Stimulation parameter determination method, device and system

Abstract

The invention discloses a stimulation parameter determination method, device and system. The invention relates to the technical field of nerve regulation. The method comprises the following steps: acquiring physiological signal data of a target object under at least two time scales at a current sampling moment; determining a regulation and control target value of the current sampling moment based on the real physiological signal data and the predicted physiological signal data of the target object under the at least two time scales of the current sampling moment; and determining a target stimulation parameter at the current sampling moment based on the regulation target value at the current sampling moment. According to the technical scheme, the regulation target value is dynamically adjusted according to the physiological signal data of the target object under different time scales, namely, the regulation target value can be dynamically adjusted according to the individual difference of the target object and the dynamic change rule of different time scales, the adaptability of the regulation target value to the target object is improved, and the regulation accuracy is improved. Therefore, the accuracy of the stimulation parameter determined by the regulation and control target value is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of neural regulation technology, and in particular to a stimulation parameter determination method, device, stimulator, program-controlled equipment, system, medium and product. Background Art

[0002] With the rapid development of neuroscience, biomedical engineering and materials science, neuromodulation technology is increasingly used in clinical medicine and basic research, becoming an important means to treat neurological diseases, restore neural function and explore neural mechanisms.

[0003] In current neuromodulation technology, stimulation parameters can be set by doctors or determined based on control target values, which are usually set as fixed values ​​or artificially defined dynamic modes such as sine waves or square waves.

[0004] In the process of implementing the present disclosure, it is found that there are at least the following technical problems in the prior art: In the above-mentioned prior art solutions, the stimulation parameters are inaccurate. Summary of the invention

[0005] The present disclosure provides a stimulation parameter determination method, apparatus, stimulator, programmable device, system, equipment and product, which realizes dynamic adjustment of the regulation target value according to the physiological signal data of the target object at different time scales, thereby improving the accuracy of the stimulation parameters determined by the regulation target value.

[0006] According to one aspect of the present disclosure, there is provided a method for determining stimulation parameters, comprising:

[0007] Acquire physiological signal data of the target object at at least two time scales at a current sampling moment, wherein the physiological signal data at least includes real physiological signal data and predicted physiological signal data of the target object;

[0008] Determine a regulation target value at the current sampling moment based on the real physiological signal data and predicted physiological signal data of the target object at at least two time scales at the current sampling moment;

[0009] The target stimulation parameter at the current sampling moment is determined based on the regulation target value at the current sampling moment.

[0010] According to another aspect of the present disclosure, there is provided a stimulation parameter determination device, comprising:

[0011] A multi-time scale data acquisition module, used to acquire physiological signal data of a target object at at least two time scales at a current sampling moment, wherein the physiological signal data at least includes real physiological signal data and predicted physiological signal data of the target object;

[0012] A control target value determination module, used to determine the control target value at the current sampling moment based on the real physiological signal data and the predicted physiological signal data of the target object at at least two time scales at the current sampling moment;

[0013] The target stimulation parameter determination module is used to determine the target stimulation parameter at the current sampling moment based on the control target value at the current sampling moment.

[0014] According to another aspect of the present disclosure, a stimulator is provided, which is implanted in a target object and connected to a stimulation electrode implanted in a target point of the target object, the stimulator acquires real physiological data of the target point through the stimulation electrode, and delivers stimulation pulses to the target point through the stimulation electrode, and the stimulator is configured to execute the stimulation parameter determination method described in any embodiment of the present disclosure.

[0015] According to another aspect of the present disclosure, there is provided a programmable device, the programmable device being communicatively connected to a stimulator implanted in a target subject;

[0016] The stimulator is connected to a stimulation electrode implanted in a target point of a target object, the stimulator acquires real physiological data of the target point through the stimulation electrode, and delivers stimulation pulses to the target point through the stimulation electrode;

[0017] The program-controlled device is configured to execute the stimulation parameter determination method described in any embodiment of the present disclosure to obtain the target stimulation parameter at the current sampling moment, and send the target stimulation parameter at the current sampling moment to the stimulator.

[0018] According to another aspect of the present disclosure, there is provided an implantable medical system, comprising:

[0019] The stimulator according to any embodiment of the present disclosure; or

[0020] The program-controlled device described in any embodiment of the present disclosure.

[0021] According to another aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the stimulation parameter determination method described in any embodiment of the present disclosure when executed.

[0022] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the computer program implements the stimulation parameter determination method as described in any one of the embodiments of the present disclosure.

[0023] The technical solution of the disclosed embodiment obtains the physiological signal data of the target object at at least two time scales at the current sampling moment, and the physiological signal data at least includes the real physiological signal data and the predicted physiological signal data of the target object, and then determines the control target value at the current sampling moment based on the real physiological signal data and the predicted physiological signal data of the target object at at least two time scales at the current sampling moment, and then determines the target stimulation parameters at the current sampling moment based on the control target value at the current sampling moment. In the above technical solution, the control target value can be determined according to the real physiological signal data and the predicted physiological signal data of the target object at the current sampling moment at different time scales, and the dynamic adjustment of the control target value according to the physiological signal data of the target object at different time scales is realized, that is, the control target value can be adjusted according to the individual differences of the target object and the dynamic change laws of different time scales, and the adaptability of the control target value to the target object is improved, thereby improving the accuracy of the stimulation parameters determined by the control target value, and thus improving the accuracy and effectiveness of neural regulation.

[0024] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1 is a flow chart of a method for determining stimulation parameters according to an embodiment of the present disclosure;

[0027] Figure 2 is a schematic diagram of a closed-loop neural regulation strategy provided according to an embodiment of the present disclosure;

[0028] Figure 3 is a flow chart of another method for determining stimulation parameters provided according to an embodiment of the present disclosure;

[0029] Figure 4 is a flow chart of another method for determining stimulation parameters provided according to an embodiment of the present disclosure;

[0030] Figure 5 is a schematic diagram of calculating a control target value according to an embodiment of the present disclosure;

[0031] Figure 6is a schematic diagram of another control target value calculation provided according to an embodiment of the present disclosure;

[0032] Figure 7 is a flow chart of calculating a control target value according to an embodiment of the present disclosure;

[0033] Figure 8 is a structural schematic diagram of a stimulation parameter determination device provided according to an embodiment of the present disclosure;

[0034] Fig. 9 It is a structural schematic diagram of an electronic device for implementing the stimulation parameter determination method of an embodiment of the present disclosure. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the scheme of the present disclosure, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present disclosure.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of the present disclosure comply with the relevant provisions of national laws and regulations.

[0037] The technical field and related terms of the embodiments of the present disclosure are briefly described below.

[0038] Implantable medical systems include implantable neural stimulation systems, implantable cardiac stimulation systems (also known as pacemakers), implantable drug delivery systems (IDDS), and lead switching systems. Examples of implantable neural stimulation systems include deep brain stimulation (DBS), implantable cortical nerve stimulation (CNS), implantable spinal cord stimulation (SCS), implantable sacral nerve stimulation (SNS), and implantable vagus nerve stimulation (VNS).

[0039] The implantable neural electrical stimulation system includes a stimulator implanted in the patient's body (i.e., an implantable neural stimulator) and a programmable device disposed outside the patient's body. In other words, the stimulator is a medical device, or in other words, the medical device includes the stimulator. The relevant neural regulation technology mainly implants electrodes (electrodes, for example, in the form of electrode wires) in specific parts of the tissues of the organism (i.e., target points) through stereotactic surgery, and emits discharge pulses to the target points through the electrodes to regulate the electrical activity and function of the corresponding neural structures and networks, thereby improving symptoms and relieving pain.

[0040] As an example, DBS includes an IPG (Implantable Pulse Generator), an extension wire and an electrode wire, and the IPG is connected to the electrode wire via the extension wire. The IPG is implanted in the patient's body, for example, in the patient's chest or other body parts.

[0041] As another example, DBS includes an IPG and an electrode lead, and the IPG is directly connected to the electrode lead. The IPG is implanted in the patient's head, for example, a groove is made in the patient's skull, and then the IPG is installed in the groove of the skull. In this case, the IPG may not protrude from the outer surface of the skull, or may partially protrude from the outer surface of the skull.

[0042] The IPG responds to the program-controlled instructions sent by the program-controlled device, and relies on sealed batteries and circuits to provide controllable electrical stimulation therapy (or electrical stimulation energy) to the tissues in the body. The IPG delivers one or more controllable specific electrical stimulations to specific areas of the tissues in the body through electrode wires.

[0043] In some embodiments, the extension lead is used in conjunction with the IPG as a transmission medium for electrical stimulation, and transmits the electrical stimulation generated by the IPG to the electrode lead.

[0044] In some embodiments, the electrical stimulation may be delivered in the form of a pulse signal or in the form of a non-pulse signal. For example, the electrical stimulation may be delivered as a signal having various waveform shapes, frequencies, and amplitudes. Thus, the electrical stimulation in the form of a non-pulse signal may be a continuous signal, which may have a sinusoidal waveform or other continuous waveform.

[0045] After receiving the electrical stimulation transmitted by the IPG or the extension wire, the electrode wire delivers the electrical stimulation to a specific area of ​​the tissue in the body through a plurality of electrode contacts. The stimulator is provided with, for example, one or more electrode wires on one side or both sides, and a plurality of electrode contacts are provided on the electrode wire, and the electrode contacts can be arranged uniformly or non-uniformly in the circumferential direction of the electrode wire. As an example, the electrode contacts can be arranged in an array of 4 rows and 3 columns (a total of 12 electrode contacts) in the circumferential direction of the electrode wire. The electrode contacts can include stimulation electrode contacts and / or collection electrode contacts. The electrode contacts can be in the shape of sheets, rings, dots, etc., for example.

[0046] In some embodiments, the stimulated in vivo tissue may be the patient's brain tissue, and the stimulated site may be a specific site of the brain tissue. When the patient's disease type is different, the stimulated site is generally different, and the number of stimulation contacts (single source or multiple sources), the use of one or more (single channel or multiple channels) of specific electrical stimulation, and the stimulation parameters (values) are also different.

[0047] The embodiments of the present disclosure do not limit the types of diseases that can be used, and can be diseases that can be used for deep brain stimulation (DBS), spinal cord stimulation (SCS), sacral nerve stimulation, gastric stimulation, peripheral nerve stimulation, and functional electrical stimulation. Among them, the types of diseases that DBS can be used to treat or manage include, but are not limited to: spastic diseases (e.g., epilepsy), pain, migraine, mental illness (e.g., major depressive disorder (MDD)), bipolar disorder, anxiety, post-traumatic stress disorder, mild depression, obsessive-compulsive disorder (OCD), behavioral disorders, mood disorders, memory disorders, mental state disorders, movement disorders (e.g., essential tremor or Parkinson's disease), Huntington's disease, Alzheimer's disease, drug addiction, autism, or other neurological or psychiatric diseases and injuries.

[0048] In the disclosed embodiment, when the programmable device and the stimulator establish a programmable connection, the programmable device can be used to adjust one or more stimulation parameters of the stimulator (or one or more stimulation parameters of the pulse generator, different stimulation parameters correspond to different electrical stimulations), or the stimulator can sense the patient's electrophysiological activities to collect electrophysiological signals, and the collected electrophysiological signals can be used to continue to adjust the stimulation parameters of the stimulator, thereby realizing closed-loop control (or adaptive adjustment) of the stimulation parameters.

[0049] The stimulation parameters may include at least one of the following: the electrode contact identification used to deliver electrical stimulation (for example, electrode contact #2 and electrode contact #3), frequency (for example, the number of electrical stimulation pulse signals within a unit time of 1s, in Hz), pulse width (the duration of each pulse, in μs), amplitude (generally expressed in voltage, that is, the intensity of each pulse, in V), timing (for example, it can be continuous or burst, and burst refers to discontinuous timing behavior composed of multiple processes), stimulation mode (including one or more of current mode, voltage mode, timed stimulation mode and cyclic stimulation mode), upper and lower limits controlled by the doctor (the range that can be adjusted by the doctor) and upper and lower limits controlled by the patient (the range that can be adjusted autonomously by the patient).

[0050] In some embodiments, various stimulation parameters of the stimulator can be adjusted in current mode or voltage mode.

[0051] Programmable devices may include doctor programmable devices (i.e. programmable devices used by doctors) and / or patient programmable devices (i.e. programmable devices used by patients). Doctor programmable devices are, for example, tablet computers, laptop computers, desktop computers, mobile phones and other intelligent terminal devices equipped with programmable software. Patient programmable devices are, for example, tablet computers, laptop computers, desktop computers, mobile phones and other intelligent terminal devices equipped with programmable software. Patient programmable devices may also be other electronic devices with programmable functions (e.g., chargers with programmable functions, electrophysiological acquisition devices, etc.).

[0052] In the existing neural regulation technology, due to the individual differences between the disease state and physiological signals of patients, and the fact that physiological signals will dynamically fluctuate with different time scales, it is impossible to dynamically adjust the regulation target value according to the dynamic rhythm of the patient's neural activity itself or the influence of external factors (such as medication, etc.) on neural activity, which seriously affects the accuracy of the stimulation parameters. To this end, the embodiments of the present disclosure provide a method, device, stimulator, program-controlled equipment, system, medium and product for determining stimulation parameters, which can effectively solve this problem. The following will further describe in detail the stimulation parameter determination method, device, stimulator, program-controlled equipment, system, medium and product provided by the embodiments of the present disclosure.

[0053] Figure 1 This is a flowchart of a stimulation parameter determination method provided by an embodiment of the present disclosure. This embodiment can be applied to the case of adaptively adjusting stimulation parameters in closed-loop neural regulation. The method can be executed by a stimulation parameter determination device, which can be implemented in the form of hardware and / or software. The stimulation parameter determination device can be configured in electronic devices such as stimulators and programmable devices. It should be noted that the stimulation parameter determination method is used to determine stimulation parameters suitable for neural regulation, and does not directly perform stimulation on the target object. Figure 1 As shown, the method includes:

[0054] S110, acquiring physiological signal data of a target object at at least two time scales at a current sampling moment, wherein the physiological signal data at least includes real physiological signal data and predicted physiological signal data of the target object.

[0055] Among them, the target object refers to the object currently undergoing neural regulation, which can be a patient or an animal, etc. Physiological signal data refers to the neural activity data of the target object, which can be the electrophysiological signal amplitude or other electrophysiological signal characteristics, which are not specifically limited here. Preferably, the physiological signal data can be the mean of neural activity, for example, the physiological signal data can be the mean of neural activity in the target area of ​​the patient's brain, etc. The mean of neural activity refers to the average energy of the activity of neurons or neural groups within a preset time range, which is used to quantify the overall activity state of the nervous system or the activity intensity of a specific area. Time scale refers to a standard for describing or measuring time spans. Physiological signal data under different time scales can be the same or there can be differences. Preferably, the time scale includes at least two of milliseconds, seconds, minutes, hours, days, months and years.

[0056] In the embodiments of the present disclosure, the real physiological signal data is the physiological signal data after the collected real physiological signal is processed, and the processing method can be mean processing, denoising or other data processing methods, which are not specifically limited here. The predicted physiological signal data refers to the predicted physiological signal data, which can be predicted based on the historical physiological signal data.

[0057] Exemplarily, the mean value of the patient's neural activity at the current sampling moment at the time scale of seconds, minutes, and hours can be obtained respectively; the mean value of the patient's neural activity at the current sampling moment at the time scale of seconds and minutes can also be obtained respectively.

[0058] It should be noted that neural activity has dynamics at different time scales such as milliseconds, seconds, minutes, hours, days, months and years, that is, the mean value of neural activity can change dynamically according to time scales such as medication rhythm, circadian rhythm and seasonality.

[0059] S120: Determine a control target value at the current sampling moment based on the real physiological signal data and predicted physiological signal data of the target object at at least two time scales at the current sampling moment.

[0060] Among them, the control target value refers to a dynamic target value that matches the current neural state of the target object, that is, the control target value can be dynamically adjusted according to the physiological signal data of the target object at different time scales.

[0061] Specifically, the difference or ratio of the real physiological signal data and the predicted physiological signal data of the target object at the current sampling moment under different time scales can be used as the control target value at the current sampling moment, or the above difference or ratio can be corrected and the corrected value can be used as the control target value at the current sampling moment.

[0062] S130. Determine a target stimulation parameter at the current sampling moment based on the control target value at the current sampling moment.

[0063] The target stimulation parameters refer to the stimulation parameters calculated according to the control target values.

[0064] Specifically, the target stimulation parameters corresponding to the control target value can be calculated by a preset control algorithm, wherein the preset control algorithm can be a control algorithm based on a proportional-integral-differential controller or a control algorithm based on other controllers, which is not specifically limited here.

[0065] In some embodiments, a correspondence table between stimulation parameters and control target values ​​may be set in advance, that is, different correspondence tables may be set for different diseases or patients, so that when determining the control target value, the corresponding stimulation parameters may be found by calling the correspondence table.

[0066] In another embodiment of the present specification, after the target stimulation parameters are determined, a stimulation instruction needs to be sent to the pulse generating unit in the stimulator, for example, the stimulation instruction can be sent by the processor unit of the stimulator to the pulse generating unit, in order to avoid a large degree of intensity change caused by the adjustment of the stimulation parameters, resulting in a poor user experience for the patient, such as a feeling of discomfort. The output stimulation instruction can also be adjusted according to the current actual stimulation parameters and the target stimulation parameters.

[0067] For example, different stimulation strategies can be determined according to the gap between the current actual stimulation parameters and the target stimulation parameters. When the gap between the two is small, the patient will not feel any abnormality when the stimulation signal is immediately switched to the target stimulation parameters, and the stimulation switching can be performed directly. When the gap between the two is large, direct stimulation switching will cause discomfort to the patient. Therefore, based on the current actual stimulation parameters, the stimulation parameters can be gradually adjusted to the target stimulation parameters, so that the patient has an adaptation process, thereby improving the patient's symptoms while improving the patient's user experience.

[0068] Furthermore, the stimulation parameters may be increased or decreased by the same amount within a specified time, gradually transitioning to the target stimulation parameters.

[0069] For example, Figure 2 It is a schematic diagram of a closed-loop neural regulation strategy provided according to an embodiment of the present disclosure. Figure 2The control target value determination module and the target stimulation parameter determination module in the closed-loop neural control strategy are software function modules. Specifically, the closed-loop neural control strategy includes: after obtaining the physiological signal data of the target object at at least two time scales at the current sampling moment, the physiological signal data of the target object at at least two time scales at the current sampling moment can be input into the control target value determination module, and then the control target value determination module calculates the control target value at the current sampling moment according to the physiological signal data of the target object at at least two time scales at the current sampling moment, and then the control target value at the current sampling moment is input into the target stimulation parameter determination module, and then the target stimulation parameter determination module calculates the target stimulation parameters at the current sampling moment according to the control target value at the current sampling moment, and then adjusts the stimulation parameters of the stimulator according to the target stimulation parameters, and applies the stimulation generated by the stimulator to the target object, continues to obtain the physiological signal data at the next sampling moment and dynamically adjusts the control target value to form a closed-loop neural control.

[0070] The technical solution of the disclosed embodiment obtains the physiological signal data of the target object at at least two time scales at the current sampling moment, and the physiological signal data at least includes the real physiological signal data and the predicted physiological signal data of the target object, and then determines the control target value at the current sampling moment based on the real physiological signal data and the predicted physiological signal data of the target object at at least two time scales at the current sampling moment, and then determines the target stimulation parameters at the current sampling moment based on the control target value at the current sampling moment. In the above technical solution, the control target value can be determined according to the real physiological signal data and the predicted physiological signal data of the target object at the current sampling moment at different time scales, and the dynamic adjustment of the control target value according to the physiological signal data of the target object at different time scales is realized, that is, the control target value can be adjusted according to the individual differences of the target object and the dynamic change laws of different time scales, and the adaptability of the control target value to the target object is improved, thereby improving the accuracy of the stimulation parameters determined by the control target value, and thus improving the accuracy and effectiveness of neural regulation.

[0071] Figure 3 A flowchart of a method for determining stimulation parameters provided in an embodiment of the present disclosure, the method of this embodiment can be combined with the various optional schemes in the method for determining stimulation parameters provided in the above embodiments. Based on the above embodiments, this embodiment further refines the acquisition of physiological signal data of the target object at at least two time scales at the current sampling moment.

[0072] like Figure 3 As shown, the method includes:

[0073] S210. Acquire a real physiological signal of the target object at a current sampling moment under a first time scale, and determine real physiological signal data of the target object at the current sampling moment under the first time scale based on the real physiological signal of the target object at the current sampling moment under the first time scale.

[0074] The real physiological signal is an electrophysiological signal collected in real time.

[0075] Exemplarily, the physiological signal acquisition device can acquire the patient's true physiological signal at the current sampling moment on a time scale of seconds in real time, and then calculate the mean of the true physiological signal, that is, obtain the patient's neural activity mean at the current sampling moment on a time scale of seconds, and the neural activity mean is the true physiological signal data.

[0076] S220: Acquire historical physiological signal data of the target object, and predict predicted physiological signal data of the target object at a current sampling moment in a second time scale based on the historical physiological signal data of the target object.

[0077] In the embodiment of the present disclosure, the historical physiological signal data refers to the physiological signal before the current sampling time, and the sampling number may be one or more. For example, the historical physiological signal data may be the electrophysiological signal at n sampling times before the current sampling time k.

[0078] Specifically, artificial intelligence algorithms such as deep learning or machine learning can be used to predict the predicted physiological signal data of the target object at the current sampling moment in the current time scale based on the historical physiological signal data.

[0079] On the basis of the above embodiments, optionally, predicted physiological signal data of the target object at the current sampling moment under a second time scale is obtained based on the historical physiological signal data of the target object, including: obtaining a window length corresponding to the second time scale; determining the historical physiological signal data of the target object corresponding to the window length of the second time scale; inputting the historical physiological signal data of the target object corresponding to the window length of the current time scale into a pre-trained physiological signal data prediction model to obtain the predicted physiological signal data of the target object at the current sampling moment under the second time scale.

[0080] The window length corresponding to the second time scale refers to the duration of the second time scale. For example, when the time scale is minutes, the window length can be one minute; when the time scale is hours, the window length can be one hour. The physiological signal data prediction model is an artificial intelligence model for physiological signal data prediction, and its network architecture can be a long short-term memory network (Long Short-Term Memory, LSTM), an improved network of LSTM, or other networks, which are not limited here.

[0081] It should be noted that the historical physiological signal data of the window length corresponding to the second time scale can be used to predict the mean value of neural activity in the future (with the same window length as the current time scale). This mean value of neural activity can not only calculate the control target value at the current sampling moment, but also take into account the lag of neural activity in response to neural regulation. Clinically, dystonia among movement disorders and mental disorders are typical indications.

[0082] Based on the above embodiments, optionally, the window length corresponding to the second time scale is greater than the window length corresponding to the first time scale.

[0083] It can be understood that the window length corresponding to the second time scale is greater than the window length corresponding to the first time scale, indicating that the duration corresponding to the second time scale is greater than the duration corresponding to the first time scale. For example, the first time scale is the time scale of seconds, and the second time scale is the time scale of minutes. The duration of the time scale of seconds can be 1 second, and the duration of the time scale of minutes can be 1 minute, that is, the window length corresponding to the second time scale is greater than the window length corresponding to the first time scale.

[0084] It should be noted that the mean value of the neural activity at the second time scale of the present application is not the actual collected physiological signal data, but is predicted based on the historical physiological signal data. This is because it takes a long time to collect the actual physiological signal data. If the mean value of the neural activity at the second time scale is obtained using the real physiological signal, the real-time nature of the neural regulation cannot be guaranteed. In order to ensure the real-time nature of the neural regulation, the present disclosure uses a prediction method to obtain the physiological signal data at the second time scale.

[0085] Exemplarily, the time scale can be minutes, that is, the historical physiological signal data of the target object of one minute before the current sampling moment can be intercepted, and then the historical physiological signal data of the target object of one minute before the current sampling moment is input into the pre-trained LSTM-based physiological signal data prediction model, and the LSTM-based physiological signal data prediction model outputs the predicted physiological signal data of the target object at the current sampling moment under the minute time scale. Among them, the training steps of the LSTM-based physiological signal data prediction model may include: obtaining multiple physiological signal samples and labels corresponding to the physiological signal samples, the labels are the true values ​​of the physiological signal data, inputting multiple physiological signal samples into the LSTM-based initial model to be trained, outputting the physiological signal data prediction value based on the LSTM-based initial model, and then determining the model loss based on the physiological signal data prediction value and the true value of the physiological signal data, and then updating the model parameters of the LSTM-based initial model according to the model loss until the model training stop condition is met, and obtaining the LSTM-based physiological signal data prediction model.

[0086] S230: Determine a control target value at the current sampling moment based on the real physiological signal data of the target object at the current sampling moment under the first time scale and the predicted physiological signal data of the target object at the current sampling moment under the second time scale.

[0087] In some embodiments, the predicted physiological signal data of the target object at the current sampling moment under a third time scale and the predicted physiological signal data of the target object at the current sampling moment under more time scales can also be predicted through the historical physiological signal data of the target object. Further, the control target value at the current sampling moment can be determined based on the physiological signal data of the target object at the current sampling moment under multiple time scales.

[0088] S240: Determine a target stimulation parameter at the current sampling moment based on the control target value at the current sampling moment.

[0089] The technical solution of the disclosed embodiment is to obtain the real physiological signal of the target object at the current sampling moment on a first time scale by collecting, and determine the real physiological signal data of the target object at the current sampling moment on the current time scale based on the real physiological signal of the target object at the current sampling moment on the first time scale; obtain the historical physiological signal data of the target object, and predict the predicted physiological signal data of the target object at the current sampling moment on a second time scale based on the historical physiological signal data of the target object. The above technical solution realizes the calculation or prediction of physiological signal data at different time scales, and provides accurate and reliable data basis for determining the control target value.

[0090] Figure 4 A flowchart of a method for determining stimulation parameters provided in an embodiment of the present disclosure, the method of this embodiment can be combined with the various optional schemes in the method for determining stimulation parameters provided in the above embodiments. Based on the above embodiments, this embodiment further refines the determination of the control target value at the current sampling moment based on the real physiological signal data and predicted physiological signal data of the target object at at least two time scales at the current sampling moment.

[0091] like Figure 4 As shown, the method includes:

[0092] S310: Acquire physiological signal data of a target object at at least two time scales at a current sampling moment, wherein the physiological signal data at least includes real physiological signal data and predicted physiological signal data of the target object.

[0093] S320: Determine deviation values ​​between the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment.

[0094] The deviation value is used to characterize the deviation between the real physiological signal data and the predicted physiological signal data.

[0095] Exemplarily, the number of layers of the time scale can be two layers, that is, when the time scale includes a first time scale and a second time scale, the real physiological signal data of the target object at the current sampling moment of the first time scale can be subtracted from the predicted physiological signal data of the target object at the current sampling moment of the second time scale to obtain the deviation value of the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment. When the number of layers of the time scale is three or more layers, the physiological signal data corresponding to each layer of time scale can be subtracted in sequence to obtain the deviation value of the physiological signal data of the target object at different time scales at the current sampling moment.

[0096] S330: Determine a control target value at the current sampling moment based on deviation values ​​of the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment.

[0097] Specifically, the deviation value can be directly used as the control target value at the current sampling moment, or the deviation value can be corrected or compensated, and the corrected or compensated deviation value can be used as the control target value at the current sampling moment to improve the accuracy of the control target value.

[0098] On the basis of the above embodiments, optionally, the control target value at the current sampling moment is determined based on the deviation value of the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment, including: obtaining a pre-set control coefficient, wherein the control coefficient is associated with the time scale corresponding to the predicted physiological signal data; determining the control target value at the current sampling moment based on the deviation value of the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment and the pre-set control coefficient.

[0099] Among them, the control coefficient is used to correct or compensate for the deviation value of the physiological signal data of the target object at different time scales at the current sampling moment to improve the accuracy of the control target value. The control coefficient can be set to any value between 0-100%, and the specific setting value can be determined by the user in combination with clinical practice. The meaning of the control coefficient being associated with the time scale corresponding to the predicted physiological signal data is that each predicted physiological signal data has a corresponding control coefficient. In other words, the number of control coefficients can be multiple, and each control coefficient can be used to control the deviation value of the predicted physiological signal data at the corresponding time scale.

[0100] Exemplarily, taking the three-layer time scale as an example, the predicted physiological signal data of the target object at the current sampling moment at the second time scale has a first control coefficient, and the first control coefficient is used to control the deviation value between the predicted physiological signal data at the second time scale and the real physiological signal data at the first time scale. The predicted physiological signal data of the target object at the current sampling moment at the third time scale has a second control coefficient, and the second control coefficient is used to control the deviation value between the predicted physiological signal data at the third time scale and the physiological signal data at the first two time scales.

[0101] It should be noted that if the stimulation parameters are obtained only through real collected data and predicted data, a strong stimulation intensity may be obtained, and the patient will have a strong sense of discomfort when using it, affecting their usage experience or safety. By setting the control coefficient, the large stimulation contrast caused by the adjustment of stimulation parameters during closed-loop stimulation can be effectively reduced, thereby achieving gradual stimulation adjustment and improving the patient's usage experience.

[0102] On the basis of the above embodiments, optionally, obtaining a preset control coefficient includes: determining a state parameter of the target object associated with the target disease according to a preset period, the state parameter characterizing a recovery state of the target object; and periodically determining the control coefficient based on the state parameter of the target object associated with the target disease.

[0103] Among them, the preset period can be a time period set by the user, which can be one or more signal sampling periods, which is not specifically limited here. The target disease can be a spasm disease (e.g., epilepsy), pain, migraine, mental illness (e.g., major depressive disorder (MDD)), bipolar disorder, anxiety, post-traumatic stress disorder, mild depression, obsessive-compulsive disorder (OCD), behavioral disorder, emotional disorder, memory disorder, mental state disorder, movement disorder (e.g., essential tremor or Parkinson's disease), Huntington's disease, Alzheimer's disease, drug addiction, autism or other neurological or psychiatric diseases. The state parameter can characterize the disease recovery state of the target object, and can be evaluated by scores or grades, such as 80 points or the first grade.

[0104] Specifically, the patient's physiological signal data, patient self-evaluation, patient posture and heart rate data are collected at regular intervals, and then the patient's symptom recovery status is scored or evaluated based on the physiological signal data, patient self-evaluation, patient posture and heart rate data to obtain status parameters.

[0105] In some embodiments, the state parameter of the target object associated with the target disease may be positively correlated with the control coefficient, that is, the larger the state parameter of the target object associated with the target disease, the larger the control coefficient. It is understandable that the larger the state parameter, the better the recovery of the target object. In some embodiments, the state parameter of the target object associated with the target disease and the control coefficient may also have other mapping relationships, which are not limited here.

[0106] For example, Figure 5 Schematic diagram of a control target value calculation provided according to an embodiment of the present disclosure. The present disclosure embodiment takes three-layer time scale as an example, and the window lengths of the three-layer time scale are n 1 、n 2 and n 3 , n 1 <n 2 <n 3 , for example 1 Can be seconds, n 2 Can be minutes, n 3 It can be hours. In the first time scale (i.e., time scale n 1 ), the blue solid line represents the real physiological signal (i.e., the physiological signal amplitude), which can be collected by the physiological signal acquisition device; the yellow solid line represents the mean value of the neural activity at the current sampling time k in the first time scale, which can be calculated by the real physiological signal. The mean value of the neural activity at the current sampling time k in the first time scale can be recorded as In the second time scale (i.e., time scale n 2 ), the yellow dotted line represents the mean value of the neural activity at the current sampling time k in the second time scale predicted by the historical physiological signal data. The mean value of the neural activity at the current sampling time k in the second time scale can be recorded as Furthermore, combined with the preset first control coefficient p 1 , the control target value of the integrated two time scales at the current sampling time k can be calculated, represented by the red dot, and the formula is as follows:

[0107]

[0108] Among them, t 1 (k) represents the control target value of the two time scales at the current sampling time k.

[0109] Furthermore, in the third time scale (i.e., time scale n 3 ), the yellow dotted line represents the mean value of the neural activity at the current sampling time k in the third time scale predicted by the historical physiological signal data. The mean value of the neural activity at the current sampling time k in the third time scale can be recorded as Furthermore, using and t 1 (k), and combined with the pre-set second control coefficient p 2 , the control target value of the integrated three time scales at the current sampling time k can be calculated, represented by the red dot, and the formula is as follows:

[0110]

[0111] Among them, t 2 (k) represents the control target value of the three time scales at the current sampling time k.

[0112] It should be noted that Figure 5 In order to facilitate the understanding of the calculation process of the control target value, the same sampling time k under the three time scales is not aligned. The schematic diagram after the sampling time k is aligned is as follows: Figure 6 shown.

[0113] S340: Determine a target stimulation parameter at the current sampling moment based on the control target value at the current sampling moment.

[0114] Figure 7 1 is a flow chart of a control target value calculation provided according to an embodiment of the present disclosure. The control target value calculation step includes:

[0115] 1. Collect the patient's physiological signals;

[0116] 2. Set the time scale layers and window length according to the patient's needs;

[0117] 3. Predict the mean value of neural activity at different time scales based on the patient's physiological signals;

[0118] 4. Set the control coefficient. The number of control coefficients is the number of time scale layers minus 1.

[0119] 5. The control target value is calculated based on the mean value of neural activity at different time scales and the control coefficient.

[0120] It should be noted that the embodiments of the present disclosure can perform individualized settings for the time scale layers, the time scale window length, and the control coefficient according to the individual conditions of the patients, thereby improving the adaptability of the control target value.

[0121] The technical solution of the disclosed embodiment determines the control target value according to the deviation value of the physiological signal data of the target object at the current sampling moment under different time scales, and realizes the dynamic adjustment of the control target value according to the physiological signal data of the target object under different time scales, thereby improving the accuracy of the stimulation parameters, and further improving the precision and effectiveness of neural regulation.

[0122] Figure 8FIG. 1 is a schematic diagram of a device for determining stimulation parameters provided by an embodiment of the present disclosure. Figure 8 As shown, the device comprises:

[0123] A multi-time scale data acquisition module 410 is used to acquire physiological signal data of a target object at at least two time scales at a current sampling moment, wherein the physiological signal data at least includes real physiological signal data and predicted physiological signal data of the target object;

[0124] A control target value determination module 420, configured to determine a control target value at a current sampling moment based on the real physiological signal data and the predicted physiological signal data of the target object at at least two time scales at the current sampling moment;

[0125] The target stimulation parameter determination module 430 is used to determine the target stimulation parameter at the current sampling moment based on the control target value at the current sampling moment.

[0126] The technical solution of the disclosed embodiment obtains the physiological signal data of the target object at at least two time scales at the current sampling moment, and the physiological signal data at least includes the real physiological signal data and the predicted physiological signal data of the target object, and then determines the control target value at the current sampling moment based on the real physiological signal data and the predicted physiological signal data of the target object at at least two time scales at the current sampling moment, and then determines the target stimulation parameters at the current sampling moment based on the control target value at the current sampling moment. In the above technical solution, the control target value can be determined according to the real physiological signal data and the predicted physiological signal data of the target object at the current sampling moment at different time scales, and the dynamic adjustment of the control target value according to the physiological signal data of the target object at different time scales is realized, that is, the control target value can be adjusted according to the individual differences of the target object and the dynamic change laws of different time scales, and the adaptability of the control target value to the target object is improved, thereby improving the accuracy of the stimulation parameters determined by the control target value, and thus improving the accuracy and effectiveness of neural regulation.

[0127] Based on any optional technical solution in the embodiments of the present disclosure, optionally, the time scale includes at least two of milliseconds, seconds, minutes, hours, days, months and years.

[0128] Based on any optional technical solution in the embodiments of the present disclosure, optionally, the multi-time scale data acquisition module 410 includes:

[0129] A first time scale data acquisition unit, used for acquiring a real physiological signal of the target object at a current sampling moment at a first time scale, and determining the real physiological signal data of the target object at the current sampling moment at the first time scale based on the real physiological signal of the target object at the current sampling moment at the first time scale;

[0130] The second time scale data acquisition unit is used to acquire the historical physiological signal data of the target object, and predict the predicted physiological signal data of the target object at the current sampling moment under the second time scale based on the historical physiological signal data of the target object.

[0131] On the basis of any optional technical solution in the embodiments of the present disclosure, optionally, the second time scale data acquisition unit may be specifically used to:

[0132] Obtain the window length corresponding to the second time scale;

[0133] Determine historical physiological signal data of the target object corresponding to the window length of the second time scale;

[0134] The historical physiological signal data of the target object corresponding to the window length of the second time scale is input into a pre-trained physiological signal data prediction model to obtain the predicted physiological signal data of the target object at the current sampling moment under the second time scale.

[0135] Based on any optional technical solution in the embodiments of the present disclosure, optionally, the window length corresponding to the second time scale is greater than the window length corresponding to the first time scale.

[0136] Based on any optional technical solution in the embodiments of the present disclosure, optionally, the control target value determination module 420 includes:

[0137] A different time scale data deviation value determination unit, used to determine the deviation value between the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment;

[0138] The control target value determination unit at the current moment is used to determine the control target value at the current sampling moment based on the deviation value of the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment.

[0139] On the basis of any optional technical solution in the embodiments of the present disclosure, optionally, the control target value determination unit at the current moment includes:

[0140] A control coefficient acquisition subunit, used to acquire a preset control coefficient, wherein the control coefficient is associated with a time scale corresponding to the predicted physiological signal data;

[0141] The control target value determination subunit is used to determine the control target value at the current sampling moment based on the deviation value of the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment and the preset control coefficient.

[0142] On the basis of any optional technical solution in the embodiments of the present disclosure, optionally, the control coefficient acquisition subunit may also be specifically used for:

[0143] determining a state parameter of the target object associated with a target disease according to a preset period, the state parameter representing a recovery state of the target object;

[0144] A control coefficient is periodically determined based on a state parameter of the target object associated with a target disease.

[0145] Based on any optional technical solution in the embodiments of the present disclosure, optionally, the physiological signal data is a mean value of neural activity.

[0146] The stimulation parameter determination device provided in the embodiments of the present disclosure can execute the stimulation parameter determination method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0147] An embodiment of the present disclosure provides a stimulator, which is implanted into a target object and connected to a stimulation electrode implanted in a target point of the target object. The stimulator obtains real physiological data of the target point through the stimulation electrode, and delivers stimulation pulses to the target point through the stimulation electrode. The stimulator is configured to execute the stimulation parameter determination method described in any one of the embodiments of the present disclosure.

[0148] An embodiment of the present disclosure provides a programmable device, which is communicatively connected to a stimulator implanted in a target object; the stimulator is connected to a stimulation electrode implanted in a target point of the target object, the stimulator obtains real physiological data of the target point through the stimulation electrode, and delivers stimulation pulses to the target point through the stimulation electrode; the programmable device is configured to execute the stimulation parameter determination method described in any one of the embodiments of the present disclosure to obtain the target stimulation parameters at the current sampling moment, and send the target stimulation parameters at the current sampling moment to the stimulator.

[0149] An embodiment of the present disclosure provides an implantable medical system, which includes the stimulator described in any one of the embodiments of the present disclosure or the programmable device described in any one of the embodiments of the present disclosure.

[0150] The technical solution of the disclosed embodiment obtains the physiological signal data of the target object at at least two time scales at the current sampling moment, and the physiological signal data at least includes the real physiological signal data and the predicted physiological signal data of the target object, and then determines the control target value at the current sampling moment based on the real physiological signal data and the predicted physiological signal data of the target object at at least two time scales at the current sampling moment, and then determines the target stimulation parameters at the current sampling moment based on the control target value at the current sampling moment. In the above technical solution, the control target value can be determined according to the real physiological signal data and the predicted physiological signal data of the target object at the current sampling moment at different time scales, and the dynamic adjustment of the control target value according to the physiological signal data of the target object at different time scales is realized, that is, the control target value can be adjusted according to the individual differences of the target object and the dynamic change laws of different time scales, and the adaptability of the control target value to the target object is improved, thereby improving the accuracy of the stimulation parameters determined by the control target value, and thus improving the accuracy and effectiveness of neural regulation.

[0151] Fig. 9 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0152] like Fig. 9 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The I / O interface 15 is also connected to the bus 14.

[0153] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0154] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 performs the various methods and processes described above, such as a stimulation parameter determination method, which includes:

[0155] Acquire physiological signal data of the target object at at least two time scales at a current sampling moment, wherein the physiological signal data at least includes real physiological signal data and predicted physiological signal data of the target object;

[0156] Determine a regulation target value at the current sampling moment based on the real physiological signal data and predicted physiological signal data of the target object at at least two time scales at the current sampling moment;

[0157] The target stimulation parameter at the current sampling moment is determined based on the regulation target value at the current sampling moment.

[0158] In some embodiments, the stimulation parameter determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the stimulation parameter determination method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the stimulation parameter determination method in any other appropriate manner (e.g., by means of firmware).

[0159] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0160] Computer programs for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0161] In the context of the present disclosure, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0162] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0163] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0164] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0165] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of this disclosure can be achieved, and this document is not limited here.

[0166] The embodiments of the present disclosure also provide a computer program product, including a computer program, which, when executed by a processor, implements the stimulation parameter determination method provided in any embodiment of the present disclosure.

[0167] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code for the disclosed operation, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "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 separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0168] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for determining stimulation parameters, characterized in that: include: Acquire physiological signal data of the target object at at least two time scales at a current sampling moment, wherein the physiological signal data at least includes real physiological signal data and predicted physiological signal data of the target object; Determine a regulation target value at the current sampling moment based on the real physiological signal data and predicted physiological signal data of the target object at at least two time scales at the current sampling moment; The target stimulation parameter at the current sampling moment is determined based on the regulation target value at the current sampling moment.

2. The method according to claim 1, characterized in that The time scale includes at least two of milliseconds, seconds, minutes, hours, days, months and years.

3. The method according to claim 1, characterized in that The step of obtaining physiological signal data of the target object at at least two time scales at the current sampling moment includes: Acquire a real physiological signal of the target object at a current sampling moment under a first time scale, and determine real physiological signal data of the target object at the current sampling moment under the first time scale based on the real physiological signal of the target object at the current sampling moment under the first time scale; The historical physiological signal data of the target object is acquired, and the predicted physiological signal data of the target object at the current sampling moment in a second time scale is predicted based on the historical physiological signal data of the target object.

4. The method according to claim 3, characterized in that The step of predicting the target object's predicted physiological signal data at the current sampling moment at the second time scale based on the target object's historical physiological signal data includes: Obtain the window length corresponding to the second time scale; Determine historical physiological signal data of the target object corresponding to the window length of the second time scale; The historical physiological signal data of the target object corresponding to the window length of the second time scale is input into a pre-trained physiological signal data prediction model to obtain the predicted physiological signal data of the target object at the current sampling moment under the second time scale.

5. The method according to claim 4, characterized in that The window length corresponding to the second time scale is greater than the window length corresponding to the first time scale.

6. The method according to claim 1, characterized in that The determining of the regulation target value at the current sampling moment based on the real physiological signal data and the predicted physiological signal data of the target object at at least two time scales at the current sampling moment includes: Determine the deviation value between the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment; The regulation target value at the current sampling moment is determined based on the deviation values ​​of the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment.

7. The method according to claim 6, characterized in that The determining of the regulation target value at the current sampling moment based on the deviation value of the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment includes: Acquiring a preset control coefficient, wherein the control coefficient is associated with a time scale corresponding to the predicted physiological signal data; The control target value at the current sampling moment is determined based on the deviation value between the real physiological signal data and the predicted physiological signal data of the target object at different time scales at the current sampling moment and the preset control coefficient.

8. The method according to claim 7, characterized in that The obtaining of a preset control coefficient includes: determining a state parameter of the target object associated with a target disease according to a preset period, the state parameter representing a recovery state of the target object; A control coefficient is periodically determined based on a state parameter of the target object associated with a target disease.

9. The method according to any one of claims 1 to 8, characterized in that: The physiological signal data is the mean value of neural activity.

10. A device for determining stimulation parameters, characterized in that: include: A multi-time scale data acquisition module, used to acquire physiological signal data of a target object at at least two time scales at a current sampling moment, wherein the physiological signal data at least includes real physiological signal data and predicted physiological signal data of the target object; A control target value determination module, used to determine the control target value at the current sampling moment based on the real physiological signal data and the predicted physiological signal data of the target object at at least two time scales at the current sampling moment; The target stimulation parameter determination module is used to determine the target stimulation parameter at the current sampling moment based on the control target value at the current sampling moment.

11. A stimulator, characterized in that: The stimulator is implanted into the body of the target object and connected to a stimulation electrode implanted in a target point of the target object. The stimulator obtains real physiological data of the target point through the stimulation electrode, and delivers stimulation pulses to the target point through the stimulation electrode. The stimulator is configured to execute the stimulation parameter determination method described in any one of claims 1 to 9.

12. A program-controlled device, characterized in that: The program-controlled device is in communication with a stimulator implanted in the target subject; The stimulator is connected to a stimulation electrode implanted in a target point of a target object, the stimulator acquires real physiological data of the target point through the stimulation electrode, and delivers stimulation pulses to the target point through the stimulation electrode; The program-controlled device is configured to execute the stimulation parameter determination method according to any one of claims 1 to 9 to obtain the target stimulation parameter at the current sampling moment, and send the target stimulation parameter at the current sampling moment to the stimulator.

13. An implantable medical system, characterized in that: The implantable medical system comprises: The stimulator of claim 11; or The program-controlled device of claim 12.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the stimulation parameter determination method according to any one of claims 1 to 9 when executed.

15. A computer program product, characterized in that The computer program product comprises a computer program which, when executed by a processor, implements the stimulation parameter determination method according to any one of claims 1 to 9.

Images