Electrical stimulation awakening treatment system and device based on unsupervised learning model

Through the unsupervised learning model and electrical stimulation system, combined with EEG signal classification and electrical stimulation intervention, the problem of insufficient timeliness and effectiveness of narcolepsy treatment in the prior art is solved, and a safe and highly specific non-existential treatment is achieved Drug treatment plans avoid side effects of drugs.

CN119034070AActive Publication Date: 2024-11-29XUANWU HOSPITAL OF CAPITAL UNIV OF MEDICAL SCI
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411558082.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-04
Publication Date
2024-11-29
Estimated Expiration
2044-11-04

AI Technical Summary

Technical Problem

In the treatment of narcolepsy, pure EEG signal monitoring and identification of awake and sleep states is not effectively regulated, resulting in insufficient timeliness and effectiveness of treatment, and the side effects of relying on drug treatment.

Method used

Using an electrical stimulation pro-awakening therapy system based on an unsupervised learning model, the patient's sleep state is detected and regulated by automatic classification of real-time EEG signals and electrical stimulation intervention, combining electrical stimulation of the vagus and trigeminal nerves with an autoencoder and K-Means algorithm. , realize non-drug treatment.

Benefits of technology

It improves the timeliness and effectiveness of treatment, avoids side effects of drugs, can accurately capture sleep state transitions and individual differences, enhances the specificity and safety of treatment, and provides a non-invasive, automated wake-up program.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119034070A_ABST
    Figure CN119034070A_ABST
Patent Text Reader

Abstract

The invention relates to an electrical stimulation awakening treatment system and device based on an unsupervised learning model. The system and device are used for solving the problem that in the prior art, personalized awakening cannot be effectively conducted on a narcolepsy patient in time. The system comprises a first stimulation module and a second stimulation module, the first stimulation module is configured to continuously stimulate the vagus nerve of the patient during the day; the second stimulation module is configured in the working period of the first stimulation module, and based on the time-frequency characteristics of EEG signals collected at the frontal center Fz position, the state of the patient is detected and classified in an unsupervised learning mode; and when it is detected that the patient is in the sleep or sleep state, performing pulse stimulation on the trigeminal nerves of the patient until it is detected that the patient is in a waking state. According to the scheme, non-invasive electrical stimulation awakening treatment is adopted, safety is achieved, sudden daytime sleep can be intervened in time, and personalized awakening treatment can be carried out on different patients under the condition that no external label exists through the adopted unsupervised learning method.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This disclosure relates to the field of medical technology, and more particularly to an electrical stimulation-induced wakefulness therapy system based on an unsupervised learning model. This technical solution is a major project under the Science and Technology Innovation 2030 project, "Brain Science and Brain-Inspired Research," and is designated "Science and Technology Innovation 2030+2021ZD0204300." Background Art

[0002] Narcolepsy is a chronic neurological disorder whose primary symptoms include uncontrollable daytime sleepiness and sudden onset of sleep, which increases the risk of sudden events and severely impacts patients' work and personal lives. Currently, common treatments rely heavily on medication, but drug dependency and side effects are driving a growing demand for non-drug treatments.

[0003] Existing technologies mainly focus on simply identifying wakefulness and sleep states through EEG signal monitoring, but do not use this to regulate or regulate electrical stimulators based on other parameters for real-time wakefulness-promoting treatment. For patients with narcolepsy, the timeliness and effectiveness are slightly insufficient. Summary of the Invention

[0004] To address the aforementioned issues in existing technologies, this disclosure proposes an electrical stimulation wakefulness therapy system based on an unsupervised learning model. This system combines automatic classification of real-time EEG signals with electrical stimulation wakefulness intervention to provide a novel wakefulness-promoting solution for narcolepsy patients. The specific technical solution is as follows.

[0005] On the first aspect, this case proposes an electrical stimulation wakefulness treatment system based on an unsupervised learning model, the system comprising a first stimulation module and a second stimulation module; the first stimulation module is configured to continuously stimulate the patient's vagus nerve during the day; the second stimulation module is configured during the operation of the first stimulation module, and uses an unsupervised learning method to detect and classify the patient's status based on the time-frequency characteristics of the EEG signal collected at the frontal central Fz position; when the patient is detected to be in a sleeping or drowsy state, the patient's trigeminal nerve is stimulated with electrical pulses until the patient is detected to be in an awake state.

[0006] In one embodiment of the above technical solution, the EEG signal collected based on the fronto-central Fz position is preprocessed, and the preprocessed EEG data is subjected to a short-time Fourier transform;

[0007] The preprocessing is to use a Butterworth filter to perform 0.5 Hz high-pass filtering and 35 Hz low-pass filtering to remove low-frequency drift, electrocardiogram and electromyography artifacts to obtain EEG data.

[0008] In one embodiment of the above technical solution, detection and classification are achieved through an unsupervised learning model. The unsupervised learning model first extracts local features based on the EEG signal collected at the fronto-central Fz position, and reduces the spatial size to achieve preliminary dimensionality reduction. After flattening the features of the preliminary dimensionality reduction, sequence features are obtained. The sequence features are then compressed into a vector of a fixed length in the time dimension to achieve time dimensionality reduction, and the patient state features are obtained. Finally, the patient state features are detected and classified.

[0009] In one implementation of the above technical solution, the unsupervised learning model is composed of an autoencoder model and a clustering algorithm.

[0010] In one implementation of the above technical solution, the autoencoder model is composed of a convolutional neural network and a long short-term memory network.

[0011] In one implementation of the above technical solution, the clustering algorithm is preferably a K-Means algorithm.

[0012] In one embodiment of the above technical solution, the first stimulation module implements stimulation on the inner and outer sides of the middle of the tragus at the entrance of the unilateral external auditory canal, and the stimulation parameters are current intensity 0.5mA, frequency 25Hz, stimulation time 30s, interval time 30s, and pulse width 200-300μs.

[0013] In one embodiment of the above technical solution, the second stimulation module is implemented in the supraorbital nerve, and automatically triggers the stimulation pulse when it is detected that the patient is in a sleep or drowsy state. The stimulation parameters are a current intensity in the range of 10-15 mA, a stimulation frequency of 40 Hz, and a pulse width of 200 μs.

[0014] In one embodiment of the above technical solution, the EEG signal of the frontocentral FZ is collected with the left or right ear electrode as a reference, with a sampling rate of 512 Hz.

[0015] In a second aspect, the present disclosure proposes an electrical stimulation awakening therapy device based on an unsupervised learning model, characterized in that it includes a memory and a processor, and the memory stores a computer program that can be loaded by the processor and executed by any of the above systems.

[0016] Beneficial technical effects:

[0017] (1) Through EEG signal regulation, non-invasive electrical stimulation to promote wakefulness treatment is implemented. Compared with the existing treatment methods for narcolepsy, which mainly rely on drugs and are prone to drug side effects, this program is safe. However, compared with sudden daytime sleepiness, it is impossible to provide timely intervention. Existing EEG monitoring methods are mostly used for analysis of sleep structure and lack direct combination with treatment methods. This program effectively utilizes the advantages of EEG technology in highly sensitive and accurate judgment of sleep status, thereby improving the effectiveness and timeliness of treatment.

[0018] (2) This scheme adopts a machine learning model to construct an autoencoder to extract deep features of EEG signals. Compared with the existing threshold control method based on HRV heart rate variability parameters, this scheme can effectively capture subtle changes in the sleep state transition process and automatically adapt to the subtle differences in individual sleep patterns. The classification accuracy is improved, and the accuracy and specificity of the control stimulation treatment are also stronger.

[0019] (3) This program uses an unsupervised learning model, which can effectively deal with data differences between different patients without external labels. Even if the sleep pattern of the same individual may change over time, it can adapt to data changes through dynamic clustering methods, thereby significantly improving the specificity and convenience of the overall treatment plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 、 one Schematic diagram of the overall process in this embodiment.

[0022] In the figure, 110 - trigeminal nerve stimulation, 111 - frontal area EEG signal acquisition, 112 - time-frequency feature extraction and construction of autoencoder model dimensionality reduction, 113 - unsupervised real-time clustering analysis, 114 - determination of wakefulness, 115 - stopping trigeminal nerve electrical stimulation, 116 - triggering trigeminal nerve electrical stimulation, 120 - vagus nerve stimulation, 130 - wake-up treatment for patients with narcolepsy. DETAILED DESCRIPTION

[0023] For patients with narcolepsy, the symptoms of daytime sleepiness have a significant impact on these patients and are difficult to control and respond to in a timely manner. They are also sudden and pose risks to patients' lives. This program proposes an electrical stimulation wake-up treatment system based on an unsupervised learning model to effectively help patients control the risks brought by the disease.

[0024] The following provides a clear and complete description of how the technical solution of this case is implemented. Obviously, the described implementation methods are only part of the implementation methods of this case, not all of them. Based on the implementation methods of this case, all other implementation methods obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0025] (1) Data acquisition module

[0026] The data acquisition module is configured to collect single-channel EEG (electroencephalogram) data from the frontal region of patients with narcolepsy. During acquisition, the location of the frontal center Fz is determined according to the international 10-20 system, with the left or right ear electrode as the reference electrode. The sampling rate is 512Hz. This data is used to monitor the patient's brain activity characteristics in real time under different states.

[0027] (2) Signal preprocessing module

[0028] The collected frontal EEG signals were preprocessed by using a Butterworth filter with a 0.5 Hz high-pass filter and a 35 Hz low-pass filter to remove low-frequency drift, ECG and EMG artifacts, and obtain cleaner EEG signals for subsequent feature extraction.

[0029] (3) Signal processing module

[0030] Short-time Fourier transform (STFT) analysis is performed on the preprocessed EEG data to extract the time-frequency characteristics of the signal. The spectrum amplitude calculated by STFT provides information about the energy distribution across the entire frequency range.

[0031] Dimensionality reduction is performed using a trained autoencoder model to compress high-dimensional input features into low-dimensional representations for easier analysis. Real-time unsupervised cluster analysis is performed on the reduced feature data to classify EEG signals into two states: awake or asleep. Compared to traditional supervised learning, this unsupervised learning approach eliminates the need for clinician intervention and pre-classification when constructing patient-specific datasets. While maintaining specificity and accuracy, it improves overall process efficiency and ensures independent user operation.

[0032] In one embodiment, the autoencoder model comprises a CNN model and an LSTM model connected in series. First, the input time-frequency features are processed by a convolutional neural network (CNN). The CNN extracts local features and reduces the spatial dimension through convolution and pooling operations, thereby achieving preliminary dimensionality reduction. These features are then flattened and input into a long short-term memory (LSTM) network. The LSTM further encodes the sequence features in the temporal dimension, compressing them into a fixed-length vector to achieve temporal dimensionality reduction. This entire process, through the spatial dimensionality reduction of the CNN and the temporal dimensionality reduction of the LSTM, ultimately results in a low-dimensional representation that contains the original information while removing a significant amount of redundancy and noise, providing a more effective feature representation for subsequent clustering or classification.

[0033] In one implementation, the cluster analysis uses a K-Means algorithm.

[0034] (IV) Stimulus Control Feedback Module

[0035] The stimulation control and feedback module consists of two parts: the first stimulation module and the second stimulation module, which respectively stimulate the vagus nerve and the trigeminal nerve. Both utilize transcutaneous electrical stimulation. For vagus nerve stimulation, positive and negative electrodes are placed between the medial and lateral sides of the tragus at the entrance to the left (or right) external auditory canal (where branches of the vagus nerve afferent fibers are located) for continuous daytime stimulation. Stimulation parameters are set as a current of 0.5 mA, a frequency of 25 Hz, a stimulation duration of 30 seconds, a rest interval of 30 seconds, and a pulse width of 200-300 μs. Trigeminal nerve stimulation targets the supraorbital nerve, which branches from the supraorbital notch to the forehead and parietal skin. Based on real-time clustering results, the stimulation module determines whether the patient is asleep or drowsy. If sleep or drowsy is detected, a wake-promoting electrical stimulation pulse is automatically triggered to stimulate the supraorbital nerve until a wakeful EEG state is detected. Under safe conditions, the current is within the range of 10-15 mA, the stimulation frequency is 40 Hz, and the pulse width is 200 μs.

[0036] The above-mentioned daytime is the patient's activity time other than normal sleeping time. Normal sleeping time is the patient's sleep and rest time like normal people, not the patient's sudden sleep time.

[0037] The terms "first" and "second" mentioned above are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the quantity of the technical features indicated. Therefore, the terms "first" and "second" may explicitly or implicitly include one or more of the features.

[0038] Figure 1The figure is a schematic diagram of the overall process in one embodiment. The stimulation performed when performing wakefulness treatment (130) on a narcoleptic patient includes two parts, one part is trigeminal nerve stimulation (110), and the other part is vagus nerve stimulation (120). The patient's vagus nerve is continuously stimulated during the day. When implementing trigeminal nerve stimulation, frontal EEG signal acquisition (111), video feature extraction and construction of an autoencoder model for dimensionality reduction (112), and unsupervised real-time clustering analysis (113) are performed in sequence. The patient's state of awakening is determined based on the analysis results (114). If the patient is awake, the trigeminal nerve electrical stimulation is stopped (115); otherwise, the trigeminal nerve electrical stimulation is triggered (116).

[0039] In summary, this solution combines EEG monitoring and non-invasive electrical stimulation therapy to provide a more immediate and effective narcolepsy treatment system. Compared with other methods such as the HRV fatigue index, this solution provides a timely warning method with greater specificity and accuracy. It does not rely on manual labeling by experts and is more efficient. The system can monitor the patient's condition in real time and intervene promptly when daytime sleep attacks occur. It also enhances the patient's daytime excitability by continuously stimulating the vagus nerve. This dual mode ensures the patient's quality of life and avoids drug side effects and long-term dependence. In addition, this solution uses non-invasive treatment methods, which are safer and suitable for long-term treatment and daily management.

[0040] Through the above description of the embodiments, those skilled in the art will clearly understand that the disclosed system can be implemented using software plus necessary general-purpose hardware. Of course, it can also be implemented using dedicated hardware, including application-specific integrated circuits, dedicated CPUs, dedicated memories, and dedicated components. Generally speaking, any function performed by a computer program can be easily implemented using corresponding hardware. Moreover, the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits, or dedicated circuits. However, for the present disclosure, software implementation is often the preferred embodiment.

[0041] Although the embodiments of the present disclosure have been described above with reference to the accompanying drawings, the present disclosure is not limited to the aforementioned specific embodiments and application areas. For example, the present disclosure may also be applied to preventing drowsiness and preventing driver fatigue. The aforementioned specific embodiments are merely illustrative and instructive, and are not restrictive. A person of ordinary skill in the art, guided by this specification and without departing from the scope of protection of the claims of the present disclosure, may also devise various other forms, all of which fall within the scope of protection of the present disclosure.

Claims

1. An electrical stimulation awakening therapy system based on an unsupervised learning model, characterized in that: The system includes a first stimulation module and a second stimulation module; The first stimulation module is configured to continuously stimulate the patient's vagus nerve during the day; The second stimulation module is configured during the operation of the first stimulation module to detect and classify the patient's condition based on the time-frequency characteristics of the EEG signal collected at the frontal central Fz position using an unsupervised learning method; when it is detected that the patient is in a sleeping or drowsy state, the patient's trigeminal nerve is pulsed stimulated until the patient is detected to be in an awake state.

2. The system according to claim 1, characterized in that: The EEG signals collected based on the fronto-central Fz position were preprocessed, and the preprocessed EEG data were subjected to short-time Fourier transform; The preprocessing is to use a Butterworth filter to perform 0.5 Hz high-pass filtering and 35 Hz low-pass filtering to remove low-frequency drift, electrocardiogram and electromyography artifacts to obtain EEG data.

3. The system according to claim 1, characterized in that: Detection and classification are achieved through an unsupervised learning model. The unsupervised learning model first extracts local features based on the EEG signal collected at the frontal central Fz position, and reduces the spatial size to achieve preliminary dimensionality reduction. After flattening the features of the preliminary dimensionality reduction, the sequence features are obtained. The sequence features are then compressed into a vector of a fixed length in the time dimension to achieve time dimensionality reduction, and the patient state features are obtained. Finally, the patient state features are detected and classified.

4. The system according to claim 3, characterized in that The unsupervised learning model is composed of an autoencoder model and a clustering algorithm.

5. The system according to claim 4, characterized in that The autoencoder model is composed of a convolutional neural network and a long short-term memory network.

6. The system according to claim 4, characterized in that The clustering algorithm is preferably a K-Means algorithm.

7. The system according to claim 1, characterized in that The first stimulation module implements stimulation at the inner and outer sides of the middle of the tragus at the entrance of the unilateral external auditory canal, and the stimulation parameters are current intensity 0.5mA, frequency 25Hz, stimulation time 30s, interval time 30s, and pulse width 200-300μs.

8. The system according to claim 1, characterized in that The second stimulation module is implemented on the supraorbital nerve, and automatically triggers a stimulation pulse when it detects that the patient is in a sleeping or drowsy state. The stimulation parameters are a current intensity in the range of 10-15 mA, a stimulation frequency of 40 Hz, and a pulse width of 200 μs.

9. The system according to claim 1, characterized in that Features: The EEG signals of the frontocentral FZ were collected using the left or right ear electrodes as reference, with a sampling rate of 512 Hz.

10. An electrical stimulation awakening treatment device based on an unsupervised learning model, characterized in that: The system comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the system as claimed in any one of claims 1 to 9.

Citation Information

Patent Citations

  • Method and device for detection of sleep apnea fragment based on unsupervised feature learning

    CN110801221A

  • Wearable peripheral nerve stimulation for the treatment of diseases utilizing rhythmic biological processes

    CN113784748A

  • Awakening promoting instrument

    CN113908395A

  • Sleep quality analysis method and device, electronic equipment and computer readable medium

    CN115192042A

  • Electric nerve stimulation device and method for resisting fatigue and promoting alertness

    CN118161748A