A depression population determination system and method based on asynchronous electroencephalogram

Abstract

The application discloses a kind of depression crowd determination system and method based on asynchronous electroencephalogram, including asynchronous electroencephalogram acquisition module, asynchronous electroencephalogram signal preprocessing module, asynchronous electroencephalogram timing feature extraction module, asynchronous electroencephalogram depression crowd determination model and feedback module, the output of asynchronous electroencephalogram acquisition module is connected with the input of asynchronous electroencephalogram signal preprocessing module, the output of asynchronous electroencephalogram signal preprocessing module is connected with the input of asynchronous electroencephalogram timing feature extraction module, the output of asynchronous electroencephalogram timing feature extraction module is connected with the input of asynchronous electroencephalogram depression crowd determination model, the output of asynchronous electroencephalogram depression crowd determination model is connected with the input of feedback module.The application uses the above-mentioned one kind of depression crowd determination system and method based on asynchronous electroencephalogram, by collecting and analyzing the timing feature of electroencephalogram signal, in combination machine learning algorithm, realize the accurate determination and early identification to depression.

Description

Technical Field

[0001] This invention relates to the fields of electroencephalogram (EEG) signal analysis and mental health monitoring, and in particular to a system and method for identifying depressed individuals based on asynchronous EEG. Background Technology

[0002] Currently, the diagnosis of depression mainly relies on clinical symptom assessment, psychological questionnaires, and physician judgment. While these methods are effective in screening for depression, they have the following limitations:

[0003] High Subjectivity: Traditional depression assessment methods rely on doctors' subjective judgment, and the results may be influenced by factors such as the doctor's experience and the patient's self-report. Insufficient Sensitivity: Many patients with depression may mask their mood fluctuations due to social and family pressures, making it difficult for traditional diagnostic methods to accurately identify early or mild depression. Lack of Physiological Indicators: Current depression diagnostic methods lack objective physiological indicators to support their findings, resulting in a lack of precise evidence in pathological research and early diagnosis. To make depression diagnoses more objective and accurate, scientists have begun to focus on electroencephalography (EEG) signals, especially the potential of EEG temporal characteristics for identifying depression. Although EEG, as a non-invasive, real-time physiological signal detection technology, has been applied to research on neurological diseases, existing EEG-based methods for determining depression have the following problems: Limitations of Synchronous Acquisition Methods: Most existing EEG acquisition methods are based on synchronous acquisition mechanisms, which cannot effectively capture the asynchronous nature of different brain regions processing emotional information. This makes temporal analysis of EEG unable to reflect true brain electrical activity. Lack of high temporal accuracy analysis: Existing methods typically lack detailed analysis of the temporal sequence of EEG signals, making it difficult to extract key temporal features related to depression from asynchronous signals. Significant individual differences: The EEG activity of patients with depression exhibits strong individual variations, which traditional methods fail to account for, resulting in low recognition rates and accuracy.

[0004] Therefore, there is an urgent need for a new method for identifying depression that can accurately capture asynchronous activity in EEG signals and combine it with high-time-precision analysis methods to improve the sensitivity and accuracy of diagnosis. Summary of the Invention

[0005] The purpose of this invention is to provide a system and method for identifying depressed individuals based on asynchronous EEG. By acquiring and analyzing the temporal characteristics of EEG signals and combining them with machine learning algorithms, it achieves accurate identification and early recognition of depression, especially in the application of asynchronous EEG signal acquisition and high temporal accuracy analysis.

[0006] This invention provides a system and method for identifying depressed individuals based on asynchronous EEG, comprising an asynchronous EEG acquisition module, an asynchronous EEG signal preprocessing module, an asynchronous EEG temporal feature extraction module, an asynchronous EEG depression identification model, and a feedback module. The asynchronous EEG acquisition module includes a specific event stimulation unit and an asynchronous sampling mechanism unit. The output of the asynchronous EEG acquisition module is connected to the input of the asynchronous EEG signal preprocessing module, the output of the asynchronous EEG signal preprocessing module is connected to the input of the asynchronous EEG temporal feature extraction module, the output of the asynchronous EEG temporal feature extraction module is connected to the input of the asynchronous EEG depression identification model, and the output of the asynchronous EEG depression identification model is connected to the input of the feedback module.

[0007] Preferably, the specific event stimulation unit includes positive, negative, and neutral audio stimuli; the asynchronous sampling mechanism unit includes an asynchronous neuromorphic chip and an analog-to-digital converter (ADC).

[0008] Preferably, the asynchronous EEG timing feature extraction module includes a timing analysis method.

[0009] Preferably, the asynchronous EEG model for identifying depressed individuals employs a deep learning model that combines RCNN and LSTM.

[0010] Preferably, a method for identifying depressed individuals based on asynchronous EEG includes the following steps:

[0011] Step S1: In the asynchronous EEG acquisition module, brain region activity is induced by stimulating specific event units in the asynchronous EEG acquisition module, and EEG signals from different brain regions are accurately acquired by the asynchronous sampling mechanism unit in the asynchronous EEG acquisition module.

[0012] The subjects were stimulated with six positive, six negative, and six neutral audio segments. The subjects listened to 18 audio segments with their eyes closed. Each audio segment lasted 1-6 seconds. After a specific event was induced at each EEG acquisition point, the event feature matching unit of the asynchronous neuromorphic chip matched the event and controlled the pulse generator to generate an enable signal, which activated the analog-to-digital converter (ADC) to acquire EEG signals for 6 seconds. After all channels were activated, the playback of the audio segment stopped. After the acquisition was completed, the next audio segment was played, and the cycle continued until all audio segments were played.

[0013] Step S2: In the asynchronous EEG signal preprocessing module, the acquired EEG signals are denoised, filtered, and segmented.

[0014] Step S3: In the asynchronous EEG temporal feature extraction module, key temporal features of the EEG signal are extracted based on the temporal analysis method;

[0015] Step S4: In the asynchronous EEG depression diagnosis model, the RCNN-LSTM fusion deep learning model is used to diagnose depression based on the extracted temporal features.

[0016] The intermediate layer features and emotional information of EEG data and temporal information are extracted by RCNN. The temporal features are fused by LSTM and the temporal characteristics are modeled. The combination of brain regions and audio stimulus data segments is optimized through cross-validation experiments to obtain the optimal classification results.

[0017] Step S5: In the feedback module, the diagnostic results are output in real time, providing patients with personalized treatment suggestions and linking with other medical devices to form an intelligent diagnosis and treatment closed loop.

[0018] Preferably, in step S1, all 18 audio segments are selected from the International Emotional Sounds Database (IADS-2).

[0019] Preferably, in step S1, the EEG acquisition points are calibrated with high precision using an asynchronous neuromorphic chip.

[0020] Therefore, the present invention adopts the above-mentioned asynchronous EEG-based system and method for identifying people with depression. By collecting and analyzing the temporal characteristics of EEG signals and combining them with machine learning algorithms, it achieves accurate identification and early recognition of depression, especially in the application of asynchronous EEG signal acquisition and high temporal accuracy analysis.

[0021] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0022] Figure 1 This is an overall system block diagram of the depressive population identification system and method based on asynchronous EEG of the present invention;

[0023] Figure 2 This is a schematic diagram of the audio-induced asynchronous EEG acquisition experimental process for a system and method for identifying depressed individuals based on asynchronous EEG, as described in this invention.

[0024] Figure 3 This is a schematic diagram of the audio stimulation process of the asynchronous EEG-based system and method for identifying depressed individuals according to the present invention.

[0025] Figure 4 This is a schematic diagram of the RCNN-LSTM fusion deep learning model of the depressive population identification system and method based on asynchronous EEG of the present invention;

[0026] Figure 5 This is a schematic diagram of the overall process of a system and method for identifying depressed individuals based on asynchronous EEG, as described in this invention. Detailed Implementation

[0027] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0028] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0029] The terms "first," "second," and similar words used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0030] Example 1

[0031] like Figures 1-5 As shown, this invention discloses a system and method for identifying depressed individuals based on asynchronous EEG, comprising an asynchronous EEG acquisition module, an asynchronous EEG signal preprocessing module, an asynchronous EEG temporal feature extraction module, an asynchronous EEG model for identifying depressed individuals, and a feedback module. The asynchronous EEG acquisition module includes a specific event stimulation unit and an asynchronous sampling mechanism unit. The specific event stimulation unit includes positive, negative, and neutral audio stimuli; the asynchronous sampling mechanism unit includes an asynchronous neuromorphic chip and an analog-to-digital converter (ADC).

[0032] The output of the asynchronous EEG acquisition module is connected to the input of the asynchronous EEG signal preprocessing module, used to transmit the acquired raw asynchronous EEG signals to the preprocessing module. The output of the asynchronous EEG signal preprocessing module is connected to the input of the asynchronous EEG temporal feature extraction module, so as to send the preprocessed signal to the feature extraction module; the asynchronous EEG temporal feature extraction module includes a temporal analysis method.

[0033] The output of the asynchronous EEG temporal feature extraction module is connected to the input of the asynchronous EEG depression diagnosis model, providing temporal feature data for the model. The asynchronous EEG depression diagnosis model employs an RCNN-LSTM fusion deep learning model. The output of the asynchronous EEG depression diagnosis model is connected to the input of the feedback module, transmitting the diagnosis results to the feedback module.

[0034] Step S1: In the asynchronous EEG acquisition module, brain region activity is induced by stimulating specific event units in the asynchronous EEG acquisition module, and EEG signals from different brain regions are accurately acquired by the asynchronous sampling mechanism unit in the asynchronous EEG acquisition module.

[0035] Six positive, six negative, and six neutral audio stimuli were used on the subjects in step S1. All 18 audio segments were selected from the International Emotional Sound System Database (IADS-2). The subjects listened to the 18 audio segments with their eyes closed. Each segment lasted 1-6 seconds. A specific event (e.g., spike signal, specific frequency band power, multiple neural impulses) was induced at each EEG acquisition point. The event feature matching unit of the asynchronous neuromorphic chip matched the signals, controlling the pulse generator to produce an enable signal, activating the analog-to-digital converter (ADC), and performing a 6-second EEG signal acquisition. Once all channels were activated, playback of the current audio segment stopped. After acquisition was complete, the next audio segment was played, and the cycle continued until all audio segments had been played. In step S1, the asynchronous neuromorphic chip performed high-precision timing calibration of the EEG acquisition points.

[0036] Step S2: In the asynchronous EEG signal preprocessing module, the acquired EEG signals are denoised, filtered, and segmented to remove interference and ensure signal purity.

[0037] Step S3: In the asynchronous EEG timing feature extraction module, based on the timing analysis method, extract key timing features of the EEG signal, including the excitation time sequence of brain regions, phase changes, amplitude changes, etc.

[0038] Step S4: In the asynchronous EEG-based depression diagnosis model, convolutional neural networks (CNN) and long short-term memory networks (LSTM) from deep learning are used as the foundation. An RCNN-LSTM fusion deep learning model is designed to improve the recognition rate of depressive disorders. Using the RCNN-LSTM fusion deep learning model, depression is diagnosed based on the extracted temporal features.

[0039] This study uses RCNN to extract intermediate layer features and emotional information from EEG data and temporal information. A recurrent convolutional neural network (RCNN) based on an improved traditional CNN model is employed to extract intermediate layer features and their underlying information from EEG data and temporal information generated by audio stimulation in different brain regions. This approach aims to fully explore the temporal characteristics of EEG signals from different brain regions and the inherent emotional information conveyed by EEG signals under different audio stimuli. Simultaneously, attention is paid to the temporal correlation information in the input EEG signals from different brain regions, allowing this temporal information to be better reflected in the activation of various modules and the correlation mechanisms within the model.

[0040] By utilizing LSTM to fuse temporal features and model temporal characteristics, and comprehensively considering the temporal properties of asynchronous EEG signals, the abstract and deep features of asynchronous EEG signals are preserved more comprehensively. Finally, through continuous cross-validation experiments, different combinations of brain regions and audio stimulus data segments are tried to find the optimal combination. The optimal combination of brain regions and audio stimulus data segments is obtained by optimizing the combination of brain regions and audio stimulus data segments through cross-validation experiments.

[0041] Step S5: In the feedback module, the diagnostic results are output in real time, providing patients with personalized treatment suggestions and linking with other medical devices to form an intelligent diagnosis and treatment closed loop.

[0042] Therefore, this invention employs the aforementioned asynchronous EEG-based system and method for identifying depressed individuals, accurately reflecting the asynchronous characteristics of EEG: Unlike traditional synchronous acquisition methods, this invention uses an asynchronous EEG acquisition mechanism, inducing brain region activity through specific event stimuli such as audio and visual stimuli, and collecting data according to the trigger sequence of the events, thus accurately reflecting the true temporal characteristics of EEG. This invention, through asynchronous EEG acquisition technology, can more accurately reflect the asynchronous activity of different brain regions during information processing, overcoming the limitations of traditional synchronous acquisition methods. High temporal accuracy analysis: By employing advanced temporal analysis methods (such as LSTM) to extract fine temporal features from EEG signals, it provides more accurate physiological evidence for the early diagnosis of depression. Using advanced temporal analysis methods to perform fine analysis of EEG signals can reveal the EEG characteristics of depressed patients at the temporal level, providing higher accuracy than existing methods. Personalized assessment: Combining individual differences in EEG, this invention trains a personalized depression assessment model through machine learning algorithms, effectively improving diagnostic accuracy and sensitivity. The depression diagnosis model of this invention can make personalized judgments based on the differences in each individual's EEG characteristics, reducing reliance on standardized EEG models and improving the sensitivity and accuracy of diagnosis.

[0043] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A system for identifying depressed individuals based on asynchronous electroencephalography (EEG), characterized in that, It includes an asynchronous EEG acquisition module, an asynchronous EEG signal preprocessing module, an asynchronous EEG temporal feature extraction module, an asynchronous EEG depression diagnosis model, and a feedback module. The asynchronous EEG acquisition module includes a specific event stimulation unit and an asynchronous sampling mechanism unit. The output of the asynchronous EEG acquisition module is connected to the input of the asynchronous EEG signal preprocessing module, the output of the asynchronous EEG signal preprocessing module is connected to the input of the asynchronous EEG temporal feature extraction module, the output of the asynchronous EEG temporal feature extraction module is connected to the input of the asynchronous EEG depression diagnosis model, and the output of the asynchronous EEG depression diagnosis model is connected to the input of the feedback module. In the asynchronous EEG acquisition module, brain region activity is induced by specific event units within the module, and EEG signals from different brain regions are precisely acquired through the asynchronous sampling mechanism unit within the module. The subjects were stimulated with six positive, six negative, and six neutral audio segments. The subjects listened to 18 audio segments with their eyes closed. Each audio segment lasted 1-6 seconds. After a specific event was induced at each EEG acquisition point, the event feature matching unit of the asynchronous neuromorphic chip matched the event and controlled the pulse generator to generate an enable signal, which activated the analog-to-digital converter (ADC) to acquire EEG signals for 6 seconds. After all channels were activated, the playback of the audio segment stopped. After the acquisition was completed, the next audio segment was played, and the cycle continued until all audio segments were played. In the asynchronous EEG signal preprocessing module, the acquired EEG signals are denoised, filtered, and segmented. In the asynchronous EEG temporal feature extraction module, key temporal features of EEG signals are extracted based on temporal analysis methods. In the asynchronous EEG-based depression diagnosis model, an RCNN-LSTM fusion deep learning model is used to diagnose depression based on extracted temporal features. The intermediate layer features and emotional information of EEG data and temporal information are extracted by RCNN. The temporal features are fused by LSTM and the temporal characteristics are modeled. The combination of brain regions and audio stimulus data segments is optimized through cross-validation experiments to obtain the optimal classification results. The feedback module outputs diagnostic results in real time, provides patients with personalized treatment suggestions, and works in conjunction with other medical devices to form an intelligent diagnosis and treatment closed loop.

2. The system for determining depression based on asynchronous EEG according to claim 1, characterized in that, The specific event stimulation unit includes positive, negative, and neutral audio stimuli; the asynchronous sampling mechanism unit includes an asynchronous neuromorphic chip and an analog-to-digital converter (ADC).

3. The system for determining depression based on asynchronous EEG according to claim 1, characterized in that, All 18 audio clips were selected from the International Emotional Voices Database (IADS-2).

4. The system for determining depression based on asynchronous EEG according to claim 1, characterized in that, High-precision timing calibration of EEG acquisition points is performed using an asynchronous neuromorphic chip.

Images