Depression feedback regulation stimulation experiment device

Abstract

The invention relates to a depression feedback regulation stimulation experiment device which comprises a behavioral container, a camera group, an electrocardio acquisition module, a computer, an electrical stimulator and a stimulation electrode, the behavioral container is used for simulating an environment corresponding to the depression phenotype; the camera group is used for acquiring a video image of the subject in the behavioral container; the electrocardio acquisition module is used for acquiring an electrocardio signal of a subject; the computer is used for determining whether to perform electrical stimulation on the subject according to the video image and the electrocardiosignal, if so, determining an electrical stimulation parameter according to the video image and the electrocardiosignal, and sending the electrical stimulation parameter to the electrical stimulator; the electrical stimulator outputs corresponding electrical stimulation signals to a stimulation electrode according to the electrical stimulation parameters, the stimulation electrode is installed on the body of the subject, and electrical stimulation is conducted on the subject through the stimulation electrode. According to the experimental device, electrical stimulation parameters are adjusted according to the real-time internal state of a subject, the intervention precision and effectiveness are improved, and the requirements of neuroscience experiments are met.

Description

Technical Field

[0001] This manual relates to the field of intelligent emotion monitoring, and in particular to an experimental device for feedback regulation stimulation of depression. Background Technology

[0002] Existing stimulation devices for depression are all open-loop designs, meaning that the stimulation on / off switch and parameters are fixed and do not change with the subject's real-time state, resulting in poor experimental results and low accuracy in neuroscience experiments. Summary of the Invention

[0003] To address the problems in the prior art, this embodiment provides a feedback modulation stimulation experimental device for depression, which explores the key behavioral and physiological parameters that best reflect the subject's inner state, and explores the electrical stimulation parameters that should be used under different inner states to meet the needs of neuroscience experiments.

[0004] On one hand, the embodiments of this specification provide an experimental device for feedback regulation stimulation of depression, including:

[0005] Behavioral device, camera assembly, electrocardiogram acquisition module, computer, electrical stimulator, and stimulation electrodes;

[0006] The behavioral container is used to simulate the environment corresponding to the depressive phenotype;

[0007] The camera array is used to acquire video images of the subject in the behavioral container and transmit the video images to the computer;

[0008] The electrocardiogram (ECG) acquisition module is used to acquire the ECG signal of the subject and transmit the ECG signal to the computer;

[0009] The computer is used to determine whether to perform electrical stimulation on the subject based on video images and electrocardiogram signals. If so, it determines the electrical stimulation parameters based on the video images and electrocardiogram signals and sends the electrical stimulation parameters to the electrical stimulator.

[0010] The electrical stimulator outputs a corresponding electrical stimulation signal to the stimulation electrode according to the electrical stimulation parameters. The stimulation electrode is installed on the subject's body, and the subject is electrically stimulated through the stimulation electrode.

[0011] Furthermore, the computer is further configured to: convert the video image into a behavioral feature vector; convert the electrocardiogram signal into a physiological feature vector; integrate the behavioral feature vector and the physiological feature vector to obtain a final state parameter; and adjust the initial electrical stimulation parameter according to the final state parameter to obtain the electrical stimulation parameter.

[0012] Furthermore, the computer adjusts the initial electrical stimulation parameters based on the final state parameters to obtain the electrical stimulation parameters, which further include:

[0013] The computer adjusts the initial electrical stimulation parameters based on the difference between the final state parameters and the standard state parameters to obtain the electrical stimulation parameters.

[0014] Furthermore, the computer adjusts the initial electrical stimulation parameters based on the difference between the final state parameters and the standard state parameters, resulting in electrical stimulation parameters that further include:

[0015] The computer takes the difference between the current final state parameters and the standard state parameters as the current difference, and the difference between the historical state parameters of the last electrical stimulation of the subject and the standard state parameters as the historical difference. Based on the difference between the current difference and the historical difference, it determines the adjustment direction of the historical electrical stimulation parameters corresponding to the historical state parameters, and adjusts the historical electrical stimulation parameters according to a predetermined step size and the adjustment direction to obtain the current electrical stimulation parameters.

[0016] Furthermore, the computer is further configured to: when the current difference meets a predetermined minimum difference requirement, use the historical electrical stimulation parameters as the optimal electrical stimulation parameters corresponding to the depressive phenotype, and provide the optimal electrical stimulation parameters to the user.

[0017] Furthermore, the computer's determination of whether to perform electrical stimulation on the subject based on video images and electrocardiogram signals further includes: not performing electrical stimulation on the subject when the current difference meets a predetermined minimum difference requirement, and otherwise performing electrical stimulation on the subject.

[0018] Furthermore, the computer runs behavior analysis software, which is used to extract the motion time series of key points in the video image, convert the motion time series of key points into a behavior sequence and a first confidence level of the behavior sequence through an action segmentation algorithm, determine a first state parameter and a second confidence level of the first state parameter based on the behavior sequence, and generate a behavior feature vector based on the first confidence level, the second confidence level and the first state parameter.

[0019] Furthermore, the computer runs electrophysiological signal analysis software, which is used to convert the electrocardiogram signal into electrocardiogram parameters, determine a second state parameter and a third confidence level of the second state parameter based on the electrocardiogram parameters, and generate a physiological feature vector based on the third confidence level and the second state parameter.

[0020] Furthermore, the camera group includes two or more cameras.

[0021] Furthermore, the ECG acquisition module includes ECG recording electrodes, connecting wires, adapters, and wireless transmission components;

[0022] The electrocardiogram recording electrode is mounted on the subject's body and is connected to the wireless transmission component via the connecting cable and adapter.

[0023] The wireless transmission component is wirelessly connected to the computer.

[0024] The feedback modulation stimulation experimental device for depression described in this specification uses a behavioral container to simulate the environment corresponding to the depressive phenotype. Subjects are placed inside the container, causing them to exhibit depressive behaviors and psychological manifestations. A camera group acquires video images of the subjects within the container and transmits them to a computer. An electrocardiogram (ECG) acquisition module acquires the subjects' ECG signals and transmits them to the computer. The computer determines whether to apply electrical stimulation to the subjects based on the video images and ECG signals. If so, it determines the electrical stimulation parameters based on these parameters and sends them to a point stimulator. The stimulator then applies electrical stimulation to the subjects. Subsequently, the camera group and ECG acquisition module continue to acquire video images and ECG signals from the subjects. The computer adjusts the electrical stimulation parameters based on subsequent video images and ECG signals, achieving a closed-loop modulation mode. This allows for adjustment of electrical stimulation parameters according to the subjects' real-time internal state, improving the accuracy and effectiveness of intervention and determining the optimal electrical stimulation parameters corresponding to the depressive phenotype, providing a data foundation for subsequent experimental research. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments or prior art described herein, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this article. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram of the structure of a feedback regulation stimulation experimental device for depression, as described in the embodiments of this specification.

[0027] [Explanation of Labels in the Attached Image]

[0028] 1. Behavioral container;

[0029] 2. Camera assembly;

[0030] 3. Electrocardiogram (ECG) acquisition module;

[0031] 4. Computer;

[0032] 5. Electrical stimulator;

[0033] 6. Stimulating electrode. Detailed Implementation

[0034] The technical solutions in the embodiments described below will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments described herein, and not all of the embodiments. Based on the embodiments described herein, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this document.

[0035] Figure 1 The diagram shown is a schematic of the structure of a feedback regulation stimulation experimental device for depression in an embodiment of this specification, including a behavioral container 1, a camera group 2, an electrocardiogram acquisition module 3, a computer 4, an electrical stimulator 5, and stimulation electrodes 6.

[0036] like Figure 1 As shown, the behavioral container 1 is used to simulate the environment corresponding to the depressive phenotype;

[0037] The camera group 2 is used to acquire video images of the subject in the behavioral container and transmit the video images to the computer 4;

[0038] The electrocardiogram acquisition module 3 is used to acquire the electrocardiogram signal of the subject and transmit the electrocardiogram signal to the computer 4;

[0039] The computer 4 is used to determine whether to perform electrical stimulation on the subject based on the video image and electrocardiogram signal. If so, it determines the electrical stimulation parameters based on the video image and electrocardiogram signal and sends the electrical stimulation parameters to the electrical stimulator 5.

[0040] The electrical stimulator 5 outputs a corresponding electrical stimulation signal to the stimulation electrode 6 according to the electrical stimulation parameters. The stimulation electrode 6 is installed on the subject's body, and the subject is electrically stimulated through the stimulation electrode.

[0041] The feedback modulation stimulation experimental device for depression described in this specification uses a behavioral container to simulate the environment corresponding to the depressive phenotype. Subjects are placed inside the container, causing them to exhibit depressive behaviors and psychological manifestations. A camera group acquires video images of the subjects within the container and transmits them to a computer. An electrocardiogram (ECG) acquisition module acquires the subjects' ECG signals and transmits them to the computer. The computer determines whether to apply electrical stimulation to the subjects based on the video images and ECG signals. If so, it determines the electrical stimulation parameters based on these parameters and sends them to a point stimulator. The stimulator then applies electrical stimulation to the subjects. Subsequently, the camera group and ECG acquisition module continue to acquire video images and ECG signals from the subjects. The computer adjusts the electrical stimulation parameters based on subsequent video images and ECG signals, achieving a closed-loop modulation mode. This allows for adjustment of electrical stimulation parameters according to the subjects' real-time internal state, improving the accuracy and effectiveness of intervention and determining the optimal electrical stimulation parameters corresponding to the depressive phenotype, providing a data foundation for subsequent experimental research.

[0042] In the embodiments of this specification, the subject can be an experimental mouse. The mouse is placed in a behavioral container 1, which can simulate the environment corresponding to the depressive phenotype, such as sucrose preference, tail suspension, forced swimming, etc. The behavioral container 1 should be transparent or large enough to facilitate the camera group 2 to take pictures.

[0043] like Figure 1 The scene shown, Figure 1 The simulated depressive phenotype environment was forced swimming. In this scenario, the subject was placed in a behavioral container 1, and the camera group 2 included multiple cameras that simultaneously captured video images of the subject from different angles. The electrocardiogram acquisition module 3 collected the subject's electrocardiogram signals in real time through electrodes and transmitted the video images and electrocardiogram signals to the computer.

[0044] Before data collection begins, the time of each camera in camera group 2 must be accurately calibrated and the position of each camera must be fixed.

[0045] The ECG acquisition module 3 includes ECG recording electrodes, connecting wires, adapters, and wireless transmission components;

[0046] The electrocardiogram recording electrode is mounted on the subject's body and is connected to the wireless transmission component via the connecting cable and adapter.

[0047] The wireless transmission component is wirelessly connected to the computer.

[0048] The electrodes can be two-leaded and implanted in the subcutaneous muscles of the subject, such as the pectoralis major muscle. They are connected to an adapter and wireless transmission component on the top of the head by thin wires running through the subcutaneous tissue. The wireless transmission component wirelessly transmits the electrocardiogram signal to a computer.

[0049] In the embodiments of this specification, the ECG acquisition module 3 may also be deployed on the subject's body in other ways in the prior art to collect the subject's ECG signals, and the embodiments of this specification do not impose any limitations.

[0050] Computer 4 converts the video image into a behavioral feature vector; converts the electrocardiogram signal into a physiological feature vector; integrates the behavioral feature vector and the physiological feature vector to obtain the final state parameters; and adjusts the initial electrical stimulation parameters according to the final state parameters to obtain the electrical stimulation parameters.

[0051] In this embodiment of the specification, the computer 4 runs behavior analysis software. The behavior analysis software is used to extract the motion time sequence of key points in the video image, convert the motion time sequence of the key points into a behavior sequence and a first confidence level of the behavior sequence through an action segmentation algorithm, determine a first state parameter and a second confidence level of the first state parameter based on the behavior sequence, and generate a behavior feature vector based on the first confidence level, the second confidence level and the first state parameter.

[0052] In the embodiments of this specification, the behavior analysis software can extract the motion time sequence of key points such as the tip of the nose, the base of the tailbone, the hip bone, both ears, and the four feet of the subject in the video image. Then, the Keypoint-Moseq action segmentation algorithm is used to obtain the subject's real-time behavior sequence and a first confidence level. Then, a first state parameter corresponding to the behavior sequence is determined by a pre-constructed first mapping table. The first mapping table includes the correspondence between the behavior sequence and the first state parameter and the second confidence level of the correspondence. In the embodiments of this specification, the first state parameter can, for example, explore the behavior corresponding to moderate arousal, low stress, high motivation, etc. The first state parameter can reflect the subject's depressive performance. The first state parameter is used as a behavior feature vector, and the product of the first confidence level and the second confidence level is calculated to obtain the confidence level of the behavior feature vector.

[0053] In this embodiment of the specification, the computer 4 runs electrophysiological signal analysis software. This software converts the electrocardiogram (ECG) signal into ECG parameters, determines a second state parameter and a third confidence level of the second state parameter based on the ECG parameters, and generates a physiological feature vector based on the third confidence level and the second state parameter. In this embodiment of the specification, the ECG parameters may include heart rate value, heart rate coefficient of variation, etc. The second state parameter corresponding to the ECG parameter can be determined through a pre-constructed second mapping table. The second mapping table includes the correspondence between the ECG parameter and the second state parameter and the third confidence level of this correspondence. The second state parameter may be, for example, moderate arousal, low stress, or high motivation corresponding to exploratory behavior. The second state parameter is used as the physiological feature vector, and the third confidence level is used as the confidence level of the physiological feature vector.

[0054] In the embodiments of this specification, the first mapping table and the second mapping table can be set by staff based on experience, and the embodiments of this specification do not impose any restrictions.

[0055] This can be understood as follows: the embodiments in this specification determine the state parameters corresponding to the behavioral sequence and electrocardiogram parameters, and the state parameters reflect depressive manifestations. Then, the state parameters of the two are weighted and averaged according to their respective confidence levels to obtain the final state parameters.

[0056] In the embodiments of this specification, the electrical stimulation parameters include positive pulses and / or negative pulses, and both positive and negative pulses include current magnitude, pulse width, and frequency.

[0057] The initial electrical stimulation parameters can be set based on experience. For example, the initial electrical stimulation parameters for high frequency can be set to a symmetrical square wave with a frequency of 130 Hz, a pulse width of 60 μs, and a current of 200 μA; the initial electrical stimulation parameters for low frequency can be set to a symmetrical square wave with a frequency of 1 Hz, a pulse width of 90 μs, and a current of 150 μA; and the initial electrical stimulation parameters for medium frequency can be set to a symmetrical square wave with a frequency of 40 Hz, a pulse width of 75 μs, and a current of 200 μA.

[0058] A neural network model for adjusting the initial electrical stimulation parameters can be pre-trained, deployed in a computer, and the final state parameters and initial electrical stimulation parameters can be used as inputs to the neural network model. The neural network model outputs the adjusted electrical stimulation parameters.

[0059] Computer 4 sends the adjusted electrical stimulation parameters to electrical stimulator 5. Electrical stimulator 5 outputs the corresponding electrical stimulation signal to stimulation electrode 6 according to the electrical stimulation parameters. The stimulation electrode is installed on the subject's body, and electrical stimulation is performed on the subject through stimulation electrode 6, thereby causing the subject to change depressive behavior and psychological manifestations.

[0060] In the embodiments described in this specification, the stimulation electrode 6 can be implanted into the target brain region of the subject, thereby enabling the subject to change depressive behaviors and psychological manifestations under electrical stimulation.

[0061] In the embodiments of this specification, after electrical stimulation of the subject, the altered depressive behavior and psychological manifestations may still indicate that the subject is in a depressive stage. Therefore, in the embodiments of this specification, after electrical stimulation, the camera group 2 and the electrocardiogram acquisition module 3 will continue to acquire video images and electrocardiogram signals of the subject and transmit them to the computer to realize feedback regulation of electrical stimulation.

[0062] This can be understood as follows: through continuous electrical stimulation and feedback adjustment of the initial electrical stimulation parameters, the optimal electrical stimulation parameters corresponding to the depressive phenotype simulated by the current behavioral container 1 can be obtained, and the optimal electrical stimulation parameters can be provided to the user, thereby providing the user with a data basis for neurological experiments.

[0063] Specifically, the computer adjusts the initial electrical stimulation parameters based on the final state parameters to obtain the electrical stimulation parameters, which further include:

[0064] The computer adjusts the initial electrical stimulation parameters based on the difference between the final state parameters and the standard state parameters to obtain the electrical stimulation parameters.

[0065] In the embodiments of this specification, the standard state parameter can be the state parameter set by the staff based on experience when there are no depressive symptoms. The difference between the final state parameter and the standard state parameter can be the magnitude relationship between the final state parameter and the standard state parameter. The initial electrical stimulation parameter is adjusted according to the magnitude relationship. For example, if the final state parameter is greater than the standard state parameter, the frequency of the high-frequency initial electrical stimulation parameter is reduced. The specific adjustment method can be set by the staff based on experience. This embodiment of the specification does not limit this.

[0066] To achieve closed-loop adjustment of electrical stimulation parameters, according to one embodiment of this specification, the computer adjusts the initial electrical stimulation parameters based on the difference between the final state parameters and the standard state parameters, thereby obtaining the electrical stimulation parameters further comprising:

[0067] The computer takes the difference between the current final state parameters and the standard state parameters as the current difference, and the difference between the historical state parameters of the last electrical stimulation of the subject and the standard state parameters as the historical difference. Based on the difference between the current difference and the historical difference, it determines the adjustment direction of the historical electrical stimulation parameters corresponding to the historical state parameters, and adjusts the historical electrical stimulation parameters according to a predetermined step size and the adjustment direction to obtain the current electrical stimulation parameters.

[0068] In the embodiments of this specification, the current difference between the current final state parameter and the standard state parameter can include the magnitude relationship and difference between the current final state parameter and the standard state parameter. The historical difference between the historical state parameter and the standard state parameter from the last electrical stimulation of the subject includes the magnitude relationship and difference between the historical state parameter and the standard state parameter. Then, the difference between the current difference and the historical difference is compared. For example, in the current difference, the historical state parameter is greater than the standard state parameter, and the difference between the historical state parameter and the standard state parameter is A. In the historical difference, the historical state parameter is greater than the standard state parameter, and the difference between the historical state parameter and the standard state parameter is B. Then, the difference between the current difference and the historical difference can be the magnitude relationship between the difference A and the difference B. The adjustment direction of the historical electrical stimulation parameter is determined based on this magnitude relationship. For example, if the difference A is less than the difference B, the adjustment direction can be to lower it.

[0069] It should be noted that the above-mentioned determination of the adjustment direction based on the size relationship can be set by the staff based on experience, and then the rules are formed. The rules are deployed in computer 4, and computer 4 takes the difference between the current difference and the historical difference as the input of the rules, and the rules output the adjustment direction.

[0070] In the embodiments of this specification, the predetermined step size can also be set by the staff based on experience, and this embodiment of the specification does not impose any restrictions.

[0071] In this embodiment of the specification, the computer is further configured to: when the current difference meets a predetermined minimum difference requirement, use the historical electrical stimulation parameters as the optimal electrical stimulation parameters corresponding to the depressive phenotype, and provide the optimal electrical stimulation parameters to the user. The predetermined minimum difference requirement can be set according to actual needs, and this embodiment of the specification does not impose any limitations.

[0072] In the embodiments of this specification, when the current difference meets the predetermined minimum difference requirement, the subject is not subjected to electrical stimulation; otherwise, the subject is subjected to electrical stimulation.

[0073] In some other embodiments of this specification, the behavioral container 1 may be an open field experimental component, a social interaction component, or other experimental components used to assess phenotypes related to depression or mental illness. The embodiments in this specification are not limited to these components.

[0074] In addition, the ECG acquisition module 3 can also be used as a module for acquiring other physiological indicators such as EEG, blood oxygenation, and body temperature, thereby enriching the dimensions of state assessment and improving experimental results.

[0075] In the embodiments of this specification, the electrical stimulator 5 can also be replaced by a photostimulator, a drug micro-infusion module, etc., to achieve different types of closed-loop intervention methods.

[0076] The experimental apparatus described in this specification can also be used to determine the optimal intervention parameters for other mental illnesses such as anxiety disorder and schizophrenia, so that users can explore corresponding closed-loop intervention programs. This specification does not impose any limitations on the embodiments described.

[0077] It should be understood that in the various embodiments of this document, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.

[0078] It should also be understood that, in the embodiments herein, the term "and / or" is merely a description of the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following associated objects have an "or" relationship.

[0079] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different means to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document.

[0080] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing device embodiments, and will not be repeated here.

[0081] In the embodiments provided herein, it should be understood that the disclosed systems and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0082] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described herein, depending on actual needs.

[0083] Furthermore, the functional units in the various embodiments of this document can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0084] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this document, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the computer described in the various embodiments of this document. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0085] This document uses specific embodiments to illustrate the principles and implementation methods described herein. The descriptions of the embodiments are only for the purpose of helping to understand the apparatus and its core ideas. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas described herein. Therefore, the content of this specification should not be construed as a limitation of this document.

Claims

1. A device for feedback regulation stimulation experiment of depression, characterized in that, The application relates to a system for simulating a depressive phenotype, comprising: a behavioral container, a camera group, an electrocardio acquisition module, a computer, an electrical stimulator and a stimulation electrode; the behavioral container is used for simulating an environment corresponding to the depressive phenotype; the camera group is used for acquiring video images of a subject in the behavioral container and transmitting the video images to the computer; the electrocardio acquisition module is used for acquiring electrocardio signals of the subject and transmitting the electrocardio signals to the computer; the computer is used for determining whether to perform electrical stimulation on the subject according to the video images and the electrocardio signals, and if so, determining electrical stimulation parameters according to the video images and the electrocardio signals and sending the electrical stimulation parameters to the electrical stimulator; the electrical stimulator outputs corresponding electrical stimulation signals to the stimulation electrode according to the electrical stimulation parameters, and the stimulation electrode is installed on the body of the subject and performs electrical stimulation on the subject through the stimulation electrode.

2. The apparatus of claim 1, wherein the apparatus is configured to administer the feedback control stimulation to the subject in response to the subject's depression level. The computer is further used for converting the video images into a behavioral feature vector, converting the electrocardio signals into a physiological feature vector, integrating the behavioral feature vector and the physiological feature vector to obtain a final state parameter, adjusting initial electrical stimulation parameters according to the final state parameter to obtain the electrical stimulation parameters.

3. The apparatus of claim 2, wherein the feedback control stimulation is applied to the subject in a manner that is dependent on the subject's current state of depression. The computer adjusts the initial electrical stimulation parameters according to the final state parameter to obtain the electrical stimulation parameters further comprises: the computer adjusts the initial electrical stimulation parameters according to the difference between the final state parameter and a standard state parameter to obtain the electrical stimulation parameters.

4. The experimental device for feedback regulation of depression according to claim 3, characterized in that, The computer adjusts the initial electrical stimulation parameters according to the difference between the final state parameter and a standard state parameter to obtain the electrical stimulation parameters further comprises: the computer takes the difference between the current final state parameter and the standard state parameter as a current difference, takes the difference between a historical state parameter corresponding to the last electrical stimulation on the subject and the standard state parameter as a historical difference, determines an adjustment direction of the historical electrical stimulation parameter corresponding to the historical state parameter according to the difference between the current difference and the historical difference, adjusts the historical electrical stimulation parameter according to a predetermined step size and the adjustment direction to obtain the current electrical stimulation parameter.

5. The experimental apparatus for feedback regulation of depression according to claim 4, characterized in that, The computer is further used for: when the current difference meets a predetermined minimum difference requirement, taking the historical electrical stimulation parameter as an optimal electrical stimulation parameter corresponding to the depressive phenotype and providing the optimal electrical stimulation parameter to a user.

6. The apparatus of claim 5, wherein the feedback control stimulation is applied to the subject in a manner that is dependent on the subject's current state of depression. The computer determines whether to perform electrical stimulation on the subject according to the video images and the electrocardio signals further comprises: when the current difference meets a predetermined minimum difference requirement, not performing electrical stimulation on the subject, otherwise, performing electrical stimulation on the subject.

7. The apparatus of claim 2, wherein the apparatus is configured to provide a feedback control stimulation experiment for depression. The computer runs a behavior analysis software, which is used to extract the motion time series of key points in the video image, convert the motion time series of the key points into a behavior sequence and a first confidence of the behavior sequence through a motion segmentation algorithm, determine a first state parameter and a second confidence of the first state parameter according to the behavior sequence, and generate a behavior feature vector according to the first confidence, the second confidence and the first state parameter.

8. The apparatus of claim 2, wherein the apparatus is configured to provide a feedback control stimulation experiment for depression. The computer runs an electrophysiological signal analysis software, which is used to convert the electrocardio signal into an electrocardio parameter, determine a second state parameter and a third confidence of the second state parameter according to the electrocardio parameter, and generate a physiological feature vector according to the third confidence and the second state parameter.

9. The apparatus of claim 1, wherein the apparatus is configured to administer a feedback control stimulation experiment for depression. The camera group comprises two or more cameras.

10. The apparatus of claim 1, wherein the apparatus is configured to administer a feedback control stimulation experiment for depression. The electrocardio acquisition module comprises electrocardio recording electrodes, connecting lines, an adapter and a wireless transmission assembly. The electrocardio recording electrodes are installed on the body of the subject, and the electrocardio recording electrodes are connected to the wireless transmission assembly through the connecting lines and the adapter. The wireless transmission assembly is wirelessly connected to the computer.

Images