Adaptive closed-loop neuromodulation decision method, apparatus and electronic device

Abstract

The application discloses a self-adaptive closed-loop neuromodulation decision method and device and electronic equipment, and the method comprises the following steps: obtaining a corresponding target feedback variable based on an electrophysiological signal of a target object at a current sampling moment, wherein the target feedback variable comprises at least one electrophysiological signal feature; obtaining a dynamic target value at the current sampling moment according to the target feedback variable based on a pre-constructed dynamic control target model; and obtaining a target stimulation parameter corresponding to the current sampling moment based on the target feedback variable and the dynamic target value. The method can effectively improve the accuracy of neuromodulation by constructing a dynamic control target model to obtain a real-time dynamic target value, and then making a closed-loop neuromodulation decision to obtain a corresponding target stimulation parameter, so that real-time and personalized self-adaptive closed-loop neuromodulation decision can be realized when the application is used for neuromodulation under a dynamic brain state.

Description

Technical Field

[0001] This invention relates to the field of medical electronic systems, and more particularly to an adaptive closed-loop neural modulation decision-making method, device, and electronic device. Background Technology

[0002] Abnormalities in brain neural activity lead to various neurological and psychiatric disorders. Neuromodulation technology has become an effective clinical treatment for diseases such as Parkinson's disease and epilepsy, encompassing various stimulation methods, including invasive and non-invasive approaches. Currently used continuous open-loop stimulation involves doctors adjusting and fixing stimulation parameters until the next follow-up visit. These parameters, including amplitude, frequency, and pulse width, cannot be appropriately adjusted based on the patient's instantaneous or long-term state changes, and may also cause side effects such as language impairment and cognitive dysfunction. Research on neural circuit modulation strategies has shown that designing closed-loop modulation strategies can modulate neural activity to a preset, constant target level. However, current clinical trials have not yet solved the problem of modulating neural activity to a target level that matches the current neural state.

[0003] Therefore, how to precisely regulate neural activity related to the improvement of disease symptoms to a target level that matches the current neural state has become an important problem to be solved in neuromodulation. Summary of the Invention

[0004] The purpose of this invention is to provide an adaptive closed-loop neural modulation decision-making method, device, and electronic device, which can provide effective decisions for closed-loop modulation of dynamic and random neural activity.

[0005] To achieve the above-mentioned objectives, the present invention proposes the following technical solution:

[0006] Firstly, an adaptive closed-loop neural modulation decision-making method is provided, the method comprising:

[0007] The target feedback variable is obtained based on the electrophysiological signal of the target object at the current sampling time, and the target feedback variable includes at least one electrophysiological signal feature;

[0008] Based on a pre-built dynamic control target model, the dynamic target value at the current sampling time is obtained according to the target feedback variable;

[0009] The target stimulus parameters corresponding to the current sampling time are obtained based on the target feedback variable and the dynamic target value.

[0010] In a preferred embodiment, obtaining the corresponding target feedback variable based on the electrophysiological signal of the target object at the current sampling time includes:

[0011] Obtain the types of diseases of the target group;

[0012] Preprocess the electrophysiological signal of the target object at the current sampling time;

[0013] Based on the pre-acquired correspondence between disease types and electrophysiological signal characteristics, target feedback variables are determined based on the preprocessed electrophysiological signals.

[0014] In a preferred embodiment, the method further includes: determining a dynamic target anchor value based on the modulation range of the electrophysiological signal characteristics of the target object obtained in advance;

[0015] The method based on the pre-built dynamic control target model, obtaining the dynamic target value corresponding to the current sampling time according to the target feedback variable, includes:

[0016] Obtain the mean electrophysiological signal characteristics of the target object at n sampling times prior to the current sampling time;

[0017] The dynamic target value corresponding to the current sampling time is obtained based on the mean value of the electrophysiological signal characteristics and the dynamic target anchor value.

[0018] In a preferred embodiment, the dynamic target value corresponding to the current sampling time is obtained based on the mean value of the electrophysiological signal features and the dynamic target anchor value, calculated using the following formula (Ⅰ):

[0019]

[0020] Where k represents the current sampling time, and target(k) represents the dynamic target value at time k. b represents the mean of the electrophysiological signal characteristics at n sampling times prior to the current sampling time k. anchor denoted by , where p represents the dynamic target anchor value and p∈[0,1].

[0021] In a preferred embodiment, the mean value of the electrophysiological signal characteristics of the target object at n sampling times prior to the current sampling time is calculated using the following formula (II):

[0022]

[0023] Where n represents the number of sampling points before the current sampling time k, and N represents the total number of sampling points.

[0024] In a preferred embodiment, obtaining the target stimulus parameters corresponding to the current sampling time based on the target feedback variable and the dynamic target value includes:

[0025] Calculate the mean error between the target feedback variable and the corresponding dynamic target value at the current sampling time;

[0026] The target stimulus parameters corresponding to the current sampling time are obtained based on the mean of the error values.

[0027] In a preferred embodiment, the mean error between the target feedback variable and the corresponding dynamic target value at the current sampling time is calculated using the following formula (Ⅲ):

[0028]

[0029] Where e(k) represents the mean error between the target feedback variable and the corresponding dynamic target value at the current sampling time k, and Nc represents the number of sampling points used to calculate the stimulus parameters before the current sampling time k.

[0030] In a preferred embodiment, when a PID controller is used to obtain the target stimulus parameters corresponding to the current sampling time, the target stimulus parameters corresponding to the current sampling time are obtained based on the mean error value, calculated using the following formulas (Ⅳ)(Ⅴ):

[0031]

[0032]

[0033] Where u(k) is the target stimulus parameter, u max with u min Let K represent the maximum and minimum values ​​of u(k), respectively, and Δu(k) represent the increment of the stimulus parameter corresponding to the current sampling time k compared to the previous sampling time. p K i K d This represents the gain parameter of the PID controller, Δu. max This represents the maximum increment of the stimulus parameter, -Δu max This represents the minimum increment of the stimulus parameter.

[0034] Secondly, an adaptive closed-loop neural modulation decision-making device is provided, the device comprising:

[0035] The first processing module is used to obtain corresponding target feedback variables based on the electrophysiological signals of the target object at the current sampling time, wherein the target feedback variables include at least one electrophysiological signal feature;

[0036] The second processing module is used to obtain the dynamic target value at the current sampling time based on the target feedback variable according to the pre-built dynamic control target model.

[0037] The third processing module is used to obtain the target stimulus parameters corresponding to the current sampling time based on the target feedback variable and the dynamic target value.

[0038] Thirdly, an electronic device is provided, comprising:

[0039] One or more processors; and,

[0040] A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the method as described in any one of the first aspects.

[0041] In a preferred embodiment, when the processor performs the method as described in any of the first aspects, the processor's input signal may originate from the electronic device's own signal acquisition and processing hardware module or from other external signal acquisition and processing hardware devices, and the processor's output signal may be sent to the electronic device's own stimulation module or to other external stimulation devices.

[0042] Fourthly, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by one or more processors, implements the steps of the method as described in any one of the first aspects.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] This invention provides an adaptive closed-loop neural modulation decision-making method, device, and electronic device. The method includes: obtaining a corresponding target feedback variable based on the electrophysiological signal of the target object at the current sampling time, wherein the target feedback variable includes at least one electrophysiological signal feature; obtaining a dynamic target value at the current sampling time based on the target feedback variable according to a pre-constructed dynamic control target model; and obtaining target stimulation parameters corresponding to the current sampling time based on the target feedback variable and the dynamic target value. This method obtains a real-time dynamic target value by constructing a dynamic control target model, and then performs closed-loop neural modulation decision-making to obtain the corresponding target stimulation parameters, thereby effectively improving the accuracy of neural modulation. When this invention is used for neural modulation in dynamic brain states, it can realize real-time, personalized adaptive closed-loop neural modulation decision-making. Furthermore, this method helps to preserve the inherent dynamic rhythm of neural activity while achieving long-term stable neural modulation, improving the therapeutic effect on neurological and psychiatric diseases and reducing side effects. Attached Figure Description

[0045] Figure 1 This is a flowchart of the adaptive closed-loop neural modulation decision-making method in this embodiment;

[0046] Figure 2This is a schematic diagram illustrating the principle of applying the adaptive closed-loop neural modulation decision-making method to closed-loop neural modulation in this embodiment.

[0047] Figure 3 This is a schematic diagram illustrating the principle of the dynamic target model in the embodiment;

[0048] Figure 4 This is a schematic diagram of the PID controller in this embodiment;

[0049] Figure 5 This is a flowchart of the method for obtaining target stimulus parameters in this embodiment;

[0050] Figure 6 This is a schematic diagram of the structure of the computer-readable storage medium in this embodiment. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0052] In the description of this invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0053] With the development of neuromodulation technology, closed-loop neuromodulation technology has emerged. To improve the accuracy of neuromodulation strategies, adaptive parameter adjustment is often employed. However, in closed-loop adaptive neuromodulation, how to effectively design modulation strategies to improve the neuromodulation effect remains a serious problem for the industry. Therefore, this embodiment provides an adaptive closed-loop neuromodulation strategy method, device, and electronic device that can effectively solve this problem. The following will provide a further detailed description of an adaptive closed-loop neuromodulation decision-making method, device, and electronic device according to this embodiment.

[0054] Example

[0055] like Figure 1 , 2As shown, this embodiment provides an adaptive closed-loop neuromodulation decision-making method, device, and electronic device. The neuromodulation methods referred to in this embodiment include, but are not limited to, invasive or non-invasive neuromodulation methods such as deep brain stimulation, transcranial magnetic stimulation, and vagal stimulation. It should be noted that this adaptive closed-loop neuromodulation decision-making method determines stimulation parameters suitable for dynamic neural activity for subsequent stimulation, but does not directly execute the stimulation. It should also be noted that the stimulation in this embodiment includes, but is not limited to, electrical stimulation and magnetic stimulation.

[0056] Specifically, the adaptive closed-loop neural modulation decision-making method includes the following steps:

[0057] S1. Obtain the corresponding target feedback variable based on the electrophysiological signal of the target object at the current sampling time k. The target feedback variable includes at least one electrophysiological signal feature.

[0058] It should be noted that, given the identified disease type of the target individual (including but not limited to Parkinson's disease, epilepsy, and depression), only a portion of the electrophysiological signal features acquired through electrodes or sensors can reflect this disease type. Therefore, at least one corresponding electrophysiological signal feature is used as the electrophysiological signal feature of the target individual. The preferred sampling frequency range for the electrophysiological signals in this process is 200 SPS to 50 k SPS.

[0059] Before step S1, the target object is continuously stimulated with different parameters, and its behavior is assessed to clarify the range of regulation of the target object's electrophysiological signal characteristics, the range of regulation of the stimulation parameters, and the dynamic target anchor value b. anchor Adjust the intensity p.

[0060] It should be noted that the principle for determining the range of stimulation parameters is: (1) the change of stimulation parameters can regulate the electrophysiological signal characteristics and improve the disease symptoms; (2) within the tolerance range of the target subject, it does not cause adverse reactions.

[0061] And, b anchor Theoretically, it can be set to any preset value within an adjustable range; the specific setting should be determined by the doctor based on clinical practice. In this embodiment, the dynamic target anchor value b... anchor It is determined based on the regulatory range of the target object's electrophysiological signal characteristics. In b anchor Under the influence of closed-loop regulation, the electrophysiological signal characteristics should be in b anchor The price fluctuated smoothly in the vicinity. When b... anchor When the stimulation exceeds the regulation range of the electrophysiological signal characteristics, the stimulation parameters calculated by the controller have adaptive capabilities, thus switching to a non-stimulation or continuous stimulation mode.

[0062] The modulation intensity p can be set to any value between 0 and 1, and the specific setting should be determined by the physician based on clinical practice. In this embodiment, the modulation intensity p is determined based on the electrophysiological signal characteristics and symptom improvement of the target subject, and can vary according to different modulation stages.

[0063] In a preferred embodiment, step S1 specifically includes:

[0064] S11. Obtain the types of diseases of the target object.

[0065] S12. Preprocess the electrophysiological signal of the target object at the current sampling time k.

[0066] Preprocessing includes, but is not limited to, signal processing such as filtering of electrophysiological signals.

[0067] S13. Based on the pre-obtained correspondence between disease types and electrophysiological signal characteristics, determine the target feedback variable based on the preprocessed electrophysiological signal.

[0068] S2, Combination Figure 3 As shown, based on the pre-built dynamic control target model, the dynamic target value at the current sampling time k is obtained according to the target feedback variable, where k≥1.

[0069] Specifically, step S2 includes:

[0070] S21. Obtain the mean value of the electrophysiological signal characteristics of the target object at n sampling times prior to the current sampling time k. Specifically, it is calculated using the following formula (II):

[0071]

[0072] Where k represents the current sampling time, Let N represent the mean value of the electrophysiological signal characteristics at n sampling times prior to the current sampling time k, where n represents the number of sampling points prior to the current sampling time k, and N represents the total number of sampling points, where N≥n.

[0073] S22. Based on the mean value of electrophysiological signal characteristics and the dynamic target anchor value, obtain the dynamic target value corresponding to the current sampling time k. Specifically, it is calculated using the following formula (Ⅰ):

[0074]

[0075] Where target(k) represents the dynamic target value at time k. Let p represent the mean value of the electrophysiological signal characteristics at n sampling times prior to the current sampling time k, where p is the modulation intensity and p∈[0,1].

[0076] When p = 0, it indicates that the dynamic target anchor value, i.e., the control target, is the mean of the current electrophysiological signal characteristics, meaning no regulation is performed; when p = 1, it indicates that the dynamic target anchor value, i.e., the control target, is b. anchor .

[0077] The dynamic control target model in step S2 described above is a combination of formulas (II) and (I). Furthermore, the dynamic control target model in this embodiment is constructed based on a large amount of sample data, which will not be described in detail here.

[0078] S3, Combination Figure 4 , 5 As shown, the target stimulus parameters corresponding to the current sampling time k are obtained based on the target feedback variable and the dynamic target value. Specifically, when a PID controller is used to obtain the target stimulus parameters corresponding to the current sampling time k, step S3 includes:

[0079] S31. Calculate the mean error between the target feedback variable and the corresponding dynamic target value at the current sampling time k. Specifically, it is calculated using the following formula (Ⅲ):

[0080]

[0081] Where e(k) represents the mean error between the target feedback variable and the corresponding dynamic target value at the current sampling time k, and Nc represents the number of sampling points used to calculate the stimulus parameters before the current sampling time k, and Nc≥1.

[0082] It should be noted that when Nc = 1, the mean error value e(k) of the dynamic target value is calculated as shown in equation (VI):

[0083]

[0084] S32. Obtain the target stimulus parameters corresponding to the current sampling time k based on the mean of the error values. Specifically, they are calculated using the following formulas (Ⅳ)(Ⅴ):

[0085]

[0086]

[0087] Where u(k) represents the target stimulus parameters (including but not limited to amplitude, frequency, and pulse width), u max with u min Let K represent the maximum and minimum values ​​of u(k) (i.e., the pre-determined range of stimulus parameter adjustment before step S1), Δu(k) represent the increment of the stimulus parameter corresponding to the current sampling time k compared to the previous sampling time, and K p K i K dThis represents the gain parameter of the PID controller, Δu. max This represents the maximum increment of the stimulus parameter, -Δu max This represents the minimum increment of the stimulus parameter.

[0088] Of course, this embodiment only uses the PID controller—Proportional-Integral-Differential (PID) controller—as an example to further refine step S3. When other controllers are used, corresponding calculations can be made according to the specific principles of the controller. This embodiment is not limited.

[0089] Furthermore, this embodiment does not limit the update frequency of the stimulus parameters; updates can be performed once per sampling period or once every multiple sampling periods.

[0090] In summary, this embodiment provides an adaptive closed-loop neural modulation decision-making method. This method includes: obtaining a corresponding target feedback variable based on the electrophysiological signal of the target object at the current sampling time k, where the target feedback variable includes at least one electrophysiological signal feature; obtaining a dynamic target value at the current sampling time k based on a pre-constructed dynamic control target model and the target feedback variable; and obtaining target stimulation parameters corresponding to the current sampling time k based on the target feedback variable and the dynamic target value. This method obtains real-time dynamic target values ​​by constructing a dynamic control target model, and then performs closed-loop neural modulation decision-making to obtain corresponding target stimulation parameters, thereby effectively improving the accuracy of neural modulation. When this embodiment is used for neural modulation in dynamic brain states, it can achieve real-time, personalized adaptive closed-loop neural modulation decision-making. Furthermore, this method helps to preserve the inherent dynamic rhythm of neural activity while achieving long-term stable neural modulation, improving the therapeutic effect on neurological and psychiatric diseases and reducing side effects.

[0091] Corresponding to the above method embodiments, this embodiment further provides an adaptive closed-loop neural modulation decision-making device, which includes:

[0092] The first processing module is used to obtain the corresponding target feedback variable based on the electrophysiological signal of the target object at the current sampling time k, wherein the target feedback variable includes at least one electrophysiological signal feature.

[0093] The second processing module is used to obtain the dynamic target value at the current sampling time k based on the target feedback variable according to the pre-built dynamic control target model.

[0094] The third processing module is used to obtain the target stimulus parameters corresponding to the current sampling time k based on the target feedback variable and the dynamic target value.

[0095] The acquisition module is used to determine the dynamic target anchor value based on the modulation range of the electrophysiological signal characteristics of the target object obtained in advance.

[0096] Specifically, the first processing module includes:

[0097] The first acquisition unit is used to acquire the types of diseases of the target object;

[0098] The preprocessing unit is used to preprocess the electrophysiological signal of the target object at the current sampling time k;

[0099] The determination unit is used to determine the target feedback variable based on the preprocessed electrophysiological signal according to the pre-acquired correspondence between disease types and electrophysiological signal characteristics.

[0100] The second processing module includes:

[0101] The second acquisition unit is used to acquire the mean value of the electrophysiological signal characteristics of the target object at n sampling times prior to the current sampling time k. Specifically, it is calculated using the following formula (II):

[0102]

[0103] Where n represents the number of sampling points before the current sampling time k, and N represents the total number of sampling points.

[0104] The first calculation unit is used to obtain the dynamic target value corresponding to the current sampling time k based on the mean value of the electrophysiological signal characteristics, the dynamic target anchor value, and the modulation intensity. Specifically, it is calculated using the following formula (Ⅰ):

[0105]

[0106] Where target(k) represents the dynamic target value at time k. Let p represent the mean value of the electrophysiological signal characteristics at n sampling times prior to the current sampling time k, where p is the modulation intensity and p∈[0,1].

[0107] The third processing module includes:

[0108] The second calculation unit is used to calculate the mean error between the target feedback variable and the corresponding dynamic target value at the current sampling time k. Specifically, it is calculated using the following formula (Ⅲ):

[0109]

[0110] Where e(k) represents the mean error between the target feedback variable and the corresponding dynamic target value at the current sampling time k, and Nc represents the number of sampling points used to calculate the stimulus parameters before the current sampling time k, and Nc≥1.

[0111] The third calculation unit is used to obtain the target stimulus parameter corresponding to the current sampling time k based on the mean error value. Specifically, when the PID controller is used to obtain the target stimulus parameter corresponding to the current sampling time k, the target stimulus parameter corresponding to the current sampling time k is obtained based on the mean error value using the following formulas (Ⅳ)(Ⅴ):

[0112]

[0113]

[0114] Where u(k) is the target stimulus parameter, u max with u min Let K represent the maximum and minimum values ​​of u(k), respectively, and Δu(k) represent the increment of the stimulus parameter corresponding to the current sampling time k compared to the previous sampling time. p K i K d This represents the gain parameter of the PID controller, Δu. max This represents the maximum increment of the stimulus parameter, -Δu max This represents the minimum increment of the stimulus parameter.

[0115] It should be noted that the adaptive closed-loop neural modulation decision-making device provided in the above embodiments is only illustrated by the division of the above functional modules when triggering adaptive closed-loop neural modulation decision-making services. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above. In addition, the adaptive closed-loop neural modulation decision-making device and the embodiments of the adaptive closed-loop neural modulation decision-making method provided in the above embodiments belong to the same concept, that is, the system is based on the method, and its specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0116] In addition, this embodiment also provides an electronic device, including:

[0117] One or more processors; and

[0118] A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the aforementioned adaptive closed-loop neural modulation decision-making method.

[0119] The specific execution details and corresponding beneficial effects of the data processing methods executed by the program instructions are consistent with the descriptions in the aforementioned methods, and will not be repeated here.

[0120] Furthermore, when the processor executes the aforementioned adaptive closed-loop neural modulation decision-making method, the processor's input signal can originate from the electronic device's own signal acquisition and processing hardware module, or from other external signal acquisition and processing hardware devices. The processor's output signal can be sent to the electronic device's own stimulation module, or to other external stimulation devices.

[0121] And, such as Figure 6 As shown, this embodiment also provides a computer-readable storage medium 31 on which a computer program 310 is stored, which, when executed by one or more processors 32, implements the aforementioned adaptive closed-loop neural modulation decision-making method.

[0122] Specifically, any combination of one or more computer-readable media may be used. A computer-readable storage medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in connection with an instruction execution system, apparatus, or device.

[0123] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0124] Program code contained on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0125] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0126] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0127] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0128] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0129] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0130] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0131] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0132] All the above-mentioned optional technical solutions can be combined in any way to form optional embodiments of the present invention. That is, any number of embodiments can be combined to meet the needs of different application scenarios. All of these are within the protection scope of this application and will not be described in detail here.

[0133] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An adaptive closed-loop neural modulation decision-making device, characterized in that, The device includes: The first processing module is used to obtain a corresponding target feedback variable based on the electrophysiological signal of the target object at the current sampling time. The target feedback variable includes at least one electrophysiological signal feature, and the target feedback variable is the average value of the electrophysiological signal features of the target object at n sampling times before the current sampling time. The second processing module is used to obtain the dynamic target value at the current sampling time based on the target feedback variable according to the pre-constructed dynamic control target model; including: obtaining the dynamic target value corresponding to the current sampling time based on the target feedback variable and the dynamic target anchor value, wherein the dynamic target anchor value is determined based on the modulation range of the electrophysiological signal characteristics of the target object obtained in advance; The third processing module is used to obtain the target stimulus parameters corresponding to the current sampling time based on the target feedback variable and the dynamic target value.

2. The apparatus as claimed in claim 1, characterized in that, The method of obtaining the corresponding target feedback variables based on the electrophysiological signals of the target object at the current sampling time includes: Obtain the types of diseases of the target group; Preprocess the electrophysiological signal of the target object at the current sampling time; Based on the pre-acquired correspondence between disease types and electrophysiological signal characteristics, target feedback variables are determined based on the preprocessed electrophysiological signals.

3. The apparatus as described in claim 1, characterized in that, Based on the mean value of the electrophysiological signal features and the dynamic target anchor value, the dynamic target value corresponding to the current sampling time is obtained, and is calculated using the following formula (Ⅰ): (Ⅰ) Where k represents the current sampling time, express Dynamic target value at all times This represents the mean value of the electrophysiological signal characteristics at n sampling times prior to the current sampling time k. express This indicates the adjustment intensity, p∈[0,1].

4. The apparatus as described in claim 3, characterized in that, The mean electrophysiological signal characteristics of the target object at n sampling times prior to the current sampling time are calculated using the following formula (II): （Ⅱ） Where n represents the number of sampling points before the current sampling time k, and N represents the total number of sampling points.

5. The apparatus as claimed in claim 1, characterized in that, The step of obtaining the target stimulus parameters corresponding to the current sampling time based on the target feedback variable and the dynamic target value includes: Calculate the mean error between the target feedback variable and the corresponding dynamic target value at the current sampling time; The target stimulus parameters corresponding to the current sampling time are obtained based on the mean of the error values.

6. The apparatus as claimed in claim 5, characterized in that, The mean error between the target feedback variable and the corresponding dynamic target value at the current sampling time is calculated using the following formula (Ⅲ): (Ⅲ) Where e(k) represents the mean error between the target feedback variable and the corresponding dynamic target value at the current sampling time k, and Nc represents the number of sampling points used to calculate the stimulus parameters before the current sampling time k.

7. The apparatus as claimed in claim 5, characterized in that, When a PID controller is used to obtain the target stimulus parameters corresponding to the current sampling time, the target stimulus parameters corresponding to the current sampling time are obtained based on the mean error value, and are calculated using the following formulas (Ⅳ)(Ⅴ): (Ⅳ) (Ⅴ) in, For the target stimulus parameters, and They represent The maximum and minimum values, This represents the increment of the stimulus parameter corresponding to the current sampling time k compared to the previous sampling time. , , This represents the gain parameter of the PID controller. This represents the maximum increment of the stimulus parameter. This represents the minimum increment of the stimulus parameter.

Images