Epileptic seizure early warning and help seeking system and method

Abstract

The invention provides an epileptic seizure early warning and help seeking system and method, and relates to the technical field of medical assistance. The system comprises a neck ring body, an electroencephalogram signal acquisition module, a respiration-heart rate acquisition module, a blood pressure value acquisition module, a blood oxygen value acquisition module, an electromyographic signal acquisition module, a muscle pressure value acquisition module, a first chip, a second chip, Bluetooth, a wireless transmitting coil, an early warning and help seeking unit and an upper computer. The electroencephalogram signal acquisition module and the electromyographic signal acquisition module are both connected with the first chip, the first chip, the respiration-heart rate acquisition module, the blood pressure value acquisition module, the blood oxygen value acquisition module, the muscle pressure value acquisition module and the Bluetooth are all connected with the second chip, and the wireless transmitting coil and the early warning and help seeking unit are both connected with the Bluetooth. And the wireless transmitting coil is wirelessly connected with an upper computer. According to the invention, the danger caused by epileptic seizure and the probability of accidental death can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of medical assistance technology, and in particular to an epileptic seizure early warning and rescue system and method. Background Art

[0002] Epilepsy is a chronic disease characterized by abnormal neuronal discharges in the brain, leading to brain dysfunction. The incidence of epilepsy is high. The consequences of an epileptic seizure are extremely serious. If an epileptic seizure persists and remains uncontrolled, it can lead to irreversible brain damage due to hypoxia and the accumulation of toxic metabolites. Furthermore, it can cause falls, spasms, and convulsions, which can be dangerous if not detected promptly.

[0003] Currently, there is no wearable device on the market that can perform early monitoring of epilepsy patients, which leads to a rapid progression of the disease in latent epilepsy patients, greatly affecting people's physical health and causing double physical and mental harm to patients. Summary of the Invention

[0004] The purpose of the present invention is to provide an epileptic seizure warning and rescue system and method, which is used to solve the problem that there is no wearable device in the prior art that can perform early monitoring of epilepsy patients, which may cause dangers, and can reduce the dangers and probability of accidental death caused by epileptic seizures.

[0005] To achieve the above-mentioned objectives, the present invention provides an epileptic seizure early warning and help-seeking system, comprising a neck collar body, an electroencephalogram (EEG) signal acquisition module, a respiration-heart rate (HR) acquisition module, a blood pressure (BP) value acquisition module, a blood oxygen value (O2) value acquisition module, an electromyogram (EMG) signal acquisition module, a muscle pressure value acquisition module, a first chip, a second chip, Bluetooth, a wireless transmitting coil, an early warning and help-seeking unit, and a host computer. The EEG signal acquisition module and the EMG signal acquisition module are both connected to the first chip, the first chip, the respiratory-heart rate acquisition module, the blood pressure value acquisition module, the blood oxygen value acquisition module, the muscle pressure value acquisition module and Bluetooth are all connected to the second chip, the wireless transmitting coil and the early warning and rescue unit are both connected to Bluetooth, and the wireless transmitting coil is wirelessly connected to the host computer.

[0006] According to an epileptic seizure early warning and rescue system provided by the present invention, adjustment buckles are provided on both sides of the neck ring body; the early warning and rescue unit includes a luminous alarm, a voice alarm, a call for help, a locator and a reset button.

[0007] According to an epileptic seizure early warning and rescue system provided by the present invention, the EEG signal acquisition module includes two EEG acquisition patches. When the user uses it, the two EEG acquisition patches are respectively attached to the skin behind the user's left ear and the skin behind the right ear, thereby collecting two-channel EEG signals; the first chip filters, amplifies and performs analog-to-digital conversion on the two-channel EEG signals to obtain digital signals, and the second chip slices the two-channel EEG signals according to the time length, and sends the original EEG signals to Bluetooth in the form of window fragments. Bluetooth transmits the original EEG signals to the host computer through the wireless transmitting coil. According to an epileptic seizure early warning and rescue system provided by the present invention, the breathing-heart rate acquisition module includes a breathing-heart rate monitoring patch, which is applied to the user's chest or abdomen. An optical breathing sensor and a heart rate monitoring sensor are provided in the breathing-heart rate monitoring patch to respectively collect the breathing frequency changing over time signal, the breathing depth changing over time signal and the heart rate changing over time signal; the second chip slices the breathing frequency changing over time signal, the breathing depth changing over time signal and the heart rate changing over time signal according to the time length, and obtains the breathing frequency characteristics, breathing depth characteristics and heart rate characteristics corresponding to multiple window segments.

[0008] According to an epileptic seizure early warning and rescue system provided by the present invention, the blood pressure value acquisition module includes a blood pressure monitoring sensor, which is applied to the carotid artery on one side of the user. The blood pressure monitoring sensor measures the blood pressure change signal over time and transmits it to the second chip. The second chip slices the blood pressure change signal over time according to the time length to obtain blood pressure characteristics corresponding to multiple window segments.

[0009] According to an epileptic seizure early warning and rescue system provided by the present invention, the blood oxygen value acquisition module includes a blood oxygen monitoring sensor, which is applied to the carotid artery on the other side of the user. The blood oxygen monitoring sensor measures the blood oxygen saturation change signal over time and transmits it to the second chip. The second chip slices the blood oxygen saturation change signal over time according to the time length to obtain blood oxygen saturation characteristics corresponding to multiple window segments. According to an epileptic seizure early warning and rescue system provided by the present invention, the electromyographic signal acquisition module includes multiple electromyographic signal collectors, which are attached to the muscle groups on the back of the user's neck, and the multiple electromyographic signal collectors measure the electromyographic signal sequences of multiple muscle groups; The first chip filters, amplifies and performs analog-to-digital conversion on the electromyographic signal sequences of multiple muscle groups to obtain digital signals. The second chip slices the electromyographic signal sequences of multiple muscle groups according to time length to obtain multiple electromyographic signal features corresponding to multiple window segments.

[0010] According to an epileptic seizure early warning and rescue system provided by the present invention, the muscle pressure value acquisition module includes multiple muscle pressure sensors, and the multiple muscle pressure sensors are attached to the muscle groups on the back of the user's neck. Multiple muscle pressure time-varying signals are measured by the multiple muscle pressure sensors and transmitted to the second chip. The second chip slices the multiple muscle pressure time-varying signals according to the time length to obtain multiple muscle pressure features corresponding to the multiple window segments. According to an epileptic seizure early warning and rescue system provided by the present invention, the host computer extracts the time domain features of each window segment from the two-channel EEG signals based on the original EEG signals; the original EEG signals of each window segment of the two-channel EEG signals are frequency-band decomposed into multiple frequency bands, and the frequency domain features of the original EEG signals of each frequency band are extracted. In a second aspect, the present invention provides an epileptic seizure early warning and rescue method, which uses the epileptic seizure early warning and rescue system of the first aspect, and the method comprises: Based on a pre-trained epilepsy recognition model, the host computer determines the epilepsy recognition result for each window segment according to the time domain features, frequency domain features, respiratory rate features, respiratory depth features, blood pressure features, blood oxygen saturation features, multiple electromyographic signal features, and multiple muscle pressure features corresponding to each window segment. If n consecutive window segments are determined to be epileptic seizures, the first window segment among the n consecutive window segments is set as the first calculation window; Starting from the first calculation window, within the next N window segments, if N1 window segments are all judged to be epileptic seizures, then the user is recorded as being highly suspected of having an epileptic seizure; When a user is highly suspected of having an epileptic seizure, the host computer sends an epilepsy confirmation command to the early warning and rescue unit; After receiving the epilepsy confirmation command, the early warning and rescue unit activates the early warning; When the early warning and rescue unit responds to the first instruction input by the user, it turns off the early warning and transmits the user operation result corresponding to the first instruction to the host computer, and the host computer restarts the determination; When the early warning and emergency call unit responds to the second instruction input by the user, it turns off the early warning, sends the user's current location, and makes an emergency call; When the early warning rescue unit receives the epilepsy confirmation command, it waits If no response is received within the specified time, reconfirmation is performed, including: If n consecutive window segments are determined to be epileptic seizures, the first window segment in the n consecutive window segments is again recorded as the first calculation window; Starting from the first calculation window, within the next N window segments, if N2 window segments are all judged to be epileptic seizures, it is recorded that the user has had an epileptic seizure and is unconscious; When the user has had an epileptic seizure and is unconscious, the host computer sends an epilepsy reconfirmation command to the early warning and rescue unit; After receiving the epilepsy reconfirmation command, the early warning and rescue unit sends the user's current location and makes a rescue call.

[0011] The present invention has at least the following technical effects: To prevent the dangers and even accidental death caused by epileptic seizures, the present invention proposes an epileptic seizure early warning and rescue system and method. By collecting indicators such as EEG signals, respiratory rate and depth, blood pressure, blood oxygen saturation, myoelectric signals, and muscle pressure signals before the user's epileptic seizure, a comprehensive assessment is made of whether the user is experiencing an epileptic seizure. Once an epileptic seizure is confirmed, the system can promptly transmit the user's abnormal condition and location to others, providing an early warning and rescue call. This can reduce the dangers and accidental death caused by epileptic seizures. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] In the attached figure: Figure 1 This is a structural diagram of the epilepsy attack early warning and rescue system of the present invention; Figure 2 This is a physical diagram of the neck ring body of the present invention; Figure 3 A schematic diagram of setting a first calculation window for the present invention; Figure 4 This is a physical picture of the limiting ring belt of the present invention. DETAILED DESCRIPTION

[0014] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0015] The following will describe some embodiments of the present invention in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments may be combined with each other.

[0016] See also Figure 1 and Figure 2 The embodiment of the present invention provides an epileptic seizure early warning and rescue system, comprising a neck collar body 101, an electroencephalogram signal acquisition module, a respiration-heart rate acquisition module, a blood pressure value acquisition module, a blood oxygen value acquisition module, an electromyogram signal acquisition module, a muscle pressure value acquisition module, a first chip 1, a second chip 2, Bluetooth, a wireless transmission coil, an early warning and rescue unit, and a host computer; The EEG signal acquisition module and the EMG signal acquisition module are both connected to the first chip 1, the first chip 1, the respiratory-heart rate acquisition module, the blood pressure value acquisition module, the blood oxygen value acquisition module, the muscle pressure value acquisition module and Bluetooth are all connected to the second chip 2, the wireless transmitting coil and the early warning and rescue unit are both connected to Bluetooth, and the wireless transmitting coil is wirelessly connected to the host computer.

[0017] The neck ring body 101 is wrapped around the user's neck, and the adjustment buckles 102 are provided on both sides of the neck ring body 101 for adjusting the tightness of the neck ring body 101 .

[0018] Specifically, the neckband body 101 has a cavity inside and a groove outside. The grooves accommodate the EEG acquisition patches 201 and 202 and the respiration and heart rate monitoring patch 203. The myoelectric signal collector 303 and muscle pressure sensor 304 are arranged alternately. The first chip 1, the second chip 2, and the Bluetooth are all located in the cavity inside the neckband body 101.

[0019] Specifically, the early warning and rescue unit includes a luminous alarm, a voice alarm, a call for help, a locator and a reset button.

[0020] Table 1 shows an introduction to the epileptic seizure early warning and rescue system proposed by the present invention.

[0021] Table 1 System Introduction

[0022] The EEG signal acquisition module includes two EEG acquisition patches 201 and 202. When the user wears the neck ring body 101, the two EEG acquisition patches 201 and 202 are removed from the grooves on the outside of the neck ring body 101, the patch connection line is stretched to an appropriate length, and then the two EEG acquisition patches 201 and 202 are respectively attached to the skin behind the left ear and the skin behind the right ear, thereby collecting two-channel EEG signals. The first chip 1 filters, amplifies, and converts the two-channel EEG signals collected by the two EEG acquisition patches 201 and 202 into digital signals. The second chip 2 slices the two-channel EEG signals according to the time length and sends the original EEG signals to Bluetooth in the form of window segments. Bluetooth transmits the original EEG signals to the host computer, such as a mobile phone or PC, through the wireless transmitting coil.

[0023] The respiratory-heart rate acquisition module includes a respiratory-heart rate monitoring patch 203, which is applied to the user's chest or abdomen to collect the respiratory frequency variation signal, the respiratory depth variation signal, and the heart rate variation signal. The second chip 2 slices the respiratory frequency variation signal, the respiratory depth variation signal, and the heart rate variation signal according to the time length, and obtains the respiratory frequency characteristics, respiratory depth characteristics, and heart rate characteristics corresponding to multiple window segments. For example, the maximum amplitude corresponding to the i-th window segment is , mean And other features, then the window fragment 、 Equal The respiratory rate feature is transmitted to Bluetooth. The maximum amplitude corresponding to the i-th window segment , mean And other features, then the window fragment 、 Equal The maximum amplitude corresponding to the i-th window segment is transmitted to Bluetooth. , mean And other features, then the window fragment 、 Equal The heart rate characteristics are transmitted to Bluetooth.

[0024] The respiration-heart rate monitoring patch 203 is provided with an optical respiration sensor and a heart rate monitoring sensor.

[0025] An optical respiration sensor can be one or more LED sensors that use optical principles to monitor the fluctuations of breathing. When a person breathes, the chest or abdomen rises and falls, which are captured by the LED sensors and converted into electrical signals. These signals are processed to calculate respiratory rate and depth, and thus respiratory pressure.

[0026] Heart rate monitor sensors primarily use photoelectric measurement to monitor heartbeats. This method generates a signal related to the heartbeat by emitting light of a specific wavelength (usually green or red) through the skin and measuring the intensity of the light reflected or transmitted back by the skin tissue. As the heart beats, blood flows through the blood vessels beneath the skin, causing changes in vascular volume, which in turn affects the transmission and reflection of light. The photosensors on the heart rate monitor sensor receive these changing light signals and convert them into electrical signals. These electrical signals are processed and analyzed to determine the heart rate.

[0027] The blood pressure value acquisition module includes a blood pressure monitoring sensor 301, which is attached to the carotid artery on one side of the user. The blood pressure monitoring sensor 301 measures the blood pressure change signal over time and transmits it to the second chip 2. The second chip 2 slices the blood pressure change signal over time according to the time length to obtain blood pressure features corresponding to multiple window segments, such as the maximum amplitude and mean. The present invention does not make specific restrictions, and feature screening can be performed according to the specific epilepsy recognition model. For example, the maximum amplitude corresponding to the i-th window segment is , mean And other features, then the window fragment 、 Equal The blood pressure characteristics are transmitted to Bluetooth.

[0028] The blood oxygen value acquisition module includes a blood oxygen monitoring sensor 302. The blood oxygen monitoring sensor 302 is located at the carotid artery on the other side of the user. The blood oxygen saturation change signal over time is measured by the blood oxygen monitoring sensor 302 and transmitted to the second chip 2. The second chip 2 slices the blood oxygen saturation change signal over time according to the time length to obtain blood oxygen saturation features corresponding to multiple window segments, such as the maximum amplitude and mean. The present invention is not specifically limited and feature screening can be performed according to the specific epilepsy recognition model. For example, the maximum amplitude corresponding to the i-th window segment is , mean And other features, then the window fragment 、 Equal The blood oxygen characteristics are transmitted to Bluetooth.

[0029] The electromyographic signal acquisition module includes multiple electromyographic signal collectors 303, and the multiple electromyographic signal collectors 303 are attached to the muscle groups of the user's back neck. Multiple electromyographic signal sequences of multiple muscle groups are measured by the multiple electromyographic signal collectors 303; the first chip 1 filters, amplifies and performs analog-to-digital conversion on the electromyographic signal sequences of multiple muscle groups to obtain digital signals, and the second chip 2 slices the electromyographic signal sequences of multiple muscle groups according to the time length to obtain multiple electromyographic signal features corresponding to multiple window segments. For example, assuming there are M electromyographic signal collectors, M muscle group electromyographic signal sequences are measured by M electromyographic signal collectors, first transmitted to the first chip 1 for filtering, amplification, and analog-to-digital conversion, and then transmitted to the second chip 2. The mean value corresponding to the M i-th window segments is obtained. , the number of zero-crossing axes , the difference between the maximum positive amplitude and the maximum negative amplitude Other features, including , and then the window fragment 、 、 、 、 、 ...、 、 、 Equal The electromyographic signal characteristics are transmitted to Bluetooth.

[0030] The muscle pressure value acquisition module includes multiple muscle pressure sensors 304, and the multiple muscle pressure sensors 304 are attached to the muscle groups of the user's back neck. Multiple muscle pressure signals varying with time are measured by the multiple muscle pressure sensors 304 and transmitted to the second chip 2. The second chip 2 slices the multiple muscle pressure signals varying with time according to the length of time to obtain multiple muscle pressure features corresponding to multiple window segments, such as maximum amplitude and mean. The present invention does not make specific restrictions, and feature screening can be performed according to the specific epilepsy identification model. For example, assuming there are N muscle pressure sensors, N muscle pressure signals varying with time are measured by the N muscle pressure sensors and transmitted to the second chip 2. The maximum amplitude corresponding to the N i-th window segments is obtained. , mean Other features, including , and then the window fragment 、 、 、 ... 、 Equal The muscle pressure characteristics are transmitted to Bluetooth.

[0031] Based on the original EEG signals, the host computer extracts the time domain features of each window segment from the two channel EEG signals, such as the mean, the number of zero crossings, the difference between the maximum positive amplitude and the maximum negative amplitude, etc. For example, the mean value mean_D, the number of zero crossings zero_D, and the difference between the maximum positive amplitude and the maximum negative amplitude mxin_D of the i-th window segment constitute feature list 1: , and similarly we get , a total of time domain features.

[0032] The host computer also performs frequency band decomposition on the original EEG signals of each window segment of the two channel EEG signals, decomposing them into multiple frequency bands, and extracting frequency domain features from the original EEG signals in each frequency domain, such as average frequency, spectral peak frequency, spectral entropy, etc. Assuming that the decomposition is into p frequency bands, the original EEG signals of each window segment of each channel are disassembled into p frequency domain signals, and frequency domain features are extracted from each frequency domain signal, such as average frequency, spectral peak frequency, spectral entropy, etc., a total of q frequency domain features, so that the EEG signals of each channel can be obtained. frequency domain features.

[0033] Of course, the time domain features and frequency domain features are shown in Table 2. The above are just a few of them.

[0034] Table 2. Time domain characteristics and frequency domain characteristics

[0035] Based on the same inventive concept, another embodiment of the present invention provides an epileptic seizure warning and rescue method, which uses the epileptic seizure warning and rescue system of the above embodiment, and specifically includes the following steps: The host computer is based on a pre-trained epilepsy recognition model, such as a machine learning model (such as SVM (Support Vector Machine, support vector machine), decision tree, gradient boosting tree, etc.), BP neural network, etc., and inputs the EEG features, respiratory rate features, respiratory depth features, blood pressure features, blood oxygen saturation features, multiple electromyographic signal features, and multiple muscle pressure features corresponding to each window segment to determine the epilepsy recognition result corresponding to each window segment; for example, as mentioned above, a total of + + + + + + + features, and obtain the epilepsy recognition result corresponding to the current k-th window segment.

[0036] In order to reduce the rate of misidentification of epilepsy, Figure 3 As shown, if n consecutive window segments are determined to be epileptic seizures, the first window segment among the n consecutive window segments (n can be 3, 5, 7, etc., which is not specifically limited here) is set as the first calculation window; Starting from the first calculation window, within the next N window segments, if N1 window segments are all judged to be epileptic seizures, then the user is recorded as being highly suspected of having an epileptic seizure; When the user is highly suspected of having an epileptic seizure, the host computer sends an epilepsy confirmation command to the early warning and rescue unit (in the form of vibration, voice, etc., no specific restrictions are made here); After receiving the epilepsy confirmation command, the early warning and rescue unit activates the early warning; for example, the voice alarm issues a voice prompt and makes a voice call for help, which is expressed as "I am having an epileptic seizure and need help"; the luminous alarm issues a light prompt, which is expressed as the three-letter SOS mark on the neck ring body 101 flashing red; the rescue device automatically dials 120 or dials the reserved contact number; the locator locates the user's location.

[0037] When the early warning and rescue unit responds to the first instruction input by the user, it turns off the early warning and transmits the user operation result corresponding to the first instruction to the host computer, and the host computer restarts the determination; It should be noted that in actual use, if the user is not experiencing an epileptic seizure and is conscious, that is, the user is mistakenly identified as having an epileptic seizure, the user can quickly and continuously press the reset button three times (i.e., the first instruction input by the user) to indicate that the epileptic seizure is not occurring, and the corresponding user operation result is transmitted to the host computer, which clears the aforementioned determination process and restarts the determination; When the early warning and emergency call unit responds to the second instruction input by the user, it turns off the early warning, sends the user's current location, and makes an emergency call; It should be noted that in actual use, if the user has indeed had an epileptic seizure but is still able to control themselves, the user can quickly and continuously press the reset button twice (i.e., the first command input by the user) to indicate that the user has had an epileptic seizure and is able to control themselves and is conscious. The early warning and rescue unit can then call 120 for help and call the reserved accompanying personnel, and automatically send the current user's location; When the early warning rescue unit receives the epilepsy confirmation command, it waits If no response is received within the specified time, reconfirmation is performed, including: If n consecutive window segments (n can be 3, 5, 7, etc., and is not specifically limited here) are determined to be epileptic seizures, the first window segment in the n consecutive window segments is again recorded as the first calculation window; Starting from the first calculation window, within the next N window segments, if N2 window segments are all judged to be epileptic seizures, it is recorded that the user has had an epileptic seizure and is unconscious; When the user has had an epileptic seizure and is unconscious, the host computer sends an epilepsy reconfirmation command to the early warning and rescue unit; After receiving the epilepsy reconfirmation command, the early warning and emergency call unit transmits the user's current location and initiates a call for help. Furthermore, a voice call for help function is activated, alerting nearby people. The distress call can be pre-set, such as "I'm having an epileptic seizure and need help," or customized. If the user's epileptic seizure occurs at night, a warning light on the collar flashes "SOS." The color can be red, yellow, or other colors, but this is not limited here.

[0038] In a specific implementation case, sunset can be identified as night by a mobile phone or PC, and a night instruction can be sent to the neck ring, but the present invention does not limit the night recognition method to this specific recognition method.

[0039] Specifically, a battery indicator is provided on the outer surface of the neck ring body 101 to display the battery level, thereby providing a battery reminder. The battery can be charged via a wired method, such as using a Type-C, USB interface, etc., which is not specifically limited here; or wireless charging can be used.

[0040] The neck ring body 101 is provided with a limiting ring belt, which can be of general or customized type: If it is a universal type, the concave arc of the limiting ring is designed according to the shape of the human neck, which can meet the basic limiting requirements; If it is customized, such as Figure 4 As shown, 3D modeling can be performed based on the user's neck shape, fully adapting to the user's needs, meeting the neck ring's position limit while providing the best comfort experience. When worn by the user, all sensors and patches are in the optimal contact position.

[0041] The adjustment buckle can adjust the tightness of the neck ring to make the user comfortable to wear; rotate the neck ring to put the limiting ring belt in the best position; the rotating neck ring can be disassembled into the front neck section and the back neck section. The front neck section is a universal accessory, and the back neck section can be customized according to user needs.

[0042] In summary, the epilepsy attack early warning and rescue system and method of the present invention have the following advantages: 1. Because EEG signals are generally decomposed by frequency bands, time-frequency features and frequency domain features need to be extracted. Since the host computer, such as a PC or mobile phone, has better computing power, feature extraction of EEG signals is performed on the PC or mobile phone. Feature extraction of other signals besides EEG signals can reduce Bluetooth power consumption and increase data transmission volume.

[0043] 2. It can reduce the misidentification rate of epilepsy.

[0044] 3. The main body of the neck ring is divided into the front neck section and the back neck section by the adjustment buckle. Among them, the front neck section is a universal design, and the back neck section is divided into two shapes: universal structure and customized structure, which is more convenient for users to use.

[0045] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the embodiments disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and variations can be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. An epileptic seizure warning and rescue system, characterized in that: It includes a neck ring body, an EEG signal acquisition module, a respiration-heart rate acquisition module, a blood pressure value acquisition module, a blood oxygen value acquisition module, an EMG signal acquisition module, a muscle pressure value acquisition module, a first chip, a second chip, Bluetooth, a wireless transmission coil, an early warning and rescue unit and a host computer; The EEG signal acquisition module and the electromyographic signal acquisition module are both connected to the first chip, the first chip, the respiration-heart rate acquisition module, the blood pressure value acquisition module, the blood oxygen value acquisition module, the muscle pressure value acquisition module and Bluetooth are all connected to the second chip, the wireless transmitting coil and the early warning and rescue unit are both connected to Bluetooth, and the wireless transmitting coil is wirelessly connected to the host computer.

2. The epileptic seizure early warning and rescue system according to claim 1, characterized in that: Adjustment buckles are provided on both sides of the neck ring body; the early warning and rescue unit includes a luminous alarm, a voice alarm, a call for help, a locator and a reset button.

3. The epileptic seizure early warning and rescue system according to claim 1, characterized in that: The EEG signal acquisition module includes two EEG acquisition patches. When used by the user, the two EEG acquisition patches are respectively attached to the skin behind the user's left ear and right ear, thereby collecting two-channel EEG signals; the first chip filters, amplifies and converts the two-channel EEG signals into digital signals, and the second chip slices the two-channel EEG signals according to the time length, and sends the original EEG signals to Bluetooth in the form of window fragments. Bluetooth transmits the original EEG signals to the host computer through the wireless transmitting coil.

4. The epileptic seizure early warning and rescue system according to claim 3, characterized in that: The respiration-heart rate acquisition module includes a respiration-heart rate monitoring patch, which is applied to the user's chest or abdomen. An optical respiration sensor and a heart rate monitoring sensor are provided in the respiration-heart rate monitoring patch to respectively collect signals of respiration frequency changing over time, respiration depth changing over time, and heart rate changing over time; a second chip slices the signals of respiration frequency changing over time, respiration depth changing over time, and heart rate changing over time according to time length to obtain respiration frequency features, respiration depth features, and heart rate features corresponding to multiple window segments.

5. The epileptic seizure early warning and rescue system according to claim 4, characterized in that: The blood pressure value acquisition module includes a blood pressure monitoring sensor, which is attached to the carotid artery on one side of the user. The blood pressure monitoring sensor measures the blood pressure change signal over time and transmits it to the second chip. The second chip slices the blood pressure change signal according to the time length to obtain blood pressure characteristics corresponding to multiple window segments.

6. The epileptic seizure early warning and rescue system according to claim 5, characterized in that: The blood oxygen value acquisition module includes a blood oxygen monitoring sensor, which is applied to the carotid artery on the other side of the user. The blood oxygen monitoring sensor measures the blood oxygen saturation change signal over time and transmits it to the second chip. The second chip slices the blood oxygen saturation change signal over time according to the time length to obtain blood oxygen saturation characteristics corresponding to multiple window segments.

7. The epileptic seizure early warning and rescue system according to claim 6, characterized in that: The myoelectric signal acquisition module includes multiple myoelectric signal collectors, which are attached to the muscle groups on the back of the user's neck, and measure multiple muscle group myoelectric signal sequences through the multiple myoelectric signal collectors; The first chip filters, amplifies and performs analog-to-digital conversion on the electromyographic signal sequences of multiple muscle groups to obtain digital signals. The second chip slices the electromyographic signal sequences of multiple muscle groups according to time length to obtain multiple electromyographic signal features corresponding to multiple window segments.

8. The epileptic seizure early warning and rescue system according to claim 7, characterized in that: The muscle pressure value acquisition module includes multiple muscle pressure sensors, which are attached to the muscle groups on the back of the user's neck. Multiple muscle pressure time-varying signals are measured by the multiple muscle pressure sensors and transmitted to the second chip. The second chip slices the multiple muscle pressure time-varying signals according to time length to obtain multiple muscle pressure features corresponding to multiple window segments.

9. The epileptic seizure early warning and rescue system according to claim 8, characterized in that: The host computer extracts the time domain features of each window segment from the two-channel EEG signals based on the original EEG signals; performs frequency band decomposition on the original EEG signals of each window segment of the two-channel EEG signals into multiple frequency bands, and extracts frequency domain features from the original EEG signals of each frequency band.

10. A method for early warning and seeking help for epileptic seizures, characterized in that: Using the epileptic seizure early warning and rescue system according to claim 9, the method comprises: Based on a pre-trained epilepsy recognition model, the host computer determines the epilepsy recognition result for each window segment according to the time domain features, frequency domain features, respiratory rate features, respiratory depth features, blood pressure features, blood oxygen saturation features, multiple electromyographic signal features, and multiple muscle pressure features corresponding to each window segment. If n consecutive window segments are determined to be epileptic seizures, the first window segment among the n consecutive window segments is set as the first calculation window; Starting from the first calculation window, within the next N window segments, if N1 window segments are all judged to be epileptic seizures, then the user is recorded as being highly suspected of having an epileptic seizure; When a user is highly suspected of having an epileptic seizure, the host computer sends an epilepsy confirmation command to the early warning and rescue unit; After receiving the epilepsy confirmation instruction, the early warning and rescue unit starts the early warning; When the early warning and rescue unit responds to the first instruction input by the user, the early warning is turned off, and the user operation result corresponding to the first instruction is transmitted to the host computer, and the host computer restarts the determination; When the early warning and emergency call unit responds to the second instruction input by the user, the early warning is turned off, the user's current location is sent, and an emergency call is made; When the early warning and rescue unit receives the epilepsy confirmation instruction, it waits If no response is received within the specified time, reconfirmation is performed, including: If n consecutive window segments are determined to be epileptic seizures, the first window segment in the n consecutive window segments is again recorded as the first calculation window; Starting from the first calculation window, within the next N window segments, if N2 window segments are all judged to be epileptic seizures, it is recorded that the user has had an epileptic seizure and is unconscious; When the user has had an epileptic seizure and is unconscious, the host computer sends an epilepsy reconfirmation command to the early warning and rescue unit; After receiving the epilepsy reconfirmation instruction, the early warning and help-seeking unit sends the user's current location and makes a help-seeking call.

Images