A new smart rapid screening device for depression / alzheimer's disease

Abstract

This invention discloses a novel intelligent rapid screening device for depression / Alzheimer's disease, used for early auxiliary detection of either condition. It comprises: an EEG acquisition module, a human-computer interaction module, a wireless transmission module, and an intelligent analysis module. The EEG acquisition module collects resting-state and task-oriented EEG signals from the subject. The human-computer interaction module selects the screening mode, inputs subject information, performs impedance detection, signal verification, and provides task guidance. The wireless transmission module enables data transmission between the modules. The intelligent analysis module receives the EEG signals, analyzes the data using a machine learning model, and outputs the screening results. This device uses dry electrode technology, eliminating the need for conductive adhesive. The brain-computer interface is made of skin-friendly material for comfortable wear. Wireless transmission and cloud analysis provide high flexibility. AI-based data analysis and pattern recognition improve diagnostic efficiency and accuracy.

Description

Technical Field

[0001] This invention relates to the field of medical devices, and more specifically, to a novel intelligent rapid screening device for depression / Alzheimer's disease. Background Technology

[0002] In existing technologies, the first technical solution for screening depression / Alzheimer's disease uses a combination of EEG acquisition equipment and physician analysis and diagnosis. The EEG acquisition equipment includes a wet EEG cap and a desktop EEG recorder. The wet EEG cap uses a wet electrode cap with multiple built-in wet electrodes, requiring conductive gel to collect EEG signals. The desktop EEG recorder is equipped with a portable EEG signal recorder, capable of recording EEG data in real time, but only supports wired data transmission to a computer system. The data acquisition procedure includes a standardized acquisition procedure and a multi-time-point acquisition procedure. The standardized acquisition procedure involves establishing a standardized EEG data acquisition process, including conducting the test in a quiet, controlled environment and guiding the patient to perform the test in a specific psychological state (such as relaxation and focus). Multi-time-point acquisition involves performing multiple EEG acquisitions on the same patient at different times (such as morning and evening) to assess intraday changes. The data processing and analysis steps include preprocessing, feature extraction, and machine learning classification. Preprocessing uses specialized software to preprocess the collected EEG data, including artifact removal, filtering, and signal amplification. Feature extraction involves extracting EEG features related to depression, such as the characteristics of frequency bands (theta waves, alpha waves, beta waves, etc.) and brain region connectivity. Machine learning classification uses machine learning algorithms, such as support vector machines (SVM) or deep learning models, to classify the EEGs of normal and depressed patients. During the physician's diagnosis, the processed data is first presented to the physician graphically, including EEG waveforms and brain activity maps. The physician then conducts a comprehensive analysis, considering EEG data, clinical symptoms, medical history, and other information to make a comprehensive diagnosis. Finally, a detailed diagnostic report is generated, including the EEG analysis results and the physician's professional opinion. In addition, after the diagnosis, regular follow-up examinations and treatment adjustments are necessary. Regular EEG follow-ups are conducted to monitor changes in the patient's condition and treatment effectiveness, and the treatment plan is adjusted based on changes in EEG and clinical responses.

[0003] The first existing technology described above has the following defects and shortcomings: (1) The complexity of data interpretation: The interpretation of EEG data is very complex and requires highly specialized knowledge.

[0004] (2) Technology acceptance: Popularizing new technologies in clinical practice may face challenges in terms of acceptance from medical professionals.

[0005] (3) Standardization and validation: Further research and validation are needed to establish standardized diagnostic procedures and evaluation criteria.

[0006] (4) Diagnostic accuracy: The accuracy needs to be improved and the misdiagnosis rate is too high.

[0007] (5) Complex operation: It requires the application of conductive glue for EEG collection.

[0008] In existing technologies, the second approach to screening for depression involves using medical scales for analysis. The primary consideration is selecting an appropriate medical scale, typically a widely used and validated depression assessment scale such as the Hamilton Depression Rating Scale (HAM-D), the Self-Rating Depression Scale (BDI), and the Depression and Anxiety Coping Questionnaire (DASS). When selecting a scale, factors such as the patient's age, cultural background, and language proficiency are taken into account. The patient completes the corresponding depression assessment scale, recording their self-reported scores according to the scale's instructions. The physician observes and records the patient's clinical manifestations and medical records, in conjunction with the scale results. Then, based on the scale's scoring criteria, the patient's total score and scores for each dimension are calculated. The scale scores are then combined with clinical diagnostic criteria to analyze the severity and type of the patient's symptoms, determining whether they meet the diagnostic criteria for depression. During the assessment, the physician needs to comprehensively consider scale scores, patient-reported symptoms, clinical manifestations, and other information to conduct a comprehensive assessment of depression, subsequently generating a detailed diagnostic report, including scale analysis results, the physician's professional opinion, and treatment recommendations. After diagnosis, treatment monitoring and adjustment are still required. Scales need to be used regularly to track and monitor the patient's symptoms, assess treatment effectiveness and symptom changes, and adjust the treatment plan based on scale assessment results and clinical response.

[0009] The second prior art described above has the following defects and shortcomings: (1) Subjective influence: The completion of the scale may be affected by the patient's subjective factors, such as emotional state and memory deviation.

[0010] (2) Scale selection: Different scales have different characteristics and applicable scopes. It is necessary to select the appropriate scale for assessment according to the specific situation.

[0011] (3) Clinical experience: Physicians need to have rich clinical experience and professional knowledge when analyzing scale results and making diagnoses.

[0012] (4) Diagnostic accuracy: The accuracy needs to be improved and the misdiagnosis rate is too high. Summary of the Invention

[0013] This invention provides a novel intelligent rapid screening device for depression / Alzheimer's disease, in order to solve the technical problems existing in the prior art.

[0014] To achieve the above objectives, the present invention provides a novel intelligent rapid screening device for depression / Alzheimer's disease, used for early auxiliary detection of depression or Alzheimer's disease, comprising: an EEG acquisition module, a human-computer interaction module, a wireless transmission module, and an intelligent analysis module. The EEG acquisition module is used to acquire the subject's resting-state EEG signals and task-oriented EEG signals; The human-computer interaction module is used to select screening modes, enter subject information, perform impedance detection, signal verification, and task guidance. The wireless transmission module is used to enable data transmission between the various modules; The intelligent analysis module is used to receive EEG signals, perform data analysis through machine learning models, and output screening results.

[0015] In one embodiment of the present invention, optionally, the intelligent analysis module employs a dual-modal fusion algorithm of resting-state EEG signals and task-state EEG signals; By combining and weighting the basic EEG characteristics during the resting phase with eyes closed, as well as the evoked EEG characteristics during the emotion picture classification task, the accuracy and specificity of early screening for depression or Alzheimer's disease can be improved.

[0016] In one embodiment of the present invention, the device may optionally be able to adaptively switch the weights of the EEG acquisition channels and the analysis model according to the screening mode; In the depression screening model, priority is given to extracting EEG features from brain regions related to emotion regulation; In the Alzheimer's disease screening model, the electroencephalogram (EEG) characteristics of brain regions related to cognitive function are extracted first to achieve targeted collection and analysis for screening different diseases.

[0017] In one embodiment of the present invention, optionally, the EEG acquisition module is an EEG cap, which includes multiple dry EEG sensors. The dry EEG sensor includes an outer EEG probe, a connecting cavity, a threaded base, an inner EEG probe, a built-in spring, and a flexible shell. The dry EEG sensor can be self-fixed without external limiting devices, which can reduce contact impedance and motion artifacts, and acquire high signal-to-noise ratio EEG signals. The inner ring EEG probe is used to part the hair and make close contact with the scalp, reducing contact resistance; The dry EEG sensor is self-fixed by a ring-shaped raised plane, reducing motion artifacts; The built-in spring and flexible shell allow the probe to adapt and fit closely to the scalp; The threaded base allows for the removal and replacement of electrodes.

[0018] In one embodiment of the present invention, optionally, the human-computer interaction module is a tablet computer, which is equipped with an interactive interface that supports the selection of depression screening mode and Alzheimer's disease screening mode, input of basic information of subjects, impedance detection, real-time display of EEG waveforms, three-minute guided rest with eyes closed, presentation of emotion picture classification tasks, and voice-assisted operation.

[0019] In one embodiment of the present invention, optionally, the wireless transmission module includes a router, and the tablet computer and the laptop computer are wirelessly connected via WiFi to achieve low-latency and stable data transmission.

[0020] In one embodiment of the present invention, optionally, the intelligent analysis module is a laptop computer with a built-in pre-trained machine learning model, which can preprocess, extract features and recognize patterns of resting-state EEG signals and task-state EEG signals, and output screening conclusions or risk warnings in PDF format.

[0021] In one embodiment of the present invention, optionally, the working process of the device includes: S1: Subjects wear EEG caps, select screening modes and enter information via tablet computers. Screening modes include depression screening or Alzheimer's disease screening. S2: Impedance detection and device status verification. Impedance detection is used to confirm whether the EEG cap is in normal contact with the scalp, and device status verification is used to verify whether the device is in normal working condition. S3: Collect the subject's resting brain signals with eyes closed for three minutes using an EEG cap; S4: The tablet computer displays mixed images containing both negative and positive content. Subjects classify the emotional attributes of the images based on their subjective judgments, while task-oriented EEG signals are collected. S5: The signal is wirelessly transmitted to the computer for intelligent analysis; S6: Output the screening result report.

[0022] In one embodiment of the present invention, optionally, task-state EEG signals are collected simultaneously when the subject subjectively categorizes images of mixed positive and negative emotions.

[0023] In one embodiment of the present invention, the screening results are optionally saved and output as a PDF file, including risk warnings or auxiliary diagnostic conclusions, for clinicians to make quick judgments.

[0024] The novel intelligent rapid screening device for depression / Alzheimer's disease provided by this invention has the following beneficial technical effects: (1) Comfort and flexibility: This device uses dry electrode technology, eliminating the need for conductive adhesive. Furthermore, the brain-computer interface is made of skin-friendly materials, ensuring user comfort. It utilizes wireless transmission and cloud-based analysis, offering high flexibility in use. (2) AI-enhanced analysis: AI is used for data analysis and pattern recognition, which improves the efficiency and accuracy of diagnosis.

[0025] (3) Personalized diagnosis: Based on individual bioelectrical signals and psychological assessment data, more personalized diagnosis of depression can be achieved.

[0026] (4) Diagnostic accuracy: The accuracy rate has increased dramatically, and the misdiagnosis rate has decreased significantly.

[0027] This invention, through a comprehensive approach that integrates electroencephalography (EEG) technology and AI analysis, can greatly enhance the diagnostic capabilities for depression / Alzheimer's disease, providing patients with more accurate, rapid, and personalized medical services. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is an overall schematic diagram of a novel intelligent rapid screening device for depression / Alzheimer's disease according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a dry EEG sensor according to an embodiment of the present invention; Figure 3 This is a cross-sectional view of a dry EEG sensor according to an embodiment of the present invention.

[0030] Explanation of reference numerals in the attached diagram: 1-Outer ring EEG probe; 2-Connecting cavity; 3-Threaded base; 4-Inner ring EEG probe; 5-Built-in spring; 6-Flexible outer shell. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] Figure 1 This is a schematic diagram of an embodiment of the novel intelligent rapid screening device for depression / Alzheimer's disease according to an invention. Figure 1As shown, the present invention provides a novel intelligent rapid screening device for depression / Alzheimer's disease, used for early auxiliary detection of depression or Alzheimer's disease, comprising: an EEG acquisition module, a human-computer interaction module, a wireless transmission module, and an intelligent analysis module; The EEG acquisition module is used to acquire the subject's resting-state EEG signals and task-oriented EEG signals; The human-computer interaction module is used to select screening modes, enter subject information, perform impedance detection, signal verification, and task guidance. The wireless transmission module is used to enable data transmission between the various modules; The intelligent analysis module is used to receive EEG signals, perform data analysis through machine learning models, and output screening results.

[0033] In one embodiment of the present invention, optionally, the intelligent analysis module employs a dual-modal fusion algorithm of resting-state EEG signals and task-state EEG signals; By combining and weighting the basic EEG characteristics during the resting phase with eyes closed, as well as the evoked EEG characteristics during the emotion picture classification task, the accuracy and specificity of early screening for depression or Alzheimer's disease can be improved.

[0034] In one embodiment of the present invention, the device may optionally be able to adaptively switch the weights of the EEG acquisition channels and the analysis model according to the screening mode; In the depression screening model, priority is given to extracting EEG features from brain regions related to emotion regulation; In the Alzheimer's disease screening model, the electroencephalogram (EEG) characteristics of brain regions related to cognitive function are extracted first to achieve targeted collection and analysis for screening different diseases.

[0035] Through dual-modal signal fusion and mode adaptive analysis, the device enables early, rapid, non-invasive, and intelligent assisted screening for depression and Alzheimer's disease. It has advantages such as comfortable wear, strong anti-artifact effect, simple operation, and reliable results, making it suitable for promotion and use in outpatient clinics, physical examination centers, communities, and primary healthcare institutions.

[0036] In one embodiment of the present invention, optionally, the EEG acquisition module is an EEG cap, which includes multiple dry EEG sensors. Figure 2 This is a schematic diagram of an embodiment of the dry EEG sensor of the present invention. Figure 3 This is a cross-sectional view of a dry EEG sensor according to an embodiment of the present invention. The dry EEG sensor includes an outer EEG probe 1, a connecting cavity 2, a threaded base 3, an inner EEG probe 4, a built-in spring 5, and a flexible shell 6. The dry EEG sensor can be self-fixed without external limiting devices, which can reduce contact impedance and motion artifacts, and acquire high signal-to-noise ratio EEG signals. The inner circle EEG probe 4 is used to part the hair and make close contact with the scalp, reducing contact resistance; The dry EEG sensor is self-fixed by a ring-shaped raised plane, reducing motion artifacts; The built-in spring 5 and flexible shell 6 allow the probe to adapt and fit closely to the scalp; The threaded base 3 allows for the removal and replacement of electrodes.

[0037] The dry EEG sensor utilizes the inner ring EEG probe 4 to part the hair, ensuring close contact between the probe and the scalp, reaching the scalp layer and reducing contact resistance between the electrodes and the skin. It eliminates the need for external limiting devices; the annular protrusion, under pressure, can be inserted between the hair ends for fixation, effectively reducing motion artifacts caused by electrode displacement during wear and enabling high signal-to-noise ratio EEG signals in conjunction with the inner ring EEG probe 4. The dry EEG sensor features a flexible shell 6 and an internal spring 5, ensuring close contact between the probe and the head. The dry EEG sensor connects to the EEG helmet frame via a threaded base 3, allowing for easy replacement of damaged or expired electrodes.

[0038] In one embodiment of the present invention, optionally, the human-computer interaction module is a tablet computer, which is equipped with an interactive interface that supports the selection of depression screening mode and Alzheimer's disease screening mode, input of basic information of subjects, impedance detection, real-time display of EEG waveforms, three-minute guided rest with eyes closed, presentation of emotion picture classification tasks, and voice-assisted operation.

[0039] Tablet computers are used for human-computer interaction, and their operation is simple and direct. Users can perform related functions through simple touch operations, which improves the ease of use and operational efficiency of the device.

[0040] In one embodiment of the present invention, optionally, the wireless transmission module includes a router, and the tablet computer and the laptop computer are wirelessly connected via WiFi to achieve low-latency and stable data transmission.

[0041] Routers act as data bridges, responsible for establishing a stable, high-speed local area network communication environment to ensure that tablets and laptops can communicate in real time.

[0042] In one embodiment of the present invention, optionally, the intelligent analysis module is a laptop computer with a built-in pre-trained machine learning model, which can preprocess, extract features and recognize patterns of resting-state EEG signals and task-state EEG signals, and output screening conclusions or risk warnings in PDF format.

[0043] The laptop computer serves as the computing power core and model hub of the entire system, storing deep learning models trained on a large amount of clinical data and a complex algorithm library. It performs data preprocessing and analysis on the collected EEG signals and outputs prediction results.

[0044] In one embodiment of the present invention, optionally, the working process of the device includes: S1: Subjects wear EEG caps, select screening modes and enter information via tablet computers. Screening modes include depression screening or Alzheimer's disease screening. S2: Impedance detection and device status verification. Impedance detection is used to confirm whether the EEG cap is in normal contact with the scalp, and device status verification is used to verify whether the device is in normal working condition. S3: Collect the subject's resting brain signals with eyes closed for three minutes using an EEG cap; S4: The tablet computer displays mixed images containing both negative and positive content. Subjects classify the emotional attributes of the images based on their subjective judgments, while task-oriented EEG signals are collected. S5: The signal is wirelessly transmitted to the computer for intelligent analysis; S6: Output the screening result report.

[0045] In one embodiment of the present invention, optionally, task-state EEG signals are collected simultaneously when the subject subjectively categorizes images of mixed positive and negative emotions.

[0046] In one embodiment of the present invention, the screening results are optionally saved and output as a PDF file, including risk warnings or auxiliary diagnostic conclusions, for clinicians to make quick judgments.

[0047] This invention integrates an EEG cap, a tablet device, a computer device, and a router device. The EEG cap is well-designed, made of skin-friendly materials, increasing wearing comfort and effectively reducing discomfort and pressure points on the head, thus improving comfort during extended wear. Data transmission is achieved through a wireless network (such as Wi-Fi), providing users with a convenient and comfortable experience for monitoring brain activity and processing data. The EEG cap is the core component, made of lightweight materials and equipped with multiple electrodes, designed to provide a comfortable wearing experience while maintaining stability and ensuring the accuracy of EEG data. The tablet device provides a user interface, guiding users to obtain more accurate EEG signals. The tablet device connects to the computer device through the router device, responsible for transmitting EEG data and providing a user-friendly control interface. The router acts as a data bridge in the entire system, responsible for establishing a stable, high-speed local area network communication environment. It ensures low-latency, uninterrupted data flow between the intelligent analysis tablet and the laptop. The laptop is the computing power core and model hub of the entire device. It stores machine learning models trained on a large amount of clinical data and complex algorithm libraries.

[0048] The relevant process parameters of this invention are as follows: (1) EEG signal acquisition: ● Number of electrodes: Multi-electrode design, such as 8-channel or 19-channel.

[0049] ● Sampling rate: Usually above 100 Hz.

[0050] ●Frequency range: Typically covers a frequency range from 0.1 Hz to 100 Hz.

[0051] (2) Scale data collection: ● Input method: Input via the device's user interface or external input devices (such as keyboards or touchscreens).

[0052] ●Data types: Qualitative or quantitative psychological scores, emotional states, etc.

[0053] (3) Data transmission and processing: ●Transmission method: Data transmission is performed via Bluetooth and Wi-Fi wireless networks.

[0054] ●Data processing: The device's built-in processing module can perform real-time data processing and analysis.

[0055] (4) Power requirements: ● Battery capacity: The battery capacity that can support the device for a long time.

[0056] ● Charging method: USB charging or a specific charging interface.

[0057] (5) Equipment dimensions and weight: ● Device size: Head-mounted EEG devices are typically designed to be lightweight and portable, suitable for prolonged wear.

[0058] ● Equipment weight: To ensure comfort, the weight should be as light as possible.

[0059] (6) Operating system and software support: ●Supported Platforms: Compatible with common operating systems such as Windows, iOS, and Android.

[0060] ●Software support: The device is equipped with corresponding applications or software for data acquisition, processing and analysis.

[0061] (7) Other functions: ● Real-time monitoring and data display: The device can monitor and display EEG signal data in real time.

[0062] ●Data storage and output: It can store and output analysis results, and supports report generation or data export.

[0063] This invention enables convenient collection of EEG signals associated with depression and Alzheimer's disease using an EEG cap, allows interaction with the subject through a graphical interface on a tablet device, and performs intelligent analysis of the EEG signals based on AI technology, thereby achieving rapid screening for functional brain disorders related to depression and Alzheimer's disease.

[0064] The device provided by this invention can quickly and accurately capture a user's electroencephalogram (EEG) signals, significantly improving detection accuracy compared to traditional methods. The device is simple and direct to operate, allowing users to easily complete the test without complicated procedures. Users can obtain test results in a short time, improving testing efficiency and saving time. Clinically validated, the device achieves a testing accuracy of 95%, ensuring the reliability and accuracy of the test results and providing users with trustworthy data support.

[0065] The novel intelligent rapid screening device for depression / Alzheimer's disease provided by this invention has the following beneficial technical effects: (1) Comfort and flexibility: This device uses dry electrode technology, eliminating the need for conductive adhesive. Furthermore, the brain-computer interface is made of skin-friendly materials, ensuring user comfort. It utilizes wireless transmission and cloud-based analysis, offering high flexibility in use. (2) AI-enhanced analysis: AI is used for data analysis and pattern recognition, which improves the efficiency and accuracy of diagnosis.

[0066] (3) Personalized diagnosis: Based on individual bioelectrical signals and psychological assessment data, more personalized diagnosis of depression can be achieved.

[0067] (4) Diagnostic accuracy: The accuracy rate has increased dramatically, and the misdiagnosis rate has decreased significantly.

[0068] This invention, through a comprehensive approach that integrates electroencephalography (EEG) technology and AI analysis, can greatly enhance the diagnostic capabilities for depression / Alzheimer's disease, providing patients with more accurate, rapid, and personalized medical services.

[0069] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of one embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing the present invention.

[0070] Those skilled in the art will understand that the modules in the apparatus of the embodiments can be distributed in the apparatus of the embodiments as described in the embodiments, or they can be located in one or more devices different from this embodiment with corresponding changes. The modules of the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A novel intelligent rapid screening device for depression / Alzheimer's disease, used for early auxiliary detection of depression or Alzheimer's disease, characterized in that, include: EEG acquisition module, human-computer interaction module, wireless transmission module, and intelligent analysis module; The EEG acquisition module is used to acquire the subject's resting-state EEG signals and task-oriented EEG signals; The human-computer interaction module is used to select screening modes, enter subject information, perform impedance detection, signal verification, and task guidance. The wireless transmission module is used to enable data transmission between the various modules; The intelligent analysis module is used to receive EEG signals, perform data analysis through machine learning models, and output screening results.

2. The device according to claim 1, characterized in that, The intelligent analysis module employs a dual-modal fusion algorithm that combines resting-state and task-state EEG signals. By combining and weighting the basic EEG characteristics during the resting phase with eyes closed, as well as the evoked EEG characteristics during the emotion picture classification task, the accuracy and specificity of early screening for depression or Alzheimer's disease can be improved.

3. The device according to claim 1, characterized in that, The device can adaptively switch the weights of the EEG acquisition channels and the analysis model according to the screening mode; In the depression screening model, priority is given to extracting EEG features from brain regions related to emotion regulation; In the Alzheimer's disease screening model, the electroencephalogram (EEG) characteristics of brain regions related to cognitive function are extracted first to achieve targeted collection and analysis for screening different diseases.

4. The device according to claim 1, characterized in that, The EEG acquisition module is an EEG cap, which contains multiple dry EEG sensors; The dry EEG sensor includes an outer EEG probe, a connecting cavity, a threaded base, an inner EEG probe, a built-in spring, and a flexible shell. The dry EEG sensor can be self-fixed without external limiting devices, which can reduce contact impedance and motion artifacts, and acquire high signal-to-noise ratio EEG signals. The inner ring EEG probe is used to part the hair and make close contact with the scalp, reducing contact resistance; The dry EEG sensor is self-fixed by a ring-shaped raised plane, reducing motion artifacts; The built-in spring and flexible shell allow the probe to adapt and fit closely to the scalp; The threaded base allows for the removal and replacement of electrodes.

5. The device according to claim 1, characterized in that, The human-computer interaction module is a tablet computer, which is equipped with an interactive interface that supports the selection of depression screening mode and Alzheimer's disease screening mode, input of basic information of subjects, impedance detection, real-time display of EEG waveforms, three-minute guided rest with eyes closed, presentation of emotion picture classification tasks, and voice-assisted operation.

6. The device according to claim 1, characterized in that, The wireless transmission module includes a router, enabling tablets and laptops to connect wirelessly via WiFi, achieving low-latency and stable data transmission.

7. The device according to claim 1, characterized in that, The intelligent analysis module is a laptop computer with a built-in pre-trained machine learning model. It can preprocess, extract features, and recognize patterns from resting-state and task-state EEG signals, and output screening conclusions or risk warnings in PDF format.

8. The device according to claim 1, characterized in that, The equipment's workflow includes: S1: Subjects wear EEG caps, select screening modes and enter information via tablet computers. Screening modes include depression screening or Alzheimer's disease screening. S2: Impedance detection and device status verification. Impedance detection is used to confirm whether the EEG cap is in normal contact with the scalp, and device status verification is used to verify whether the device is in normal working condition. S3: Collect the subject's resting brain signals with eyes closed for three minutes using an EEG cap; S4: The tablet computer displays mixed images containing both negative and positive content. Subjects classify the emotional attributes of the images based on their subjective judgments, while task-oriented EEG signals are collected. S5: The signal is wirelessly transmitted to the computer for intelligent analysis; S6: Output the screening result report.

9. The device according to claim 1, characterized in that, Task-oriented EEG signals were collected simultaneously as subjects subjectively categorized images of mixed positive and negative emotions.

10. The device according to claim 8, characterized in that, The screening results are saved and output as PDF files, containing risk warnings or auxiliary diagnostic conclusions for clinicians to make quick judgments.

Images