spreads to other areas of the brain, it is called a generalized seizure. For people with epilepsy and their caregivers, the fear of seizures is ever-present. Their lives will also be dominated by the fear of possible epileptic seizures, which seriously reduces their quality of life. Based on the above-mentioned difficulties in epileptic seizure detection and the serious impact of epileptic seizures on patients, the automatic detection method of epileptic seizures is one of the important research topics in the current medical community and medical electronics field.

The current automatic epilepsy detection system mainly distinguishes epileptic seizures from normal states based on the differences in some characteristics of abnormal physiological activities during epileptic seizures and normal physiological activities in terms of EEG, ECG, and limb movements. Most of them use EEG signals, acceleration, etc. Signals, ECG signals, EMG signals, etc. are used as inputs, and there are mainly the following implementation methods:

(1) Automatic detection of epilepsy based on EEG signals: The patent "Multi-level epilepsy EEG signal automatic identification method based on supervised gradient booster" (Patent No. CN109934089A) applied for by Gong Guanghong and others in 2019 uses a gradient boosting classifier to identify epilepsy signals. examine.

(2) Automatic detection of epilepsy based on ECG signals: The "Intelligent Early Warning System for Abnormal Heartbeats in Epilepsy Patients" (Patent No. CN104997499A) applied by Song Xiaoyu and others in 2015 collects signals through several electrodes around the patient's chest and detects heartbeats through heart rate changes. Signal anomalies; the patent "IDENTIFYINGSEIZURES USING HEART DATA FROM TWO OR MORE WINDOWS" (Patent No. US9498162 B2) applied by Wangcai Liao and others in 2016 also detects abnormalities by counting heart rate changes.

(3) Automatic detection of epilepsy based on the acceleration signal of the human trunk or head: The "Epilepsy Detection Device and Epilepsy Detection Method" (Patent No. CN105232000A) applied by Chen Lei and others in 2016 is used in a bracelet containing a three-axis wireless acceleration sensor. Epilepsy detection methods perform the detection of epileptic seizures.

However, the shortcomings of the above-mentioned various epilepsy alarm devices are the lack of accuracy in judging epileptic seizures. Using data from a single physiological sensor for analysis is prone to false positives; such devices are also inconvenient to carry and increase stigma. The disadvantage is that patients cannot be monitored at all times.

A wearable device is a portable device that can be worn directly on the body or integrated into the patient's clothes or accessories. Hardware-based devices can achieve powerful functions through software support, data interaction, and cloud interaction. The realization of epilepsy alarm based on wearable devices can greatly reduce the harm caused by epileptic seizures to patients and improve the patients' quality of life. On the one hand, it can meet the needs of epilepsy monitoring and alarm, reduce patient injuries while improving the quality of life. On the other hand, due to the commonness and concealment of the device, the patient's sense of shame is completely eliminated.

In response to the above problems, the existing technology has proposed technical solutions for epilepsy recognition based on a variety of physiological signals. For example, the patent number is ZL 202011240677.4, and the invention title is an invention patent for a multi-input signal epilepsy seizure detection system based on feedback regulation. Acceleration, angular velocity, skin electrode signal, myoelectric signal and temperature are obtained through the sensor, and the signals are combined, and then signal processing and analysis are performed on each signal combination, that is, feature extraction is performed on the preprocessed signal, and then based on the extracted The characteristics are analyzed to obtain the final detection result, which can overcome the problem of low accuracy in detecting epilepsy with a single signal. Although this detection device collects a variety of physiological signals, it does not collect EEG signals, which undoubtedly greatly reduces the accuracy of the detection.

Contents of the invention

The purpose of the present invention is to provide an epilepsy detection method and system, which partially solves or alleviates the above-mentioned deficiencies in the prior art and can predict epilepsy more accurately.

In order to solve the above-mentioned technical problems, the present invention specifically adopts the following technical solutions:

A first aspect of the present invention is to provide an epilepsy detection system, which includes:

The signal acquisition module is used to collect various physiological signals of the monitored user; the various physiological signals include: brain wave signals and electrocardiogram signals;

A preprocessing module, connected to the signal acquisition module, is used to preprocess the physiological signals collected by the signal acquisition module;

A data analysis module, connected to the preprocessing module, is used to perform data analysis on the time-frequency physiological signals obtained through preprocessing through a neural network model to identify whether the monitored user has epilepsy;

An early warning module, connected to the data analysis module, is used to provide an early warning when the data analysis module identifies that the monitored user has an epileptic seizure;

Wherein, the preprocessing module includes: a bandpass filter, used to filter out-of-band noise signals to obtain the physiological signal retaining only in-band information; a median filter, used to filter the denoised said physiological signal. The physiological signal is subjected to baseline offset elimination; a smoothing filter is used to denoise the physiological signal after baseline offset elimination, so as to eliminate noise in the signal band and obtain a true original physiological signal; a differential filter, Used to filter the original physiological signal to eliminate noise in the signal band to obtain the time-frequency physiological signal to be analyzed.

In some embodiments of the present invention, the signal collection module includes: at least four EEG signal collection microelectrodes that can be attached to the brain of the monitored user and used to collect the EEG signal of the monitored user. ; A wireless communication unit integrated with the EEG signal collection microelectrode for sending the EEG signal collected by the EEG signal collection microelectrode to the preprocessing module; and the preprocessing module , the data analysis module and the early warning module are integrated together and are used to collect the heart rate sensor of the monitored user's electrocardiogram signal.

In some embodiments of the present invention, the signal acquisition module further includes: integrated with the preprocessing module, the data analysis module, and the early warning module, and connected to the data analysis module, respectively using There are myoelectric signal collection electrodes for collecting myoelectric signals, an acceleration sensor for collecting acceleration, and a gyroscope sensor for collecting angular velocity.

In some embodiments of the present invention, the heart rate sensor, the preprocessing module, the data analysis module, and the early warning module are integrated on a wearable device, and the wearable device includes a bracelet.

In some embodiments of the present invention, the early warning module includes: a voice unit, connected to the data analysis module, for automatically broadcasting pre-stored distress voice information when the data analysis module identifies that the user has an epileptic seizure. ; And/or, an early warning notification unit, connected to the data analysis module, is used to send an early warning message to the mobile terminal of the pre-associated guardian through the Internet of Things when the data analysis module identifies the user's epileptic seizure.

In some embodiments of the present invention, the early warning module further includes: a positioning unit, connected to the data analysis module, for feeding back the information to the data analysis module when the data identifies the user's epileptic seizure. The current positioning information of the monitored user is described, and the medical institution information of the nearest medical institution is obtained; the automatic help-seeking unit is connected to the data analysis module, and is used to call the user when the data analysis module recognizes that the user has an epileptic seizure. The positioning information and the physiological signal are sent to the medical institution.

In some embodiments of the present invention, the epilepsy detection system further includes: a wireless communication module connected to the data analysis module for conducting data processing with the pre-bound mobile terminal of the monitored user or guardian. communication.

In some embodiments of the present invention, the data analysis module includes: a first data analysis unit, configured to match the corresponding signal combination method according to the seizure type when the seizure type of the monitored user has been specified, And trigger the signal collection module to collect the corresponding physiological signal according to the matched signal combination method; or, when the seizure type of the monitored user is not specified, obtain the preset default signal combination method, and collect the corresponding physiological signal according to the default The signal combination method triggers the signal acquisition module to collect corresponding physiological signals; the second data analysis unit is used to perform data analysis on the physiological signals preprocessed by the preprocessing module to identify whether the monitored user Epilepsy occurs.

In some embodiments of the present invention, the signal combination method includes: the first combination method: EEG, ECG + acceleration; the second combination method: EEG + acceleration; the third combination method: EEG + ECG + EMG + acceleration; the fourth combination method: EEG + EMG; the fifth combination method: EEG + EMG + acceleration.

A second aspect of the present invention is to provide an epilepsy detection method based on the above-mentioned epilepsy detection system. The epilepsy detection system includes: a signal acquisition module for collecting multiple physiological signals of the monitored user; the multiple Physiological signals include: brain wave signals, electrocardiogram signals, myoelectric signals, acceleration and angular velocity; a preprocessing module for preprocessing the physiological signals collected by the signal acquisition module; and a preprocessing module for preprocessing through the neural network model. A data analysis module for performing data analysis on the processed time-frequency physiological signals to identify whether the monitored user has epilepsy; and an early warning module for providing an early warning when the data analysis module identifies that the monitored user has epilepsy. ; Correspondingly, the epilepsy detection method specifically includes the steps:

The epileptic seizure type of the monitored user is obtained through the data analysis module, and the corresponding signal combination method is obtained by matching in the database according to the epileptic seizure type; wherein the signal combination method includes: a first combination method: brain Electrical signal, ECG signal + acceleration; the second combination method: EEG signal + acceleration; the third combination method: EEG signal + ECG signal + EMG signal + acceleration; the fourth combination method: EEG signal + EMG Signal; fifth combination method: EEG signal + EMG signal + acceleration;

The data analysis module triggers the signal collection module to collect corresponding physiological signals according to the matched signal combination;

The physiological signals collected by the signal acquisition module are preprocessed by the preprocessing module to obtain time-frequency physiological signals;

The data analysis module performs data analysis on the video physiological signals preprocessed by the preprocessing module to identify whether the monitored user has epilepsy; if so, the data analysis module triggers the early warning module Provide early warning.

The third aspect of the present invention is to provide an epilepsy early warning system, which includes the above-mentioned epilepsy detection system, a server and a user terminal, and the epilepsy detection system and the user terminal perform data communication with the server through a wireless network; wherein , an epilepsy detection system, used to collect the physiological signals of the monitored user, and use the built-in processing module to preprocess the physiological signals before performing data analysis, and then use the wireless network to transmit the collected physiological signals and/or the data analysis results are sent to the server and/or the user terminal; wherein the preprocessing module includes: a band-pass filter for filtering out-of-band noise signals to obtain only in-band information. the physiological signal; a median filter, used to perform baseline offset elimination on the denoised physiological signal; a smoothing filter, used to denoise the physiological signal after baseline offset elimination, to eliminate the noise in the signal band to obtain the real original physiological signal; the differential filter is used to filter the original physiological signal that eliminates the noise in the signal band to obtain the time-frequency physiological signal to be analyzed.

Beneficial effects: In the present invention, real time-frequency physiological signals are obtained by preprocessing the collected original physiological signals through bandpass filters, median filters, balance filters, and differential filters in sequence, and the pre-trained neural signals are input The network model is used for identification. Compared with the method of extracting features only through band-pass filtering and median filtering, and then identifying based on the extracted features, since the input to the neural network model is a real physiological signal, it will not be affected by the use of feature extraction. And missing or missing data, therefore, its detection accuracy is higher.

In the present invention, a variety of physiological signals are collected, and each signal combination includes the EEG signal that most directly reflects the discharge pattern of the monitored user during epilepsy. Compared with the multi-signal detection method without EEG signals, the detection method is greatly improved. The accuracy is improved; on the other hand, brain waves are collected through four microelectrodes placed at fixed positions on the brain of the monitored user, making it easy to carry. There is no need for the monitored user to go to the hospital or use large equipment for detection, so that the user can monitor at any time.

Description of the drawings

In order to more clearly explain the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Throughout the drawings, similar elements or portions are generally identified by similar reference numerals. In the drawings, elements or parts are not necessarily drawn to actual scale. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting any creative effort.

Figure 1 is a functional module diagram of an epilepsy detection system according to an exemplary embodiment of the present invention;

Figures 2a and 2b are respectively schematic diagrams of four EEG signal microelectrodes attached to a fixed position on the head in an epilepsy detection system according to an exemplary embodiment of the present invention;

Figure 3a shows the original brainwave signal collected from the monitored user;

Figure 3b is the brainwave signal after band-pass filtering of the original brainwave signal shown in Figure 3a;

Figure 3c is the brainwave signal after median filtering of the brainwave signal shown in Figure 3b;

Figure 3d is the brainwave time-frequency signal after smoothing and filtering the brainwave signal shown in Figure 3c;

Figures 4a to 4g show the recognition results of 30 monitored users using two types of epilepsy detection bracelets respectively.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

Herein, suffixes such as "module", "component" or "unit" used to represent elements are used only to facilitate the description of the present invention and have no specific meaning in themselves. Therefore, "module", "component" or "unit" may be used interchangeably.

In this article, the terms "upper", "lower", "inner", "outer", "front", "back", "one end", "other end", etc. indicate the orientation or positional relationship based on the orientation shown in the drawings. or positional relationships are only for the convenience of describing the present invention and simplifying the description, but do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance.

In this article, unless otherwise expressly stipulated and limited, the terms "installed", "provided with", "connected", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection or a detachable connection, or Integrated connection; it can be mechanical connection, direct connection, indirect connection through an intermediary, or internal connection between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood on a case-by-case basis.

As used herein, "and/or" includes any and all combinations of one or more of the associated listed items.

"Plural" in this article means two or more, that is, it includes two, three, four, five, etc.

It should be noted that, in this document, the terms "comprising", "comprises" or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or device that includes a series of elements not only includes those elements, It also includes other elements not expressly listed or inherent in the process, method, article or apparatus. Without further limitation, an element defined by the statement "comprises a..." does not exclude the presence of additional identical elements in a process, method, article or apparatus that includes that element.

Embodiment 1

Referring to Figure 1, which is a functional module diagram of an exemplary embodiment of the epilepsy detection system of the present invention. Specifically, the epilepsy detection system includes:

The signal acquisition module is used to collect various physiological signals of the monitored user; wherein the physiological signals include: brain wave signals and electrocardiogram signals;

A preprocessing module is used to preprocess the physiological signals collected by the signal acquisition module; specifically, the preprocessing module includes: a bandpass filter, used to filter out-of-band noise signals to obtain only in-band information. the physiological signal; a median filter, used to perform baseline offset elimination on the denoised physiological signal; a smoothing filter, used to denoise the physiological signal after baseline offset elimination, to eliminate the noise in the signal band to obtain the real original physiological signal; the differential filter is used to filter the physiological signal that eliminates the noise in the signal band to obtain the time-frequency physiological signal to be analyzed;

The data analysis module is used to perform data analysis on pre-processed signals through a neural network model to identify whether the monitored user has epilepsy; specifically, pre-collect a large number of epilepsy patients (including patients with different types of epilepsy) during epileptic seizures. Physiological signals, and use the above-mentioned preprocessing module to preprocess the collected physiological signals as training samples for training the neural network module; specifically, the CNN neural network model can be used;

An early warning module is used to issue an early warning when the above-mentioned data analysis module identifies an epileptic seizure in the monitored user.

In this embodiment, the out-of-band noise signal is first filtered through a band-pass filter, and only the in-band information of the physiological signal is retained. For the in-band signal, if there is a baseline shift, the signal feature detection will be affected by the baseline drift, and there is a high probability of errors. Therefore, the baseline offset must be eliminated; there is still in-band noise in the signal band after the baseline offset is eliminated. At this time, the in-band noise is filtered through the adaptive smoothing filter to restore the original signal more realistically; in order to make the The signal change characteristics of physiological signals are more obvious. Use a differential filter to filter them, and the signal amplitude changes after filtering are more obvious. After being sent to the neural network CNN, the detection accuracy is higher. Specifically, as shown in Figure 3a, in order to collect the brainwave signal of the monitored user, as shown in Figure 3b, the brainwave signal is processed by a band-pass filter. Compared with the original signal, the brainwave signal eliminates The out-of-band interference noise is shown in Figure 3c. The brainwave signal is processed by the median filter and the baseline drift is eliminated. As shown in Figure 3d, the brainwave signal is processed by the smoothing filter. Radio signal eliminates burrs in the signal. Finally, the signal is amplified through a differential filter. That is to say, the signal quality is improved through the above four filters, so that high-quality physiological signals can be input into the data analysis module for machine learning or automatic recognition, which greatly improves the accuracy of recognition.

The order of the above four filters cannot be changed. If the difference is performed first and then baseline elimination and smoothing filtering are performed, signals such as noise glitches with high amplitude changes in the band will also be misjudged as physiological in the subsequent smoothing filter due to large amplitude changes. Signal.

Compared with the existing technology, in order to extract features, only band-pass filtering and median filtering are performed on the collected signals; then feature extraction is performed, and the extracted time domain or frequency domain feature models are sent to CNN In this embodiment, the time-frequency signal obtained after preprocessing the collected physiological signals is directly input into the pre-trained CNN neural network for epilepsy recognition, which greatly improves the detection accuracy.

In order to prove the accuracy of the epilepsy detection system of the present invention, epilepsy detection was performed on 30 monitored users using the feature extraction method and the method of this embodiment. Specifically, the 30 patients wore two types of epilepsy detection systems on their left and right hands respectively. , the detection results are shown in Figure 4a-Figure 4g. For the 30 monitored users, the epilepsy detection system in this embodiment identified that all 30 monitored users had epileptic seizures, which was consistent with the hospital diagnosis results. The accuracy rate was 100%, and the feature extraction method was used for epilepsy identification. The device identified 28 of the 30 monitored users as having epileptic seizures, and 2 cases were inconsistent with the hospital diagnosis results, with an accuracy rate of 93.33%.

In some embodiments, the signal acquisition module specifically includes:

At least four EEG signal collection microelectrodes that can be attached to the brain of the user to be monitored and used to collect the EEG signal of the user to be monitored;

A wireless communication unit integrated with the EEG signal collection microelectrodes and used to send the EEG signals collected by the EEG signal collection microelectrodes to the preprocessing module;

Integrated with the preprocessing module, data analysis module, and early warning module, it is a heart rate sensor used to collect the ECG signal of the monitored user.

In some embodiments, four microelectrodes for collecting EEG signals can be respectively attached to four fixed positions on the brain of the user being monitored, see Figure 2a and Figure 2b. By setting the four microelectrodes and integrating them with the wireless communication unit, but independent of the above-mentioned data analysis module, preprocessing module and early warning module, that is, the four microelectrodes and the wireless communication unit serve as the detection system. The portable accessory eliminates the need for the monitored user to go to hospitals and other medical institutions to use special equipment to collect EEG signals. It is also easy to carry and has good concealment, and it also facilitates the monitored user to better monitor at any time. Of course, an analog-to-digital converter can further be provided between the two.

In some embodiments, the above-mentioned signal acquisition module also includes: integrated with the above-mentioned preprocessing module, the above-mentioned data analysis module, and the above-mentioned early warning module, and connected to the above-mentioned data analysis module, respectively used to collect myoelectric signals. Signal collection electrodes, acceleration sensors for collecting acceleration, and gyroscope sensors for collecting angular velocity. Wherein, the above-mentioned heart rate sensor, the above-mentioned preprocessing module, the above-mentioned data analysis module, and the above-mentioned early warning module are integrated on a wearable device, and the above-mentioned wearable device includes a bracelet.

In some embodiments, the above-mentioned early warning module includes: a voice unit, connected to the above-mentioned data analysis module, for automatically broadcasting pre-stored distress voice information when the data analysis module identifies that the monitored user has an epileptic seizure; and/or an early warning notification. The unit is connected to the above-mentioned data analysis module and is used to send an early warning message to the mobile terminal of the pre-associated guardian through the Internet of Things when the data analysis module identifies the epileptic seizure of the monitored user.

When the monitored user goes out, especially when traveling or on a business trip, if an epileptic attack occurs, people around him usually do not know the specific situation, and naturally cannot provide corresponding assistance immediately. Therefore, a voice unit is set up to play the pre-stored SOS voice messages, for example, "The patient has an epileptic seizure, please dial Knowing the specific situation of the monitored user, it can also provide immediate assistance based on the voice information. On the other hand, the early warning notification unit can also be used to immediately notify the guardian of the epileptic seizure of the monitored user, so that the guardian can quickly take corresponding measures. For example, when the guardian is close to the monitored user, he can quickly come to the monitored user. for rescue.

In some embodiments, the above-mentioned early warning module also includes: a positioning unit, connected to the data analysis module, for feeding back the monitored user to the data analysis module when the data identifies the user's epileptic seizure. current positioning information, and obtain the medical institution information of the nearest medical institution; an automatic help-seeking unit is connected to the data analysis module, and is used to provide the positioning information when the data analysis module identifies that the user has an epileptic seizure. and the physiological signals are sent to the medical institution.

When the monitored user goes out, especially when traveling or on a business trip, if an epilepsy occurs, the current location information of the monitored user can be accurately located through the positioning unit (for example, GPS, etc.), thereby not only sending an early warning notification to the guardian, but also Positioning information can be sent to it, so that even if the guardian is far away from the monitored user, he can still keep track of his status; at the same time, it can also automatically search for the nearest medical institution based on the current positioning information of the monitored user, so as to provide him/her (for example, the medical The emergency clinic of the institution) sends corresponding help information (including positioning information, physiological signals and basic information of the monitored user, etc.).

In some embodiments, the epilepsy detection system further includes: a wireless communication module, connected to the data analysis module, for performing data communication with the pre-bound mobile terminal of the monitored user or guardian.

In some embodiments, the above-mentioned data analysis module includes: a first data analysis unit, configured to match the corresponding signal combination method according to the seizure type when the seizure type of the monitored user has been specified, and according to the matched The signal combination method obtained triggers the signal acquisition module to collect the corresponding physiological signal; or, when the seizure type of the monitored user is not specified, the preset default signal combination method is obtained, and the trigger is triggered according to the default signal combination method. The signal acquisition module collects corresponding physiological signals;

The second data analysis unit is configured to use a pre-trained neural network model to perform data analysis on the physiological signals preprocessed by the preprocessing module to identify whether the monitored user has epilepsy.

In some embodiments, the above signal combination method includes: first combination method: EEG signal, ECG signal + acceleration; second combination method: EEG signal + acceleration; third combination method: EEG signal + ECG signal + EMG signal + acceleration; the fourth combination method: EEG signal + EMG signal; the fifth combination method: EEG signal + EMG signal + acceleration.

The epilepsy detection system of this embodiment will be described below in conjunction with the working principle.

When the monitored user starts the epilepsy detection system for the first time, he or she can select his/her epilepsy seizure type through the input module (for example, touch screen, etc.) of the epilepsy detection system;

The data analysis module triggers the signal acquisition module to collect corresponding physiological signals according to the epileptic seizure type selected by the monitored user; wherein, the physiological signal combination method corresponding to each epileptic seizure type is pre-stored in the data analysis module. Therefore, Once an epileptic seizure type is selected, the corresponding physiological signal combination will be automatically matched according to the epileptic seizure type, and then the corresponding sensor in the signal acquisition module will be triggered to collect the corresponding physiological signal;

Under the triggering effect of the data analysis module, the signal acquisition module uses the corresponding physiological signals and sends them to the preprocessing module for preprocessing, and then sends the preprocessed physiological signals to the data analysis module for data analysis to identify the Whether the monitored user has epilepsy; if so, the early warning module automatically broadcasts the alarm signal with voice, so that when the monitored user has an epileptic seizure, it can attract nearby people and inform them of the specific situation, so that nearby people can provide help, and also through wireless communication The module sends early warning information to the mobile terminal of the pre-associated guardian, so that the guardian can keep track of the status of the monitored user at any time.

Of course, further, when the data analysis module identifies that the monitored user has epilepsy, the early warning module automatically searches for the nearest medical institution based on the current positioning information of the monitored user, dials the corresponding distress call, and sends the positioning information to the medical institution at the same time. institutions, thereby improving the efficiency of rescue.

Of course, if the user does not select an attack type, all physiological signals (i.e., EEG signals, ECG signals, acceleration, angular velocity, and EMG signals) will be collected by default, and data analysis will be performed based on the combination of all the above signals for identification. , and then dynamically determine a signal combination based on the feedback of the monitored user or his guardian. For the monitored user, in the later stage, only the physiological signals in the signal combination will be collected, and other signal combinations will not be considered to reduce the efficiency. Consumption.

Embodiment 2: Based on the above-mentioned epilepsy detection system, the present invention also provides an epilepsy early warning system, the above-mentioned epilepsy detection system, server and user terminal, wherein the epilepsy detection system and the user terminal communicate with the server through a wireless network. Communication; specifically, the epilepsy detection system is used to collect the physiological signals of the monitored user, and uses the built-in pre-processing module to pre-process the physiological signals before performing data analysis, and then transmits the recognition results and/or all the data through the wireless network. The collected physiological signals and/or data analysis results are sent to the server and/or the user terminal.

In some embodiments, the user terminal includes a mobile terminal of the monitored user and/or a guardian's mobile terminal, so that the monitored user and/or guardian can understand the monitoring situation at any time.

Embodiment 3: Based on the epilepsy detection system of the above-mentioned Embodiment 1, the present invention also provides an epilepsy detection method. Specifically, the epilepsy detection method includes the steps:

The epileptic seizure type of the monitored user is obtained through the data analysis module, and the corresponding signal combination method is obtained by matching in the database according to the epileptic seizure type; usually, the monitored user uses the epilepsy detection system for the first time, for example, wearing the epilepsy detection system in the form of a bracelet for the first time. When using the epilepsy detection system, you will set your own epilepsy seizure type in the epilepsy detection system, thereby realizing the initialization of the epilepsy detection system, that is, automatically matching the corresponding signal combination method according to the set epilepsy seizure type, so that the subsequent detection process , trigger the corresponding signal acquisition unit in the signal acquisition module to collect the corresponding physiological signal according to the matched signal combination method; specifically, the signal combination method includes: first combination method: EEG signal, ECG signal + acceleration ; The second combination method: EEG signal + acceleration; The third combination method: EEG signal + ECG signal + EMG signal + acceleration; The fourth combination method: EEG signal + EMG signal; The fifth combination method: Brain Electrical signal + electromyographic signal + acceleration; of course, in other embodiments, if the monitored user who uses the system for the first time does not specify the type of epileptic seizure, the data analysis module triggers the signal acquisition module to collect signals according to the default signal combination method. Collect corresponding physiological signals; preferably, all physiological signals are collected by default, or matched to the above third signal combination method by default;

The signal acquisition module is triggered by the data analysis module to collect corresponding physiological signals according to the matched signal combination mode; for example, when the data analysis module matches the first combination mode, the trigger signal acquisition module only collects EEG signals, ECG signal and acceleration are enough;

The physiological signals collected by the signal acquisition module are preprocessed through the above preprocessing module to obtain time-frequency physiological signals;

The data analysis module performs data analysis on the video physiological signals preprocessed by the preprocessing module to identify whether the monitored user has epilepsy; if so, the data analysis module triggers an early warning module to issue an early warning.

In some embodiments, the method of triggering the early warning module to perform early warning includes any one or more of the following: 1) sending early warning information to the mobile terminal of the pre-associated guardian; 2) automatically performing voice broadcast according to the pre-stored voice information; 3 ) Obtain the current positioning information of the monitored user and nearby medical institutions, and send the monitored user’s positioning information and basic information, as well as the collected physiological signals to the medical institution, so that the medical institution can make preparations in advance Rescue preparations and accurately obtain the location of the monitored user.

The specific early warning method can be preset according to the type and severity of the attack of the user being monitored.

It should be noted that, in this document, the terms "comprising", "comprises" or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or device that includes a series of elements not only includes those elements, It also includes other elements not expressly listed or inherent in the process, method, article or apparatus. Without further limitation, an element defined by the statement "comprises a..." does not exclude the presence of additional identical elements in a process, method, article or apparatus that includes that element.

The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above-mentioned specific implementations. The above-mentioned specific implementations are only illustrative and not restrictive. Those of ordinary skill in the art will Under the inspiration of the present invention, many forms can be made without departing from the spirit of the present invention and the scope protected by the claims, and these all fall within the protection of the present invention.

Claims (7)

1. An epilepsy detection system, characterized by comprising: The signal acquisition module is used to collect various physiological signals of the monitored user; the various physiological signals include: brain wave signals, electrocardiogram signals, acceleration, and electromyographic signals; A preprocessing module, connected to the signal acquisition module, is used to preprocess the signal combination signal of various physiological signals collected by the signal acquisition module; A data analysis module, connected to the preprocessing module, is used to perform data analysis on the preprocessed time-frequency physiological signal combination signal through a neural network model to identify whether the monitored user has epilepsy; An early warning module, connected to the data analysis module, is used to provide an early warning when the data analysis module identifies that the monitored user has an epileptic seizure; Among them, the preprocessing module includes: A bandpass filter, used to filter out-of-band noise signals to obtain the physiological signal combination signal that only retains in-band information; A median filter, used to eliminate baseline offsets on the denoised physiological signal combination signal; A smoothing filter, used to denoise the physiological signal combination signal after baseline offset elimination, so as to eliminate noise in the signal band and obtain a true original physiological signal combination signal; A differential filter, used to filter the original physiological signal combination signal to eliminate noise in the signal band, and obtain the time-frequency physiological signal combination signal to be analyzed; Among them, the training samples of the neural network model are pre-collected physiological signal combinations of a large number of patients with epilepsy of different types during epileptic seizures, and are sequentially passed through the band-pass filter, median filter, and smoothing in the pre-processing module. Filters and differential filters are used for preprocessing; different types of epilepsy correspond to corresponding signal combination methods, and the signal combination methods include: the first combination method: EEG signal, ECG signal + acceleration; the second combination method: brain Electrical signal + acceleration; the third combination method: EEG signal + ECG signal + EMG signal + acceleration; the fourth combination method: EEG signal + EMG signal; the fifth combination method: EEG signal + EMG signal + acceleration; Among them, the data analysis module includes: The first data analysis unit is configured to match the corresponding signal combination method according to the seizure type when the seizure type of the monitored user has been specified, and trigger the signal collection module to collect according to the matched signal combination method. Corresponding physiological signals; or, when the seizure type of the monitored user is not specified, obtain a preset default signal combination method, and trigger the signal acquisition module to collect the corresponding physiological signals according to the default signal combination method; The second data analysis unit is used to perform data analysis on the physiological signal combination signal preprocessed by the preprocessing module to identify whether the monitored user has epilepsy. 2. An epilepsy detection system according to claim 1, characterized in that the signal acquisition module includes: At least four EEG signal collection microelectrodes that can be attached to the brain of the monitored user and used to collect the EEG signal of the monitored user; A wireless communication unit integrated with the EEG signal collection microelectrode and used to send the EEG signal collected by the EEG signal collection microelectrode to the preprocessing module; A heart rate sensor integrated with the preprocessing module, the data analysis module, and the early warning module and used to collect the electrocardiogram signal of the monitored user. 3. An epilepsy detection system according to claim 2, characterized in that the signal acquisition module further includes: integrated with the preprocessing module, the data analysis module, and the early warning module, and The data analysis module is connected to a myoelectric signal collection electrode for collecting myoelectric signals, an acceleration sensor for collecting acceleration, and a gyroscope sensor for collecting angular velocity. 4. An epilepsy detection system according to claim 3, characterized in that the heart rate sensor, the pre-processing module, the data analysis module and the early warning module are integrated on a wearable device, and the wearable device Wearable devices include bracelets. 5. An epilepsy detection system according to claim 4, characterized in that the early warning module includes: A voice unit, connected to the data analysis module, used to automatically broadcast pre-stored help voice information when the data analysis module recognizes that the user has an epileptic seizure; and/or, An early warning notification unit, connected to the data analysis module, is used to send an early warning message to the mobile terminal of the pre-associated guardian through the Internet of Things when the data analysis module identifies that the user has an epileptic seizure; and/or, The epilepsy detection system also includes: a wireless communication module, connected to the data analysis module, for performing data communication with the pre-bound mobile terminal of the monitored user or guardian. 6. An epilepsy detection system according to claim 5, characterized in that the early warning module further includes: A positioning unit, connected to the data analysis module, used to feed back the current positioning information of the monitored user to the data analysis module when the data identifies the user's epileptic seizure, and obtain the information of the nearest medical institution. Medical institution information; An automatic help-seeking unit is connected to the data analysis module, and is used to send the positioning information and the physiological signal to the medical institution when the data analysis module identifies that the user has an epileptic seizure. 7. An epilepsy early warning system, characterized in that it includes the epilepsy detection system according to any one of claims 4 to 6, a server and a user terminal, and the epilepsy detection system and the user terminal are connected to the epilepsy detection system through a wireless network. The server performs data communication; among them, the epilepsy detection system is used to collect the physiological signal combination signal of the monitored user, and performs data analysis after preprocessing the physiological signal combination signal through the built-in pre-processing module, and then through the The wireless network sends the collected physiological signal combination signal and/or data analysis results to the server and/or the user terminal; Among them, the preprocessing module includes: A bandpass filter, used to filter out-of-band noise signals to obtain the physiological signal combination signal that only retains in-band information; A median filter, used to eliminate baseline offsets on the denoised physiological signal combination signal; A smoothing filter, used to denoise the physiological signal combination signal after baseline offset elimination, so as to eliminate noise in the signal band and obtain a true original physiological signal combination signal; A differential filter is used to filter the original physiological signal combination signal to eliminate noise in the signal band, and obtain the time-frequency physiological signal combination signal to be analyzed.